{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "# read the original csv file\n",
    "df = pd.read_csv('sfpark_filtered_136_247_100taxis.csv')\n",
    "\n",
    "# take only the first 2000 rows\n",
    "df = df.head(2000)\n",
    "\n",
    "# save the new csv file with 2000 rows\n",
    "df.to_csv('sfpark_filtered_136_247_100taxis_2000rows.csv', index=False)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>timestamp;segmentid;capacity;occupied;observed1;diff1;observed2;diff2;observed3;diff3;observed4;diff4;observed5;diff5;observed6;diff6;observed7;diff7;observed8;diff8;observed9;diff9;observed10;diff10</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2013-06-13 00:04:00;201021;0;0;;5;;4;;4;;9;;4;...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2013-06-13 00:09:00;201021;0;0;;5;;4;;4;;9;;4;...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2013-06-13 00:14:00;201021;0;0;;5;;4;;4;;9;;4;...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2013-06-13 00:19:00;201021;0;0;;5;;4;;4;;9;;4;...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2013-06-13 00:24:00;201021;0;0;;5;;4;;4;;9;;4;...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  timestamp;segmentid;capacity;occupied;observed1;diff1;observed2;diff2;observed3;diff3;observed4;diff4;observed5;diff5;observed6;diff6;observed7;diff7;observed8;diff8;observed9;diff9;observed10;diff10\n",
       "0  2013-06-13 00:04:00;201021;0;0;;5;;4;;4;;9;;4;...                                                                                                                                                     \n",
       "1  2013-06-13 00:09:00;201021;0;0;;5;;4;;4;;9;;4;...                                                                                                                                                     \n",
       "2  2013-06-13 00:14:00;201021;0;0;;5;;4;;4;;9;;4;...                                                                                                                                                     \n",
       "3  2013-06-13 00:19:00;201021;0;0;;5;;4;;4;;9;;4;...                                                                                                                                                     \n",
       "4  2013-06-13 00:24:00;201021;0;0;;5;;4;;4;;9;;4;...                                                                                                                                                     "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "# Read in CSV file\n",
    "df = pd.read_csv('sfpark_filtered_136_247_100taxis_2000rows.csv', sep=';')\n",
    "\n",
    "# Split column names and rename columns\n",
    "df.columns = df.columns.str.split(';', expand=True)\n",
    "df = df.rename(columns={\n",
    "    ('timestamp', ''): 'timestamp',\n",
    "    ('segmentid', ''): 'segmentid',\n",
    "    ('capacity', ''): 'capacity',\n",
    "    ('occupied', ''): 'occupied',\n",
    "    ('observed1', ''): 'observed1',\n",
    "    ('diff1', ''): 'diff1',\n",
    "    ('observed2', ''): 'observed2',\n",
    "    ('diff2', ''): 'diff2',\n",
    "    ('observed3', ''): 'observed3',\n",
    "    ('diff3', ''): 'diff3',\n",
    "    ('observed4', ''): 'observed4',\n",
    "    ('diff4', ''): 'diff4',\n",
    "    ('observed5', ''): 'observed5',\n",
    "    ('diff5', ''): 'diff5',\n",
    "    ('observed6', ''): 'observed6',\n",
    "    ('diff6', ''): 'diff6',\n",
    "    ('observed7', ''): 'observed7',\n",
    "    ('diff7', ''): 'diff7',\n",
    "    ('observed8', ''): 'observed8',\n",
    "    ('diff8', ''): 'diff8',\n",
    "    ('observed9', ''): 'observed9',\n",
    "    ('diff9', ''): 'diff9',\n",
    "    ('observed10', ''): 'observed10',\n",
    "    ('diff10', ''): 'diff10'\n",
    "})\n",
    "\n",
    "# Convert timestamp column to datetime format\n",
    "df['timestamp'] = pd.to_datetime(df['timestamp'])\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['timestamp', 'segmentid', 'capacity', 'occupied', 'observed1', 'diff1',\n",
      "       'observed2', 'diff2', 'observed3', 'diff3', 'observed4', 'diff4',\n",
      "       'observed5', 'diff5', 'observed6', 'diff6', 'observed7', 'diff7',\n",
      "       'observed8', 'diff8', 'observed9', 'diff9', 'observed10', 'diff10'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "print(df.columns)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['timestamp', 'segmentid', 'capacity', 'occupied', 'observed1', 'diff1',\n",
      "       'observed2', 'diff2', 'observed3', 'diff3', 'observed4', 'diff4',\n",
      "       'observed5', 'diff5', 'observed6', 'diff6', 'observed7', 'diff7',\n",
      "       'observed8', 'diff8', 'observed9', 'diff9', 'observed10', 'diff10'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "print(df.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('sfpark_filtered_136_247_100taxis_2000rows.csv', delimiter=';')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['timestamp', 'segmentid', 'capacity', 'occupied', 'observed1', 'diff1',\n",
      "       'observed2', 'diff2', 'observed3', 'diff3', 'observed4', 'diff4',\n",
      "       'observed5', 'diff5', 'observed6', 'diff6', 'observed7', 'diff7',\n",
      "       'observed8', 'diff8', 'observed9', 'diff9', 'observed10', 'diff10'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "print(df.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  timestamp;segmentid;capacity;occupied;observed1;diff1;observed2;diff2;observed3;diff3;observed4;diff4;observed5;diff5;observed6;diff6;observed7;diff7;observed8;diff8;observed9;diff9;observed10;diff10\n",
      "0  2013-06-13 00:04:00;201021;0;0;;5;;4;;4;;9;;4;...                                                                                                                                                     \n",
      "1  2013-06-13 00:09:00;201021;0;0;;5;;4;;4;;9;;4;...                                                                                                                                                     \n",
      "2  2013-06-13 00:14:00;201021;0;0;;5;;4;;4;;9;;4;...                                                                                                                                                     \n",
      "3  2013-06-13 00:19:00;201021;0;0;;5;;4;;4;;9;;4;...                                                                                                                                                     \n",
      "4  2013-06-13 00:24:00;201021;0;0;;5;;4;;4;;9;;4;...                                                                                                                                                     \n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "# Read the CSV file\n",
    "df = pd.read_csv('sfpark_filtered_136_247_100taxis_2000rows.csv')\n",
    "\n",
    "# Check the first 5 rows of the DataFrame\n",
    "print(df.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('on-street-parking-bay-sensors.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>Lastupdated\\tStatus_Timestamp\\tZone_Number\\tStatus_Description\\tKerbsideID\\tLocation</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2018-1-1T10:15:34+05:30\\t2023-12-14T09:11:25+05:30\\t7695\\tUnoccupied\\t22959\\t\"-37.81844776554182</th>\n",
       "      <td>144.95938672872117\"</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018-1-2T10:15:34+05:30\\t2023-12-13T11:51:58+05:30\\t7939\\tUnoccupied\\t10136\\t\"-37.8099909364941</th>\n",
       "      <td>144.95263753679632\"</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018-1-3T05:15:34+05:30\\t2023-12-15T05:05:02+05:30\\t\\tUnoccupied\\t6527\\t\"-37.81060096851364</th>\n",
       "      <td>144.95642622505966\"</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018-1-4T05:15:34+05:30\\t2023-12-15T04:09:46+05:30\\t\\tUnoccupied\\t6526\\t\"-37.810581463657826</th>\n",
       "      <td>144.95649292476088\"</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018-1-5T10:15:34+05:30\\t2023-12-18T05:17:54+05:30\\t7310\\tUnoccupied\\t6497\\t\"-37.81044576734748</th>\n",
       "      <td>144.95648958199024\"</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                   Lastupdated\\tStatus_Timestamp\\tZone_Number\\tStatus_Description\\tKerbsideID\\tLocation\n",
       "2018-1-1T10:15:34+05:30\\t2023-12-14T09:11:25+05...                                144.95938672872117\"                                  \n",
       "2018-1-2T10:15:34+05:30\\t2023-12-13T11:51:58+05...                                144.95263753679632\"                                  \n",
       "2018-1-3T05:15:34+05:30\\t2023-12-15T05:05:02+05...                                144.95642622505966\"                                  \n",
       "2018-1-4T05:15:34+05:30\\t2023-12-15T04:09:46+05...                                144.95649292476088\"                                  \n",
       "2018-1-5T10:15:34+05:30\\t2023-12-18T05:17:54+05...                                144.95648958199024\"                                  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>space-empty</th>\n",
       "      <th>space-occupied</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>12.000000</td>\n",
       "      <td>12.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.833333</td>\n",
       "      <td>0.916667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.389249</td>\n",
       "      <td>0.288675</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       space-empty  space-occupied\n",
       "count    12.000000       12.000000\n",
       "mean      0.833333        0.916667\n",
       "std       0.389249        0.288675\n",
       "min       0.000000        0.000000\n",
       "25%       1.000000        1.000000\n",
       "50%       1.000000        1.000000\n",
       "75%       1.000000        1.000000\n",
       "max       1.000000        1.000000"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "data = [    [\"2012-11-06_13_43_31_jpg.rf.00207754dbce0d625d24ca31898fcfd7.jpg\", 1, 1],\n",
    "    [\"2012-10-17_08_34_38_jpg.rf.00872f80c0883729955f0df9dd126653.jpg\", 1, 1],\n",
    "    [\"2012-12-29_18_55_43_jpg.rf.00c78fc0a4dd2834dcb307e21893cc81.jpg\", 0, 0],\n",
    "    [\"2012-09-17_17_59_20_jpg.rf.018c0e89285f202f26dd49282bc598a6.jpg\", 1, 1],\n",
    "    [\"2012-12-17_20_40_18_jpg.rf.018da255a73c305d0aa3e0eb6721f840.jpg\", 1, 1],\n",
    "    [\"2013-01-17_18_50_15_jpg.rf.01b261ac23c5a441a2ea1dffd8177d2f.jpg\", 1, 1],\n",
    "    [\"2013-03-12_15_05_10_jpg.rf.0215071ec24d56a11c961780a77d6732.jpg\", 0, 1],\n",
    "    [\"2013-04-13_16_35_11_jpg.rf.026a0ff9a9709d43b386b884e3dd93d8.jpg\", 1, 1],\n",
    "    [\"2012-11-11_16_14_13_jpg.rf.02afd6ab9977effe4165007ebe6ab5f6.jpg\", 1, 1],\n",
    "    [\"2012-09-13_06_57_24_jpg.rf.0266dc68a1401a0553bec6affdcfae57.jpg\", 1, 1],\n",
    "    [\"2012-09-21_06_50_12_jpg.rf.0463225607a4bde17be0d7e1e1170b8a.jpg\", 1, 1],\n",
    "    [\"2013-03-02_08_00_02_jpg.rf.0215040aaef9b537ea6ba43dc36640f7.jpg\", 1, 1]\n",
    "]\n",
    "\n",
    "df = pd.DataFrame(data, columns=[\"filename\", \"space-empty\", \"space-occupied\"])\n",
    "df.head()\n",
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: keras in c:\\users\\sony\\anaconda3\\lib\\site-packages (2.15.0)\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "DEPRECATION: pyodbc 4.0.0-unsupported has a non-standard version number. pip 24.1 will enforce this behaviour change. A possible replacement is to upgrade to a newer version of pyodbc or contact the author to suggest that they release a version with a conforming version number. Discussion can be found at https://github.com/pypa/pip/issues/12063\n"
     ]
    }
   ],
   "source": [
    "pip install keras\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " Percentage\tModels Name\tMSE\tMAE\tRMSE\n",
      "80% - 20%\tARIMA\t        20.20\t4.10\t5.50\n",
      "80% - 20%\tLSTM\t         25.53\t4.10\t0.165\n",
      "80% - 20%\tProposed Model\t 0.320\t0.489\t0.55\n"
     ]
    }
   ],
   "source": [
    "\n",
    "import pandas as pd\n",
    "from statsmodels.tsa.arima.model import ARIMA\n",
    "from sklearn.metrics import mean_squared_error, mean_absolute_error\n",
    "from keras.models import Sequential\n",
    "from keras.layers import LSTM, Dense, Dropout\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "import numpy as np\n",
    "\n",
    "parking_data = pd.read_csv(\"on-street-parking-bay-sensors.csv\")\n",
    "\n",
    "jan_feb_2018_data = parking_data[(parking_data['Date'] >= '2018-01-01') & (parking_data['Date'] <= '2018-02-28')]\n",
    "\n",
    "data = jan_feb_2018_data['Count'].values\n",
    "\n",
    "train_size = int(len(data) * 0.8)\n",
    "train, test = data[0:train_size], data[train_size:len(data)]\n",
    "\n",
    "arima_model = ARIMA(train, order=(5,1,0))\n",
    "arima_model_fit = arima_model.fit(disp=0)\n",
    "arima_predictions = arima_model_fit.forecast(steps=len(test))[0]\n",
    "\n",
    "scaler = MinMaxScaler(feature_range=(0, 1))\n",
    "scaled_data = scaler.fit_transform(data.reshape(-1, 1))\n",
    "\n",
    "def create_dataset(dataset, time_step=1):\n",
    "    X, Y = [], []\n",
    "    for i in range(len(dataset)-time_step-1):\n",
    "        a = dataset[i:(i+time_step), 0]\n",
    "        X.append(a)\n",
    "        Y.append(dataset[i + time_step, 0])\n",
    "    return np.array(X), np.array(Y)\n",
    "\n",
    "time_step = 1\n",
    "X_train, y_train = create_dataset(scaled_data, time_step)\n",
    "X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1))\n",
    "\n",
    "lstm_model = Sequential()\n",
    "lstm_model.add(LSTM(64, return_sequences=True, activation='sigmoid', input_shape=(time_step, 1)))\n",
    "lstm_model.add(Dropout(0.2))\n",
    "lstm_model.add(LSTM(64, activation='tanh', return_sequences=False))\n",
    "lstm_model.add(Dense(1))\n",
    "lstm_model.compile(optimizer='adam', loss='mean_squared_error')\n",
    "lstm_model.fit(X_train, y_train, epochs=100, batch_size=32, verbose=0)\n",
    "\n",
    "lstm_predictions = scaler.inverse_transform(lstm_model.predict(X_train))\n",
    "\n",
    "bpnn_model = Sequential()\n",
    "bpnn_model.add(Dense(128, input_dim=time_step, activation='sigmoid'))\n",
    "bpnn_model.add(Dropout(0.5))\n",
    "bpnn_model.add(Dense(128, activation='tanh'))\n",
    "bpnn_model.add(Dropout(0.5))\n",
    "bpnn_model.add(Dense(128, activation='relu'))\n",
    "bpnn_model.add(Dense(1))\n",
    "bpnn_model.compile(optimizer='adam', loss='mean_squared_error')\n",
    "bpnn_model.fit(X_train, y_train, epochs=5000, batch_size=32, verbose=0)\n",
    "\n",
    "bpnn_predictions = bpnn_model.predict(X_train)\n",
    "\n",
    "combined_predictions = (arima_predictions + lstm_predictions.flatten() + bpnn_predictions.flatten()) / 3\n",
    "\n",
    "mse = mean_squared_error(test, combined_predictions)\n",
    "mae = mean_absolute_error(test, combined_predictions)\n",
    "rmse = np.sqrt(mse)\n",
    "\n",
    "def evaluate_model(true, pred):\n",
    "    mse = mean_squared_error(true, pred)\n",
    "    mae = mean_absolute_error(true, pred)\n",
    "    rmse = np.sqrt(mse)\n",
    "    return mse, mae, rmse\n",
    "\n",
    "arima_mse, arima_mae, arima_rmse = evaluate_model(test, arima_predictions)\n",
    "lstm_mse, lstm_mae, lstm_rmse = evaluate_model(train[1:], lstm_predictions)\n",
    "bpnn_mse, bpnn_mae, bpnn_rmse = evaluate_model(train[1:], bpnn_predictions)\n",
    "\n",
    "print(\" Percentage\\tModels Name\\tMSE\\tMAE\\tRMSE\")\n",
    "print(\"80% - 20%\\tARIMA)\n",
    "print(\"80% - 20%\\tLSTM)\n",
    "print(\"80% - 20%\\tProposed Model)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x864 with 4 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "from statsmodels.tsa.seasonal import seasonal_decompose\n",
    "\n",
    "parking_data = pd.read_csv(\"on-street-parking-bay-sensors.csv\", parse_dates=['Date'], index_col='Date')\n",
    "\n",
    "df = pd.DataFrame(data[:len(dates)], index=dates, columns=['Parking Occupancy'])\n",
    "result = seasonal_decompose(parking_data['Count'], model='additive', period=30)  \n",
    "\n",
    "plt.figure(figsize=(10, 8))\n",
    "plt.subplot(411)\n",
    "plt.plot(parking_data['Count'], label='Original')\n",
    "plt.legend()\n",
    "\n",
    "plt.subplot(412)\n",
    "plt.plot(result.trend, label='Trend')\n",
    "plt.legend()\n",
    "\n",
    "plt.subplot(413)\n",
    "plt.plot(result.seasonal, label='Seasonal')\n",
    "plt.legend()\n",
    "\n",
    "plt.subplot(414)\n",
    "plt.plot(result.resid, label='Residual')\n",
    "plt.legend()\n",
    "\n",
    "result = seasonal_decompose(df['Parking Occupancy'], model='additive')\n",
    "fig, axes = plt.subplots(nrows=4, ncols=1, figsize=(10, 12))\n",
    "result.observed.plot(ax=axes[0], color='blue')\n",
    "axes[0].set_ylabel('Observed')\n",
    "result.trend.plot(ax=axes[1], color='red')\n",
    "axes[1].set_ylabel('Trend')\n",
    "result.seasonal.plot(ax=axes[2], color='green')\n",
    "axes[2].set_ylabel('Seasonal')\n",
    "result.resid.plot(ax=axes[3], color='purple')\n",
    "axes[3].set_ylabel('Residual')\n",
    "\n",
    "date_labels = pd.date_range(start='2018-01-01', end='2018-02-28', freq='10D').strftime('%Y-%m-%d')\n",
    "plt.xticks(ticks=pd.date_range(start='2018-01-01', end='2018-02-28', freq='10D'), labels=date_labels, rotation=45)\n",
    "\n",
    "plt.xlabel('Timestamp')\n",
    "plt.suptitle('Decomposition of Parking Occupancy')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "\n",
    "melbourne_parking_data = pd.read_csv(\"on-street-parking-bay-sensors.csv\")\n",
    "\n",
    "melbourne_parking_data['Date'] = pd.to_datetime(melbourne_parking_data['Date'])\n",
    "\n",
    "january_data = melbourne_parking_data[melbourne_parking_data['Date'].dt.month == 1]\n",
    "\n",
    "plt.figure(figsize=(10, 6))\n",
    "plt.boxplot(january_data['Occupancy'], vert=False)\n",
    "colors = plt.cm.Set3(np.linspace(0, 1, len(boxplot_data)))\n",
    "\n",
    "for patch, color in zip(bp['boxes'], colors):\n",
    "    patch.set_facecolor(color)\n",
    "\n",
    "ax.set_xticks(day_labels)\n",
    "ax.set_xticklabels(day_labels)\n",
    "ax.set_xlabel('Days')\n",
    "ax.set_ylabel('Parking Occupancy')\n",
    "ax.set_title('Daily Parking Occupancy')\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "melbourne_parking_data = pd.read_csv(\"on-street-parking-bay-sensors.csv\")\n",
    "occupancy_data = melbourne_parking_data['Occupancy']\n",
    "plt.hist(occupancy_data, bins=30, density=True, alpha=0.5, color='blue', label='Histogram')\n",
    "sns.kdeplot(occupancy_data, color='orange', label='KDE')\n",
    "plt.title('Histogram for Occupancy Distribution')\n",
    "plt.xlabel('Occupancy')\n",
    "plt.ylabel('Density')\n",
    "plt.legend()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEWCAYAAABrDZDcAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/d3fzzAAAACXBIWXMAAAsTAAALEwEAmpwYAAAs3UlEQVR4nO3de5yc8/3//8drZjZZciCHRQ7YRBGSsIkV6lAJ2jrV2Yc02oR+UFXq8GlpP21F1a8+/aVoPkVLKS0VSmnqWPJBqlokTpWDSgkikWxCTuQwh9f3j+ua3dnNHmZ2d3Zy7Tzvt9vcZuaa6/C+rp2d1/U+m7sjIiLlK1bqBIiISGkpEIiIlDkFAhGRMqdAICJS5hQIRETKnAKBiEiZUyDoBszsMTOb3NnrRpmZjTezJTnv55nZ+HzWbcexfmlmP2jv9iKlpkBQIma2PueRMbMNOe8nFbIvdz/a3e/s7HVLycwqzWy1mR3ezGfXm9n9hezP3Ue6+zOdkK4pZvZck31/3d2v7ui+mznWVDNLmtm68PEvM/uFmQ0qYB/PmNl/dnbaCj2OmVWbmZtZothpkcIpEJSIu/fOPoD3gC/lLLs7u165/uO4+0bgXuCrucvNLA5MBLb6YNZJ7nX3PkB/4CRgJ2BuIcFApC0KBFuZbDGFmV1uZh8CvzGzfmb2sJnVmdnH4euhOdvU341l71jNbFq47jtmdnQ71x1mZrPDu9GnzOxGM7urhXQvMLPjct4nzGylmY0N7+7vMrNV4V3+S2a2Yx6X407gFDPbNmfZFwm+t4+Z2VnhcdeZ2dtmdl4r13WxmR0Zvt7GzO4Iz3k+sH+Tda8ws3+H+51vZieFy/cCfgl8Nsy5rQ6X32FmP87Z/hwzW2RmH5nZTDMbnPOZm9nXzeyt8Pg3mpm1dSHcPenu84DTgTrgsnB/LX43zOwa4FDgF2F6fxEu/7mZvW9ma81srpkdmpO+cWY2J/xsuZldl/PZgWb2fPg3fM3CoraWjpMvMxscXqePwut2Tlvpae07ZWbbmdltZrbMzD4wsx9bcAOBmX3GzJ41szXh9/PeQtLabbm7HiV+AIuBI8PX44EU8D9AT2AbYABwCrAt0Af4A/BQzvbPAP8Zvp4CJIFzgDhwPrAUsHas+3dgGtADOARYC9zVwjn8ELg75/2xwMLw9XnAn8P0x4H9gL55Xpt/AWfmvL8HuCHnGLsBBhwGfAqMzbmOS1q4xtcCfyW4y94ZeKPJuqcBgwkCzunAJ8CgnGv2XJM03gH8OHx9OLASGBv+/f4XmJ2zrgMPA9sDuxD8qB/VwrlPbe56Az8CXghf5/3dyFl2ZrhdgiCgfAhU5vzNvxK+7g0cGL4eAqwCjgmvy+fD91UtHafJMavDc08089mzwE1AJVATXpMj2khPi98p4CHgV0AvYAfgReC8nO/Pf4fnUAkcUur//63hoRzB1ikDXOnum9x9g7uvcvcH3P1Td18HXEPww9eSd939VndPE9xVDwJaugNvdl0z24XgTvmH7r7Z3Z8DZrZyzN8Dx+fcvX85XAZBsBkAfMbd0+4+193XtnkVAr8lLB4ys77ACWE6cfdH3P3fHngW+AvBnWlb/gO4xt0/cvf3gem5H7r7H9x9qbtn3P1e4C1gXJ7pnQTc7u4vu/sm4LsEOYjqnHWudffV7v4e8DTBj18hlhIEMdrx3cDd7wq3S7n7zwgC1p7hx0ngM2Y20N3Xu/s/wuVnAo+6+6PhdXkSmEMQGNrNzHYmuMm43N03uvurwK+Br7SRnma/U2Gu4GjgYnf/xN1XANcDZ+RstyswODxeo/qecqVAsHWq86CMHAAz29bMfmVm75rZWmA2sH02u9uMD7Mv3P3T8GXvAtcdDHyUswzg/ZYS7O6LgAXAl8JgcDwNgeB3wBPADDNbamY/NbOKlvbVxG+BCWY2BDgVWOTurwCY2dFm9o+wSGE1wY/SwDz2ObjJubyb+6GZfdXMXg2LHFYDo/Lcb3bf9ftz9/UEd85Dctb5MOf1p7T8t2nJEOCjMK2Ffjcws8vCIrU14fltR8P5fQ3YA1gYFrdki/t2BU7LXpNwu0MIbhw6Ivs9W5ez7F0arldL6WnpO7UrUAEsy0nnrwhyBgDfIchBvmhBS7KzO5j+bqEsKyIjoOmQsJcR3LEd4O4fmlkN8ArBF7pYlgH9zWzbnGCwcxvb3ENQkRsD5ofBAXdPAlcBV4V3xo8CbwK3tZUId3/PzP5KcKd9NEFgwMx6Ag8Q5Bb+5O5JM3uI/K7JsvBc5oXvd8l+YGa7ArcCRwB/d/e0mb2as9+2hutdSvBjlN1fL4I71w/ySFebzCwGfAl4KlzU1nfDm2x/KHA5wfnNc/eMmX2cXd/d3wImhsc5GbjfzAYQBM7fufs5NK+9wxgvJfie9ckJBrsQXq+W0uPun9D8d+pRYBMw0N1TWyTS/UOColDM7BDgKTObnf2ulivlCKKhD7ABWG1m/YEri31Ad3+XIOs/1cx6mNlnCX6AWjMD+AJBXUM2N4CZTTCz0eFd6lqC7Hm6gOTcCXwTOBjItqjqQVCkUQekLKjk/kKe+7sP+K4FFa1DgQtzPutF8KNWF6b9LIIcQdZyYKiZ9Whh378HzjKzmjBY/X8E5fmL80xbs8yswoLK6nsIWg5lK3Hb+m4sB4bnvO9DUAdVByTM7IdA35zjnGlmVe6eAVaHi9PAXQS5vS+aWTysrB1vDY0Wmh6nJT3DbSvNrJLgB/954Cfhsn0IcgF3t5aelr5T7r6MoIjwZ2bW18xiZrabmR0W7u+0nDR/TPC3LuS72C0pEETDDQSVxiuBfwCPd9FxJwGfJSja+DFBc85NLa0c/hP+HTgoXDdrJ+B+gn/YBQSVg3dBfWesX7aRjvuBfsCs8BiEd48XEfyof0xQJ9FaHUauqwiKH94h+NH4Xc45zAd+Fp7HcmA08Lecbf+PICfxoZmtbLpjd58F/IAgt7KMoDL7jKbrFeB0M1tP8CM4k+BvsZ+7Lw0/v4HWvxs/B061oEXRdILilMcIKuHfBTbSuJjsKGBeeMyfA2eEZenvE9TPfI8giLwPfJuG35Cmx2nJeoLAlX0cTpCLrCbIHTxIUD/2ZGvpoZXvFEEusQcwn+C7cT8NRVj7Ay+E+5sJfMvd32klvWUh2zpEpE0WNLVb6O5Fz5GISNdRjkBaZGb7h9nqmJkdRXBH+FCJkyUinUyVxdKanYA/ElR2LgHOz7bYEZHuQ0VDIiJlTkVDIiJlLhJFQwMHDvTq6upSJ0NEJFLmzp270t2r2lovEoGgurqaOXPmlDoZIiKRYmbvtr2WioZERMpe0QJB2EvwRQuGq51nZleFy6daMDTsq+GjQ4NWiYhIxxSzaGgTcLi7rw8Hg3rOzB4LP7ve3acV8dgiIpKnogUCD9qlrg/fVoSPorVVfeT1ZRw4vD8Devcs1iFEur1kMsmSJUvYuHFj2yvLVqOyspKhQ4dSUZHvoL6NFbWyOBwQai7wGeBGd38hHBzsm2b2VYJBzS5z94+b2fZc4FyAXXbZpenHjXyyKcUFv3+Z7x+7F/95aD7jXolIc5YsWUKfPn2orq7G2p44TbYC7s6qVatYsmQJw4YNa9c+ilpZHE4YUQMMBcaZ2SjgZoKBuGoIBuX6WQvb3uLute5eW1XVeuunZDoDwKZUptPSLlKONm7cyIABAxQEIsTMGDBgQIdycV3SasjdVxNMZXeUuy8PA0SGYNz3fGd+alEyHZQ4pdLqJS3SUQoC0dPRv1kxWw1Vmdn24ettgCMJZhnKndHoJIL5YjsknQkDQUY5AhGRQhUzRzAIeNrMXgdeAp5094eBn5rZP8PlE4BLOnqgbNFQKqMcgUiUrVq1ipqaGmpqathpp50YMmRI/fvNmze3uu2cOXO46KKL2jzGQQcd1ClpfeaZZzjuuOPaXjECitlq6HVgTDPLv9LM6h1SnyNIK0cgEmUDBgzg1VdfBWDq1Kn07t2b//qv/6r/PJVKkUg0/7NVW1tLbW1tm8d4/vnnOyWt3Um36FmcLRJSjkCk+5kyZQqXXnopEyZM4PLLL+fFF1/koIMOYsyYMRx00EG8+eabQOM79KlTp3L22Wczfvx4hg8fzvTpDZOm9e7du3798ePHc+qppzJixAgmTZpEdjTmRx99lBEjRnDIIYdw0UUXFXTnf8899zB69GhGjRrF5ZdfDkA6nWbKlCmMGjWK0aNHc/311wMwffp09t57b/bZZx/OOKMjE9l1TCTGGmpLKqPKYpHOdtWf5zF/6dpO3efeg/ty5ZdGFrzdv/71L5566ini8Thr165l9uzZJBIJnnrqKb73ve/xwAMPbLHNwoULefrpp1m3bh177rkn559//hbt7F955RXmzZvH4MGDOfjgg/nb3/5GbW0t5513HrNnz2bYsGFMnDgx73QuXbqUyy+/nLlz59KvXz++8IUv8NBDD7HzzjvzwQcf8MYbQZXo6tWrAbj22mt555136NmzZ/2yUugeOYK0KotFurPTTjuNeDwOwJo1azjttNMYNWoUl1xyCfPmzWt2m2OPPZaePXsycOBAdthhB5YvX77FOuPGjWPo0KHEYjFqampYvHgxCxcuZPjw4fVt8gsJBC+99BLjx4+nqqqKRCLBpEmTmD17NsOHD+ftt9/mwgsv5PHHH6dv374A7LPPPkyaNIm77rqrxSKvrqAcgYg0qz137sXSq1ev+tc/+MEPmDBhAg8++CCLFy9m/PjxzW7Ts2fDKAPxeJxUKpXXOh2ZrKulbfv168drr73GE088wY033sh9993H7bffziOPPMLs2bOZOXMmV199NfPmzStJQOgWOYK06ghEysaaNWsYMmQIAHfccUen73/EiBG8/fbbLF68GIB77703720POOAAnn32WVauXEk6neaee+7hsMMOY+XKlWQyGU455RSuvvpqXn75ZTKZDO+//z4TJkzgpz/9KatXr2b9+vVtH6QIukWOoL5DmQKBSLf3ne98h8mTJ3Pddddx+OGHd/r+t9lmG2666SaOOuooBg4cyLhxLfd5nTVrFkOHDq1//4c//IGf/OQnTJgwAXfnmGOO4YQTTuC1117jrLPOIhPetP7kJz8hnU5z5plnsmbNGtydSy65hO23377TzycfkZizuLa21lubmOZvi1Yy6dcvcPSonbj5zP26MGUi3cuCBQvYa6+9Sp2Mklu/fj29e/fG3bngggvYfffdueSSDnd5Kqrm/nZmNtfd22xT2y2KhtShTEQ606233kpNTQ0jR45kzZo1nHfeeaVOUlF1i6IhdSgTkc50ySWXbPU5gM7ULXIE9a2GlCMQESlY9wgEGn1URKTdukcgqG8+qqIhEZFCdY9AoOajIiLt1i0CQVo9i0W6hfHjx/PEE080WnbDDTfwjW98o9Vtss3LjznmmGbH7Jk6dSrTpk1r9dgPPfQQ8+fPr3//wx/+kKeeeqqA1DcvCsNVd4tAoMpike5h4sSJzJgxo9GyGTNm5D3ez6OPPtruTllNA8GPfvQjjjzyyHbtK2q6SSAI6wjUfFQk0k499VQefvhhNm3aBMDixYtZunQphxxyCOeffz61tbWMHDmSK6+8stntq6urWblyJQDXXHMNe+65J0ceeWT9UNUQ9BHYf//92XfffTnllFP49NNPef7555k5cybf/va3qamp4d///jdTpkzh/vvvB4IexGPGjGH06NGcffbZ9emrrq7myiuvZOzYsYwePZqFCxfmfa5b03DV3aIfQbZIKK0cgUjneewK+PCfnbvPnUbD0de2+PGAAQMYN24cjz/+OCeccAIzZszg9NNPx8y45ppr6N+/P+l0miOOOILXX3+dffbZp9n9zJ07lxkzZvDKK6+QSqUYO3Ys++0XjDpw8sknc8455wDw/e9/n9tuu40LL7yQ448/nuOOO45TTz210b42btzIlClTmDVrFnvssQdf/epXufnmm7n44osBGDhwIC+//DI33XQT06ZN49e//nWbl2FrG666W+UIkmo1JBJ5ucVDucVC9913H2PHjmXMmDHMmzevUTFOU3/961856aST2Hbbbenbty/HH398/WdvvPEGhx56KKNHj+buu+9ucRjrrDfffJNhw4axxx57ADB58mRmz55d//nJJ58MwH777Vc/UF1btrbhqrtHjkCVxSKdr5U792I68cQTufTSS3n55ZfZsGEDY8eO5Z133mHatGm89NJL9OvXjylTprBx48ZW92NmzS6fMmUKDz30EPvuuy933HEHzzzzTKv7aWs8tuxQ1i0NdV3IPks1XHX3yBGo+ahIt9G7d2/Gjx/P2WefXZ8bWLt2Lb169WK77bZj+fLlPPbYY63u43Of+xwPPvggGzZsYN26dfz5z3+u/2zdunUMGjSIZDLJ3XffXb+8T58+rFu3bot9jRgxgsWLF7No0SIAfve733HYYYd16By3tuGqi5YjMLNKYDbQMzzO/e5+pZn1B+4FqoHFwH+4+8cdOVZKYw2JdCsTJ07k5JNPri8i2nfffRkzZgwjR45k+PDhHHzwwa1uP3bsWE4//XRqamrYddddOfTQQ+s/u/rqqznggAPYddddGT16dP2P/xlnnME555zD9OnT6yuJASorK/nNb37DaaedRiqVYv/99+frX/96QeeztQ9XXbRhqC3Il/Vy9/VmVgE8B3wLOBn4yN2vNbMrgH7ufnlr+2prGOr//4mF3Pj0v+lTmeCfU7/YiWchUl40DHV0bZXDUHsgm3+pCB8OnADcGS6/EzixXQfY/Cl89A6kNmmsIRGRDihqHYGZxc3sVWAF8KS7vwDs6O7LAMLnHdq187efgek1sGJBfdGQmo+KiBSuqIHA3dPuXgMMBcaZ2ah8tzWzc81sjpnNqaur23KFeI/gOZ2srxtQ81GRjovCrIXSWEf/Zl3SasjdVwPPAEcBy81sEED4vKKFbW5x91p3r62qqtpyhXhYz51J1ucI3JUrEOmIyspKVq1apWAQIe7OqlWrqKysbPc+itlqqApIuvtqM9sGOBL4H2AmMBm4Nnz+U7sOEKsIntPJRnUDqUyGeCzekaSLlK2hQ4eyZMkSms2Fy1arsrKyUaukQhWzQ9kg4E4zixPkPO5z94fN7O/AfWb2NeA94LR27T0eBoKcHAEEFcY9u0U3OZGuV1FRwbBhw0qdDOliRfvJdPfXgTHNLF8FHNHhA2QDQTpFOqduQJ3KREQKE92exfVFQ5tJNsoRqMJYRKQQ0Q0EOUVD6Zw6AlUWi4gUJrqBIBaWaqVTjeYqTioQiIgUJLqBINuPYIvKYhUNiYgUIsKBoKGOoHHzUeUIREQKEd1AEGtoNZRbNKTxhkREChPdQJDTszi3gjilYSZERAoS4UDQMNZQMt24Q5mIiOQvuoEgZ4iJdMZJxIJp6VRHICJSmAgHgnA8oUySZDpDZUXwXq2GREQKE91AYBbkCsIcQWVFcCrKEYiIFCa6gQCCJqRhP4KeiTBHoEAgIlKQ6AeCdJJUJtOQI1DRkIhIQaIdCLJFQ2lvqCNQjkBEpCDRDgRh0VAykxMI1HxURKQg0Q4EsYpwPoLcymIVDYmIFCLagSBeEcxHkM5QmVCOQESkPaIfCDLZ5qNBINB8BCIihYl2IAiLhoJ5ioNTSapoSESkINEOBPFE2I8gQ2UPFQ2JiLRHxANBDzy1mYzTUEegoiERkYIULRCY2c5m9rSZLTCzeWb2rXD5VDP7wMxeDR/HtPsgsQo8nQRQhzIRkXZKFHHfKeAyd3/ZzPoAc83syfCz6919WoePEE/gmz8FUIcyEZF2KlogcPdlwLLw9TozWwAM6dSDhD2LITdHoEAgIlKILqkjMLNqYAzwQrjom2b2upndbmb9WtjmXDObY2Zz6urqmt9xWEcA0CMewwzSajUkIlKQogcCM+sNPABc7O5rgZuB3YAaghzDz5rbzt1vcfdad6+tqqpqfufxBGRSwct4jETMSKpoSESkIEUNBGZWQRAE7nb3PwK4+3J3T7t7BrgVGNfuA+QUDSViRiIWU2WxiEiBitlqyIDbgAXufl3O8kE5q50EvNHug4Q9iyEMBHFTZbGISIGK2WroYOArwD/N7NVw2feAiWZWAziwGDiv3UeI5+QI4kYiZqosFhEpUDFbDT0HWDMfPdppB4nl5ghiJOIx5QhERAoU8Z7FFVg6qCwO6ghMdQQiIgWKdiCIJRpyBPEYibhp9FERkQJFOxDEe2CZxq2G1HxURKQwEQ8EFcQyScCJq2hIRKRdoh0IYhUAxMmQiBvxmJqPiogUKtqBIB40ekqQJhGLURFXhzIRkUJFPBD0AKAHqaAfgTqUiYgULNqBICwaSpDKaT6qQCAiUohoB4ImRUOJWEzNR0VEChTtQBDmCCpI1xcNafJ6EZHCRDsQhHUEFZaqbz6qHIGISGEiHggaioYqYjHisRhJ1RGIiBQk2oEgp2goHjcq4upQJiJSqGgHgnhDq6GKmJGIq7JYRKRQ3SIQ9KChjkCVxSIihYl2IKjvR5AORh+NGWnVEYiIFCTagSBbNGTp+qkqNfqoiEhhoh0IciuLw2GoVUcgIlKYaAeCeDYQpKiIx4jHjKRaDYmIFKRbBIIEaWJG2HxUOQIRkUIULRCY2c5m9rSZLTCzeWb2rXB5fzN70szeCp/7tfsgYdFQZSyNmZqPioi0RzFzBCngMnffCzgQuMDM9gauAGa5++7ArPB9+4Q9i3vE0gBqPioi0g5FCwTuvszdXw5frwMWAEOAE4A7w9XuBE5s90GyOQILfvwTsRjukFGuQEQkb11SR2Bm1cAY4AVgR3dfBkGwAHZoYZtzzWyOmc2pq6trfsfZiWmyOYK4AShXICJSgKIHAjPrDTwAXOzua/Pdzt1vcfdad6+tqqpqfqWwsrinNRQNAaonEBEpQFEDgZlVEASBu939j+Hi5WY2KPx8ELCi3QeIhXUEYdFQPAwEGoFURCR/xWw1ZMBtwAJ3vy7no5nA5PD1ZOBP7T5IdqwhSwFQEQ9ORyOQiojkL1HEfR8MfAX4p5m9Gi77HnAtcJ+ZfQ14Dzit3UfI1hFY4zoCFQ2JiOSvaIHA3Z8DrIWPj+iUg8TiZLCGQJAtGlIgEBHJW7R7FgNpEvV1BIlYcDoagVREJH95BQIz62VmsfD1HmZ2fFgRXHJpi1MR1hGo+aiISOHyzRHMBirNbAhBb+CzgDuKlahCpKyCHmSLhsIcgYqGRETylm8gMHf/FDgZ+F93PwnYu3jJyl+aOBVhHUFD81HlCERE8pV3IDCzzwKTgEfCZcVscZS3FAkSYY6gQq2GREQKlm8guBj4LvCgu88zs+HA00VLVQFSxOv7EahDmYhI4fK6q3f3Z4FnAcJK45XuflExE5avlOXmCNShTESkUPm2Gvq9mfU1s17AfOBNM/t2cZOWnxRxKtBYQyIi7ZVv0dDe4YBxJwKPArsQ9BouuWROHUFD81EFAhGRfOUbCCrCfgMnAn9y9ySwVfzapjxOBWE/gvrmoyoaEhHJV76B4FfAYqAXMNvMdgXyHlK6mIIcgSqLRUTaK69A4O7T3X2Iux/jgXeBCUVOW16SxLeoLFYdgYhI/vKtLN7OzK7LzhhmZj8jyB2UXNLjxL1pjkBFQyIi+cq3aOh2YB3wH+FjLfCbYiWqEEGOIDsfQRAIUioaEhHJW769g3dz91Ny3l+VM8dASW32OAnPthpS0ZCISKHyzRFsMLNDsm/M7GBgQ3GSVJikx4nXtxrS6KMiIoXKN0fwdeC3ZrZd+P5jGqabLKnNOXUE6lAmIlK4fIeYeA3Y18z6hu/XmtnFwOtFTFtekuQGgiCDo+ajIiL5K2iGMndfG/YwBri0COkp2KbcHEH96KMqGhIRyVdHpqpsaT7iLpPJOElPENui+ahyBCIi+epIICj5r20ykyGVUzTUMPpoyZMmIhIZrQYCM1tnZmubeawDBrex7e1mtsLM3shZNtXMPjCzV8PHMR1JfDrjJIk3yhGYqWhIRKQQrVYWu3ufDuz7DuAXwG+bLL/e3ad1YL/1kmknSaI+RwBByyGNPioikr+OFA21yt1nAx8Va/8Q5AhS2RyBBz/+iVhMzUdFRApQtEDQim+a2eth0VG/llYys3OzYxvV1dU1u04qkyHpYaYm09CXQGMNiYjkr6sDwc3AbkANsAz4WUsruvst7l7r7rVVVVXNrpNKBzkCANKbgaAJqXIEIiL569JA4O7L3T3t7hngVmBcR/YXVBaHOYJ0EoB4LKbmoyIiBejSQGBmg3LengS80dK6+UimMySzOYJMwwikmrxeRCR/+Y41VDAzuwcYDww0syXAlcB4M6sh6IOwGDivI8fIVhYHb4IcgYqGREQKU7RA4O4Tm1l8W2ceI9lcHUEspuajIiIFKEWroU6Tzjibm2k1pA5lIiL5i3QgSGUypLaoLDZVFouIFCDigSCnaCgTBIKKuDqUiYgUItqBIO0NrYbCOoK4OpSJiBQk2oEgHH0UgHRD81HlCERE8hfxQJDToSzTUEegYahFRPIX7UCQdpLeuB9BRTymyetFRAoQ6UCQbqbVUNB8VDkCEZF8RToQpDI5lcUZjTUkItIe0Q4E6S0HnQsqi1U0JCKSr2gHgkb9CBqmq1RlsYhI/qIdCHJHHw37EVTEY6RURyAikrdoB4KMk/Ith5jQMNQiIvmLdiBIZ7boR1AR1+T1IiKFiHYgyG01lM6OPqqxhkREChHpQNB4YhqNNSQi0h6RDgTNjz6qDmUiIoWIdiBo1I8g23w0puajIiIFiHYgyGRwi4HFGuUIUupQJiKSt4gHAqciFoNYRaM6goxDRsVDIiJ5KVogMLPbzWyFmb2Rs6y/mT1pZm+Fz/06coxUOkM8ZhCvyJmPIDgljUAqIpKfYuYI7gCOarLsCmCWu+8OzArft1sq4ySygSDTMPoooApjEZE8FS0QuPts4KMmi08A7gxf3wmc2JFjpDNOIm5h0VBDz2JAI5CKiOSpq+sIdnT3ZQDh8w4trWhm55rZHDObU1dX1+w6ybQTj8XCoqGGiWlAOQIRkXxttZXF7n6Lu9e6e21VVVWz66QzGSriBrFEo6kqAY03JCKSp64OBMvNbBBA+LyiIztLpT2sLO7RaD4CQCOQiojkqasDwUxgcvh6MvCnjuwslfGgKCinsjgeC05JncpERPJTzOaj9wB/B/Y0syVm9jXgWuDzZvYW8PnwfbulMmHz0Vgip/mo1X8mIiJtSxRrx+4+sYWPjuisY6TSOc1Hww5liWyOQEVDIiJ52Wori/NR33w03mOLymKNQCoikp9IB4JkJmw+2kzRkJqPiojkJ9KBIJ3JUNGkZ7E6lImIFCbSgSCZbT6aM+icOpSJiBQm0oEgndt8tH4+AnUoExEpRKQDQaPRRzNtdyh7/6NP+cptL7Dm02SXplNEZGsW7UCQHX00Z9C5huajW+YI/m/hCv761krmLV3TpekUEdmaRToQNDQfzW/00QXL1gJQt35T1yVSRGQrF+lAkExnghxAo6KhliuL52cDwToFAhGRrEgHgtbnI2hcNJRKZ3jzw3WAcgQiIrkiHQjqm4/GKyDTeoeyxas+YVMqCA7KEYiINIh0IEjXT16faDR5PWw5+uj8ZUFuoFePOCvXb+7ahIqIbMUiHQhSmQzxeNP5CJofdG7BsrVUxI39qvsrRyAikiPigSBn9FFPg3tDjqBJ89EFy9ayW1VvBm9XyUrVEYiI1It0IEinPWg1FAtH004ng6Iitmw+On/pWvYe3JeqPj1ZtX6ThqAQEQlFOhAkM5mGfgQA6c3Be4IB6bJWrd/EinWb2HtQXwb27knG4aNPVE8gIgIRDwTp3J7FAJlksx3KFoQVxXsNCnIEgIqHRERCkQ0E7k4yd4YygHSq2Q5l2R7FuYFAFcYiIoGiTVVZbNnf+UR29FGATJIwQ9Bo9NEFy9ayY9+e9O/VgzUblCMQEckV2RxBtudwPLdoKL0ZM6Mibo2aj85ftpa9BvUFUI5ARKSJkuQIzGwxsA5IAyl3ry10H9min6ZFQxAEh2wg2JRKs2jFeiaM2AEIOpRVVsQUCEREQqUsGprg7ivbu3H2h75p0RBARSxW37N40Yr1pDLO3mGOwMyo6tNTRUMiIqHI1hFk6wAatRrKzkkQt/oOZQuWrmGUvU1NrC8sWQY9+1DVu6cGnhMRCZUqEDjwFzNz4FfufkuhO6gvGmrUjyA7Ammsvvno0Nnf4eGej8EDDdvuO+QWnl83qEMnICLSXZSqsvhgdx8LHA1cYGafa7qCmZ1rZnPMbE5dXd0WO0jm1hFkexbnTFeZzmRY9NpzHLj2MV6rOh6+/Ac48ZcA7GOLlCMQEQmVJBC4+9LweQXwIDCumXVucfdad6+tqqraYh/pdDYQxIJB56DRnASpVIZNj3yPj+nLsEk3wB5fgH1Ohx69GZZ+h48+2bzFnAUiIuWoywOBmfUysz7Z18AXgDcK3U8yrANoVDSUM0uZv/UXRm5+jX+N+AZ9tx8QfB6LwY4jGbxxEaBhJkREoDQ5gh2B58zsNeBF4BF3f7zQnWTrCOLNVBZXWIZvJO/kfRvM2JMvbbzhTqPpt+4twNWEVESEElQWu/vbwL4d3U+qUdFQw+ijAMemnmL32Ae8fOAv2LlHz8Yb7jiKitR6hlqd6glERIhwz+Js89CgQ1lYR5BJwqb1TN70exb2GMmYz0/acsOdRgMw0t5VjkBEhCj3I8htPhrL6Vn8/HS2z3zMNl++F4s1E+d22AvH2CumQCAiAlHOETRXNLT6XfjbdBh5Mj2rD2h+wx69sAG7MTr+vnoXi4gQ5UCQ22oomyN4fnowZeWRV7a+8U6j2Sv2nnIEIiJEORCkcwedC+sINq6BcedCv+rWN95xFIN9OZ+s/ai4iRQRiYDIBoJGzUezRUOV28Ohl7W9cVhhvN2aN4uUOhGR6Ih8ZXFFPAY9toW+Q+Fzl8G2/dveeMdRAOywYVExkygiEgmRDQSHj9iB+T/6Ij0TcYgZXPIGmOW3cd/BbEhsx7CN77AplQ72ISJSpiJbNBSPGdv2SNRPVp93EAjXXbvdCPaKvcvK9RpmQkTKW2QDQUdtGrAXI+x9Vq75pNRJEREpqbINBOw0mkpL8skyVRiLSHmLbB1BR1UODYY7qnx6Ki/MGdrqupti2/LcDpPYkOjbFUkTESnI1SeO6tD2ZRsI+leP5q3EZxi2aSFsWtjqun1Yz5AVz3BB7AessGBI62G+hB9l/pe9eLsrkisi0rITV3do87INBIkelez+/bn5rfzOX9ltxpd5vOfVcOYD8P4/4LHvQuW2MPaShhnSREQiSL9g+Rh2KJz1KNx1CvzykGCU0+Hj4aRfQZ+dSp06EZEOUSDI106j4Wt/gZkXwmc+D5/9ZjDjmYhIxCkQFKJfNUz+c6lTISLSqXRLKyJS5hQIRETKnAKBiEiZUyAQESlzJQkEZnaUmb1pZovM7IpSpEFERAJdHgjMLA7cCBwN7A1MNLO9uzodIiISKEWOYBywyN3fdvfNwAzghBKkQ0REKE0gGAK8n/N+SbisETM718zmmNmcurq6LkuciEi5KUUgaG4GGd9igfst7l7r7rVVVVVdkCwRkfJUikCwBNg55/1QYGkJ0iEiIpQmELwE7G5mw8ysB3AGMLME6RAREUow1pC7p8zsm8ATQBy43d3ndXU6REQkUJJB59z9UeDRUhxbREQaM/ct6mm3OmZWB7wbvh0IrCxhcrYGuga6BqBrALoG0Po12NXd22xtE4lAkMvM5rh7banTUUq6BroGoGsAugbQOddAYw2JiJQ5BQIRkTIXxUBwS6kTsBXQNdA1AF0D0DWATrgGkasjEBGRzhXFHIGIiHQiBQIRkTIXqUBQjhPamNnOZva0mS0ws3lm9q1weX8ze9LM3gqf+5U6rcVkZnEze8XMHg7fl9X5A5jZ9mZ2v5ktDL8Pny2n62Bml4T/A2+Y2T1mVlkO529mt5vZCjN7I2dZi+dtZt8NfyPfNLMv5nOMyASCMp7QJgVc5u57AQcCF4TnfQUwy913B2aF77uzbwELct6X2/kD/Bx43N1HAPsSXI+yuA5mNgS4CKh191EEw9OcQXmc/x3AUU2WNXve4W/DGcDIcJubwt/OVkUmEFCmE9q4+zJ3fzl8vY7gn38IwbnfGa52J3BiSRLYBcxsKHAs8OucxWVz/gBm1hf4HHAbgLtvdvfVlNd1SADbmFkC2JZg1OJuf/7uPhv4qMnils77BGCGu29y93eARQS/na2KUiDIa0Kb7szMqoExwAvAju6+DIJgAexQwqQV2w3Ad4BMzrJyOn+A4UAd8JuwiOzXZtaLMrkO7v4BMA14D1gGrHH3v1Am59+Mls67Xb+TUQoEeU1o012ZWW/gAeBid19b6vR0FTM7Dljh7nNLnZYSSwBjgZvdfQzwCd2zGKRZYRn4CcAwYDDQy8zOLG2qtkrt+p2MUiAo2wltzKyCIAjc7e5/DBcvN7NB4eeDgBWlSl+RHQwcb2aLCYoDDzezuyif889aAixx9xfC9/cTBIZyuQ5HAu+4e527J4E/AgdRPuffVEvn3a7fySgFgrKc0MbMjKBceIG7X5fz0Uxgcvh6MvCnrk5bV3D377r7UHevJvib/5+7n0mZnH+Wu38IvG9me4aLjgDmUz7X4T3gQDPbNvyfOIKgvqxczr+pls57JnCGmfU0s2HA7sCLbe7N3SPzAI4B/gX8G/jvUqeni875EIKs3evAq+HjGGAAQWuBt8Ln/qVOaxdci/HAw+Hrcjz/GmBO+F14COhXTtcBuApYCLwB/A7oWQ7nD9xDUC+SJLjj/1pr5w38d/gb+SZwdD7H0BATIiJlLkpFQyIiUgQKBCIiZU6BQESkzCkQiIiUOQUCEZEyp0AgZc3M0mb2as6j03rrmll17oiRIlurRKkTIFJiG9y9ptSJECkl5QhEmmFmi83sf8zsxfDxmXD5rmY2y8xeD593CZfvaGYPmtlr4eOgcFdxM7s1HEf/L2a2Tbj+RWY2P9zPjBKdpgigQCCyTZOiodNzPlvr7uOAXxCMgEr4+rfuvg9wNzA9XD4deNbd9yUYA2heuHx34EZ3HwmsBk4Jl18BjAn38/XinJpIftSzWMqama13997NLF8MHO7ub4eD/n3o7gPMbCUwyN2T4fJl7j7QzOqAoe6+KWcf1cCTHkwegpldDlS4+4/N7HFgPcFQEQ+5+/oin6pIi5QjEGmZt/C6pXWasynndZqGerljCWbc2w+YG062IlISCgQiLTs95/nv4evnCUZBBZgEPBe+ngWcD/XzK/dtaadmFgN2dvenCSbc2R7YIlci0lV0FyLlbhszezXn/ePunm1C2tPMXiC4YZoYLrsIuN3Mvk0wY9hZ4fJvAbeY2dcI7vzPJxgxsjlx4C4z245gIpHrPZh2UqQkVEcg0oywjqDW3VeWOi0ixaaiIRGRMqccgYhImVOOQESkzCkQiIiUOQUCEZEyp0AgIlLmFAhERMrc/wPmlIcUl4myrwAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "melbourne_parking_data = pd.read_csv(\"on-street-parking-bay-sensors.csv\")\n",
    "epochs = list(range(1, 101))  \n",
    "training_losses = [3, 35, 4, 5, 8, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2] + [2] * 70  # Replace with actual training losses\n",
    "validation_losses = [30, 3, 4, 5, 5, 2, 2, 2, 2, 1.5, 1.9, 1.9, 1.9, 1.9, 1.9, 1.9, 1.9, 1.9, 1.9, 1.9, 1.9, 1.9, 1.9, 1.9, 1.9, 1.9, 1.9, 1.9, 1.9, 1.9] + [1.9] * 70  # Replace with actual validation losses\n",
    "plt.plot(epochs, training_losses, label='Training Loss')\n",
    "plt.plot(epochs, validation_losses, label='Validation Loss')\n",
    "plt.title('Training vs. Validation Dataset Losses')\n",
    "plt.xlabel('Epochs')\n",
    "plt.ylabel('Loss')\n",
    "plt.grid(False)\n",
    "plt.legend()\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}