{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "a1bdecfb",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import seaborn as sns \n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.impute import SimpleImputer\n",
    "from sklearn.neighbors import LocalOutlierFactor\n",
    "from scipy.stats import probplot\n",
    "from scipy.stats import zscore"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "d9ec9c9f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STATION CODE</th>\n",
       "      <th>LOCATIONS</th>\n",
       "      <th>STATE</th>\n",
       "      <th>Temp</th>\n",
       "      <th>D.O. (mg/l)</th>\n",
       "      <th>PH</th>\n",
       "      <th>CONDUCTIVITY (µmhos/cm)</th>\n",
       "      <th>B.O.D. (mg/l)</th>\n",
       "      <th>NITRATENAN N+ NITRITENANN (mg/l)</th>\n",
       "      <th>FECAL COLIFORM (MPN/100ml)</th>\n",
       "      <th>TOTAL COLIFORM (MPN/100ml)Mean</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1393</td>\n",
       "      <td>DAMANGANGA AT D/S OF MADHUBAN, DAMAN</td>\n",
       "      <td>DAMAN &amp; DIU</td>\n",
       "      <td>30.6</td>\n",
       "      <td>6.7</td>\n",
       "      <td>7.5</td>\n",
       "      <td>203</td>\n",
       "      <td>NAN</td>\n",
       "      <td>0.1</td>\n",
       "      <td>11</td>\n",
       "      <td>27</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1399</td>\n",
       "      <td>ZUARI AT D/S OF PT. WHERE KUMBARJRIA CANAL JOI...</td>\n",
       "      <td>GOA</td>\n",
       "      <td>29.8</td>\n",
       "      <td>5.7</td>\n",
       "      <td>7.2</td>\n",
       "      <td>189</td>\n",
       "      <td>2</td>\n",
       "      <td>0.2</td>\n",
       "      <td>4953</td>\n",
       "      <td>8391</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1475</td>\n",
       "      <td>ZUARI AT PANCHAWADI</td>\n",
       "      <td>GOA</td>\n",
       "      <td>29.5</td>\n",
       "      <td>6.3</td>\n",
       "      <td>6.9</td>\n",
       "      <td>179</td>\n",
       "      <td>1.7</td>\n",
       "      <td>0.1</td>\n",
       "      <td>3243</td>\n",
       "      <td>5330</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3181</td>\n",
       "      <td>RIVER ZUARI AT BORIM BRIDGE</td>\n",
       "      <td>GOA</td>\n",
       "      <td>29.7</td>\n",
       "      <td>5.8</td>\n",
       "      <td>6.9</td>\n",
       "      <td>64</td>\n",
       "      <td>3.8</td>\n",
       "      <td>0.5</td>\n",
       "      <td>5382</td>\n",
       "      <td>8443</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3182</td>\n",
       "      <td>RIVER ZUARI AT MARCAIM JETTY</td>\n",
       "      <td>GOA</td>\n",
       "      <td>29.5</td>\n",
       "      <td>5.8</td>\n",
       "      <td>7.3</td>\n",
       "      <td>83</td>\n",
       "      <td>1.9</td>\n",
       "      <td>0.4</td>\n",
       "      <td>3428</td>\n",
       "      <td>5500</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  STATION CODE                                          LOCATIONS  \\\n",
       "0         1393               DAMANGANGA AT D/S OF MADHUBAN, DAMAN   \n",
       "1         1399  ZUARI AT D/S OF PT. WHERE KUMBARJRIA CANAL JOI...   \n",
       "2         1475                                ZUARI AT PANCHAWADI   \n",
       "3         3181                        RIVER ZUARI AT BORIM BRIDGE   \n",
       "4         3182                       RIVER ZUARI AT MARCAIM JETTY   \n",
       "\n",
       "         STATE  Temp D.O. (mg/l)   PH CONDUCTIVITY (µmhos/cm) B.O.D. (mg/l)  \\\n",
       "0  DAMAN & DIU  30.6         6.7  7.5                     203           NAN   \n",
       "1          GOA  29.8         5.7  7.2                     189             2   \n",
       "2          GOA  29.5         6.3  6.9                     179           1.7   \n",
       "3          GOA  29.7         5.8  6.9                      64           3.8   \n",
       "4          GOA  29.5         5.8  7.3                      83           1.9   \n",
       "\n",
       "  NITRATENAN N+ NITRITENANN (mg/l) FECAL COLIFORM (MPN/100ml)  \\\n",
       "0                              0.1                         11   \n",
       "1                              0.2                       4953   \n",
       "2                              0.1                       3243   \n",
       "3                              0.5                       5382   \n",
       "4                              0.4                       3428   \n",
       "\n",
       "  TOTAL COLIFORM (MPN/100ml)Mean  year  \n",
       "0                             27  2014  \n",
       "1                           8391  2014  \n",
       "2                           5330  2014  \n",
       "3                           8443  2014  \n",
       "4                           5500  2014  "
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data=pd.read_csv('WQI.csv',encoding=\"ISO-8859-1\")\n",
    "data.fillna(0, inplace=True)\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "69c58589",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "STATION CODE                         object\n",
       "LOCATIONS                            object\n",
       "STATE                                object\n",
       "Temp                                float64\n",
       "D.O. (mg/l)                         float64\n",
       "PH                                  float64\n",
       "CONDUCTIVITY (µmhos/cm)             float64\n",
       "B.O.D. (mg/l)                       float64\n",
       "NITRATENAN N+ NITRITENANN (mg/l)    float64\n",
       "FECAL COLIFORM (MPN/100ml)           object\n",
       "TOTAL COLIFORM (MPN/100ml)Mean      float64\n",
       "year                                  int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data['Temp']=pd.to_numeric(data['Temp'],errors='coerce')\n",
    "data['D.O. (mg/l)']=pd.to_numeric(data['D.O. (mg/l)'],errors='coerce')\n",
    "data['PH']=pd.to_numeric(data['PH'],errors='coerce')\n",
    "data['B.O.D. (mg/l)']=pd.to_numeric(data['B.O.D. (mg/l)'],errors='coerce')\n",
    "data['CONDUCTIVITY (µmhos/cm)']=pd.to_numeric(data['CONDUCTIVITY (µmhos/cm)'],errors='coerce')\n",
    "data['NITRATENAN N+ NITRITENANN (mg/l)']=pd.to_numeric(data['NITRATENAN N+ NITRITENANN (mg/l)'],errors='coerce')\n",
    "data['TOTAL COLIFORM (MPN/100ml)Mean']=pd.to_numeric(data['TOTAL COLIFORM (MPN/100ml)Mean'],errors='coerce')\n",
    "data.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "406d3f71",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dtype('float64')"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "start=2\n",
    "end=1779\n",
    "station=data.iloc [start:end ,0]\n",
    "location=data.iloc [start:end ,1]\n",
    "state=data.iloc [start:end ,2]\n",
    "do= data.iloc [start:end ,4].astype(np.float64)\n",
    "value=0\n",
    "ph = data.iloc[ start:end,5]  \n",
    "co = data.iloc [start:end ,6].astype(np.float64)   \n",
    "  \n",
    "year=data.iloc[start:end,11]\n",
    "tc=data.iloc [2:end ,10].astype(np.float64)\n",
    "\n",
    "\n",
    "bod = data.iloc [start:end ,7].astype(np.float64)\n",
    "na= data.iloc [start:end ,8].astype(np.float64)\n",
    "na.dtype"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "237338ec",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STATION CODE</th>\n",
       "      <th>LOCATIONS</th>\n",
       "      <th>STATE</th>\n",
       "      <th>Temp</th>\n",
       "      <th>D.O. (mg/l)</th>\n",
       "      <th>PH</th>\n",
       "      <th>CONDUCTIVITY (µmhos/cm)</th>\n",
       "      <th>B.O.D. (mg/l)</th>\n",
       "      <th>NITRATENAN N+ NITRITENANN (mg/l)</th>\n",
       "      <th>FECAL COLIFORM (MPN/100ml)</th>\n",
       "      <th>TOTAL COLIFORM (MPN/100ml)Mean</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1393</td>\n",
       "      <td>DAMANGANGA AT D/S OF MADHUBAN, DAMAN</td>\n",
       "      <td>DAMAN &amp; DIU</td>\n",
       "      <td>30.6</td>\n",
       "      <td>6.7</td>\n",
       "      <td>7.5</td>\n",
       "      <td>203.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.1</td>\n",
       "      <td>11</td>\n",
       "      <td>27.0</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1399</td>\n",
       "      <td>ZUARI AT D/S OF PT. WHERE KUMBARJRIA CANAL JOI...</td>\n",
       "      <td>GOA</td>\n",
       "      <td>29.8</td>\n",
       "      <td>5.7</td>\n",
       "      <td>7.2</td>\n",
       "      <td>189.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.2</td>\n",
       "      <td>4953</td>\n",
       "      <td>8391.0</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1475</td>\n",
       "      <td>ZUARI AT PANCHAWADI</td>\n",
       "      <td>GOA</td>\n",
       "      <td>29.5</td>\n",
       "      <td>6.3</td>\n",
       "      <td>6.9</td>\n",
       "      <td>179.0</td>\n",
       "      <td>1.7</td>\n",
       "      <td>0.1</td>\n",
       "      <td>3243</td>\n",
       "      <td>5330.0</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3181</td>\n",
       "      <td>RIVER ZUARI AT BORIM BRIDGE</td>\n",
       "      <td>GOA</td>\n",
       "      <td>29.7</td>\n",
       "      <td>5.8</td>\n",
       "      <td>6.9</td>\n",
       "      <td>64.0</td>\n",
       "      <td>3.8</td>\n",
       "      <td>0.5</td>\n",
       "      <td>5382</td>\n",
       "      <td>8443.0</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3182</td>\n",
       "      <td>RIVER ZUARI AT MARCAIM JETTY</td>\n",
       "      <td>GOA</td>\n",
       "      <td>29.5</td>\n",
       "      <td>5.8</td>\n",
       "      <td>7.3</td>\n",
       "      <td>83.0</td>\n",
       "      <td>1.9</td>\n",
       "      <td>0.4</td>\n",
       "      <td>3428</td>\n",
       "      <td>5500.0</td>\n",
       "      <td>2014</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  STATION CODE                                          LOCATIONS  \\\n",
       "0         1393               DAMANGANGA AT D/S OF MADHUBAN, DAMAN   \n",
       "1         1399  ZUARI AT D/S OF PT. WHERE KUMBARJRIA CANAL JOI...   \n",
       "2         1475                                ZUARI AT PANCHAWADI   \n",
       "3         3181                        RIVER ZUARI AT BORIM BRIDGE   \n",
       "4         3182                       RIVER ZUARI AT MARCAIM JETTY   \n",
       "\n",
       "         STATE  Temp  D.O. (mg/l)   PH  CONDUCTIVITY (µmhos/cm)  \\\n",
       "0  DAMAN & DIU  30.6          6.7  7.5                    203.0   \n",
       "1          GOA  29.8          5.7  7.2                    189.0   \n",
       "2          GOA  29.5          6.3  6.9                    179.0   \n",
       "3          GOA  29.7          5.8  6.9                     64.0   \n",
       "4          GOA  29.5          5.8  7.3                     83.0   \n",
       "\n",
       "   B.O.D. (mg/l)  NITRATENAN N+ NITRITENANN (mg/l) FECAL COLIFORM (MPN/100ml)  \\\n",
       "0            NaN                               0.1                         11   \n",
       "1            2.0                               0.2                       4953   \n",
       "2            1.7                               0.1                       3243   \n",
       "3            3.8                               0.5                       5382   \n",
       "4            1.9                               0.4                       3428   \n",
       "\n",
       "   TOTAL COLIFORM (MPN/100ml)Mean  year  \n",
       "0                            27.0  2014  \n",
       "1                          8391.0  2014  \n",
       "2                          5330.0  2014  \n",
       "3                          8443.0  2014  \n",
       "4                          5500.0  2014  "
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "f04ed04f",
   "metadata": {},
   "outputs": [],
   "source": [
    "data=pd.concat([station,location,state,do,ph,co,bod,na,tc,year],axis=1)\n",
    "data. columns = ['station','location','state','do','ph','co','bod','na','tc','year']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "fd3eae3d",
   "metadata": {},
   "outputs": [],
   "source": [
    "data['npH']=data.ph.apply(lambda x: (100 if (8.5>=x>=7)  \n",
    "                                 else(80 if  (8.6>=x>=8.5) or (6.9>=x>=6.8) \n",
    "                                      else(60 if (8.8>=x>=8.6) or (6.8>=x>=6.7) \n",
    "                                          else(40 if (9>=x>=8.8) or (6.7>=x>=6.5)\n",
    "                                              else 0)))))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "c7e2ae8b",
   "metadata": {},
   "outputs": [],
   "source": [
    "data['ndo']=data.do.apply(lambda x:(100 if (x>=6)  \n",
    "                                 else(80 if  (6>=x>=5.1) \n",
    "                                      else(60 if (5>=x>=4.1)\n",
    "                                          else(40 if (4>=x>=3) \n",
    "                                              else 0)))))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "b3adcfcd",
   "metadata": {},
   "outputs": [],
   "source": [
    "data['nco']=data.tc.apply(lambda x:(100 if (5>=x>=0)  \n",
    "                                 else(80 if  (50>=x>=5) \n",
    "                                      else(60 if (500>=x>=50)\n",
    "                                          else(40 if (10000>=x>=500) \n",
    "                                              else 0)))))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "8211529f",
   "metadata": {},
   "outputs": [],
   "source": [
    "data['nbdo']=data.bod.apply(lambda x:(100 if (3>=x>=0)  \n",
    "                                 else(80 if  (6>=x>=3) \n",
    "                                      else(60 if (80>=x>=6)\n",
    "                                          else(40 if (125>=x>=80) \n",
    "                                              else 0)))))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "a2d489b4",
   "metadata": {},
   "outputs": [],
   "source": [
    "data['nec']=data.co.apply(lambda x:(100 if (75>=x>=0)  \n",
    "                                 else(80 if  (150>=x>=75) \n",
    "                                      else(60 if (225>=x>=150)\n",
    "                                          else(40 if (300>=x>=225) \n",
    "                                              else 0)))))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "cbc648f3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "station      object\n",
       "location     object\n",
       "state        object\n",
       "do          float64\n",
       "ph          float64\n",
       "co          float64\n",
       "bod         float64\n",
       "na          float64\n",
       "tc          float64\n",
       "year          int64\n",
       "npH           int64\n",
       "ndo           int64\n",
       "nco           int64\n",
       "nbdo          int64\n",
       "nec           int64\n",
       "nna           int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data['nna']=data.na.apply(lambda x:(100 if (20>=x>=0)  \n",
    "                                 else(80 if  (50>=x>=20) \n",
    "                                      else(60 if (100>=x>=50)\n",
    "                                          else(40 if (200>=x>=100) \n",
    "                                              else 0)))))\n",
    "\n",
    "data.head()\n",
    "data.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "c36c4e8f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>station</th>\n",
       "      <th>location</th>\n",
       "      <th>state</th>\n",
       "      <th>do</th>\n",
       "      <th>ph</th>\n",
       "      <th>co</th>\n",
       "      <th>bod</th>\n",
       "      <th>na</th>\n",
       "      <th>tc</th>\n",
       "      <th>year</th>\n",
       "      <th>...</th>\n",
       "      <th>nbdo</th>\n",
       "      <th>nec</th>\n",
       "      <th>nna</th>\n",
       "      <th>wph</th>\n",
       "      <th>wdo</th>\n",
       "      <th>wbdo</th>\n",
       "      <th>wec</th>\n",
       "      <th>wna</th>\n",
       "      <th>wco</th>\n",
       "      <th>wqi</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1475</td>\n",
       "      <td>ZUARI AT PANCHAWADI</td>\n",
       "      <td>GOA</td>\n",
       "      <td>6.300</td>\n",
       "      <td>6.900</td>\n",
       "      <td>179.0</td>\n",
       "      <td>1.7</td>\n",
       "      <td>0.1</td>\n",
       "      <td>5330.0</td>\n",
       "      <td>2014</td>\n",
       "      <td>...</td>\n",
       "      <td>100</td>\n",
       "      <td>60</td>\n",
       "      <td>100</td>\n",
       "      <td>13.2</td>\n",
       "      <td>28.10</td>\n",
       "      <td>23.40</td>\n",
       "      <td>0.54</td>\n",
       "      <td>2.8</td>\n",
       "      <td>11.24</td>\n",
       "      <td>79.28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3181</td>\n",
       "      <td>RIVER ZUARI AT BORIM BRIDGE</td>\n",
       "      <td>GOA</td>\n",
       "      <td>5.800</td>\n",
       "      <td>6.900</td>\n",
       "      <td>64.0</td>\n",
       "      <td>3.8</td>\n",
       "      <td>0.5</td>\n",
       "      <td>8443.0</td>\n",
       "      <td>2014</td>\n",
       "      <td>...</td>\n",
       "      <td>80</td>\n",
       "      <td>100</td>\n",
       "      <td>100</td>\n",
       "      <td>13.2</td>\n",
       "      <td>22.48</td>\n",
       "      <td>18.72</td>\n",
       "      <td>0.90</td>\n",
       "      <td>2.8</td>\n",
       "      <td>11.24</td>\n",
       "      <td>69.34</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3182</td>\n",
       "      <td>RIVER ZUARI AT MARCAIM JETTY</td>\n",
       "      <td>GOA</td>\n",
       "      <td>5.800</td>\n",
       "      <td>7.300</td>\n",
       "      <td>83.0</td>\n",
       "      <td>1.9</td>\n",
       "      <td>0.4</td>\n",
       "      <td>5500.0</td>\n",
       "      <td>2014</td>\n",
       "      <td>...</td>\n",
       "      <td>100</td>\n",
       "      <td>80</td>\n",
       "      <td>100</td>\n",
       "      <td>16.5</td>\n",
       "      <td>22.48</td>\n",
       "      <td>23.40</td>\n",
       "      <td>0.72</td>\n",
       "      <td>2.8</td>\n",
       "      <td>11.24</td>\n",
       "      <td>77.14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>1400</td>\n",
       "      <td>MANDOVI AT NEGHBOURHOOD OF PANAJI, GOA</td>\n",
       "      <td>GOA</td>\n",
       "      <td>5.500</td>\n",
       "      <td>7.400</td>\n",
       "      <td>81.0</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.1</td>\n",
       "      <td>4049.0</td>\n",
       "      <td>2014</td>\n",
       "      <td>...</td>\n",
       "      <td>100</td>\n",
       "      <td>80</td>\n",
       "      <td>100</td>\n",
       "      <td>16.5</td>\n",
       "      <td>22.48</td>\n",
       "      <td>23.40</td>\n",
       "      <td>0.72</td>\n",
       "      <td>2.8</td>\n",
       "      <td>11.24</td>\n",
       "      <td>77.14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>1476</td>\n",
       "      <td>MANDOVI AT TONCA, MARCELA, GOA</td>\n",
       "      <td>GOA</td>\n",
       "      <td>6.100</td>\n",
       "      <td>6.700</td>\n",
       "      <td>308.0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.3</td>\n",
       "      <td>5672.0</td>\n",
       "      <td>2014</td>\n",
       "      <td>...</td>\n",
       "      <td>100</td>\n",
       "      <td>0</td>\n",
       "      <td>100</td>\n",
       "      <td>9.9</td>\n",
       "      <td>28.10</td>\n",
       "      <td>23.40</td>\n",
       "      <td>0.00</td>\n",
       "      <td>2.8</td>\n",
       "      <td>11.24</td>\n",
       "      <td>75.44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1774</th>\n",
       "      <td>1428</td>\n",
       "      <td>KHARKHLA NEAR SUTNGA KHLIERIAT,JAINTIA HILLS D...</td>\n",
       "      <td>NAN</td>\n",
       "      <td>4.600</td>\n",
       "      <td>3.000</td>\n",
       "      <td>350.0</td>\n",
       "      <td>6.2</td>\n",
       "      <td>2.2</td>\n",
       "      <td>49.0</td>\n",
       "      <td>2006</td>\n",
       "      <td>...</td>\n",
       "      <td>60</td>\n",
       "      <td>0</td>\n",
       "      <td>100</td>\n",
       "      <td>0.0</td>\n",
       "      <td>16.86</td>\n",
       "      <td>14.04</td>\n",
       "      <td>0.00</td>\n",
       "      <td>2.8</td>\n",
       "      <td>22.48</td>\n",
       "      <td>56.18</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1775</th>\n",
       "      <td>1631</td>\n",
       "      <td>MYNTDU RIVER JOWAI, MEGHALAYA</td>\n",
       "      <td>NAN</td>\n",
       "      <td>8.800</td>\n",
       "      <td>7.000</td>\n",
       "      <td>172.0</td>\n",
       "      <td>1.6</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2800.0</td>\n",
       "      <td>2006</td>\n",
       "      <td>...</td>\n",
       "      <td>100</td>\n",
       "      <td>60</td>\n",
       "      <td>100</td>\n",
       "      <td>16.5</td>\n",
       "      <td>28.10</td>\n",
       "      <td>23.40</td>\n",
       "      <td>0.54</td>\n",
       "      <td>2.8</td>\n",
       "      <td>11.24</td>\n",
       "      <td>82.58</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1776</th>\n",
       "      <td>1632</td>\n",
       "      <td>GANOL RIVER TURA, MEGHALAYA</td>\n",
       "      <td>NAN</td>\n",
       "      <td>10.000</td>\n",
       "      <td>7.100</td>\n",
       "      <td>150.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>350.0</td>\n",
       "      <td>2006</td>\n",
       "      <td>...</td>\n",
       "      <td>100</td>\n",
       "      <td>80</td>\n",
       "      <td>100</td>\n",
       "      <td>16.5</td>\n",
       "      <td>28.10</td>\n",
       "      <td>23.40</td>\n",
       "      <td>0.72</td>\n",
       "      <td>2.8</td>\n",
       "      <td>16.86</td>\n",
       "      <td>88.38</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1777</th>\n",
       "      <td>1633</td>\n",
       "      <td>SIMSANG RIVER WILLIAMNAGAR, MEGHALAYA</td>\n",
       "      <td>NAN</td>\n",
       "      <td>9.000</td>\n",
       "      <td>7.300</td>\n",
       "      <td>158.0</td>\n",
       "      <td>1.8</td>\n",
       "      <td>7.2</td>\n",
       "      <td>280.0</td>\n",
       "      <td>2006</td>\n",
       "      <td>...</td>\n",
       "      <td>100</td>\n",
       "      <td>60</td>\n",
       "      <td>100</td>\n",
       "      <td>16.5</td>\n",
       "      <td>28.10</td>\n",
       "      <td>23.40</td>\n",
       "      <td>0.54</td>\n",
       "      <td>2.8</td>\n",
       "      <td>16.86</td>\n",
       "      <td>88.20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1778</th>\n",
       "      <td>2050</td>\n",
       "      <td>TLAWNG UPSTREAM AIZAWL</td>\n",
       "      <td>NAN</td>\n",
       "      <td>7.767</td>\n",
       "      <td>7.543</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.5</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2006</td>\n",
       "      <td>...</td>\n",
       "      <td>100</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>16.5</td>\n",
       "      <td>28.10</td>\n",
       "      <td>23.40</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>68.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1777 rows × 23 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     station                                           location state      do  \\\n",
       "2       1475                                ZUARI AT PANCHAWADI   GOA   6.300   \n",
       "3       3181                        RIVER ZUARI AT BORIM BRIDGE   GOA   5.800   \n",
       "4       3182                       RIVER ZUARI AT MARCAIM JETTY   GOA   5.800   \n",
       "5       1400             MANDOVI AT NEGHBOURHOOD OF PANAJI, GOA   GOA   5.500   \n",
       "6       1476                     MANDOVI AT TONCA, MARCELA, GOA   GOA   6.100   \n",
       "...      ...                                                ...   ...     ...   \n",
       "1774    1428  KHARKHLA NEAR SUTNGA KHLIERIAT,JAINTIA HILLS D...   NAN   4.600   \n",
       "1775    1631                      MYNTDU RIVER JOWAI, MEGHALAYA   NAN   8.800   \n",
       "1776    1632                        GANOL RIVER TURA, MEGHALAYA   NAN  10.000   \n",
       "1777    1633              SIMSANG RIVER WILLIAMNAGAR, MEGHALAYA   NAN   9.000   \n",
       "1778    2050                             TLAWNG UPSTREAM AIZAWL   NAN   7.767   \n",
       "\n",
       "         ph     co  bod   na      tc  year  ...  nbdo  nec  nna   wph    wdo  \\\n",
       "2     6.900  179.0  1.7  0.1  5330.0  2014  ...   100   60  100  13.2  28.10   \n",
       "3     6.900   64.0  3.8  0.5  8443.0  2014  ...    80  100  100  13.2  22.48   \n",
       "4     7.300   83.0  1.9  0.4  5500.0  2014  ...   100   80  100  16.5  22.48   \n",
       "5     7.400   81.0  1.5  0.1  4049.0  2014  ...   100   80  100  16.5  22.48   \n",
       "6     6.700  308.0  1.4  0.3  5672.0  2014  ...   100    0  100   9.9  28.10   \n",
       "...     ...    ...  ...  ...     ...   ...  ...   ...  ...  ...   ...    ...   \n",
       "1774  3.000  350.0  6.2  2.2    49.0  2006  ...    60    0  100   0.0  16.86   \n",
       "1775  7.000  172.0  1.6  5.0  2800.0  2006  ...   100   60  100  16.5  28.10   \n",
       "1776  7.100  150.0  1.0  4.0   350.0  2006  ...   100   80  100  16.5  28.10   \n",
       "1777  7.300  158.0  1.8  7.2   280.0  2006  ...   100   60  100  16.5  28.10   \n",
       "1778  7.543    NaN  0.5  NaN     NaN  2006  ...   100    0    0  16.5  28.10   \n",
       "\n",
       "       wbdo   wec  wna    wco    wqi  \n",
       "2     23.40  0.54  2.8  11.24  79.28  \n",
       "3     18.72  0.90  2.8  11.24  69.34  \n",
       "4     23.40  0.72  2.8  11.24  77.14  \n",
       "5     23.40  0.72  2.8  11.24  77.14  \n",
       "6     23.40  0.00  2.8  11.24  75.44  \n",
       "...     ...   ...  ...    ...    ...  \n",
       "1774  14.04  0.00  2.8  22.48  56.18  \n",
       "1775  23.40  0.54  2.8  11.24  82.58  \n",
       "1776  23.40  0.72  2.8  16.86  88.38  \n",
       "1777  23.40  0.54  2.8  16.86  88.20  \n",
       "1778  23.40  0.00  0.0   0.00  68.00  \n",
       "\n",
       "[1777 rows x 23 columns]"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data['wph']=data.npH * 0.165\n",
    "data['wdo']=data.ndo * 0.281\n",
    "data['wbdo']=data.nbdo * 0.234\n",
    "data['wec']=data.nec* 0.009\n",
    "data['wna']=data.nna * 0.028\n",
    "data['wco']=data.nco * 0.281\n",
    "data['wqi']=data.wph+data.wdo+data.wbdo+data.wec+data.wna+data.wco \n",
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "6527d036",
   "metadata": {},
   "outputs": [],
   "source": [
    "ag=data.groupby('year')['wqi'].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "ecc1f22b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "year\n",
       "22      44.580000\n",
       "2006    71.308824\n",
       "2007    72.663220\n",
       "2008    72.578854\n",
       "2009    74.085193\n",
       "Name: wqi, dtype: float64"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ag.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "f0c85665",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>year</th>\n",
       "      <th>wqi</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>22</td>\n",
       "      <td>44.580000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2006</td>\n",
       "      <td>71.308824</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2007</td>\n",
       "      <td>72.663220</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2008</td>\n",
       "      <td>72.578854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2009</td>\n",
       "      <td>74.085193</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2010</td>\n",
       "      <td>74.648723</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2011</td>\n",
       "      <td>75.949912</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>2012</td>\n",
       "      <td>78.857770</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>2013</td>\n",
       "      <td>75.009425</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>2014</td>\n",
       "      <td>76.826667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>2015</td>\n",
       "      <td>77.140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>2016</td>\n",
       "      <td>78.740000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>2017</td>\n",
       "      <td>82.760000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>2018</td>\n",
       "      <td>80.833333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>2019</td>\n",
       "      <td>70.090000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>2020</td>\n",
       "      <td>76.470000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>2021</td>\n",
       "      <td>80.706667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>2022</td>\n",
       "      <td>76.430000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>2023</td>\n",
       "      <td>69.924000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    year        wqi\n",
       "0     22  44.580000\n",
       "1   2006  71.308824\n",
       "2   2007  72.663220\n",
       "3   2008  72.578854\n",
       "4   2009  74.085193\n",
       "5   2010  74.648723\n",
       "6   2011  75.949912\n",
       "7   2012  78.857770\n",
       "8   2013  75.009425\n",
       "9   2014  76.826667\n",
       "10  2015  77.140000\n",
       "11  2016  78.740000\n",
       "12  2017  82.760000\n",
       "13  2018  80.833333\n",
       "14  2019  70.090000\n",
       "15  2020  76.470000\n",
       "16  2021  80.706667\n",
       "17  2022  76.430000\n",
       "18  2023  69.924000"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data=ag.reset_index(level=0,inplace=False)\n",
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "19e4fe99",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\DELL\\AppData\\Local\\Temp\\ipykernel_19168\\1969322661.py:10: MatplotlibDeprecationWarning: Axes3D(fig) adding itself to the figure is deprecated since 3.4. Pass the keyword argument auto_add_to_figure=False and use fig.add_axes(ax) to suppress this warning. The default value of auto_add_to_figure will change to False in mpl3.5 and True values will no longer work in 3.6.  This is consistent with other Axes classes.\n",
      "  ax = Axes3D(fig)\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 2000x1000 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>year</th>\n",
       "      <th>wqi</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>22</td>\n",
       "      <td>44.580000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2006</td>\n",
       "      <td>71.308824</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2007</td>\n",
       "      <td>72.663220</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2008</td>\n",
       "      <td>72.578854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2009</td>\n",
       "      <td>74.085193</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2010</td>\n",
       "      <td>74.648723</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2011</td>\n",
       "      <td>75.949912</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>2012</td>\n",
       "      <td>78.857770</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>2013</td>\n",
       "      <td>75.009425</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>2014</td>\n",
       "      <td>76.826667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>2015</td>\n",
       "      <td>77.140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>2016</td>\n",
       "      <td>78.740000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>2017</td>\n",
       "      <td>82.760000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>2018</td>\n",
       "      <td>80.833333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>2019</td>\n",
       "      <td>70.090000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>2020</td>\n",
       "      <td>76.470000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>2021</td>\n",
       "      <td>80.706667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>2022</td>\n",
       "      <td>76.430000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>2023</td>\n",
       "      <td>69.924000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    year        wqi\n",
       "0     22  44.580000\n",
       "1   2006  71.308824\n",
       "2   2007  72.663220\n",
       "3   2008  72.578854\n",
       "4   2009  74.085193\n",
       "5   2010  74.648723\n",
       "6   2011  75.949912\n",
       "7   2012  78.857770\n",
       "8   2013  75.009425\n",
       "9   2014  76.826667\n",
       "10  2015  77.140000\n",
       "11  2016  78.740000\n",
       "12  2017  82.760000\n",
       "13  2018  80.833333\n",
       "14  2019  70.090000\n",
       "15  2020  76.470000\n",
       "16  2021  80.706667\n",
       "17  2022  76.430000\n",
       "18  2023  69.924000"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "year=data['year'].values\n",
    "AQI=data['wqi'].values\n",
    "data['wqi']=pd.to_numeric(data['wqi'],errors='coerce')\n",
    "data['year']=pd.to_numeric(data['year'],errors='coerce')\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "plt.rcParams['figure.figsize'] = (20.0, 10.0)\n",
    "from mpl_toolkits.mplot3d import Axes3D\n",
    "fig = plt.figure()\n",
    "ax = Axes3D(fig)\n",
    "ax.scatter(year,AQI, color='red')\n",
    "plt.show()\n",
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "c4150006",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>year</th>\n",
       "      <th>wqi</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>22</td>\n",
       "      <td>44.580000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2006</td>\n",
       "      <td>71.308824</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2007</td>\n",
       "      <td>72.663220</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2008</td>\n",
       "      <td>72.578854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2009</td>\n",
       "      <td>74.085193</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year        wqi\n",
       "0    22  44.580000\n",
       "1  2006  71.308824\n",
       "2  2007  72.663220\n",
       "3  2008  72.578854\n",
       "4  2009  74.085193"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = data[np.isfinite(data['wqi'])]\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "29eb0754",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 2000x1000 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "cols =['year']\n",
    "y = data['wqi']\n",
    "x=data[cols]\n",
    "\n",
    "plt.scatter(x,y)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "97cfe6c1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1500x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "data=data.set_index('year')\n",
    "data.plot(figsize=(15,6))\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "f4332162",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>year</th>\n",
       "      <th>wqi</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>22</td>\n",
       "      <td>44.580000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2006</td>\n",
       "      <td>71.308824</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2007</td>\n",
       "      <td>72.663220</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2008</td>\n",
       "      <td>72.578854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2009</td>\n",
       "      <td>74.085193</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2010</td>\n",
       "      <td>74.648723</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2011</td>\n",
       "      <td>75.949912</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>2012</td>\n",
       "      <td>78.857770</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>2013</td>\n",
       "      <td>75.009425</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>2014</td>\n",
       "      <td>76.826667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>2015</td>\n",
       "      <td>77.140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>2016</td>\n",
       "      <td>78.740000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>2017</td>\n",
       "      <td>82.760000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>2018</td>\n",
       "      <td>80.833333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>2019</td>\n",
       "      <td>70.090000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>2020</td>\n",
       "      <td>76.470000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>2021</td>\n",
       "      <td>80.706667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>2022</td>\n",
       "      <td>76.430000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>2023</td>\n",
       "      <td>69.924000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    year        wqi\n",
       "0     22  44.580000\n",
       "1   2006  71.308824\n",
       "2   2007  72.663220\n",
       "3   2008  72.578854\n",
       "4   2009  74.085193\n",
       "5   2010  74.648723\n",
       "6   2011  75.949912\n",
       "7   2012  78.857770\n",
       "8   2013  75.009425\n",
       "9   2014  76.826667\n",
       "10  2015  77.140000\n",
       "11  2016  78.740000\n",
       "12  2017  82.760000\n",
       "13  2018  80.833333\n",
       "14  2019  70.090000\n",
       "15  2020  76.470000\n",
       "16  2021  80.706667\n",
       "17  2022  76.430000\n",
       "18  2023  69.924000"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn import neighbors,datasets\n",
    "data=data.reset_index(level=0,inplace=False)\n",
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "e6e2fb5a",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn import linear_model\n",
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "14a8b24d",
   "metadata": {},
   "outputs": [],
   "source": [
    "cols =['year']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "80c12f16",
   "metadata": {},
   "outputs": [],
   "source": [
    "y = data['wqi']\n",
    "x=data[cols]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "3904ae59",
   "metadata": {},
   "outputs": [],
   "source": [
    "reg=linear_model.LinearRegression()\n",
    "x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "8594c551",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LinearRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LinearRegression</label><div class=\"sk-toggleable__content\"><pre>LinearRegression()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LinearRegression()"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reg.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "c7a5b23c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([75.46896461, 75.4223399 , 75.63992189, 75.56221403])"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "a=reg.predict(x_test)\n",
    "a"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "fef050f1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "6     75.949912\n",
       "3     72.578854\n",
       "17    76.430000\n",
       "12    82.760000\n",
       "Name: wqi, dtype: float64"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "ae06e77d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "mse:15.19\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import mean_squared_error\n",
    "print('mse:%.2f'%mean_squared_error(y_test,a))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "1a49f1b2",
   "metadata": {},
   "outputs": [],
   "source": [
    "dt = pd.DataFrame({'Actual': y_test, 'Predicted': a}) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "d2c4c41a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1.        , -4.12921726],\n",
       "       [ 1.        ,  0.2108071 ],\n",
       "       [ 1.        ,  0.21299462],\n",
       "       [ 1.        ,  0.21518213],\n",
       "       [ 1.        ,  0.21736964],\n",
       "       [ 1.        ,  0.21955715],\n",
       "       [ 1.        ,  0.22174467],\n",
       "       [ 1.        ,  0.22393218],\n",
       "       [ 1.        ,  0.22611969],\n",
       "       [ 1.        ,  0.2283072 ],\n",
       "       [ 1.        ,  0.23049471],\n",
       "       [ 1.        ,  0.23268223],\n",
       "       [ 1.        ,  0.23486974],\n",
       "       [ 1.        ,  0.23705725],\n",
       "       [ 1.        ,  0.23924476],\n",
       "       [ 1.        ,  0.24143228],\n",
       "       [ 1.        ,  0.24361979],\n",
       "       [ 1.        ,  0.2458073 ],\n",
       "       [ 1.        ,  0.24799481]])"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x = (x - x.mean()) / x.std()\n",
    "x = np.c_[np.ones(x.shape[0]), x]\n",
    "x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "1a15d404",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Gradient Descent: 74.19, 7.18\n"
     ]
    }
   ],
   "source": [
    "alpha = 0.1 #Step size\n",
    "iterations = 3000 #No. of iterations\n",
    "m = y.size #No. of data points\n",
    "np.random.seed(4) #Setting the seed\n",
    "theta = np.random.rand(2) #Picking some random values to start with\n",
    "\n",
    "def gradient_descent(x, y, theta, iterations, alpha):\n",
    "    past_costs = []\n",
    "    past_thetas = [theta]\n",
    "    for i in range(iterations):\n",
    "        prediction = np.dot(x, theta)\n",
    "        error = prediction - y\n",
    "        cost = 1/(2*m) * np.dot(error.T, error)\n",
    "        past_costs.append(cost)\n",
    "        theta = theta - (alpha * (1/m) * np.dot(x.T, error))\n",
    "        past_thetas.append(theta)\n",
    "        \n",
    "    return past_thetas, past_costs\n",
    "\n",
    "past_thetas, past_costs = gradient_descent(x, y, theta, iterations, alpha)\n",
    "theta = past_thetas[-1]\n",
    "\n",
    "#Print the results...\n",
    "print(\"Gradient Descent: {:.2f}, {:.2f}\".format(theta[0], theta[1]))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "14c6c9e9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 2000x1000 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.title('Cost Function J')\n",
    "plt.xlabel('No. of iterations')\n",
    "plt.ylabel('Cost')\n",
    "plt.plot(past_costs)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "b2bb0810",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>year</th>\n",
       "      <th>wqi</th>\n",
       "      <th>Actual</th>\n",
       "      <th>Predicted</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>22</td>\n",
       "      <td>44.580000</td>\n",
       "      <td>44.580000</td>\n",
       "      <td>65.964767</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2006</td>\n",
       "      <td>71.308824</td>\n",
       "      <td>71.308824</td>\n",
       "      <td>75.209019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2007</td>\n",
       "      <td>72.663220</td>\n",
       "      <td>72.663220</td>\n",
       "      <td>75.213679</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2008</td>\n",
       "      <td>72.578854</td>\n",
       "      <td>72.578854</td>\n",
       "      <td>75.218338</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2009</td>\n",
       "      <td>74.085193</td>\n",
       "      <td>74.085193</td>\n",
       "      <td>75.222997</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2010</td>\n",
       "      <td>74.648723</td>\n",
       "      <td>74.648723</td>\n",
       "      <td>75.227657</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2011</td>\n",
       "      <td>75.949912</td>\n",
       "      <td>75.949912</td>\n",
       "      <td>75.232316</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>2012</td>\n",
       "      <td>78.857770</td>\n",
       "      <td>78.857770</td>\n",
       "      <td>75.236976</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>2013</td>\n",
       "      <td>75.009425</td>\n",
       "      <td>75.009425</td>\n",
       "      <td>75.241635</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>2014</td>\n",
       "      <td>76.826667</td>\n",
       "      <td>76.826667</td>\n",
       "      <td>75.246294</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>2015</td>\n",
       "      <td>77.140000</td>\n",
       "      <td>77.140000</td>\n",
       "      <td>75.250954</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>2016</td>\n",
       "      <td>78.740000</td>\n",
       "      <td>78.740000</td>\n",
       "      <td>75.255613</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>2017</td>\n",
       "      <td>82.760000</td>\n",
       "      <td>82.760000</td>\n",
       "      <td>75.260273</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>2018</td>\n",
       "      <td>80.833333</td>\n",
       "      <td>80.833333</td>\n",
       "      <td>75.264932</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>2019</td>\n",
       "      <td>70.090000</td>\n",
       "      <td>70.090000</td>\n",
       "      <td>75.269591</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>2020</td>\n",
       "      <td>76.470000</td>\n",
       "      <td>76.470000</td>\n",
       "      <td>75.274251</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>2021</td>\n",
       "      <td>80.706667</td>\n",
       "      <td>80.706667</td>\n",
       "      <td>75.278910</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>2022</td>\n",
       "      <td>76.430000</td>\n",
       "      <td>76.430000</td>\n",
       "      <td>75.283570</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>2023</td>\n",
       "      <td>69.924000</td>\n",
       "      <td>69.924000</td>\n",
       "      <td>75.288229</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    year        wqi     Actual  Predicted\n",
       "0     22  44.580000  44.580000  65.964767\n",
       "1   2006  71.308824  71.308824  75.209019\n",
       "2   2007  72.663220  72.663220  75.213679\n",
       "3   2008  72.578854  72.578854  75.218338\n",
       "4   2009  74.085193  74.085193  75.222997\n",
       "5   2010  74.648723  74.648723  75.227657\n",
       "6   2011  75.949912  75.949912  75.232316\n",
       "7   2012  78.857770  78.857770  75.236976\n",
       "8   2013  75.009425  75.009425  75.241635\n",
       "9   2014  76.826667  76.826667  75.246294\n",
       "10  2015  77.140000  77.140000  75.250954\n",
       "11  2016  78.740000  78.740000  75.255613\n",
       "12  2017  82.760000  82.760000  75.260273\n",
       "13  2018  80.833333  80.833333  75.264932\n",
       "14  2019  70.090000  70.090000  75.269591\n",
       "15  2020  76.470000  76.470000  75.274251\n",
       "16  2021  80.706667  80.706667  75.278910\n",
       "17  2022  76.430000  76.430000  75.283570\n",
       "18  2023  69.924000  69.924000  75.288229"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import numpy as np\n",
    "newB=[74.76, 2.13]\n",
    "\n",
    "def rmse(y,y_pred):\n",
    "    rmse= np.sqrt(sum(y-y_pred))\n",
    "    return rmse\n",
    "   \n",
    "\n",
    "y_pred=x.dot(newB)\n",
    "\n",
    "dt = pd.DataFrame({'Actual': y, 'Predicted': y_pred})  \n",
    "dt=pd.concat([data, dt], axis=1)\n",
    "dt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "729e1862",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "6.046173641321357\n"
     ]
    }
   ],
   "source": [
    "from sklearn import metrics\n",
    "print(np.sqrt(metrics.mean_squared_error(y,y_pred)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "3bb958a2",
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "Multi-dimensional indexing (e.g. `obj[:, None]`) is no longer supported. Convert to a numpy array before indexing instead.",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[1;32m~\\AppData\\Local\\Temp\\ipykernel_19168\\3174782065.py\u001b[0m in \u001b[0;36m<cell line: 5>\u001b[1;34m()\u001b[0m\n\u001b[0;32m      3\u001b[0m \u001b[0my1_axis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mPredicted\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      4\u001b[0m \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mscatter\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx_axis\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0my_axis\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 5\u001b[1;33m \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mplot\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx_axis\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0my1_axis\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mcolor\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'r'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      6\u001b[0m \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtitle\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"linear regression\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      7\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\matplotlib\\pyplot.py\u001b[0m in \u001b[0;36mplot\u001b[1;34m(scalex, scaley, data, *args, **kwargs)\u001b[0m\n\u001b[0;32m   2755\u001b[0m \u001b[1;33m@\u001b[0m\u001b[0m_copy_docstring_and_deprecators\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mAxes\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mplot\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2756\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mplot\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mscalex\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mTrue\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mscaley\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mTrue\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2757\u001b[1;33m     return gca().plot(\n\u001b[0m\u001b[0;32m   2758\u001b[0m         \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mscalex\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mscalex\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mscaley\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mscaley\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2759\u001b[0m         **({\"data\": data} if data is not None else {}), **kwargs)\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\matplotlib\\axes\\_axes.py\u001b[0m in \u001b[0;36mplot\u001b[1;34m(self, scalex, scaley, data, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1630\u001b[0m         \"\"\"\n\u001b[0;32m   1631\u001b[0m         \u001b[0mkwargs\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcbook\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mnormalize_kwargs\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmlines\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mLine2D\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1632\u001b[1;33m         \u001b[0mlines\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_get_lines\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1633\u001b[0m         \u001b[1;32mfor\u001b[0m \u001b[0mline\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mlines\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1634\u001b[0m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0madd_line\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mline\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\matplotlib\\axes\\_base.py\u001b[0m in \u001b[0;36m__call__\u001b[1;34m(self, data, *args, **kwargs)\u001b[0m\n\u001b[0;32m    310\u001b[0m                 \u001b[0mthis\u001b[0m \u001b[1;33m+=\u001b[0m \u001b[0margs\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    311\u001b[0m                 \u001b[0margs\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0margs\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 312\u001b[1;33m             \u001b[1;32myield\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_plot_args\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mthis\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    313\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    314\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mget_next_color\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\matplotlib\\axes\\_base.py\u001b[0m in \u001b[0;36m_plot_args\u001b[1;34m(self, tup, kwargs, return_kwargs)\u001b[0m\n\u001b[0;32m    485\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    486\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mxy\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;36m2\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 487\u001b[1;33m             \u001b[0mx\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_check_1d\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mxy\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    488\u001b[0m             \u001b[0my\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_check_1d\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mxy\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    489\u001b[0m         \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\matplotlib\\cbook\\__init__.py\u001b[0m in \u001b[0;36m_check_1d\u001b[1;34m(x)\u001b[0m\n\u001b[0;32m   1325\u001b[0m                     message='Support for multi-dimensional indexing')\n\u001b[0;32m   1326\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1327\u001b[1;33m                 \u001b[0mndim\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mx\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndim\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1328\u001b[0m                 \u001b[1;31m# we have definitely hit a pandas index or series object\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1329\u001b[0m                 \u001b[1;31m# cast to a numpy array.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\series.py\u001b[0m in \u001b[0;36m__getitem__\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m   1031\u001b[0m             \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_get_values\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1032\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1033\u001b[1;33m         \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_get_with\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1034\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1035\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m_get_with\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\series.py\u001b[0m in \u001b[0;36m_get_with\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m   1046\u001b[0m             )\n\u001b[0;32m   1047\u001b[0m         \u001b[1;32melif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtuple\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1048\u001b[1;33m             \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_get_values_tuple\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1049\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1050\u001b[0m         \u001b[1;32melif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mis_list_like\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\series.py\u001b[0m in \u001b[0;36m_get_values_tuple\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m   1080\u001b[0m             \u001b[1;31m# the asarray is needed to avoid returning a 2D DatetimeArray\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1081\u001b[0m             \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0masarray\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_values\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1082\u001b[1;33m             \u001b[0mdisallow_ndim_indexing\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1083\u001b[0m             \u001b[1;32mreturn\u001b[0m \u001b[0mresult\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1084\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\indexers\\utils.py\u001b[0m in \u001b[0;36mdisallow_ndim_indexing\u001b[1;34m(result)\u001b[0m\n\u001b[0;32m    341\u001b[0m     \"\"\"\n\u001b[0;32m    342\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndim\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m>\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 343\u001b[1;33m         raise ValueError(\n\u001b[0m\u001b[0;32m    344\u001b[0m             \u001b[1;34m\"Multi-dimensional indexing (e.g. `obj[:, None]`) is no longer \"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    345\u001b[0m             \u001b[1;34m\"supported. Convert to a numpy array before indexing instead.\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mValueError\u001b[0m: Multi-dimensional indexing (e.g. `obj[:, None]`) is no longer supported. Convert to a numpy array before indexing instead."
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 2000x1000 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "x_axis=dt.year\n",
    "y_axis=dt.Actual\n",
    "y1_axis=dt.Predicted\n",
    "plt.scatter(x_axis,y_axis)\n",
    "plt.plot(x_axis,y1_axis,color='r')\n",
    "plt.title(\"linear regression\")\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "70aebf0e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1900, 12)"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(\"WQI.csv\", encoding= 'unicode_escape')\n",
    "df = df.iloc[0:1900, :]\n",
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "7f1e8e01",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.rename(columns={\"D.O. (mg/l)\": \"DO\", \"CONDUCTIVITY (µmhos/cm)\": \"Conductivity\", \"B.O.D. (mg/l)\": \"BOD\", \"NITRATENAN N+ NITRITENANN (mg/l)\": \"NI\", \"FECAL COLIFORM (MPN/100ml)\": \"Fec_col\", \"TOTAL COLIFORM (MPN/100ml)Mean\": \"Tot_col\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "e5f1301e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "STATION CODE     object\n",
       "LOCATIONS        object\n",
       "STATE            object\n",
       "Temp            float64\n",
       "DO              float64\n",
       "PH              float64\n",
       "Conductivity    float64\n",
       "BOD             float64\n",
       "NI              float64\n",
       "Fec_col         float64\n",
       "Tot_col         float64\n",
       "year              int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def convert_to_numeric(df):\n",
    "    num_col = df.shape[1]\n",
    "    # Start from index 3\n",
    "    for index in range(3, num_col):\n",
    "        col_name = df.iloc[:, index].name\n",
    "        df[col_name] = pd.to_numeric(df[col_name], errors=\"coerce\")\n",
    "    return df\n",
    "\n",
    "df = convert_to_numeric(df)\n",
    "df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "27b4aef2",
   "metadata": {},
   "outputs": [],
   "source": [
    "def convert_to_nan(df):\n",
    "    n_col = df.shape[1]\n",
    "    for index in range(n_col):\n",
    "        df.iloc[:, index]  = df.iloc[:, index].replace(\"NAN\", np.nan)\n",
    "    return df\n",
    "\n",
    "df = convert_to_nan(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "ba56c442",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "year              0\n",
       "PH                7\n",
       "Conductivity     24\n",
       "DO               30\n",
       "BOD              42\n",
       "Temp             89\n",
       "STATION CODE    120\n",
       "Tot_col         130\n",
       "LOCATIONS       183\n",
       "NI              189\n",
       "Fec_col         280\n",
       "STATE           670\n",
       "dtype: int64"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum().sort_values()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "6e0a9dc7",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_num = df.select_dtypes(exclude=\"object\")\n",
    "df_num_col = df_num.columns\n",
    "imputer = SimpleImputer(strategy=\"median\")\n",
    "\n",
    "df_num = imputer.fit_transform(df_num)\n",
    "df_num = pd.DataFrame(df_num, columns=df_num_col)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "11961297",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "STATION CODE    120\n",
       "LOCATIONS       183\n",
       "STATE           670\n",
       "dtype: int64"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_cat = df.select_dtypes(include=\"object\")\n",
    "df_cat.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "15353088",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STATION CODE</th>\n",
       "      <th>LOCATIONS</th>\n",
       "      <th>STATE</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>166</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>424</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>677</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1168</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1351</th>\n",
       "      <td>1330</td>\n",
       "      <td>NaN</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1513</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1626</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1745</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     STATION CODE                                LOCATIONS  \\\n",
       "166          1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU   \n",
       "424          1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU   \n",
       "677          1330             TAMBIRAPARANI AT ARUMUGANERI   \n",
       "1168         1330             TAMBIRAPARANI AT ARUMUGANERI   \n",
       "1351         1330                                      NaN   \n",
       "1513         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU   \n",
       "1626         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU   \n",
       "1745         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU   \n",
       "\n",
       "                                        STATE  \n",
       "166                                 TAMILNADU  \n",
       "424                                 TAMILNADU  \n",
       "677                                 TAMILNADU  \n",
       "1168                                TAMILNADU  \n",
       "1351  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  \n",
       "1513                                TAMILNADU  \n",
       "1626                                TAMILNADU  \n",
       "1745                                TAMILNADU  "
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.set_option('mode.chained_assignment', None)\n",
    "df_cat_copy = df_cat.copy()\n",
    "df_cat_copy[df_cat_copy[\"STATION CODE\"] == \"1330\"]\n",
    "df_cat_copy[\"STATE\"][df_cat_copy[\"STATION CODE\"] == \"1330\"] = df_cat_copy[\"STATE\"][df_cat_copy[\"STATION CODE\"] == \"1330\"].fillna(\"TAMILNADU\")\n",
    "df_cat_copy[df_cat_copy[\"STATION CODE\"] == \"1330\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "03c92793",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STATION CODE</th>\n",
       "      <th>LOCATIONS</th>\n",
       "      <th>STATE</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>166</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>424</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>677</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1168</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1351</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1513</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1626</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1745</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     STATION CODE                                LOCATIONS      STATE\n",
       "166          1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "424          1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "677          1330             TAMBIRAPARANI AT ARUMUGANERI  TAMILNADU\n",
       "1168         1330             TAMBIRAPARANI AT ARUMUGANERI  TAMILNADU\n",
       "1351         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU        NaN\n",
       "1513         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "1626         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "1745         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def fill_locations(df_cat):\n",
    "    location_null = df_cat[df_cat[\"LOCATIONS\"].isnull()]\n",
    "    location_null_indices = location_null.index\n",
    "    for index in location_null_indices:\n",
    "        state_value = location_null[\"STATE\"][index]\n",
    "        location_null[\"LOCATIONS\"][index] = state_value\n",
    "        location_null[\"STATE\"][index] = np.nan\n",
    "    df_cat[df_cat[\"LOCATIONS\"].isnull()] = location_null\n",
    "    return\n",
    "fill_locations(df_cat_copy)\n",
    "df_cat_copy[df_cat_copy[\"STATION CODE\"] == \"1330\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "22ad3852",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STATION CODE</th>\n",
       "      <th>LOCATIONS</th>\n",
       "      <th>STATE</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>166</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>424</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1351</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1513</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1626</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1745</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1896</th>\n",
       "      <td>NaN</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     STATION CODE                                LOCATIONS      STATE\n",
       "166          1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "424          1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "1351         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU        NaN\n",
       "1513         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "1626         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "1745         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "1896          NaN  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU        NaN"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_cat_copy[df_cat_copy[\"LOCATIONS\"] == \"TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "71944af6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STATION CODE</th>\n",
       "      <th>LOCATIONS</th>\n",
       "      <th>STATE</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>166</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>424</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1351</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1513</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1626</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1745</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1896</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     STATION CODE                                LOCATIONS      STATE\n",
       "166          1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "424          1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "1351         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU        NaN\n",
       "1513         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "1626         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "1745         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "1896         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU        NaN"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def fill_code(df_cat):\n",
    "    station_null = df_cat[df_cat[\"STATION CODE\"].isnull()]\n",
    "    station_null_indices = station_null.index\n",
    "    for index in station_null_indices:\n",
    "        stat_code = np.nan\n",
    "        location_index = station_null[\"LOCATIONS\"][index]\n",
    "        code_at_location = df_cat[\"STATION CODE\"][df_cat[\"LOCATIONS\"] == location_index]\n",
    "        for index_code in code_at_location.index:\n",
    "            if (code_at_location[index_code] != np.nan):\n",
    "                stat_code = code_at_location[index_code]\n",
    "                break\n",
    "        station_null[\"STATION CODE\"][index] = stat_code\n",
    "    df_cat[df_cat[\"STATION CODE\"].isnull()] = station_null\n",
    "    return\n",
    "\n",
    "fill_code(df_cat_copy)\n",
    "df_cat_copy[df_cat_copy[\"LOCATIONS\"] == \"TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "id": "a53fa9ca",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STATION CODE</th>\n",
       "      <th>LOCATIONS</th>\n",
       "      <th>STATE</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>166</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>424</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>677</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1168</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1351</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1513</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1626</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1745</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1896</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     STATION CODE                                LOCATIONS      STATE\n",
       "166          1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "424          1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "677          1330             TAMBIRAPARANI AT ARUMUGANERI  TAMILNADU\n",
       "1168         1330             TAMBIRAPARANI AT ARUMUGANERI  TAMILNADU\n",
       "1351         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "1513         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "1626         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "1745         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU\n",
       "1896         1330  TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU  TAMILNADU"
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def fill_state(df_cat):\n",
    "    station_code = df_cat[\"STATION CODE\"].unique()\n",
    "    for index in range(station_code.shape[0]):\n",
    "        if (station_code[index] != np.nan):\n",
    "            df_state = df_cat[\"STATE\"][df_cat[\"STATION CODE\"] == station_code[index]] \n",
    "            state_values = df_cat[\"STATE\"][df_cat[\"STATION CODE\"] == station_code[index]]\n",
    "            state = np.nan\n",
    "            for index_state in range(state_values.shape[0]):\n",
    "                if (state_values.iloc[index_state] != np.nan):\n",
    "                    state = state_values.iloc[index_state]\n",
    "                    break\n",
    "            df_state_fill = df_state.fillna(state) \n",
    "            df_cat[\"STATE\"][df_cat[\"STATION CODE\"] == station_code[index]] = df_state_fill\n",
    "    return\n",
    "fill_state(df_cat_copy)\n",
    "df_cat_copy[df_cat_copy[\"STATION CODE\"] == \"1330\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "88422f47",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "STATION CODE     4\n",
       "LOCATIONS        2\n",
       "STATE           12\n",
       "dtype: int64"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_cat_copy.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "d08c4611",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STATION CODE</th>\n",
       "      <th>LOCATIONS</th>\n",
       "      <th>STATE</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>260</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>431</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1106</th>\n",
       "      <td>1207</td>\n",
       "      <td>KABBANI AT MUTHANKARA</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1107</th>\n",
       "      <td>1208</td>\n",
       "      <td>BHAVANI AT ELACHIVAZHY</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1650</th>\n",
       "      <td>2047</td>\n",
       "      <td>NNANCHOE (ATTAWA CHOE), CHANDIGARH</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1651</th>\n",
       "      <td>2048</td>\n",
       "      <td>PATIALA KI RAO, CHANDIGARH</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1652</th>\n",
       "      <td>2049</td>\n",
       "      <td>SUKHNA CHOE, CHANDIGARH</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1770</th>\n",
       "      <td>2047</td>\n",
       "      <td>NNANCHOE (ATTAWA CHOE)</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1771</th>\n",
       "      <td>2048</td>\n",
       "      <td>PATIALA KI RAO</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1772</th>\n",
       "      <td>2049</td>\n",
       "      <td>SUKHNA CHOE</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1784</th>\n",
       "      <td>NaN</td>\n",
       "      <td>DAMANGANGA  AFTER CONFL. OF PIPARIA DRAIN, DAMAN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1785</th>\n",
       "      <td>NaN</td>\n",
       "      <td>DAMANGANGA AT CIRCUIT HOUSE, SILVASA, DADRA AN...</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     STATION CODE                                          LOCATIONS STATE\n",
       "260           NaN                                                NaN   NaN\n",
       "431           NaN                                                NaN   NaN\n",
       "1106         1207                              KABBANI AT MUTHANKARA   NaN\n",
       "1107         1208                             BHAVANI AT ELACHIVAZHY   NaN\n",
       "1650         2047                 NNANCHOE (ATTAWA CHOE), CHANDIGARH   NaN\n",
       "1651         2048                         PATIALA KI RAO, CHANDIGARH   NaN\n",
       "1652         2049                            SUKHNA CHOE, CHANDIGARH   NaN\n",
       "1770         2047                             NNANCHOE (ATTAWA CHOE)   NaN\n",
       "1771         2048                                     PATIALA KI RAO   NaN\n",
       "1772         2049                                        SUKHNA CHOE   NaN\n",
       "1784          NaN   DAMANGANGA  AFTER CONFL. OF PIPARIA DRAIN, DAMAN   NaN\n",
       "1785          NaN  DAMANGANGA AT CIRCUIT HOUSE, SILVASA, DADRA AN...   NaN"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_cat_copy[df_cat_copy[\"STATE\"].isnull()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "3e1fb54f",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_cat_copy[\"STATE\"][1106] = \"KERALA\"\n",
    "df_cat_copy[\"STATE\"][1107] = \"KERALA\"\n",
    "df_cat_copy[\"STATE\"][1650] = \"CHANDIGARH\"\n",
    "df_cat_copy[\"STATE\"][1651] = \"CHANDIGARH\"\n",
    "df_cat_copy[\"STATE\"][1652] = \"CHANDIGARH\"\n",
    "df_cat_copy[\"STATE\"][1770] = \"CHANDIGARH\"\n",
    "df_cat_copy[\"STATE\"][1771] = \"CHANDIGARH\"\n",
    "df_cat_copy[\"STATE\"][1772] = \"CHANDIGARH\"\n",
    "df_cat_copy[\"STATE\"][1784] = \"DAMAN & DIU\"\n",
    "df_cat_copy[\"STATE\"][1785] = \"DAMAN & DIU\"\n",
    "df_cat_copy[\"STATION CODE\"][1784] = \"0000\" # I am setting this according to myself\n",
    "df_cat_copy[\"STATION CODE\"][1785] = \"0000\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "58ce64b1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "STATION CODE    2\n",
       "LOCATIONS       2\n",
       "STATE           2\n",
       "dtype: int64"
      ]
     },
     "execution_count": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_cat = df_cat_copy\n",
    "df_cat.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "a832224b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Temp            0\n",
       "DO              0\n",
       "PH              0\n",
       "Conductivity    0\n",
       "BOD             0\n",
       "NI              0\n",
       "Fec_col         0\n",
       "Tot_col         0\n",
       "year            0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_num.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "a2c33e97",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "STATION CODE    2\n",
       "LOCATIONS       2\n",
       "STATE           2\n",
       "Temp            0\n",
       "DO              0\n",
       "PH              0\n",
       "Conductivity    0\n",
       "BOD             0\n",
       "NI              0\n",
       "Fec_col         0\n",
       "Tot_col         0\n",
       "year            0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_final = pd.concat([df_cat, df_num], axis=1)\n",
    "df_final.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "f01d3a92",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STATION CODE</th>\n",
       "      <th>LOCATIONS</th>\n",
       "      <th>STATE</th>\n",
       "      <th>Temp</th>\n",
       "      <th>DO</th>\n",
       "      <th>PH</th>\n",
       "      <th>Conductivity</th>\n",
       "      <th>BOD</th>\n",
       "      <th>NI</th>\n",
       "      <th>Fec_col</th>\n",
       "      <th>Tot_col</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>260</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>27.0</td>\n",
       "      <td>6.7</td>\n",
       "      <td>7.3</td>\n",
       "      <td>198.0</td>\n",
       "      <td>1.8965</td>\n",
       "      <td>0.52</td>\n",
       "      <td>233.0</td>\n",
       "      <td>465.0</td>\n",
       "      <td>2013.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>431</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>27.0</td>\n",
       "      <td>6.7</td>\n",
       "      <td>7.3</td>\n",
       "      <td>198.0</td>\n",
       "      <td>1.8965</td>\n",
       "      <td>0.52</td>\n",
       "      <td>233.0</td>\n",
       "      <td>465.0</td>\n",
       "      <td>2013.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    STATION CODE LOCATIONS STATE  Temp   DO   PH  Conductivity     BOD    NI  \\\n",
       "260          NaN       NaN   NaN  27.0  6.7  7.3         198.0  1.8965  0.52   \n",
       "431          NaN       NaN   NaN  27.0  6.7  7.3         198.0  1.8965  0.52   \n",
       "\n",
       "     Fec_col  Tot_col    year  \n",
       "260    233.0    465.0  2013.0  \n",
       "431    233.0    465.0  2013.0  "
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_null = df_final[(df_final[\"STATION CODE\"].isnull()) & (df_final[\"LOCATIONS\"].isnull()) & (df_final[\"STATE\"].isnull())]\n",
    "df_null_indices = df_null.index\n",
    "df_final.drop(df_null_indices, axis=0, inplace=True)\n",
    "df_null"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "id": "9f721fec",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1898, 12)"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_final.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "c45269dd",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of outliers using Z-Score method- 125\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STATION CODE</th>\n",
       "      <th>LOCATIONS</th>\n",
       "      <th>STATE</th>\n",
       "      <th>Temp</th>\n",
       "      <th>DO</th>\n",
       "      <th>PH</th>\n",
       "      <th>Conductivity</th>\n",
       "      <th>BOD</th>\n",
       "      <th>NI</th>\n",
       "      <th>Fec_col</th>\n",
       "      <th>Tot_col</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>741</th>\n",
       "      <td>2880</td>\n",
       "      <td>NAMBUL RIVER AT BISHNUPUR</td>\n",
       "      <td>MANIPUR</td>\n",
       "      <td>28.0</td>\n",
       "      <td>8.2</td>\n",
       "      <td>7.6</td>\n",
       "      <td>112.0</td>\n",
       "      <td>2.1</td>\n",
       "      <td>0.52</td>\n",
       "      <td>233.0</td>\n",
       "      <td>31.0</td>\n",
       "      <td>2012.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>745</th>\n",
       "      <td>2856</td>\n",
       "      <td>THOUBAL RIVER AT YAIRIPOK, THOUBAL</td>\n",
       "      <td>MANIPUR</td>\n",
       "      <td>30.0</td>\n",
       "      <td>9.3</td>\n",
       "      <td>7.6</td>\n",
       "      <td>193.0</td>\n",
       "      <td>2.3</td>\n",
       "      <td>0.52</td>\n",
       "      <td>233.0</td>\n",
       "      <td>41.0</td>\n",
       "      <td>2012.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37</th>\n",
       "      <td>2671</td>\n",
       "      <td>KUNDALIKA RIVER NEAR SALAV BRIDGE (SALINA ZONE...</td>\n",
       "      <td>MAHARASHTRA</td>\n",
       "      <td>25.3</td>\n",
       "      <td>5.3</td>\n",
       "      <td>7.7</td>\n",
       "      <td>24062.0</td>\n",
       "      <td>9.9</td>\n",
       "      <td>1.20</td>\n",
       "      <td>156.0</td>\n",
       "      <td>304.0</td>\n",
       "      <td>2014.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>88</th>\n",
       "      <td>2294</td>\n",
       "      <td>R KALLAI AT KALLAI BRIDGE</td>\n",
       "      <td>KERALA</td>\n",
       "      <td>26.3</td>\n",
       "      <td>3.7</td>\n",
       "      <td>7.7</td>\n",
       "      <td>32005.0</td>\n",
       "      <td>1.2</td>\n",
       "      <td>0.90</td>\n",
       "      <td>40000.0</td>\n",
       "      <td>60392.0</td>\n",
       "      <td>2014.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>108</th>\n",
       "      <td>2304</td>\n",
       "      <td>R MOGRAL AT MOGRAL BR.</td>\n",
       "      <td>KERALA</td>\n",
       "      <td>30.0</td>\n",
       "      <td>5.6</td>\n",
       "      <td>7.2</td>\n",
       "      <td>24360.0</td>\n",
       "      <td>2.1</td>\n",
       "      <td>0.30</td>\n",
       "      <td>92.0</td>\n",
       "      <td>447.0</td>\n",
       "      <td>2014.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>432</th>\n",
       "      <td>1023</td>\n",
       "      <td>GHAGGAR AT MUBARAKPUR REST HOUSE (PATIALA), PU...</td>\n",
       "      <td>PUNJAB</td>\n",
       "      <td>23.3</td>\n",
       "      <td>5.5</td>\n",
       "      <td>7.2</td>\n",
       "      <td>636.0</td>\n",
       "      <td>9.7</td>\n",
       "      <td>4.00</td>\n",
       "      <td>1328.0</td>\n",
       "      <td>4975.0</td>\n",
       "      <td>2013.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>685</th>\n",
       "      <td>1023</td>\n",
       "      <td>GHAGGAR AT MUBARAKPUR REST HOUSE (PATIALA)</td>\n",
       "      <td>PUNJAB</td>\n",
       "      <td>21.0</td>\n",
       "      <td>5.5</td>\n",
       "      <td>7.4</td>\n",
       "      <td>635.0</td>\n",
       "      <td>8.8</td>\n",
       "      <td>5.08</td>\n",
       "      <td>1400.0</td>\n",
       "      <td>5500.0</td>\n",
       "      <td>2012.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>172</th>\n",
       "      <td>3023</td>\n",
       "      <td>VASISTA AT SALEM, D/S OF SAGO INDUSRIES EFFLUE...</td>\n",
       "      <td>TAMILNADU</td>\n",
       "      <td>24.3</td>\n",
       "      <td>0.9</td>\n",
       "      <td>7.6</td>\n",
       "      <td>2039.0</td>\n",
       "      <td>104.5</td>\n",
       "      <td>0.90</td>\n",
       "      <td>272521616.0</td>\n",
       "      <td>511090873.0</td>\n",
       "      <td>2014.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>432</th>\n",
       "      <td>1023</td>\n",
       "      <td>GHAGGAR AT MUBARAKPUR REST HOUSE (PATIALA), PU...</td>\n",
       "      <td>PUNJAB</td>\n",
       "      <td>23.3</td>\n",
       "      <td>5.5</td>\n",
       "      <td>7.2</td>\n",
       "      <td>636.0</td>\n",
       "      <td>9.7</td>\n",
       "      <td>4.00</td>\n",
       "      <td>1328.0</td>\n",
       "      <td>4975.0</td>\n",
       "      <td>2013.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>685</th>\n",
       "      <td>1023</td>\n",
       "      <td>GHAGGAR AT MUBARAKPUR REST HOUSE (PATIALA)</td>\n",
       "      <td>PUNJAB</td>\n",
       "      <td>21.0</td>\n",
       "      <td>5.5</td>\n",
       "      <td>7.4</td>\n",
       "      <td>635.0</td>\n",
       "      <td>8.8</td>\n",
       "      <td>5.08</td>\n",
       "      <td>1400.0</td>\n",
       "      <td>5500.0</td>\n",
       "      <td>2012.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>125 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    STATION CODE                                          LOCATIONS  \\\n",
       "741         2880                          NAMBUL RIVER AT BISHNUPUR   \n",
       "745         2856                 THOUBAL RIVER AT YAIRIPOK, THOUBAL   \n",
       "37          2671  KUNDALIKA RIVER NEAR SALAV BRIDGE (SALINA ZONE...   \n",
       "88          2294                          R KALLAI AT KALLAI BRIDGE   \n",
       "108         2304                             R MOGRAL AT MOGRAL BR.   \n",
       "..           ...                                                ...   \n",
       "432         1023  GHAGGAR AT MUBARAKPUR REST HOUSE (PATIALA), PU...   \n",
       "685         1023         GHAGGAR AT MUBARAKPUR REST HOUSE (PATIALA)   \n",
       "172         3023  VASISTA AT SALEM, D/S OF SAGO INDUSRIES EFFLUE...   \n",
       "432         1023  GHAGGAR AT MUBARAKPUR REST HOUSE (PATIALA), PU...   \n",
       "685         1023         GHAGGAR AT MUBARAKPUR REST HOUSE (PATIALA)   \n",
       "\n",
       "           STATE  Temp   DO   PH  Conductivity    BOD    NI      Fec_col  \\\n",
       "741      MANIPUR  28.0  8.2  7.6         112.0    2.1  0.52        233.0   \n",
       "745      MANIPUR  30.0  9.3  7.6         193.0    2.3  0.52        233.0   \n",
       "37   MAHARASHTRA  25.3  5.3  7.7       24062.0    9.9  1.20        156.0   \n",
       "88        KERALA  26.3  3.7  7.7       32005.0    1.2  0.90      40000.0   \n",
       "108       KERALA  30.0  5.6  7.2       24360.0    2.1  0.30         92.0   \n",
       "..           ...   ...  ...  ...           ...    ...   ...          ...   \n",
       "432       PUNJAB  23.3  5.5  7.2         636.0    9.7  4.00       1328.0   \n",
       "685       PUNJAB  21.0  5.5  7.4         635.0    8.8  5.08       1400.0   \n",
       "172    TAMILNADU  24.3  0.9  7.6        2039.0  104.5  0.90  272521616.0   \n",
       "432       PUNJAB  23.3  5.5  7.2         636.0    9.7  4.00       1328.0   \n",
       "685       PUNJAB  21.0  5.5  7.4         635.0    8.8  5.08       1400.0   \n",
       "\n",
       "         Tot_col    year  \n",
       "741         31.0  2012.0  \n",
       "745         41.0  2012.0  \n",
       "37         304.0  2014.0  \n",
       "88       60392.0  2014.0  \n",
       "108        447.0  2014.0  \n",
       "..           ...     ...  \n",
       "432       4975.0  2013.0  \n",
       "685       5500.0  2012.0  \n",
       "172  511090873.0  2014.0  \n",
       "432       4975.0  2013.0  \n",
       "685       5500.0  2012.0  \n",
       "\n",
       "[125 rows x 12 columns]"
      ]
     },
     "execution_count": 80,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_num_final_norm = zscore(df_num_final, axis=0)\n",
    "\n",
    "\n",
    "def indices_of_greater_than_3(df_norm):\n",
    "    indices_arr = []\n",
    "    n_col = df_norm.shape[1]\n",
    "    for index in range(n_col):\n",
    "        col_index = df_norm.iloc[: ,index]\n",
    "        greater_than_3 = df_norm[col_index > 3]\n",
    "        greater_than_3_index = greater_than_3.index\n",
    "        indices_arr.extend(greater_than_3_index)\n",
    "    return indices_arr\n",
    "\n",
    "indices_arr = indices_of_greater_than_3(df_num_final_norm)\n",
    "print(\"Number of outliers using Z-Score method-\",len(indices_arr))\n",
    "df_final.iloc[indices_arr, :]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "d0a8a2c0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1785, 12)"
      ]
     },
     "execution_count": 81,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_final.drop(indices_arr, axis=0, inplace=True)\n",
    "df_final.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "id": "6ff068e8",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Calculating Water Quality Index of each sample\n",
    "df_num_final = df_final.select_dtypes(exclude=\"object\")\n",
    "# Dropping year and Temp attribute because they are not used for computing WQI\n",
    "df_num_final.drop([\"year\", \"Temp\"], axis=1, inplace=True)\n",
    "\n",
    "# Weight Vector(wi)\n",
    "wi = np.array([0.2213, 0.2604, 0.0022, 0.4426, 0.0492, 0.0221, 0.0022])\n",
    "\n",
    "# Standard values of parameters(si)\n",
    "si = np.array([10, 8.5, 1000, 5, 45, 100, 1000])\n",
    "\n",
    "# Ideal values of paramters(vIdeal)\n",
    "vIdeal = np.array([14.6, 7, 0, 0, 0, 0, 0])\n",
    "\n",
    "def calc_wqi(sample): \n",
    "    wqi_sample = 0\n",
    "    num_col = 7\n",
    "    for index in range(num_col):\n",
    "        v_index = sample[index] # Obeserved value of sample at index\n",
    "        v_index_ideal = vIdeal[index] # Ideal value of obeserved value\n",
    "        w_index = wi[index] # weight of corresponding parameter of obeserved value\n",
    "        std_index = si[index] # Standard value recommended for obeserved value\n",
    "        q_index = (v_index - v_index_ideal) / (std_index - v_index_ideal)\n",
    "        q_index = q_index * 100 # Final qi value of obeserved value\n",
    "        wqi_sample += q_index*w_index\n",
    "    return wqi_sample"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "100ebda4",
   "metadata": {},
   "outputs": [],
   "source": [
    "def calc_wqi_for_df(df):\n",
    "    wqi_arr = []\n",
    "    for index in range(df.shape[0]):\n",
    "        index_row = df.iloc[index, :]\n",
    "        wqi_row = calc_wqi(index_row)\n",
    "        wqi_arr.append(wqi_row)\n",
    "    return wqi_arr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "id": "619c066f",
   "metadata": {},
   "outputs": [],
   "source": [
    "wqi_arr = calc_wqi_for_df(df_num_final)\n",
    "wqi_arr = np.array(wqi_arr)\n",
    "wqi_arr = np.reshape(wqi_arr, (-1, 1))\n",
    "wqi_arr_df = pd.DataFrame(wqi_arr, columns=[\"WQI\"]).reset_index()\n",
    "df_final = df_final.reset_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "id": "146b0a2d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1785, 13)"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_wqi = pd.concat([df_final, pd.DataFrame(wqi_arr, columns=[\"WQI\"])], axis=1)\n",
    "df_wqi.drop(\"index\", axis=1, inplace=True)\n",
    "df_wqi.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "id": "c6d4d3e5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STATION CODE</th>\n",
       "      <th>LOCATIONS</th>\n",
       "      <th>STATE</th>\n",
       "      <th>Temp</th>\n",
       "      <th>DO</th>\n",
       "      <th>PH</th>\n",
       "      <th>Conductivity</th>\n",
       "      <th>BOD</th>\n",
       "      <th>NI</th>\n",
       "      <th>Fec_col</th>\n",
       "      <th>Tot_col</th>\n",
       "      <th>year</th>\n",
       "      <th>WQI</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>196</th>\n",
       "      <td>3375</td>\n",
       "      <td>LUKHA RIVER AT MYNDIHATI (TRIBUTARY OF LUNAR)</td>\n",
       "      <td>MEGHALAYA</td>\n",
       "      <td>20.5</td>\n",
       "      <td>6.7</td>\n",
       "      <td>2.7</td>\n",
       "      <td>1350.0</td>\n",
       "      <td>3.3000</td>\n",
       "      <td>1.10</td>\n",
       "      <td>7.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>-6.855044</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>231</th>\n",
       "      <td>2</td>\n",
       "      <td>DAMANGANGA AT D/S OF MADHUBAN, DAMAN</td>\n",
       "      <td>DAMAN &amp; DIU</td>\n",
       "      <td>27.0</td>\n",
       "      <td>6.7</td>\n",
       "      <td>0.0</td>\n",
       "      <td>208.0</td>\n",
       "      <td>1.8965</td>\n",
       "      <td>0.52</td>\n",
       "      <td>233.0</td>\n",
       "      <td>465.0</td>\n",
       "      <td>2013.0</td>\n",
       "      <td>-61.372099</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>234</th>\n",
       "      <td>1865</td>\n",
       "      <td>RIVER DHADAR AT KOTHADA</td>\n",
       "      <td>GUJARAT</td>\n",
       "      <td>27.0</td>\n",
       "      <td>6.7</td>\n",
       "      <td>0.0</td>\n",
       "      <td>506.0</td>\n",
       "      <td>1.8965</td>\n",
       "      <td>6.00</td>\n",
       "      <td>26.0</td>\n",
       "      <td>227.0</td>\n",
       "      <td>2013.0</td>\n",
       "      <td>-65.334452</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>446</th>\n",
       "      <td>3375</td>\n",
       "      <td>LUKHA RIVER</td>\n",
       "      <td>MEGHALAYA</td>\n",
       "      <td>21.3</td>\n",
       "      <td>6.8</td>\n",
       "      <td>2.7</td>\n",
       "      <td>1074.0</td>\n",
       "      <td>3.2000</td>\n",
       "      <td>2.33</td>\n",
       "      <td>4.0</td>\n",
       "      <td>11.0</td>\n",
       "      <td>2013.0</td>\n",
       "      <td>-8.214971</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>719</th>\n",
       "      <td>3375</td>\n",
       "      <td>LUKHA RIVER AT MYNDIHATI (TRIBUTARY OF LUNAR)</td>\n",
       "      <td>MEGHALAYA</td>\n",
       "      <td>25.0</td>\n",
       "      <td>6.9</td>\n",
       "      <td>2.6</td>\n",
       "      <td>1072.0</td>\n",
       "      <td>3.2000</td>\n",
       "      <td>1.17</td>\n",
       "      <td>3.0</td>\n",
       "      <td>21.0</td>\n",
       "      <td>2012.0</td>\n",
       "      <td>-10.579224</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    STATION CODE                                      LOCATIONS        STATE  \\\n",
       "196         3375  LUKHA RIVER AT MYNDIHATI (TRIBUTARY OF LUNAR)    MEGHALAYA   \n",
       "231            2           DAMANGANGA AT D/S OF MADHUBAN, DAMAN  DAMAN & DIU   \n",
       "234         1865                        RIVER DHADAR AT KOTHADA      GUJARAT   \n",
       "446         3375                                    LUKHA RIVER    MEGHALAYA   \n",
       "719         3375  LUKHA RIVER AT MYNDIHATI (TRIBUTARY OF LUNAR)    MEGHALAYA   \n",
       "\n",
       "     Temp   DO   PH  Conductivity     BOD    NI  Fec_col  Tot_col    year  \\\n",
       "196  20.5  6.7  2.7        1350.0  3.3000  1.10      7.0     16.0  2014.0   \n",
       "231  27.0  6.7  0.0         208.0  1.8965  0.52    233.0    465.0  2013.0   \n",
       "234  27.0  6.7  0.0         506.0  1.8965  6.00     26.0    227.0  2013.0   \n",
       "446  21.3  6.8  2.7        1074.0  3.2000  2.33      4.0     11.0  2013.0   \n",
       "719  25.0  6.9  2.6        1072.0  3.2000  1.17      3.0     21.0  2012.0   \n",
       "\n",
       "           WQI  \n",
       "196  -6.855044  \n",
       "231 -61.372099  \n",
       "234 -65.334452  \n",
       "446  -8.214971  \n",
       "719 -10.579224  "
      ]
     },
     "execution_count": 86,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_wqi[(df_wqi[\"WQI\"] < 0)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "id": "f08e1f5a",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_neg_indices = df_wqi[(df_wqi[\"WQI\"] < 0)].index\n",
    "df_wqi.drop(df_neg_indices, axis=0, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "9e8cc91b",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_wqi[\"WQI clf\"] = df_wqi[\"WQI\"].apply(lambda x: (4 if (x <= 25)\n",
    "                                        else(3 if (26<=x<=50)\n",
    "                                        else(2 if (51<=x<=75)\n",
    "                                        else(2 if (76<=x<=100)\n",
    "                                        else 0)))))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "cc351c84",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STATION CODE</th>\n",
       "      <th>LOCATIONS</th>\n",
       "      <th>STATE</th>\n",
       "      <th>Temp</th>\n",
       "      <th>DO</th>\n",
       "      <th>PH</th>\n",
       "      <th>Conductivity</th>\n",
       "      <th>BOD</th>\n",
       "      <th>NI</th>\n",
       "      <th>Fec_col</th>\n",
       "      <th>Tot_col</th>\n",
       "      <th>year</th>\n",
       "      <th>WQI</th>\n",
       "      <th>WQI clf</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1780</th>\n",
       "      <td>1329</td>\n",
       "      <td>TAMBIRAPARANI AT RAIL BDG. NR. AMBASAMUDAM, TA...</td>\n",
       "      <td>TAMILNADU</td>\n",
       "      <td>27.0</td>\n",
       "      <td>7.4</td>\n",
       "      <td>7.00</td>\n",
       "      <td>88.5</td>\n",
       "      <td>0.977</td>\n",
       "      <td>0.186</td>\n",
       "      <td>27.0</td>\n",
       "      <td>105.0</td>\n",
       "      <td>2005.0</td>\n",
       "      <td>43.946271</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1781</th>\n",
       "      <td>1330</td>\n",
       "      <td>TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU</td>\n",
       "      <td>TAMILNADU</td>\n",
       "      <td>27.0</td>\n",
       "      <td>6.6</td>\n",
       "      <td>7.81</td>\n",
       "      <td>603.2</td>\n",
       "      <td>2.675</td>\n",
       "      <td>0.263</td>\n",
       "      <td>40.0</td>\n",
       "      <td>191.0</td>\n",
       "      <td>2005.0</td>\n",
       "      <td>77.315135</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1782</th>\n",
       "      <td>1450</td>\n",
       "      <td>PALAR AT VANIYAMBADI WATER SUPPLY HEAD WORK, T...</td>\n",
       "      <td>TAMILNADU</td>\n",
       "      <td>28.0</td>\n",
       "      <td>6.6</td>\n",
       "      <td>7.49</td>\n",
       "      <td>571.5</td>\n",
       "      <td>2.091</td>\n",
       "      <td>0.256</td>\n",
       "      <td>151.0</td>\n",
       "      <td>273.0</td>\n",
       "      <td>2005.0</td>\n",
       "      <td>69.053768</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1783</th>\n",
       "      <td>1403</td>\n",
       "      <td>GUMTI AT U/S SOUTH TRIPURA,TRIPURA</td>\n",
       "      <td>TRIPURA</td>\n",
       "      <td>28.0</td>\n",
       "      <td>5.4</td>\n",
       "      <td>7.16</td>\n",
       "      <td>75.8</td>\n",
       "      <td>2.092</td>\n",
       "      <td>0.520</td>\n",
       "      <td>404.0</td>\n",
       "      <td>513.0</td>\n",
       "      <td>2005.0</td>\n",
       "      <td>74.670773</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1784</th>\n",
       "      <td>1404</td>\n",
       "      <td>GUMTI AT D/S SOUTH TRIPURA, TRIPURA</td>\n",
       "      <td>TRIPURA</td>\n",
       "      <td>30.0</td>\n",
       "      <td>5.4</td>\n",
       "      <td>7.37</td>\n",
       "      <td>104.8</td>\n",
       "      <td>1.802</td>\n",
       "      <td>0.215</td>\n",
       "      <td>456.0</td>\n",
       "      <td>557.0</td>\n",
       "      <td>2005.0</td>\n",
       "      <td>76.881207</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     STATION CODE                                          LOCATIONS  \\\n",
       "1780         1329  TAMBIRAPARANI AT RAIL BDG. NR. AMBASAMUDAM, TA...   \n",
       "1781         1330            TAMBIRAPARANI AT ARUMUGANERI, TAMILNADU   \n",
       "1782         1450  PALAR AT VANIYAMBADI WATER SUPPLY HEAD WORK, T...   \n",
       "1783         1403                 GUMTI AT U/S SOUTH TRIPURA,TRIPURA   \n",
       "1784         1404                GUMTI AT D/S SOUTH TRIPURA, TRIPURA   \n",
       "\n",
       "          STATE  Temp   DO    PH  Conductivity    BOD     NI  Fec_col  \\\n",
       "1780  TAMILNADU  27.0  7.4  7.00          88.5  0.977  0.186     27.0   \n",
       "1781  TAMILNADU  27.0  6.6  7.81         603.2  2.675  0.263     40.0   \n",
       "1782  TAMILNADU  28.0  6.6  7.49         571.5  2.091  0.256    151.0   \n",
       "1783    TRIPURA  28.0  5.4  7.16          75.8  2.092  0.520    404.0   \n",
       "1784    TRIPURA  30.0  5.4  7.37         104.8  1.802  0.215    456.0   \n",
       "\n",
       "      Tot_col    year        WQI  WQI clf  \n",
       "1780    105.0  2005.0  43.946271        3  \n",
       "1781    191.0  2005.0  77.315135        2  \n",
       "1782    273.0  2005.0  69.053768        2  \n",
       "1783    513.0  2005.0  74.670773        2  \n",
       "1784    557.0  2005.0  76.881207        2  "
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_wqi.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "e6ad4c26",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Temp</th>\n",
       "      <th>DO</th>\n",
       "      <th>PH</th>\n",
       "      <th>Conductivity</th>\n",
       "      <th>BOD</th>\n",
       "      <th>NI</th>\n",
       "      <th>Fec_col</th>\n",
       "      <th>Tot_col</th>\n",
       "      <th>year</th>\n",
       "      <th>WQI</th>\n",
       "      <th>WQI clf</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>26.241931</td>\n",
       "      <td>6.432263</td>\n",
       "      <td>7.228045</td>\n",
       "      <td>1006.325691</td>\n",
       "      <td>3.961788</td>\n",
       "      <td>1.119716</td>\n",
       "      <td>2264.420646</td>\n",
       "      <td>7242.598876</td>\n",
       "      <td>2010.461798</td>\n",
       "      <td>130.303409</td>\n",
       "      <td>1.668539</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>3.231044</td>\n",
       "      <td>1.258875</td>\n",
       "      <td>0.582761</td>\n",
       "      <td>2764.600752</td>\n",
       "      <td>7.130494</td>\n",
       "      <td>1.629483</td>\n",
       "      <td>8259.474360</td>\n",
       "      <td>40230.193629</td>\n",
       "      <td>2.869114</td>\n",
       "      <td>222.261326</td>\n",
       "      <td>1.024280</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>10.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.900000</td>\n",
       "      <td>11.000000</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2005.000000</td>\n",
       "      <td>16.795814</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>25.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>6.900000</td>\n",
       "      <td>83.000000</td>\n",
       "      <td>1.100000</td>\n",
       "      <td>0.263000</td>\n",
       "      <td>46.000000</td>\n",
       "      <td>108.750000</td>\n",
       "      <td>2008.000000</td>\n",
       "      <td>54.641036</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>27.000000</td>\n",
       "      <td>6.700000</td>\n",
       "      <td>7.224500</td>\n",
       "      <td>183.000000</td>\n",
       "      <td>1.800000</td>\n",
       "      <td>0.520000</td>\n",
       "      <td>233.000000</td>\n",
       "      <td>465.000000</td>\n",
       "      <td>2011.000000</td>\n",
       "      <td>69.840286</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>28.200000</td>\n",
       "      <td>7.200000</td>\n",
       "      <td>7.600000</td>\n",
       "      <td>489.250000</td>\n",
       "      <td>3.400000</td>\n",
       "      <td>1.100000</td>\n",
       "      <td>672.500000</td>\n",
       "      <td>1650.000000</td>\n",
       "      <td>2013.000000</td>\n",
       "      <td>94.348696</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>35.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>9.010000</td>\n",
       "      <td>18569.000000</td>\n",
       "      <td>88.000000</td>\n",
       "      <td>13.200000</td>\n",
       "      <td>150250.000000</td>\n",
       "      <td>967500.000000</td>\n",
       "      <td>2023.000000</td>\n",
       "      <td>3524.421534</td>\n",
       "      <td>4.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              Temp           DO           PH  Conductivity          BOD  \\\n",
       "count  1780.000000  1780.000000  1780.000000   1780.000000  1780.000000   \n",
       "mean     26.241931     6.432263     7.228045   1006.325691     3.961788   \n",
       "std       3.231044     1.258875     0.582761   2764.600752     7.130494   \n",
       "min      10.000000     0.000000     2.900000     11.000000     0.100000   \n",
       "25%      25.000000     6.000000     6.900000     83.000000     1.100000   \n",
       "50%      27.000000     6.700000     7.224500    183.000000     1.800000   \n",
       "75%      28.200000     7.200000     7.600000    489.250000     3.400000   \n",
       "max      35.000000    10.000000     9.010000  18569.000000    88.000000   \n",
       "\n",
       "                NI        Fec_col        Tot_col         year          WQI  \\\n",
       "count  1780.000000    1780.000000    1780.000000  1780.000000  1780.000000   \n",
       "mean      1.119716    2264.420646    7242.598876  2010.461798   130.303409   \n",
       "std       1.629483    8259.474360   40230.193629     2.869114   222.261326   \n",
       "min       0.000000       0.000000       0.000000  2005.000000    16.795814   \n",
       "25%       0.263000      46.000000     108.750000  2008.000000    54.641036   \n",
       "50%       0.520000     233.000000     465.000000  2011.000000    69.840286   \n",
       "75%       1.100000     672.500000    1650.000000  2013.000000    94.348696   \n",
       "max      13.200000  150250.000000  967500.000000  2023.000000  3524.421534   \n",
       "\n",
       "           WQI clf  \n",
       "count  1780.000000  \n",
       "mean      1.668539  \n",
       "std       1.024280  \n",
       "min       0.000000  \n",
       "25%       2.000000  \n",
       "50%       2.000000  \n",
       "75%       2.000000  \n",
       "max       4.000000  "
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_wqi.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "id": "c1561861",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Temp</th>\n",
       "      <th>DO</th>\n",
       "      <th>PH</th>\n",
       "      <th>Conductivity</th>\n",
       "      <th>BOD</th>\n",
       "      <th>NI</th>\n",
       "      <th>Fec_col</th>\n",
       "      <th>Tot_col</th>\n",
       "      <th>year</th>\n",
       "      <th>WQI</th>\n",
       "      <th>WQI clf</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>26.241931</td>\n",
       "      <td>6.432263</td>\n",
       "      <td>7.228045</td>\n",
       "      <td>1006.325691</td>\n",
       "      <td>3.961788</td>\n",
       "      <td>1.119716</td>\n",
       "      <td>2264.420646</td>\n",
       "      <td>7242.598876</td>\n",
       "      <td>2010.461798</td>\n",
       "      <td>130.303409</td>\n",
       "      <td>1.668539</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>3.231044</td>\n",
       "      <td>1.258875</td>\n",
       "      <td>0.582761</td>\n",
       "      <td>2764.600752</td>\n",
       "      <td>7.130494</td>\n",
       "      <td>1.629483</td>\n",
       "      <td>8259.474360</td>\n",
       "      <td>40230.193629</td>\n",
       "      <td>2.869114</td>\n",
       "      <td>222.261326</td>\n",
       "      <td>1.024280</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>10.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.900000</td>\n",
       "      <td>11.000000</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2005.000000</td>\n",
       "      <td>16.795814</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>25.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>6.900000</td>\n",
       "      <td>83.000000</td>\n",
       "      <td>1.100000</td>\n",
       "      <td>0.263000</td>\n",
       "      <td>46.000000</td>\n",
       "      <td>108.750000</td>\n",
       "      <td>2008.000000</td>\n",
       "      <td>54.641036</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>27.000000</td>\n",
       "      <td>6.700000</td>\n",
       "      <td>7.224500</td>\n",
       "      <td>183.000000</td>\n",
       "      <td>1.800000</td>\n",
       "      <td>0.520000</td>\n",
       "      <td>233.000000</td>\n",
       "      <td>465.000000</td>\n",
       "      <td>2011.000000</td>\n",
       "      <td>69.840286</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>28.200000</td>\n",
       "      <td>7.200000</td>\n",
       "      <td>7.600000</td>\n",
       "      <td>489.250000</td>\n",
       "      <td>3.400000</td>\n",
       "      <td>1.100000</td>\n",
       "      <td>672.500000</td>\n",
       "      <td>1650.000000</td>\n",
       "      <td>2013.000000</td>\n",
       "      <td>94.348696</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>35.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>9.010000</td>\n",
       "      <td>18569.000000</td>\n",
       "      <td>88.000000</td>\n",
       "      <td>13.200000</td>\n",
       "      <td>150250.000000</td>\n",
       "      <td>967500.000000</td>\n",
       "      <td>2023.000000</td>\n",
       "      <td>3524.421534</td>\n",
       "      <td>4.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              Temp           DO           PH  Conductivity          BOD  \\\n",
       "count  1780.000000  1780.000000  1780.000000   1780.000000  1780.000000   \n",
       "mean     26.241931     6.432263     7.228045   1006.325691     3.961788   \n",
       "std       3.231044     1.258875     0.582761   2764.600752     7.130494   \n",
       "min      10.000000     0.000000     2.900000     11.000000     0.100000   \n",
       "25%      25.000000     6.000000     6.900000     83.000000     1.100000   \n",
       "50%      27.000000     6.700000     7.224500    183.000000     1.800000   \n",
       "75%      28.200000     7.200000     7.600000    489.250000     3.400000   \n",
       "max      35.000000    10.000000     9.010000  18569.000000    88.000000   \n",
       "\n",
       "                NI        Fec_col        Tot_col         year          WQI  \\\n",
       "count  1780.000000    1780.000000    1780.000000  1780.000000  1780.000000   \n",
       "mean      1.119716    2264.420646    7242.598876  2010.461798   130.303409   \n",
       "std       1.629483    8259.474360   40230.193629     2.869114   222.261326   \n",
       "min       0.000000       0.000000       0.000000  2005.000000    16.795814   \n",
       "25%       0.263000      46.000000     108.750000  2008.000000    54.641036   \n",
       "50%       0.520000     233.000000     465.000000  2011.000000    69.840286   \n",
       "75%       1.100000     672.500000    1650.000000  2013.000000    94.348696   \n",
       "max      13.200000  150250.000000  967500.000000  2023.000000  3524.421534   \n",
       "\n",
       "           WQI clf  \n",
       "count  1780.000000  \n",
       "mean      1.668539  \n",
       "std       1.024280  \n",
       "min       0.000000  \n",
       "25%       2.000000  \n",
       "50%       2.000000  \n",
       "75%       2.000000  \n",
       "max       4.000000  "
      ]
     },
     "execution_count": 92,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_wqi.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "id": "5d3da55a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Temp</th>\n",
       "      <th>DO</th>\n",
       "      <th>PH</th>\n",
       "      <th>Conductivity</th>\n",
       "      <th>BOD</th>\n",
       "      <th>NI</th>\n",
       "      <th>Fec_col</th>\n",
       "      <th>Tot_col</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "      <td>1780.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>26.241931</td>\n",
       "      <td>6.432263</td>\n",
       "      <td>7.228045</td>\n",
       "      <td>1006.325691</td>\n",
       "      <td>3.961788</td>\n",
       "      <td>1.119716</td>\n",
       "      <td>2264.420646</td>\n",
       "      <td>7242.598876</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>3.231044</td>\n",
       "      <td>1.258875</td>\n",
       "      <td>0.582761</td>\n",
       "      <td>2764.600752</td>\n",
       "      <td>7.130494</td>\n",
       "      <td>1.629483</td>\n",
       "      <td>8259.474360</td>\n",
       "      <td>40230.193629</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>10.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.900000</td>\n",
       "      <td>11.000000</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>25.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>6.900000</td>\n",
       "      <td>83.000000</td>\n",
       "      <td>1.100000</td>\n",
       "      <td>0.263000</td>\n",
       "      <td>46.000000</td>\n",
       "      <td>108.750000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>27.000000</td>\n",
       "      <td>6.700000</td>\n",
       "      <td>7.224500</td>\n",
       "      <td>183.000000</td>\n",
       "      <td>1.800000</td>\n",
       "      <td>0.520000</td>\n",
       "      <td>233.000000</td>\n",
       "      <td>465.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>28.200000</td>\n",
       "      <td>7.200000</td>\n",
       "      <td>7.600000</td>\n",
       "      <td>489.250000</td>\n",
       "      <td>3.400000</td>\n",
       "      <td>1.100000</td>\n",
       "      <td>672.500000</td>\n",
       "      <td>1650.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>35.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>9.010000</td>\n",
       "      <td>18569.000000</td>\n",
       "      <td>88.000000</td>\n",
       "      <td>13.200000</td>\n",
       "      <td>150250.000000</td>\n",
       "      <td>967500.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              Temp           DO           PH  Conductivity          BOD  \\\n",
       "count  1780.000000  1780.000000  1780.000000   1780.000000  1780.000000   \n",
       "mean     26.241931     6.432263     7.228045   1006.325691     3.961788   \n",
       "std       3.231044     1.258875     0.582761   2764.600752     7.130494   \n",
       "min      10.000000     0.000000     2.900000     11.000000     0.100000   \n",
       "25%      25.000000     6.000000     6.900000     83.000000     1.100000   \n",
       "50%      27.000000     6.700000     7.224500    183.000000     1.800000   \n",
       "75%      28.200000     7.200000     7.600000    489.250000     3.400000   \n",
       "max      35.000000    10.000000     9.010000  18569.000000    88.000000   \n",
       "\n",
       "                NI        Fec_col        Tot_col  \n",
       "count  1780.000000    1780.000000    1780.000000  \n",
       "mean      1.119716    2264.420646    7242.598876  \n",
       "std       1.629483    8259.474360   40230.193629  \n",
       "min       0.000000       0.000000       0.000000  \n",
       "25%       0.263000      46.000000     108.750000  \n",
       "50%       0.520000     233.000000     465.000000  \n",
       "75%       1.100000     672.500000    1650.000000  \n",
       "max      13.200000  150250.000000  967500.000000  "
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "features = list(df_wqi.columns)[3:11]\n",
    "data_f = df_wqi[features]\n",
    "data_f.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "id": "c444c142",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    1780.000000\n",
       "mean        1.668539\n",
       "std         1.024280\n",
       "min         0.000000\n",
       "25%         2.000000\n",
       "50%         2.000000\n",
       "75%         2.000000\n",
       "max         4.000000\n",
       "Name: WQI clf, dtype: float64"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "features = list(df_wqi.columns)[:]\n",
    "data_cluster = df_wqi['WQI clf']\n",
    "data_cluster.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "18044839",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}