{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "081ae343", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np" ] }, { "cell_type": "code", "execution_count": 2, "id": "98308606", "metadata": {}, "outputs": [], "source": [ "data_raw = pd.read_csv(\"实验20126+20483.csv\")" ] }, { "cell_type": "code", "execution_count": 3, "id": "ea74784a", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
f.20483.0.0f.1548.0.0f.1558.0.0f.20116.0.0f.20435.0.0f.20438.0.0f.20441.0.0f.20446.0.0f.20449.0.0f.20450.0.0...f.25911.2.0f.25912.2.0f.25913.2.0f.25914.2.0f.25915.2.0f.25916.2.0f.25917.2.0f.25918.2.0f.25919.2.0f.25920.2.0
00341141111...3103.942108.26349.682454.281499.05330.691845.71509.049223.49489.589
10350151111...2729.461758.55391.491681.651240.44301.751422.23553.770157.36495.181
21111141111...3485.942086.91334.212531.931387.53385.321698.33421.880229.24404.501
31231161111...4628.373182.58546.572967.892333.54505.002671.06538.011183.91520.930
41231151111...3145.972783.52384.192612.011741.22432.291876.94442.701216.41408.791
\n", "

5 rows × 179 columns

\n", "
" ], "text/plain": [ " f.20483.0.0 f.1548.0.0 f.1558.0.0 f.20116.0.0 f.20435.0.0 f.20438.0.0 \\\n", "0 0 3 4 1 1 4 \n", "1 0 3 5 0 1 5 \n", "2 1 1 1 1 1 4 \n", "3 1 2 3 1 1 6 \n", "4 1 2 3 1 1 5 \n", "\n", " f.20441.0.0 f.20446.0.0 f.20449.0.0 f.20450.0.0 ... f.25911.2.0 \\\n", "0 1 1 1 1 ... 3103.94 \n", "1 1 1 1 1 ... 2729.46 \n", "2 1 1 1 1 ... 3485.94 \n", "3 1 1 1 1 ... 4628.37 \n", "4 1 1 1 1 ... 3145.97 \n", "\n", " f.25912.2.0 f.25913.2.0 f.25914.2.0 f.25915.2.0 f.25916.2.0 \\\n", "0 2108.26 349.68 2454.28 1499.05 330.69 \n", "1 1758.55 391.49 1681.65 1240.44 301.75 \n", "2 2086.91 334.21 2531.93 1387.53 385.32 \n", "3 3182.58 546.57 2967.89 2333.54 505.00 \n", "4 2783.52 384.19 2612.01 1741.22 432.29 \n", "\n", " f.25917.2.0 f.25918.2.0 f.25919.2.0 f.25920.2.0 \n", "0 1845.71 509.049 223.49 489.589 \n", "1 1422.23 553.770 157.36 495.181 \n", "2 1698.33 421.880 229.24 404.501 \n", "3 2671.06 538.011 183.91 520.930 \n", "4 1876.94 442.701 216.41 408.791 \n", "\n", "[5 rows x 179 columns]" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data_raw.head()" ] }, { "cell_type": "code", "execution_count": 4, "id": "71ec7917", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
f.20483.0.0f.1548.0.0f.1558.0.0f.20116.0.0f.20435.0.0f.20438.0.0f.20441.0.0f.20446.0.0f.20449.0.0f.20450.0.0...f.25911.2.0f.25912.2.0f.25913.2.0f.25914.2.0f.25915.2.0f.25916.2.0f.25917.2.0f.25918.2.0f.25919.2.0f.25920.2.0
00341141111...3103.942108.26349.682454.281499.05330.6901845.71509.049223.49489.589
10350151111...2729.461758.55391.491681.651240.44301.7501422.23553.770157.36495.181
21111141111...3485.942086.91334.212531.931387.53385.3201698.33421.880229.24404.501
31231161111...4628.373182.58546.572967.892333.54505.0002671.06538.011183.91520.930
41231151111...3145.972783.52384.192612.011741.22432.2901876.94442.701216.41408.791
..................................................................
2030330161111...4291.123194.45466.793356.212155.55377.3602547.30604.691278.93495.681
2041260161111...3604.231998.52322.442110.011777.50413.4291885.11312.789230.35291.969
2050141151111...2727.822622.36462.892096.062229.33511.2302261.56482.760279.04396.811
2061240151111...3200.322850.50469.112503.111809.41378.9401794.23478.320209.72354.389
2071240111111...3458.632004.10432.212471.801536.80379.3701980.78493.151253.46425.460
\n", "

208 rows × 179 columns

\n", "
" ], "text/plain": [ " f.20483.0.0 f.1548.0.0 f.1558.0.0 f.20116.0.0 f.20435.0.0 \\\n", "0 0 3 4 1 1 \n", "1 0 3 5 0 1 \n", "2 1 1 1 1 1 \n", "3 1 2 3 1 1 \n", "4 1 2 3 1 1 \n", ".. ... ... ... ... ... \n", "203 0 3 3 0 1 \n", "204 1 2 6 0 1 \n", "205 0 1 4 1 1 \n", "206 1 2 4 0 1 \n", "207 1 2 4 0 1 \n", "\n", " f.20438.0.0 f.20441.0.0 f.20446.0.0 f.20449.0.0 f.20450.0.0 ... \\\n", "0 4 1 1 1 1 ... \n", "1 5 1 1 1 1 ... \n", "2 4 1 1 1 1 ... \n", "3 6 1 1 1 1 ... \n", "4 5 1 1 1 1 ... \n", ".. ... ... ... ... ... ... \n", "203 6 1 1 1 1 ... \n", "204 6 1 1 1 1 ... \n", "205 5 1 1 1 1 ... \n", "206 5 1 1 1 1 ... \n", "207 1 1 1 1 1 ... \n", "\n", " f.25911.2.0 f.25912.2.0 f.25913.2.0 f.25914.2.0 f.25915.2.0 \\\n", "0 3103.94 2108.26 349.68 2454.28 1499.05 \n", "1 2729.46 1758.55 391.49 1681.65 1240.44 \n", "2 3485.94 2086.91 334.21 2531.93 1387.53 \n", "3 4628.37 3182.58 546.57 2967.89 2333.54 \n", "4 3145.97 2783.52 384.19 2612.01 1741.22 \n", ".. ... ... ... ... ... \n", "203 4291.12 3194.45 466.79 3356.21 2155.55 \n", "204 3604.23 1998.52 322.44 2110.01 1777.50 \n", "205 2727.82 2622.36 462.89 2096.06 2229.33 \n", "206 3200.32 2850.50 469.11 2503.11 1809.41 \n", "207 3458.63 2004.10 432.21 2471.80 1536.80 \n", "\n", " f.25916.2.0 f.25917.2.0 f.25918.2.0 f.25919.2.0 f.25920.2.0 \n", "0 330.690 1845.71 509.049 223.49 489.589 \n", "1 301.750 1422.23 553.770 157.36 495.181 \n", "2 385.320 1698.33 421.880 229.24 404.501 \n", "3 505.000 2671.06 538.011 183.91 520.930 \n", "4 432.290 1876.94 442.701 216.41 408.791 \n", ".. ... ... ... ... ... \n", "203 377.360 2547.30 604.691 278.93 495.681 \n", "204 413.429 1885.11 312.789 230.35 291.969 \n", "205 511.230 2261.56 482.760 279.04 396.811 \n", "206 378.940 1794.23 478.320 209.72 354.389 \n", "207 379.370 1980.78 493.151 253.46 425.460 \n", "\n", "[208 rows x 179 columns]" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data_raw " ] }, { "cell_type": "code", "execution_count": 5, "id": "660de27e", "metadata": {}, "outputs": [], "source": [ "data_null=data_raw.iloc[:,1:26]" ] }, { "cell_type": "code", "execution_count": 6, "id": "be7c2c45", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
f.1548.0.0f.1558.0.0f.20116.0.0f.20435.0.0f.20438.0.0f.20441.0.0f.20446.0.0f.20449.0.0f.20450.0.0f.20500.0.0...f.20536.0.0f.2100.0.0f.21000.0.0f.31.0.0f.6142.0.0f.1160.0.0f.21003.0.0f.4620.0.0f.20433.0.0f.20434.0.0
03411411111...301001117522.028.059.0
13501511111...101001016493.015.046.0
21111411110...201001017474.019.045.0
32311611111...111001116606.09.067.0
42311511111...2110010194320.011.050.0
..................................................................
2033301611111...211001029465.0NaNNaN
2042601611111...01100102661NaNNaN68.0
2051411511111...211001017493.017.054.0
2062401511111...10100101865150.050.068.0
2072401111111...101001037461.045.045.0
\n", "

208 rows × 25 columns

\n", "
" ], "text/plain": [ " f.1548.0.0 f.1558.0.0 f.20116.0.0 f.20435.0.0 f.20438.0.0 \\\n", "0 3 4 1 1 4 \n", "1 3 5 0 1 5 \n", "2 1 1 1 1 4 \n", "3 2 3 1 1 6 \n", "4 2 3 1 1 5 \n", ".. ... ... ... ... ... \n", "203 3 3 0 1 6 \n", "204 2 6 0 1 6 \n", "205 1 4 1 1 5 \n", "206 2 4 0 1 5 \n", "207 2 4 0 1 1 \n", "\n", " f.20441.0.0 f.20446.0.0 f.20449.0.0 f.20450.0.0 f.20500.0.0 ... \\\n", "0 1 1 1 1 1 ... \n", "1 1 1 1 1 1 ... \n", "2 1 1 1 1 0 ... \n", "3 1 1 1 1 1 ... \n", "4 1 1 1 1 1 ... \n", ".. ... ... ... ... ... ... \n", "203 1 1 1 1 1 ... \n", "204 1 1 1 1 1 ... \n", "205 1 1 1 1 1 ... \n", "206 1 1 1 1 1 ... \n", "207 1 1 1 1 1 ... \n", "\n", " f.20536.0.0 f.2100.0.0 f.21000.0.0 f.31.0.0 f.6142.0.0 f.1160.0.0 \\\n", "0 3 0 1001 1 1 7 \n", "1 1 0 1001 0 1 6 \n", "2 2 0 1001 0 1 7 \n", "3 1 1 1001 1 1 6 \n", "4 2 1 1001 0 1 9 \n", ".. ... ... ... ... ... ... \n", "203 2 1 1001 0 2 9 \n", "204 0 1 1001 0 2 6 \n", "205 2 1 1001 0 1 7 \n", "206 1 0 1001 0 1 8 \n", "207 1 0 1001 0 3 7 \n", "\n", " f.21003.0.0 f.4620.0.0 f.20433.0.0 f.20434.0.0 \n", "0 52 2.0 28.0 59.0 \n", "1 49 3.0 15.0 46.0 \n", "2 47 4.0 19.0 45.0 \n", "3 60 6.0 9.0 67.0 \n", "4 43 20.0 11.0 50.0 \n", ".. ... ... ... ... \n", "203 46 5.0 NaN NaN \n", "204 61 NaN NaN 68.0 \n", "205 49 3.0 17.0 54.0 \n", "206 65 150.0 50.0 68.0 \n", "207 46 1.0 45.0 45.0 \n", "\n", "[208 rows x 25 columns]" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data_null" ] }, { "cell_type": "code", "execution_count": 7, "id": "32181dab", "metadata": {}, "outputs": [], "source": [ "null_all = data_null.isnull().sum()" ] }, { "cell_type": "code", "execution_count": 8, "id": "a5ea2659", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "f.1548.0.0 0\n", "f.1558.0.0 0\n", "f.20116.0.0 0\n", "f.20435.0.0 0\n", "f.20438.0.0 0\n", "f.20441.0.0 0\n", "f.20446.0.0 0\n", "f.20449.0.0 0\n", "f.20450.0.0 0\n", "f.20500.0.0 0\n", "f.20508.0.0 0\n", "f.20511.0.0 0\n", "f.20514.0.0 0\n", "f.20518.0.0 0\n", "f.20519.0.0 0\n", "f.20536.0.0 0\n", "f.2100.0.0 0\n", "f.21000.0.0 0\n", "f.31.0.0 0\n", "f.6142.0.0 0\n", "f.1160.0.0 0\n", "f.21003.0.0 0\n", "f.4620.0.0 5\n", "f.20433.0.0 17\n", "f.20434.0.0 17\n", "dtype: int64" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "null_all " ] }, { "cell_type": "code", "execution_count": 9, "id": "e383a591", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
f.20483.0.0f.1548.0.0f.1558.0.0f.20116.0.0f.20435.0.0f.20438.0.0f.20441.0.0f.20446.0.0f.20449.0.0f.20450.0.0...f.25911.2.0f.25912.2.0f.25913.2.0f.25914.2.0f.25915.2.0f.25916.2.0f.25917.2.0f.25918.2.0f.25919.2.0f.25920.2.0
00341141111...3103.942108.26349.682454.281499.05330.6901845.71509.049223.49489.589
10350151111...2729.461758.55391.491681.651240.44301.7501422.23553.770157.36495.181
21111141111...3485.942086.91334.212531.931387.53385.3201698.33421.880229.24404.501
31231161111...4628.373182.58546.572967.892333.54505.0002671.06538.011183.91520.930
41231151111...3145.972783.52384.192612.011741.22432.2901876.94442.701216.41408.791
..................................................................
2030330161111...4291.123194.45466.793356.212155.55377.3602547.30604.691278.93495.681
2041260161111...3604.231998.52322.442110.011777.50413.4291885.11312.789230.35291.969
2050141151111...2727.822622.36462.892096.062229.33511.2302261.56482.760279.04396.811
2061240151111...3200.322850.50469.112503.111809.41378.9401794.23478.320209.72354.389
2071240111111...3458.632004.10432.212471.801536.80379.3701980.78493.151253.46425.460
\n", "

208 rows × 179 columns

\n", "
" ], "text/plain": [ " f.20483.0.0 f.1548.0.0 f.1558.0.0 f.20116.0.0 f.20435.0.0 \\\n", "0 0 3 4 1 1 \n", "1 0 3 5 0 1 \n", "2 1 1 1 1 1 \n", "3 1 2 3 1 1 \n", "4 1 2 3 1 1 \n", ".. ... ... ... ... ... \n", "203 0 3 3 0 1 \n", "204 1 2 6 0 1 \n", "205 0 1 4 1 1 \n", "206 1 2 4 0 1 \n", "207 1 2 4 0 1 \n", "\n", " f.20438.0.0 f.20441.0.0 f.20446.0.0 f.20449.0.0 f.20450.0.0 ... \\\n", "0 4 1 1 1 1 ... \n", "1 5 1 1 1 1 ... \n", "2 4 1 1 1 1 ... \n", "3 6 1 1 1 1 ... \n", "4 5 1 1 1 1 ... \n", ".. ... ... ... ... ... ... \n", "203 6 1 1 1 1 ... \n", "204 6 1 1 1 1 ... \n", "205 5 1 1 1 1 ... \n", "206 5 1 1 1 1 ... \n", "207 1 1 1 1 1 ... \n", "\n", " f.25911.2.0 f.25912.2.0 f.25913.2.0 f.25914.2.0 f.25915.2.0 \\\n", "0 3103.94 2108.26 349.68 2454.28 1499.05 \n", "1 2729.46 1758.55 391.49 1681.65 1240.44 \n", "2 3485.94 2086.91 334.21 2531.93 1387.53 \n", "3 4628.37 3182.58 546.57 2967.89 2333.54 \n", "4 3145.97 2783.52 384.19 2612.01 1741.22 \n", ".. ... ... ... ... ... \n", "203 4291.12 3194.45 466.79 3356.21 2155.55 \n", "204 3604.23 1998.52 322.44 2110.01 1777.50 \n", "205 2727.82 2622.36 462.89 2096.06 2229.33 \n", "206 3200.32 2850.50 469.11 2503.11 1809.41 \n", "207 3458.63 2004.10 432.21 2471.80 1536.80 \n", "\n", " f.25916.2.0 f.25917.2.0 f.25918.2.0 f.25919.2.0 f.25920.2.0 \n", "0 330.690 1845.71 509.049 223.49 489.589 \n", "1 301.750 1422.23 553.770 157.36 495.181 \n", "2 385.320 1698.33 421.880 229.24 404.501 \n", "3 505.000 2671.06 538.011 183.91 520.930 \n", "4 432.290 1876.94 442.701 216.41 408.791 \n", ".. ... ... ... ... ... \n", "203 377.360 2547.30 604.691 278.93 495.681 \n", "204 413.429 1885.11 312.789 230.35 291.969 \n", "205 511.230 2261.56 482.760 279.04 396.811 \n", "206 378.940 1794.23 478.320 209.72 354.389 \n", "207 379.370 1980.78 493.151 253.46 425.460 \n", "\n", "[208 rows x 179 columns]" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data_raw" ] }, { "cell_type": "code", "execution_count": 10, "id": "7788b909", "metadata": {}, "outputs": [], "source": [ "data=data_raw" ] }, { "cell_type": "code", "execution_count": 11, "id": "2d6989ca", "metadata": {}, "outputs": [], "source": [ "data['f.20434.0.0'] = data['f.20434.0.0'].fillna(data['f.20434.0.0'].mean())" ] }, { "cell_type": "code", "execution_count": 12, "id": "e98befd3", "metadata": {}, "outputs": [], "source": [ "data['f.20433.0.0'] = data['f.20433.0.0'].fillna(data['f.20433.0.0'].mean())" ] }, { "cell_type": "code", "execution_count": 13, "id": "5fee8180", "metadata": {}, "outputs": [], "source": [ "data['f.4620.0.0'] = data['f.4620.0.0'].fillna(data['f.4620.0.0'].mean())" ] }, { "cell_type": "code", "execution_count": 14, "id": "99174458", "metadata": {}, "outputs": [], "source": [ "data_null=data_raw.iloc[:,1:26]" ] }, { "cell_type": "code", "execution_count": 15, "id": "14d8c0fd", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "f.1548.0.0 0\n", "f.1558.0.0 0\n", "f.20116.0.0 0\n", "f.20435.0.0 0\n", "f.20438.0.0 0\n", "f.20441.0.0 0\n", "f.20446.0.0 0\n", "f.20449.0.0 0\n", "f.20450.0.0 0\n", "f.20500.0.0 0\n", "f.20508.0.0 0\n", "f.20511.0.0 0\n", "f.20514.0.0 0\n", "f.20518.0.0 0\n", "f.20519.0.0 0\n", "f.20536.0.0 0\n", "f.2100.0.0 0\n", "f.21000.0.0 0\n", "f.31.0.0 0\n", "f.6142.0.0 0\n", "f.1160.0.0 0\n", "f.21003.0.0 0\n", "f.4620.0.0 0\n", "f.20433.0.0 0\n", "f.20434.0.0 0\n", "dtype: int64" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "null_all = data_null.isnull().sum()\n", "null_all" ] }, { "cell_type": "code", "execution_count": 16, "id": "e9e280d7", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
f.1548.0.0f.1558.0.0f.20116.0.0f.20435.0.0f.20438.0.0f.20441.0.0f.20446.0.0f.20449.0.0f.20450.0.0f.20500.0.0...f.25911.2.0f.25912.2.0f.25913.2.0f.25914.2.0f.25915.2.0f.25916.2.0f.25917.2.0f.25918.2.0f.25919.2.0f.25920.2.0
03411411111...3103.942108.26349.682454.281499.05330.6901845.71509.049223.49489.589
13501511111...2729.461758.55391.491681.651240.44301.7501422.23553.770157.36495.181
21111411110...3485.942086.91334.212531.931387.53385.3201698.33421.880229.24404.501
32311611111...4628.373182.58546.572967.892333.54505.0002671.06538.011183.91520.930
42311511111...3145.972783.52384.192612.011741.22432.2901876.94442.701216.41408.791
..................................................................
2033301611111...4291.123194.45466.793356.212155.55377.3602547.30604.691278.93495.681
2042601611111...3604.231998.52322.442110.011777.50413.4291885.11312.789230.35291.969
2051411511111...2727.822622.36462.892096.062229.33511.2302261.56482.760279.04396.811
2062401511111...3200.322850.50469.112503.111809.41378.9401794.23478.320209.72354.389
2072401111111...3458.632004.10432.212471.801536.80379.3701980.78493.151253.46425.460
\n", "

208 rows × 178 columns

\n", "
" ], "text/plain": [ " f.1548.0.0 f.1558.0.0 f.20116.0.0 f.20435.0.0 f.20438.0.0 \\\n", "0 3 4 1 1 4 \n", "1 3 5 0 1 5 \n", "2 1 1 1 1 4 \n", "3 2 3 1 1 6 \n", "4 2 3 1 1 5 \n", ".. ... ... ... ... ... \n", "203 3 3 0 1 6 \n", "204 2 6 0 1 6 \n", "205 1 4 1 1 5 \n", "206 2 4 0 1 5 \n", "207 2 4 0 1 1 \n", "\n", " f.20441.0.0 f.20446.0.0 f.20449.0.0 f.20450.0.0 f.20500.0.0 ... \\\n", "0 1 1 1 1 1 ... \n", "1 1 1 1 1 1 ... \n", "2 1 1 1 1 0 ... \n", "3 1 1 1 1 1 ... \n", "4 1 1 1 1 1 ... \n", ".. ... ... ... ... ... ... \n", "203 1 1 1 1 1 ... \n", "204 1 1 1 1 1 ... \n", "205 1 1 1 1 1 ... \n", "206 1 1 1 1 1 ... \n", "207 1 1 1 1 1 ... \n", "\n", " f.25911.2.0 f.25912.2.0 f.25913.2.0 f.25914.2.0 f.25915.2.0 \\\n", "0 3103.94 2108.26 349.68 2454.28 1499.05 \n", "1 2729.46 1758.55 391.49 1681.65 1240.44 \n", "2 3485.94 2086.91 334.21 2531.93 1387.53 \n", "3 4628.37 3182.58 546.57 2967.89 2333.54 \n", "4 3145.97 2783.52 384.19 2612.01 1741.22 \n", ".. ... ... ... ... ... \n", "203 4291.12 3194.45 466.79 3356.21 2155.55 \n", "204 3604.23 1998.52 322.44 2110.01 1777.50 \n", "205 2727.82 2622.36 462.89 2096.06 2229.33 \n", "206 3200.32 2850.50 469.11 2503.11 1809.41 \n", "207 3458.63 2004.10 432.21 2471.80 1536.80 \n", "\n", " f.25916.2.0 f.25917.2.0 f.25918.2.0 f.25919.2.0 f.25920.2.0 \n", "0 330.690 1845.71 509.049 223.49 489.589 \n", "1 301.750 1422.23 553.770 157.36 495.181 \n", "2 385.320 1698.33 421.880 229.24 404.501 \n", "3 505.000 2671.06 538.011 183.91 520.930 \n", "4 432.290 1876.94 442.701 216.41 408.791 \n", ".. ... ... ... ... ... \n", "203 377.360 2547.30 604.691 278.93 495.681 \n", "204 413.429 1885.11 312.789 230.35 291.969 \n", "205 511.230 2261.56 482.760 279.04 396.811 \n", "206 378.940 1794.23 478.320 209.72 354.389 \n", "207 379.370 1980.78 493.151 253.46 425.460 \n", "\n", "[208 rows x 178 columns]" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "X=data.iloc[:,1:179]\n", "X" ] }, { "cell_type": "code", "execution_count": 17, "id": "77d1942e", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0 0\n", "1 0\n", "2 1\n", "3 1\n", "4 1\n", " ..\n", "203 0\n", "204 1\n", "205 0\n", "206 1\n", "207 1\n", "Name: f.20483.0.0, Length: 208, dtype: int64" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "y=data.iloc[:,0]\n", "y" ] }, { "cell_type": "code", "execution_count": 18, "id": "d5918a25", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[ 2.02347522, 0.66084464, 0.64818969, ..., 0.22260438,\n", " -0.12889293, 0.34214085],\n", " [ 2.02347522, 1.34470376, -0.9015052 , ..., 0.79516902,\n", " -1.96863998, 0.40649794],\n", " [-1.39833653, -1.39073274, 0.64818969, ..., -0.89342359,\n", " 0.03107298, -0.63711802],\n", " ...,\n", " [-1.39833653, 0.66084464, 0.64818969, ..., -0.11397467,\n", " 1.41651684, -0.72562052],\n", " [ 0.31256934, 0.66084464, -0.9015052 , ..., -0.17082016,\n", " -0.51197651, -1.21384588],\n", " [ 0.31256934, 0.66084464, -0.9015052 , ..., 0.01906169,\n", " 0.7048772 , -0.39590555]])" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.preprocessing import StandardScaler\n", "scaler = StandardScaler() #实例化\n", "x_std =scaler.fit_transform(X) #训练和导出结果一步达成\n", "x_std" ] }, { "cell_type": "code", "execution_count": 19, "id": "3f684f7d", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[1. , 0.6 , 0.5 , ..., 0.48052364, 0.43580355,\n", " 0.52665958],\n", " [1. , 0.8 , 0. , ..., 0.56683412, 0.05143854,\n", " 0.53658273],\n", " [0. , 0. , 0.5 , ..., 0.31228951, 0.46922406,\n", " 0.37566877],\n", " ...,\n", " [0. , 0.6 , 0.5 , ..., 0.42978649, 0.7586748 ,\n", " 0.36202267],\n", " [0.5 , 0.6 , 0. , ..., 0.42121739, 0.35576867,\n", " 0.28674376],\n", " [0.5 , 0.6 , 0. , ..., 0.44984087, 0.60999709,\n", " 0.41286105]])" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.preprocessing import MinMaxScaler\n", "scaler = MinMaxScaler() #实例化\n", "x_std =scaler.fit_transform(X) #训练和导出结果一步达成\n", "x_std" ] }, { "cell_type": "code", "execution_count": 20, "id": "45a8b28f", "metadata": {}, "outputs": [], "source": [ "data_std = pd.DataFrame(x_std)" ] }, { "cell_type": "code", "execution_count": 21, "id": "e880b4c7", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
0123456789...168169170171172173174175176177
01.00.60.51.00.61.01.01.01.01.0...0.3603340.2200360.2958270.3511110.2404120.2196360.2924860.4805240.4358040.526660
11.00.80.01.00.81.01.01.01.01.0...0.2707060.0641370.3992430.0690930.1027550.1523530.0854390.5668340.0514390.536583
20.00.00.51.00.61.01.01.01.00.0...0.4517620.2105180.2575630.3794540.1810500.3466470.2204290.3122900.4692240.375669
30.50.40.51.01.01.01.01.01.01.0...0.7251920.6989630.7828290.5385830.6846090.6248950.6960150.5364200.2057540.582275
40.50.40.51.00.81.01.01.01.01.0...0.3703940.5210640.3811870.4086840.3693180.4558500.3077550.3524740.3946530.383281
..................................................................
2031.00.40.01.01.01.01.01.01.01.0...0.6444740.7042550.5854960.6803240.5898650.3281410.6355060.6651100.7580350.537470
2040.51.00.01.01.01.01.01.01.01.0...0.4800740.1711140.2284500.2254490.3886300.4119990.3117490.1017460.4756760.175978
2050.00.60.51.00.81.01.01.01.01.0...0.2703130.4492190.5758490.2203570.6291380.6393800.4958030.4297860.7586750.362023
2060.50.60.01.00.81.01.01.01.01.0...0.3834020.5509230.5912340.3689340.4056160.3318140.2673160.4212170.3557690.286744
2070.50.60.01.00.01.01.01.01.01.0...0.4452260.1736020.4999630.3575060.2605060.3328140.3585240.4498410.6099970.412861
\n", "

208 rows × 178 columns

\n", "
" ], "text/plain": [ " 0 1 2 3 4 5 6 7 8 9 ... 168 \\\n", "0 1.0 0.6 0.5 1.0 0.6 1.0 1.0 1.0 1.0 1.0 ... 0.360334 \n", "1 1.0 0.8 0.0 1.0 0.8 1.0 1.0 1.0 1.0 1.0 ... 0.270706 \n", "2 0.0 0.0 0.5 1.0 0.6 1.0 1.0 1.0 1.0 0.0 ... 0.451762 \n", "3 0.5 0.4 0.5 1.0 1.0 1.0 1.0 1.0 1.0 1.0 ... 0.725192 \n", "4 0.5 0.4 0.5 1.0 0.8 1.0 1.0 1.0 1.0 1.0 ... 0.370394 \n", ".. ... ... ... ... ... ... ... ... ... ... ... ... \n", "203 1.0 0.4 0.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 ... 0.644474 \n", "204 0.5 1.0 0.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 ... 0.480074 \n", "205 0.0 0.6 0.5 1.0 0.8 1.0 1.0 1.0 1.0 1.0 ... 0.270313 \n", "206 0.5 0.6 0.0 1.0 0.8 1.0 1.0 1.0 1.0 1.0 ... 0.383402 \n", "207 0.5 0.6 0.0 1.0 0.0 1.0 1.0 1.0 1.0 1.0 ... 0.445226 \n", "\n", " 169 170 171 172 173 174 175 \\\n", "0 0.220036 0.295827 0.351111 0.240412 0.219636 0.292486 0.480524 \n", "1 0.064137 0.399243 0.069093 0.102755 0.152353 0.085439 0.566834 \n", "2 0.210518 0.257563 0.379454 0.181050 0.346647 0.220429 0.312290 \n", "3 0.698963 0.782829 0.538583 0.684609 0.624895 0.696015 0.536420 \n", "4 0.521064 0.381187 0.408684 0.369318 0.455850 0.307755 0.352474 \n", ".. ... ... ... ... ... ... ... \n", "203 0.704255 0.585496 0.680324 0.589865 0.328141 0.635506 0.665110 \n", "204 0.171114 0.228450 0.225449 0.388630 0.411999 0.311749 0.101746 \n", "205 0.449219 0.575849 0.220357 0.629138 0.639380 0.495803 0.429786 \n", "206 0.550923 0.591234 0.368934 0.405616 0.331814 0.267316 0.421217 \n", "207 0.173602 0.499963 0.357506 0.260506 0.332814 0.358524 0.449841 \n", "\n", " 176 177 \n", "0 0.435804 0.526660 \n", "1 0.051439 0.536583 \n", "2 0.469224 0.375669 \n", "3 0.205754 0.582275 \n", "4 0.394653 0.383281 \n", ".. ... ... \n", "203 0.758035 0.537470 \n", "204 0.475676 0.175978 \n", "205 0.758675 0.362023 \n", "206 0.355769 0.286744 \n", "207 0.609997 0.412861 \n", "\n", "[208 rows x 178 columns]" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data_std" ] }, { "cell_type": "code", "execution_count": 22, "id": "b428ed91", "metadata": {}, "outputs": [], "source": [ "data_X=data_std" ] }, { "cell_type": "code", "execution_count": 23, "id": "254e9601", "metadata": {}, "outputs": [], "source": [ "a=X.columns.values" ] }, { "cell_type": "code", "execution_count": 24, "id": "677d9425", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array(['f.1548.0.0', 'f.1558.0.0', 'f.20116.0.0', 'f.20435.0.0',\n", " 'f.20438.0.0', 'f.20441.0.0', 'f.20446.0.0', 'f.20449.0.0',\n", " 'f.20450.0.0', 'f.20500.0.0', 'f.20508.0.0', 'f.20511.0.0',\n", " 'f.20514.0.0', 'f.20518.0.0', 'f.20519.0.0', 'f.20536.0.0',\n", " 'f.2100.0.0', 'f.21000.0.0', 'f.31.0.0', 'f.6142.0.0',\n", " 'f.1160.0.0', 'f.21003.0.0', 'f.4620.0.0', 'f.20433.0.0',\n", " 'f.20434.0.0', 'f.25011.2.0', 'f.25012.2.0', 'f.25013.2.0',\n", " 'f.25014.2.0', 'f.25015.2.0', 'f.25016.2.0', 'f.25017.2.0',\n", " 'f.25018.2.0', 'f.25019.2.0', 'f.25020.2.0', 'f.25021.2.0',\n", " 'f.25022.2.0', 'f.25023.2.0', 'f.25024.2.0', 'f.25782.2.0',\n", " 'f.25783.2.0', 'f.25784.2.0', 'f.25785.2.0', 'f.25786.2.0',\n", " 'f.25787.2.0', 'f.25788.2.0', 'f.25789.2.0', 'f.25790.2.0',\n", " 'f.25791.2.0', 'f.25792.2.0', 'f.25793.2.0', 'f.25794.2.0',\n", " 'f.25795.2.0', 'f.25796.2.0', 'f.25797.2.0', 'f.25798.2.0',\n", " 'f.25799.2.0', 'f.25800.2.0', 'f.25801.2.0', 'f.25802.2.0',\n", " 'f.25803.2.0', 'f.25804.2.0', 'f.25805.2.0', 'f.25806.2.0',\n", " 'f.25807.2.0', 'f.25808.2.0', 'f.25809.2.0', 'f.25810.2.0',\n", " 'f.25811.2.0', 'f.25812.2.0', 'f.25813.2.0', 'f.25814.2.0',\n", " 'f.25815.2.0', 'f.25816.2.0', 'f.25817.2.0', 'f.25818.2.0',\n", " 'f.25819.2.0', 'f.25820.2.0', 'f.25821.2.0', 'f.25822.2.0',\n", " 'f.25823.2.0', 'f.25824.2.0', 'f.25825.2.0', 'f.25826.2.0',\n", " 'f.25827.2.0', 'f.25828.2.0', 'f.25829.2.0', 'f.25830.2.0',\n", " 'f.25831.2.0', 'f.25832.2.0', 'f.25833.2.0', 'f.25834.2.0',\n", " 'f.25835.2.0', 'f.25836.2.0', 'f.25837.2.0', 'f.25838.2.0',\n", " 'f.25839.2.0', 'f.25840.2.0', 'f.25841.2.0', 'f.25842.2.0',\n", " 'f.25843.2.0', 'f.25844.2.0', 'f.25845.2.0', 'f.25846.2.0',\n", " 'f.25847.2.0', 'f.25848.2.0', 'f.25849.2.0', 'f.25850.2.0',\n", " 'f.25851.2.0', 'f.25852.2.0', 'f.25853.2.0', 'f.25854.2.0',\n", " 'f.25855.2.0', 'f.25856.2.0', 'f.25857.2.0', 'f.25858.2.0',\n", " 'f.25859.2.0', 'f.25860.2.0', 'f.25861.2.0', 'f.25862.2.0',\n", " 'f.25863.2.0', 'f.25864.2.0', 'f.25865.2.0', 'f.25866.2.0',\n", " 'f.25867.2.0', 'f.25868.2.0', 'f.25869.2.0', 'f.25870.2.0',\n", " 'f.25871.2.0', 'f.25872.2.0', 'f.25873.2.0', 'f.25874.2.0',\n", " 'f.25875.2.0', 'f.25876.2.0', 'f.25877.2.0', 'f.25878.2.0',\n", " 'f.25879.2.0', 'f.25880.2.0', 'f.25881.2.0', 'f.25882.2.0',\n", " 'f.25883.2.0', 'f.25884.2.0', 'f.25885.2.0', 'f.25886.2.0',\n", " 'f.25887.2.0', 'f.25888.2.0', 'f.25889.2.0', 'f.25890.2.0',\n", " 'f.25891.2.0', 'f.25892.2.0', 'f.25893.2.0', 'f.25894.2.0',\n", " 'f.25895.2.0', 'f.25896.2.0', 'f.25897.2.0', 'f.25898.2.0',\n", " 'f.25899.2.0', 'f.25900.2.0', 'f.25901.2.0', 'f.25902.2.0',\n", " 'f.25903.2.0', 'f.25904.2.0', 'f.25905.2.0', 'f.25906.2.0',\n", " 'f.25907.2.0', 'f.25908.2.0', 'f.25909.2.0', 'f.25910.2.0',\n", " 'f.25911.2.0', 'f.25912.2.0', 'f.25913.2.0', 'f.25914.2.0',\n", " 'f.25915.2.0', 'f.25916.2.0', 'f.25917.2.0', 'f.25918.2.0',\n", " 'f.25919.2.0', 'f.25920.2.0'], dtype=object)" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "a" ] }, { "cell_type": "code", "execution_count": 25, "id": "62ea4d84", "metadata": {}, "outputs": [], "source": [ "data_X.columns=a" ] }, { "cell_type": "code", "execution_count": 26, "id": "03ee83ae", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
f.1548.0.0f.1558.0.0f.20116.0.0f.20435.0.0f.20438.0.0f.20441.0.0f.20446.0.0f.20449.0.0f.20450.0.0f.20500.0.0...f.25911.2.0f.25912.2.0f.25913.2.0f.25914.2.0f.25915.2.0f.25916.2.0f.25917.2.0f.25918.2.0f.25919.2.0f.25920.2.0
01.00.60.51.00.61.01.01.01.01.0...0.3603340.2200360.2958270.3511110.2404120.2196360.2924860.4805240.4358040.526660
11.00.80.01.00.81.01.01.01.01.0...0.2707060.0641370.3992430.0690930.1027550.1523530.0854390.5668340.0514390.536583
20.00.00.51.00.61.01.01.01.00.0...0.4517620.2105180.2575630.3794540.1810500.3466470.2204290.3122900.4692240.375669
30.50.40.51.01.01.01.01.01.01.0...0.7251920.6989630.7828290.5385830.6846090.6248950.6960150.5364200.2057540.582275
40.50.40.51.00.81.01.01.01.01.0...0.3703940.5210640.3811870.4086840.3693180.4558500.3077550.3524740.3946530.383281
..................................................................
2031.00.40.01.01.01.01.01.01.01.0...0.6444740.7042550.5854960.6803240.5898650.3281410.6355060.6651100.7580350.537470
2040.51.00.01.01.01.01.01.01.01.0...0.4800740.1711140.2284500.2254490.3886300.4119990.3117490.1017460.4756760.175978
2050.00.60.51.00.81.01.01.01.01.0...0.2703130.4492190.5758490.2203570.6291380.6393800.4958030.4297860.7586750.362023
2060.50.60.01.00.81.01.01.01.01.0...0.3834020.5509230.5912340.3689340.4056160.3318140.2673160.4212170.3557690.286744
2070.50.60.01.00.01.01.01.01.01.0...0.4452260.1736020.4999630.3575060.2605060.3328140.3585240.4498410.6099970.412861
\n", "

208 rows × 178 columns

\n", "
" ], "text/plain": [ " f.1548.0.0 f.1558.0.0 f.20116.0.0 f.20435.0.0 f.20438.0.0 \\\n", "0 1.0 0.6 0.5 1.0 0.6 \n", "1 1.0 0.8 0.0 1.0 0.8 \n", "2 0.0 0.0 0.5 1.0 0.6 \n", "3 0.5 0.4 0.5 1.0 1.0 \n", "4 0.5 0.4 0.5 1.0 0.8 \n", ".. ... ... ... ... ... \n", "203 1.0 0.4 0.0 1.0 1.0 \n", "204 0.5 1.0 0.0 1.0 1.0 \n", "205 0.0 0.6 0.5 1.0 0.8 \n", "206 0.5 0.6 0.0 1.0 0.8 \n", "207 0.5 0.6 0.0 1.0 0.0 \n", "\n", " f.20441.0.0 f.20446.0.0 f.20449.0.0 f.20450.0.0 f.20500.0.0 ... \\\n", "0 1.0 1.0 1.0 1.0 1.0 ... \n", "1 1.0 1.0 1.0 1.0 1.0 ... \n", "2 1.0 1.0 1.0 1.0 0.0 ... \n", "3 1.0 1.0 1.0 1.0 1.0 ... \n", "4 1.0 1.0 1.0 1.0 1.0 ... \n", ".. ... ... ... ... ... ... \n", "203 1.0 1.0 1.0 1.0 1.0 ... \n", "204 1.0 1.0 1.0 1.0 1.0 ... \n", "205 1.0 1.0 1.0 1.0 1.0 ... \n", "206 1.0 1.0 1.0 1.0 1.0 ... \n", "207 1.0 1.0 1.0 1.0 1.0 ... \n", "\n", " f.25911.2.0 f.25912.2.0 f.25913.2.0 f.25914.2.0 f.25915.2.0 \\\n", "0 0.360334 0.220036 0.295827 0.351111 0.240412 \n", "1 0.270706 0.064137 0.399243 0.069093 0.102755 \n", "2 0.451762 0.210518 0.257563 0.379454 0.181050 \n", "3 0.725192 0.698963 0.782829 0.538583 0.684609 \n", "4 0.370394 0.521064 0.381187 0.408684 0.369318 \n", ".. ... ... ... ... ... \n", "203 0.644474 0.704255 0.585496 0.680324 0.589865 \n", "204 0.480074 0.171114 0.228450 0.225449 0.388630 \n", "205 0.270313 0.449219 0.575849 0.220357 0.629138 \n", "206 0.383402 0.550923 0.591234 0.368934 0.405616 \n", "207 0.445226 0.173602 0.499963 0.357506 0.260506 \n", "\n", " f.25916.2.0 f.25917.2.0 f.25918.2.0 f.25919.2.0 f.25920.2.0 \n", "0 0.219636 0.292486 0.480524 0.435804 0.526660 \n", "1 0.152353 0.085439 0.566834 0.051439 0.536583 \n", "2 0.346647 0.220429 0.312290 0.469224 0.375669 \n", "3 0.624895 0.696015 0.536420 0.205754 0.582275 \n", "4 0.455850 0.307755 0.352474 0.394653 0.383281 \n", ".. ... ... ... ... ... \n", "203 0.328141 0.635506 0.665110 0.758035 0.537470 \n", "204 0.411999 0.311749 0.101746 0.475676 0.175978 \n", "205 0.639380 0.495803 0.429786 0.758675 0.362023 \n", "206 0.331814 0.267316 0.421217 0.355769 0.286744 \n", "207 0.332814 0.358524 0.449841 0.609997 0.412861 \n", "\n", "[208 rows x 178 columns]" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data_X" ] }, { "cell_type": "code", "execution_count": 27, "id": "7305b905", "metadata": {}, "outputs": [], "source": [ "data = pd.concat([y,data_X], axis=1)" ] }, { "cell_type": "code", "execution_count": 28, "id": "60ac5c9e", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
f.20483.0.0f.1548.0.0f.1558.0.0f.20116.0.0f.20435.0.0f.20438.0.0f.20441.0.0f.20446.0.0f.20449.0.0f.20450.0.0...f.25911.2.0f.25912.2.0f.25913.2.0f.25914.2.0f.25915.2.0f.25916.2.0f.25917.2.0f.25918.2.0f.25919.2.0f.25920.2.0
001.00.60.51.00.61.01.01.01.0...0.3603340.2200360.2958270.3511110.2404120.2196360.2924860.4805240.4358040.526660
101.00.80.01.00.81.01.01.01.0...0.2707060.0641370.3992430.0690930.1027550.1523530.0854390.5668340.0514390.536583
210.00.00.51.00.61.01.01.01.0...0.4517620.2105180.2575630.3794540.1810500.3466470.2204290.3122900.4692240.375669
310.50.40.51.01.01.01.01.01.0...0.7251920.6989630.7828290.5385830.6846090.6248950.6960150.5364200.2057540.582275
410.50.40.51.00.81.01.01.01.0...0.3703940.5210640.3811870.4086840.3693180.4558500.3077550.3524740.3946530.383281
..................................................................
20301.00.40.01.01.01.01.01.01.0...0.6444740.7042550.5854960.6803240.5898650.3281410.6355060.6651100.7580350.537470
20410.51.00.01.01.01.01.01.01.0...0.4800740.1711140.2284500.2254490.3886300.4119990.3117490.1017460.4756760.175978
20500.00.60.51.00.81.01.01.01.0...0.2703130.4492190.5758490.2203570.6291380.6393800.4958030.4297860.7586750.362023
20610.50.60.01.00.81.01.01.01.0...0.3834020.5509230.5912340.3689340.4056160.3318140.2673160.4212170.3557690.286744
20710.50.60.01.00.01.01.01.01.0...0.4452260.1736020.4999630.3575060.2605060.3328140.3585240.4498410.6099970.412861
\n", "

208 rows × 179 columns

\n", "
" ], "text/plain": [ " f.20483.0.0 f.1548.0.0 f.1558.0.0 f.20116.0.0 f.20435.0.0 \\\n", "0 0 1.0 0.6 0.5 1.0 \n", "1 0 1.0 0.8 0.0 1.0 \n", "2 1 0.0 0.0 0.5 1.0 \n", "3 1 0.5 0.4 0.5 1.0 \n", "4 1 0.5 0.4 0.5 1.0 \n", ".. ... ... ... ... ... \n", "203 0 1.0 0.4 0.0 1.0 \n", "204 1 0.5 1.0 0.0 1.0 \n", "205 0 0.0 0.6 0.5 1.0 \n", "206 1 0.5 0.6 0.0 1.0 \n", "207 1 0.5 0.6 0.0 1.0 \n", "\n", " f.20438.0.0 f.20441.0.0 f.20446.0.0 f.20449.0.0 f.20450.0.0 ... \\\n", "0 0.6 1.0 1.0 1.0 1.0 ... \n", "1 0.8 1.0 1.0 1.0 1.0 ... \n", "2 0.6 1.0 1.0 1.0 1.0 ... \n", "3 1.0 1.0 1.0 1.0 1.0 ... \n", "4 0.8 1.0 1.0 1.0 1.0 ... \n", ".. ... ... ... ... ... ... \n", "203 1.0 1.0 1.0 1.0 1.0 ... \n", "204 1.0 1.0 1.0 1.0 1.0 ... \n", "205 0.8 1.0 1.0 1.0 1.0 ... \n", "206 0.8 1.0 1.0 1.0 1.0 ... \n", "207 0.0 1.0 1.0 1.0 1.0 ... \n", "\n", " f.25911.2.0 f.25912.2.0 f.25913.2.0 f.25914.2.0 f.25915.2.0 \\\n", "0 0.360334 0.220036 0.295827 0.351111 0.240412 \n", "1 0.270706 0.064137 0.399243 0.069093 0.102755 \n", "2 0.451762 0.210518 0.257563 0.379454 0.181050 \n", "3 0.725192 0.698963 0.782829 0.538583 0.684609 \n", "4 0.370394 0.521064 0.381187 0.408684 0.369318 \n", ".. ... ... ... ... ... \n", "203 0.644474 0.704255 0.585496 0.680324 0.589865 \n", "204 0.480074 0.171114 0.228450 0.225449 0.388630 \n", "205 0.270313 0.449219 0.575849 0.220357 0.629138 \n", "206 0.383402 0.550923 0.591234 0.368934 0.405616 \n", "207 0.445226 0.173602 0.499963 0.357506 0.260506 \n", "\n", " f.25916.2.0 f.25917.2.0 f.25918.2.0 f.25919.2.0 f.25920.2.0 \n", "0 0.219636 0.292486 0.480524 0.435804 0.526660 \n", "1 0.152353 0.085439 0.566834 0.051439 0.536583 \n", "2 0.346647 0.220429 0.312290 0.469224 0.375669 \n", "3 0.624895 0.696015 0.536420 0.205754 0.582275 \n", "4 0.455850 0.307755 0.352474 0.394653 0.383281 \n", ".. ... ... ... ... ... \n", "203 0.328141 0.635506 0.665110 0.758035 0.537470 \n", "204 0.411999 0.311749 0.101746 0.475676 0.175978 \n", "205 0.639380 0.495803 0.429786 0.758675 0.362023 \n", "206 0.331814 0.267316 0.421217 0.355769 0.286744 \n", "207 0.332814 0.358524 0.449841 0.609997 0.412861 \n", "\n", "[208 rows x 179 columns]" ] }, "execution_count": 28, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data" ] }, { "cell_type": "code", "execution_count": 29, "id": "54f1a0ff", "metadata": {}, "outputs": [], "source": [ "from sklearn.feature_selection import RFECV" ] }, { "cell_type": "code", "execution_count": 30, "id": "e98849f6", "metadata": {}, "outputs": [], "source": [ "from sklearn.svm import SVC" ] }, { "cell_type": "code", "execution_count": 31, "id": "242ef6bf", "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import LeaveOneOut" ] }, { "cell_type": "code", "execution_count": 32, "id": "fb15cb51", "metadata": {}, "outputs": [], "source": [ "loo=LeaveOneOut()" ] }, { "cell_type": "code", "execution_count": 33, "id": "968388a4", "metadata": {}, "outputs": [], "source": [ "svc = SVC(kernel=\"linear\")" ] }, { "cell_type": "code", "execution_count": 34, "id": "709e46d6", "metadata": {}, "outputs": [], "source": [ "selector=RFECV(estimator=svc,step=1,cv=loo)" ] }, { "cell_type": "code", "execution_count": 35, "id": "7b59bda2", "metadata": {}, "outputs": [], "source": [ "selector=selector.fit(data_X,y)" ] }, { "cell_type": "code", "execution_count": 36, "id": "635fe6ee", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "RFECV(cv=LeaveOneOut(), estimator=SVC(kernel='linear'))" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" } ], "source": [ "selector" ] }, { "cell_type": "code", "execution_count": 37, "id": "9317e043", "metadata": {}, "outputs": [], "source": [ "X_REFCV=selector.transform(data_X)" ] }, { "cell_type": "code", "execution_count": 38, "id": "a4228413", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[1. , 0.4137931 , 0.001002 , ..., 0.22003584, 0.35111054,\n", " 0.43580355],\n", " [1. , 0.31034483, 0.00200401, ..., 0.06413663, 0.06909277,\n", " 0.05143854],\n", " [1. , 0.24137931, 0.00300601, ..., 0.2105181 , 0.37945358,\n", " 0.46922406],\n", " ...,\n", " [1. , 0.31034483, 0.00200401, ..., 0.44921941, 0.22035661,\n", " 0.7586748 ],\n", " [1. , 0.86206897, 0.1492986 , ..., 0.55092324, 0.36893399,\n", " 0.35576867],\n", " [1. , 0.20689655, 0. , ..., 0.17360176, 0.35750552,\n", " 0.60999709]])" ] }, "execution_count": 38, "metadata": {}, "output_type": "execute_result" } ], "source": [ "X_REFCV" ] }, { "cell_type": "code", "execution_count": 39, "id": "6714606c", "metadata": {}, "outputs": [], "source": [ "X_REFCV = pd.DataFrame(X_REFCV)" ] }, { "cell_type": "code", "execution_count": 40, "id": "b0fc8148", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
0123456789...11121314151617181920
01.00.4137930.0010020.3848340.7388970.3947600.6350940.2616340.4244690.363180...0.3984600.7417170.4301970.2358920.7848070.6632160.138750.2200360.3511110.435804
11.00.3103450.0020040.0955480.6267910.2917710.4333780.5326460.3196890.329092...0.4837090.0821840.0000000.5785420.3734080.3178390.025000.0641370.0690930.051439
21.00.2413790.0030060.0825370.3825210.2411180.3136140.0000000.1112180.134122...0.2265970.0124000.1288720.2544960.2386760.1090780.203750.2105180.3794540.469224
31.00.6896550.0050100.3417360.6540110.3614190.5948550.6145540.2862610.156880...0.5780920.3703660.7829380.5130210.3215680.6148820.103750.6989630.5385830.205754
41.00.1034480.0190380.3384830.7578800.5155630.7314120.6950720.6766510.371616...0.5744990.5003280.7069140.7132380.4554890.3235210.243750.5210640.4086840.394653
..................................................................
2031.00.2068970.0040080.4781460.7410460.6608260.7604070.3261800.1304920.635859...0.3881430.3900560.6222010.4342000.1439540.3935840.095000.7042550.6803240.758035
2041.00.7241380.0200550.2419190.5476360.1924050.2892270.3463640.3682660.239999...0.3567510.2104840.2814110.8051300.6165910.4441280.000000.1711140.2254490.475676
2051.00.3103450.0020040.4171580.5787970.1878010.5169500.0448380.3889650.295112...0.3835820.2780100.5890700.1725850.5904430.4062510.256250.4492190.2203570.758675
2061.00.8620690.1492990.2850170.5881090.3379110.5978660.3273620.3173120.182946...0.2786370.2730820.2494120.2802870.3910260.3668270.035000.5509230.3689340.355769
2071.00.2068970.0000000.5102660.8033670.4226590.6179970.5348560.4507210.445311...0.5451280.7196230.4820870.3975950.7007360.4155190.413750.1736020.3575060.609997
\n", "

208 rows × 21 columns

\n", "
" ], "text/plain": [ " 0 1 2 3 4 5 6 \\\n", "0 1.0 0.413793 0.001002 0.384834 0.738897 0.394760 0.635094 \n", "1 1.0 0.310345 0.002004 0.095548 0.626791 0.291771 0.433378 \n", "2 1.0 0.241379 0.003006 0.082537 0.382521 0.241118 0.313614 \n", "3 1.0 0.689655 0.005010 0.341736 0.654011 0.361419 0.594855 \n", "4 1.0 0.103448 0.019038 0.338483 0.757880 0.515563 0.731412 \n", ".. ... ... ... ... ... ... ... \n", "203 1.0 0.206897 0.004008 0.478146 0.741046 0.660826 0.760407 \n", "204 1.0 0.724138 0.020055 0.241919 0.547636 0.192405 0.289227 \n", "205 1.0 0.310345 0.002004 0.417158 0.578797 0.187801 0.516950 \n", "206 1.0 0.862069 0.149299 0.285017 0.588109 0.337911 0.597866 \n", "207 1.0 0.206897 0.000000 0.510266 0.803367 0.422659 0.617997 \n", "\n", " 7 8 9 ... 11 12 13 \\\n", "0 0.261634 0.424469 0.363180 ... 0.398460 0.741717 0.430197 \n", "1 0.532646 0.319689 0.329092 ... 0.483709 0.082184 0.000000 \n", "2 0.000000 0.111218 0.134122 ... 0.226597 0.012400 0.128872 \n", "3 0.614554 0.286261 0.156880 ... 0.578092 0.370366 0.782938 \n", "4 0.695072 0.676651 0.371616 ... 0.574499 0.500328 0.706914 \n", ".. ... ... ... ... ... ... ... \n", "203 0.326180 0.130492 0.635859 ... 0.388143 0.390056 0.622201 \n", "204 0.346364 0.368266 0.239999 ... 0.356751 0.210484 0.281411 \n", "205 0.044838 0.388965 0.295112 ... 0.383582 0.278010 0.589070 \n", "206 0.327362 0.317312 0.182946 ... 0.278637 0.273082 0.249412 \n", "207 0.534856 0.450721 0.445311 ... 0.545128 0.719623 0.482087 \n", "\n", " 14 15 16 17 18 19 20 \n", "0 0.235892 0.784807 0.663216 0.13875 0.220036 0.351111 0.435804 \n", "1 0.578542 0.373408 0.317839 0.02500 0.064137 0.069093 0.051439 \n", "2 0.254496 0.238676 0.109078 0.20375 0.210518 0.379454 0.469224 \n", "3 0.513021 0.321568 0.614882 0.10375 0.698963 0.538583 0.205754 \n", "4 0.713238 0.455489 0.323521 0.24375 0.521064 0.408684 0.394653 \n", ".. ... ... ... ... ... ... ... \n", "203 0.434200 0.143954 0.393584 0.09500 0.704255 0.680324 0.758035 \n", "204 0.805130 0.616591 0.444128 0.00000 0.171114 0.225449 0.475676 \n", "205 0.172585 0.590443 0.406251 0.25625 0.449219 0.220357 0.758675 \n", "206 0.280287 0.391026 0.366827 0.03500 0.550923 0.368934 0.355769 \n", "207 0.397595 0.700736 0.415519 0.41375 0.173602 0.357506 0.609997 \n", "\n", "[208 rows x 21 columns]" ] }, "execution_count": 40, "metadata": {}, "output_type": "execute_result" } ], "source": [ "X_REFCV" ] }, { "cell_type": "code", "execution_count": 41, "id": "652a046d", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Support is [False False False False False False False False True False False False\n", " False False False False False False False False False True True False\n", " False True False False False False False False False True False False\n", " False False False False False False False False False False False False\n", " False False False False False False False False False False False False\n", " False False False False False False False True False True False False\n", " False False False False False False False False False False False False\n", " True False False False False True False False False True True False\n", " False False False False True False False True False False False False\n", " False False False True False False False False False False True False\n", " False False False False False False False False False False False True\n", " False False False False False False False False False False False False\n", " True False False False False False False False False False False False\n", " False False True False False False False False False False False False\n", " False True False True False False False False True False]\n", "21\n", "Ranking [ 35 42 140 29 54 87 89 26 1 111 120 33 116 59 80 79 20 62\n", " 78 18 65 1 1 141 63 1 129 152 105 117 66 67 122 1 19 133\n", " 12 153 123 41 45 96 154 155 158 94 102 13 134 10 110 44 5 148\n", " 143 73 58 21 55 61 145 137 124 106 69 132 93 1 150 1 24 97\n", " 138 50 126 17 136 32 16 74 31 84 128 57 1 109 76 101 100 1\n", " 64 108 28 1 1 81 11 14 36 7 1 156 112 1 60 38 39 70\n", " 146 131 77 1 92 30 107 90 149 75 1 23 53 9 82 34 15 95\n", " 68 22 103 52 125 1 113 130 86 88 46 83 115 51 151 144 135 3\n", " 1 119 114 147 127 99 2 48 142 157 4 6 40 85 1 104 72 49\n", " 91 71 43 47 25 121 8 1 37 1 27 56 118 98 1 139]\n", "(35, 'f.1548.0.0', False)\n", "(42, 'f.1558.0.0', False)\n", "(140, 'f.20116.0.0', False)\n", "(29, 'f.20435.0.0', False)\n", "(54, 'f.20438.0.0', False)\n", "(87, 'f.20441.0.0', False)\n", "(89, 'f.20446.0.0', False)\n", "(26, 'f.20449.0.0', False)\n", "(1, 'f.20450.0.0', True)\n", "(111, 'f.20500.0.0', False)\n", "(120, 'f.20508.0.0', False)\n", "(33, 'f.20511.0.0', False)\n", "(116, 'f.20514.0.0', False)\n", "(59, 'f.20518.0.0', False)\n", "(80, 'f.20519.0.0', False)\n", "(79, 'f.20536.0.0', False)\n", "(20, 'f.2100.0.0', False)\n", "(62, 'f.21000.0.0', False)\n", "(78, 'f.31.0.0', False)\n", "(18, 'f.6142.0.0', False)\n", "(65, 'f.1160.0.0', False)\n", "(1, 'f.21003.0.0', True)\n", "(1, 'f.4620.0.0', True)\n", "(141, 'f.20433.0.0', False)\n", "(63, 'f.20434.0.0', False)\n", "(1, 'f.25011.2.0', True)\n", "(129, 'f.25012.2.0', False)\n", "(152, 'f.25013.2.0', False)\n", "(105, 'f.25014.2.0', False)\n", "(117, 'f.25015.2.0', False)\n", "(66, 'f.25016.2.0', False)\n", "(67, 'f.25017.2.0', False)\n", "(122, 'f.25018.2.0', False)\n", "(1, 'f.25019.2.0', True)\n", "(19, 'f.25020.2.0', False)\n", "(133, 'f.25021.2.0', False)\n", "(12, 'f.25022.2.0', False)\n", "(153, 'f.25023.2.0', False)\n", "(123, 'f.25024.2.0', False)\n", "(41, 'f.25782.2.0', False)\n", "(45, 'f.25783.2.0', False)\n", "(96, 'f.25784.2.0', False)\n", "(154, 'f.25785.2.0', False)\n", "(155, 'f.25786.2.0', False)\n", "(158, 'f.25787.2.0', False)\n", "(94, 'f.25788.2.0', False)\n", "(102, 'f.25789.2.0', False)\n", "(13, 'f.25790.2.0', False)\n", "(134, 'f.25791.2.0', False)\n", "(10, 'f.25792.2.0', False)\n", "(110, 'f.25793.2.0', False)\n", "(44, 'f.25794.2.0', False)\n", "(5, 'f.25795.2.0', False)\n", "(148, 'f.25796.2.0', False)\n", "(143, 'f.25797.2.0', False)\n", "(73, 'f.25798.2.0', False)\n", "(58, 'f.25799.2.0', False)\n", "(21, 'f.25800.2.0', False)\n", "(55, 'f.25801.2.0', False)\n", "(61, 'f.25802.2.0', False)\n", "(145, 'f.25803.2.0', False)\n", "(137, 'f.25804.2.0', False)\n", "(124, 'f.25805.2.0', False)\n", "(106, 'f.25806.2.0', False)\n", "(69, 'f.25807.2.0', False)\n", "(132, 'f.25808.2.0', False)\n", "(93, 'f.25809.2.0', False)\n", "(1, 'f.25810.2.0', True)\n", "(150, 'f.25811.2.0', False)\n", "(1, 'f.25812.2.0', True)\n", "(24, 'f.25813.2.0', False)\n", "(97, 'f.25814.2.0', False)\n", "(138, 'f.25815.2.0', False)\n", "(50, 'f.25816.2.0', False)\n", "(126, 'f.25817.2.0', False)\n", "(17, 'f.25818.2.0', False)\n", "(136, 'f.25819.2.0', False)\n", "(32, 'f.25820.2.0', False)\n", "(16, 'f.25821.2.0', False)\n", "(74, 'f.25822.2.0', False)\n", "(31, 'f.25823.2.0', False)\n", "(84, 'f.25824.2.0', False)\n", "(128, 'f.25825.2.0', False)\n", "(57, 'f.25826.2.0', False)\n", "(1, 'f.25827.2.0', True)\n", "(109, 'f.25828.2.0', False)\n", "(76, 'f.25829.2.0', False)\n", "(101, 'f.25830.2.0', False)\n", "(100, 'f.25831.2.0', False)\n", "(1, 'f.25832.2.0', True)\n", "(64, 'f.25833.2.0', False)\n", "(108, 'f.25834.2.0', False)\n", "(28, 'f.25835.2.0', False)\n", "(1, 'f.25836.2.0', True)\n", "(1, 'f.25837.2.0', True)\n", "(81, 'f.25838.2.0', False)\n", "(11, 'f.25839.2.0', False)\n", "(14, 'f.25840.2.0', False)\n", "(36, 'f.25841.2.0', False)\n", "(7, 'f.25842.2.0', False)\n", "(1, 'f.25843.2.0', True)\n", "(156, 'f.25844.2.0', False)\n", "(112, 'f.25845.2.0', False)\n", "(1, 'f.25846.2.0', True)\n", "(60, 'f.25847.2.0', False)\n", "(38, 'f.25848.2.0', False)\n", "(39, 'f.25849.2.0', False)\n", "(70, 'f.25850.2.0', False)\n", "(146, 'f.25851.2.0', False)\n", "(131, 'f.25852.2.0', False)\n", "(77, 'f.25853.2.0', False)\n", "(1, 'f.25854.2.0', True)\n", "(92, 'f.25855.2.0', False)\n", "(30, 'f.25856.2.0', False)\n", "(107, 'f.25857.2.0', False)\n", "(90, 'f.25858.2.0', False)\n", "(149, 'f.25859.2.0', False)\n", "(75, 'f.25860.2.0', False)\n", "(1, 'f.25861.2.0', True)\n", "(23, 'f.25862.2.0', False)\n", "(53, 'f.25863.2.0', False)\n", "(9, 'f.25864.2.0', False)\n", "(82, 'f.25865.2.0', False)\n", "(34, 'f.25866.2.0', False)\n", "(15, 'f.25867.2.0', False)\n", "(95, 'f.25868.2.0', False)\n", "(68, 'f.25869.2.0', False)\n", "(22, 'f.25870.2.0', False)\n", "(103, 'f.25871.2.0', False)\n", "(52, 'f.25872.2.0', False)\n", "(125, 'f.25873.2.0', False)\n", "(1, 'f.25874.2.0', True)\n", "(113, 'f.25875.2.0', False)\n", "(130, 'f.25876.2.0', False)\n", "(86, 'f.25877.2.0', False)\n", "(88, 'f.25878.2.0', False)\n", "(46, 'f.25879.2.0', False)\n", "(83, 'f.25880.2.0', False)\n", "(115, 'f.25881.2.0', False)\n", "(51, 'f.25882.2.0', False)\n", "(151, 'f.25883.2.0', False)\n", "(144, 'f.25884.2.0', False)\n", "(135, 'f.25885.2.0', False)\n", "(3, 'f.25886.2.0', False)\n", "(1, 'f.25887.2.0', True)\n", "(119, 'f.25888.2.0', False)\n", "(114, 'f.25889.2.0', False)\n", "(147, 'f.25890.2.0', False)\n", "(127, 'f.25891.2.0', False)\n", "(99, 'f.25892.2.0', False)\n", "(2, 'f.25893.2.0', False)\n", "(48, 'f.25894.2.0', False)\n", "(142, 'f.25895.2.0', False)\n", "(157, 'f.25896.2.0', False)\n", "(4, 'f.25897.2.0', False)\n", "(6, 'f.25898.2.0', False)\n", "(40, 'f.25899.2.0', False)\n", "(85, 'f.25900.2.0', False)\n", "(1, 'f.25901.2.0', True)\n", "(104, 'f.25902.2.0', False)\n", "(72, 'f.25903.2.0', False)\n", "(49, 'f.25904.2.0', False)\n", "(91, 'f.25905.2.0', False)\n", "(71, 'f.25906.2.0', False)\n", "(43, 'f.25907.2.0', False)\n", "(47, 'f.25908.2.0', False)\n", "(25, 'f.25909.2.0', False)\n", "(121, 'f.25910.2.0', False)\n", "(8, 'f.25911.2.0', False)\n", "(1, 'f.25912.2.0', True)\n", "(37, 'f.25913.2.0', False)\n", "(1, 'f.25914.2.0', True)\n", "(27, 'f.25915.2.0', False)\n", "(56, 'f.25916.2.0', False)\n", "(118, 'f.25917.2.0', False)\n", "(98, 'f.25918.2.0', False)\n", "(1, 'f.25919.2.0', True)\n", "(139, 'f.25920.2.0', False)\n" ] } ], "source": [ "print(\"Support is %s\" % selector.support_) # 是否保留\n", "print(selector.n_features_)\n", "print(\"Ranking %s\" % selector.ranking_) # 重要程度排名\n", "for i in zip(selector.ranking_,a,selector.support_):\n", " print(i)" ] }, { "cell_type": "code", "execution_count": 42, "id": "90f43a45", "metadata": {}, "outputs": [], "source": [ "data1 = pd.concat([y,X_REFCV], axis=1)" ] }, { "cell_type": "code", "execution_count": 43, "id": "5b7ed2ad", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
f.20483.0.0012345678...11121314151617181920
001.00.4137930.0010020.3848340.7388970.3947600.6350940.2616340.424469...0.3984600.7417170.4301970.2358920.7848070.6632160.138750.2200360.3511110.435804
101.00.3103450.0020040.0955480.6267910.2917710.4333780.5326460.319689...0.4837090.0821840.0000000.5785420.3734080.3178390.025000.0641370.0690930.051439
211.00.2413790.0030060.0825370.3825210.2411180.3136140.0000000.111218...0.2265970.0124000.1288720.2544960.2386760.1090780.203750.2105180.3794540.469224
311.00.6896550.0050100.3417360.6540110.3614190.5948550.6145540.286261...0.5780920.3703660.7829380.5130210.3215680.6148820.103750.6989630.5385830.205754
411.00.1034480.0190380.3384830.7578800.5155630.7314120.6950720.676651...0.5744990.5003280.7069140.7132380.4554890.3235210.243750.5210640.4086840.394653
..................................................................
20301.00.2068970.0040080.4781460.7410460.6608260.7604070.3261800.130492...0.3881430.3900560.6222010.4342000.1439540.3935840.095000.7042550.6803240.758035
20411.00.7241380.0200550.2419190.5476360.1924050.2892270.3463640.368266...0.3567510.2104840.2814110.8051300.6165910.4441280.000000.1711140.2254490.475676
20501.00.3103450.0020040.4171580.5787970.1878010.5169500.0448380.388965...0.3835820.2780100.5890700.1725850.5904430.4062510.256250.4492190.2203570.758675
20611.00.8620690.1492990.2850170.5881090.3379110.5978660.3273620.317312...0.2786370.2730820.2494120.2802870.3910260.3668270.035000.5509230.3689340.355769
20711.00.2068970.0000000.5102660.8033670.4226590.6179970.5348560.450721...0.5451280.7196230.4820870.3975950.7007360.4155190.413750.1736020.3575060.609997
\n", "

208 rows × 22 columns

\n", "
" ], "text/plain": [ " f.20483.0.0 0 1 2 3 4 5 \\\n", "0 0 1.0 0.413793 0.001002 0.384834 0.738897 0.394760 \n", "1 0 1.0 0.310345 0.002004 0.095548 0.626791 0.291771 \n", "2 1 1.0 0.241379 0.003006 0.082537 0.382521 0.241118 \n", "3 1 1.0 0.689655 0.005010 0.341736 0.654011 0.361419 \n", "4 1 1.0 0.103448 0.019038 0.338483 0.757880 0.515563 \n", ".. ... ... ... ... ... ... ... \n", "203 0 1.0 0.206897 0.004008 0.478146 0.741046 0.660826 \n", "204 1 1.0 0.724138 0.020055 0.241919 0.547636 0.192405 \n", "205 0 1.0 0.310345 0.002004 0.417158 0.578797 0.187801 \n", "206 1 1.0 0.862069 0.149299 0.285017 0.588109 0.337911 \n", "207 1 1.0 0.206897 0.000000 0.510266 0.803367 0.422659 \n", "\n", " 6 7 8 ... 11 12 13 \\\n", "0 0.635094 0.261634 0.424469 ... 0.398460 0.741717 0.430197 \n", "1 0.433378 0.532646 0.319689 ... 0.483709 0.082184 0.000000 \n", "2 0.313614 0.000000 0.111218 ... 0.226597 0.012400 0.128872 \n", "3 0.594855 0.614554 0.286261 ... 0.578092 0.370366 0.782938 \n", "4 0.731412 0.695072 0.676651 ... 0.574499 0.500328 0.706914 \n", ".. ... ... ... ... ... ... ... \n", "203 0.760407 0.326180 0.130492 ... 0.388143 0.390056 0.622201 \n", "204 0.289227 0.346364 0.368266 ... 0.356751 0.210484 0.281411 \n", "205 0.516950 0.044838 0.388965 ... 0.383582 0.278010 0.589070 \n", "206 0.597866 0.327362 0.317312 ... 0.278637 0.273082 0.249412 \n", "207 0.617997 0.534856 0.450721 ... 0.545128 0.719623 0.482087 \n", "\n", " 14 15 16 17 18 19 20 \n", "0 0.235892 0.784807 0.663216 0.13875 0.220036 0.351111 0.435804 \n", "1 0.578542 0.373408 0.317839 0.02500 0.064137 0.069093 0.051439 \n", "2 0.254496 0.238676 0.109078 0.20375 0.210518 0.379454 0.469224 \n", "3 0.513021 0.321568 0.614882 0.10375 0.698963 0.538583 0.205754 \n", "4 0.713238 0.455489 0.323521 0.24375 0.521064 0.408684 0.394653 \n", ".. ... ... ... ... ... ... ... \n", "203 0.434200 0.143954 0.393584 0.09500 0.704255 0.680324 0.758035 \n", "204 0.805130 0.616591 0.444128 0.00000 0.171114 0.225449 0.475676 \n", "205 0.172585 0.590443 0.406251 0.25625 0.449219 0.220357 0.758675 \n", "206 0.280287 0.391026 0.366827 0.03500 0.550923 0.368934 0.355769 \n", "207 0.397595 0.700736 0.415519 0.41375 0.173602 0.357506 0.609997 \n", "\n", "[208 rows x 22 columns]" ] }, "execution_count": 43, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data1" ] }, { "cell_type": "code", "execution_count": 44, "id": "29d1bcfc", "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import train_test_split\n", "X_train,X_test,y_train,y_test = train_test_split(X_REFCV,y,test_size=0.3,stratify=y,random_state=0)" ] }, { "cell_type": "code", "execution_count": 45, "id": "f262f7ee", "metadata": {}, "outputs": [], "source": [ "from sklearn.svm import SVC" ] }, { "cell_type": "code", "execution_count": 46, "id": "eb5c1eb2", "metadata": {}, "outputs": [], "source": [ "svmc = SVC(kernel=\"linear\")" ] }, { "cell_type": "code", "execution_count": 47, "id": "28354cac", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "SVC(kernel='linear')" ] }, "execution_count": 47, "metadata": {}, "output_type": "execute_result" } ], "source": [ "svmc.fit(X_train,y_train)" ] }, { "cell_type": "code", "execution_count": 48, "id": "03300db5", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.8344827586206897" ] }, "execution_count": 48, "metadata": {}, "output_type": "execute_result" } ], "source": [ "svmc.score(X_train,y_train)" ] }, { "cell_type": "code", "execution_count": 49, "id": "12934db2", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.7619047619047619" ] }, "execution_count": 49, "metadata": {}, "output_type": "execute_result" } ], "source": [ "svmc.score(X_test,y_test)" ] }, { "cell_type": "code", "execution_count": 50, "id": "c5d3f414", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " precision recall f1-score support\n", "\n", " 0 0.73 0.70 0.72 27\n", " 1 0.78 0.81 0.79 36\n", "\n", " accuracy 0.76 63\n", " macro avg 0.76 0.75 0.76 63\n", "weighted avg 0.76 0.76 0.76 63\n", "\n" ] } ], "source": [ "from sklearn.metrics import classification_report\n", "y_true = y_test #测试集标签\n", "y_pred = svmc.predict(X_test)#测试集预测值\n", "target_names = ['0', '1']#写入你标签的类别名，有几个就写几个\n", "print(classification_report(y_true, y_pred, target_names=target_names))" ] }, { "cell_type": "code", "execution_count": 51, "id": "23d4e949", "metadata": {}, "outputs": [], "source": [ "from sklearn.metrics import confusion_matrix\n", "tn, fp, fn, tp = confusion_matrix(y_true,y_pred).ravel()" ] }, { "cell_type": "code", "execution_count": 52, "id": "99f48138", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.7619047619047619" ] }, "execution_count": 52, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ACC=(tp+tn)/(tp+fn+fp+tn)\n", "ACC" ] }, { "cell_type": "code", "execution_count": 53, "id": "74c71579", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.8055555555555556" ] }, "execution_count": 53, "metadata": {}, "output_type": "execute_result" } ], "source": [ "TPR = tp/(tp+fn)\n", "TPR" ] }, { "cell_type": "code", "execution_count": 54, "id": "50dc898a", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.7037037037037037" ] }, "execution_count": 54, "metadata": {}, "output_type": "execute_result" } ], "source": [ "TNR = tn/(tn+fp)\n", "TNR" ] }, { "cell_type": "code", "execution_count": 55, "id": "b431bca5", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.7837837837837838" ] }, "execution_count": 55, "metadata": {}, "output_type": "execute_result" } ], "source": [ "PPV = tp/(tp+fp)\n", "PPV" ] }, { "cell_type": "code", "execution_count": 56, "id": "23edc3e9", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.7307692307692307" ] }, "execution_count": 56, "metadata": {}, "output_type": "execute_result" } ], "source": [ "NPV = tn/(tn+fn)\n", "NPV" ] }, { "cell_type": "code", "execution_count": 57, "id": "07bf4345", "metadata": {}, "outputs": [], "source": [ "#sklearn的调用，绘制ROC曲线，AUC就是ROC 曲线下的面积，通常情况下数值介于0.5-1之间，可以评价分类器的好坏，数值越大说明越好。\n", "from sklearn.metrics import roc_curve as ROC\n", "import matplotlib.pyplot as plt\n", "#导入模型，测试集\n", "def roc_auc_score_plot(svmc,X_test,y_test):\n", "\tFPR, Recall, thresholds = ROC(y_test,svmc.decision_function(X_test),pos_label=1)\n", "\tarea = roc_auc_score(y_test,svmc.decision_function(X_test))#计算auc的值\n", "\tplt.figure()\n", "\tplt.plot(FPR, Recall, color='red',\n", " label='ROC curve (area = %0.2f)' % area)\n", "\tplt.plot([0, 1], [0, 1], color='black', linestyle='--')\n", "\tplt.xlim([-0.05, 1.05])\n", "\tplt.ylim([-0.05, 1.05])\n", "\tplt.xlabel('False Positive Rate')\n", "\tplt.ylabel('Recall')\n", "\tplt.title('Receiver operating characteristic example')\n", "\tplt.legend(loc=\"lower right\")\n", "\tplt.show()" ] }, { "cell_type": "code", "execution_count": 58, "id": "0b075c42", "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "from sklearn.metrics import roc_auc_score\n", "roc_auc_score_plot(svmc,X_test,y_test)" ] }, { "cell_type": "code", "execution_count": 59, "id": "68be6e44", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "RandomForestClassifier(n_estimators=50000, random_state=0)" ] }, "execution_count": 59, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.ensemble import RandomForestClassifier\n", "forest = RandomForestClassifier(n_estimators=50000, random_state=0)\n", "forest.fit(data_X,y)" ] }, { "cell_type": "code", "execution_count": 60, "id": "e01d0711", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " 1) f.25842.2.0 0.013522\n", " 2) f.25019.2.0 0.011404\n", " 3) f.25901.2.0 0.011296\n", " 4) f.25874.2.0 0.010946\n", " 5) f.21003.0.0 0.010551\n", " 6) f.25869.2.0 0.010315\n", " 7) f.25887.2.0 0.010212\n", " 8) f.25832.2.0 0.009974\n", " 9) f.25022.2.0 0.009570\n", "10) f.25878.2.0 0.009414\n", "11) f.25879.2.0 0.009073\n", "12) f.25854.2.0 0.008789\n", "13) f.25888.2.0 0.008664\n", "14) f.25024.2.0 0.008539\n", "15) f.25843.2.0 0.008529\n", "16) f.25829.2.0 0.008266\n", "17) f.25795.2.0 0.008252\n", "18) f.25819.2.0 0.008082\n", "19) f.25828.2.0 0.007920\n", "20) f.25787.2.0 0.007909\n", "21) f.25822.2.0 0.007881\n", "22) f.25919.2.0 0.007835\n", "23) f.25904.2.0 0.007700\n", "24) f.25840.2.0 0.007490\n", "25) f.25821.2.0 0.007473\n", "26) f.25900.2.0 0.007463\n", "27) f.25792.2.0 0.007335\n", "28) f.25844.2.0 0.007267\n", "29) f.25837.2.0 0.007209\n", "30) f.25861.2.0 0.007202\n", "31) f.25849.2.0 0.007155\n", "32) f.25831.2.0 0.007135\n", "33) f.25836.2.0 0.007010\n", "34) f.25876.2.0 0.006953\n", "35) f.25886.2.0 0.006938\n", "36) f.25877.2.0 0.006897\n", "37) f.25841.2.0 0.006828\n", "38) f.25806.2.0 0.006822\n", "39) f.25914.2.0 0.006772\n", "40) f.25846.2.0 0.006663\n", "41) f.25847.2.0 0.006632\n", "42) f.25884.2.0 0.006615\n", "43) f.25860.2.0 0.006578\n", "44) f.25798.2.0 0.006550\n", "45) f.25809.2.0 0.006531\n", "46) f.25882.2.0 0.006525\n", "47) f.4620.0.0 0.006464\n", "48) f.25818.2.0 0.006448\n", "49) f.25021.2.0 0.006445\n", "50) f.25883.2.0 0.006401\n", "51) f.25866.2.0 0.006388\n", "52) f.25864.2.0 0.006369\n", "53) f.25794.2.0 0.006317\n", "54) f.25805.2.0 0.006315\n", "55) f.25815.2.0 0.006216\n", "56) f.25020.2.0 0.006175\n", "57) f.25012.2.0 0.006156\n", "58) f.25810.2.0 0.006132\n", "59) f.25804.2.0 0.006130\n", "60) f.25872.2.0 0.006103\n", "61) f.25827.2.0 0.006093\n", "62) f.25870.2.0 0.006087\n", "63) f.25801.2.0 0.006060\n", "64) f.25017.2.0 0.006002\n", "65) f.25797.2.0 0.005966\n", "66) f.25897.2.0 0.005920\n", "67) f.25912.2.0 0.005893\n", "68) f.25845.2.0 0.005888\n", "69) f.25899.2.0 0.005880\n", "70) f.25814.2.0 0.005879\n", "71) f.25816.2.0 0.005864\n", "72) f.25812.2.0 0.005853\n", "73) f.25833.2.0 0.005841\n", "74) f.25881.2.0 0.005841\n", "75) f.25800.2.0 0.005820\n", "76) f.25790.2.0 0.005812\n", "77) f.25890.2.0 0.005807\n", "78) f.25920.2.0 0.005789\n", "79) f.25889.2.0 0.005774\n", "80) f.25857.2.0 0.005746\n", "81) f.25911.2.0 0.005715\n", "82) f.25891.2.0 0.005692\n", "83) f.25823.2.0 0.005690\n", "84) f.25782.2.0 0.005661\n", "85) f.25813.2.0 0.005653\n", "86) f.25855.2.0 0.005626\n", "87) f.25851.2.0 0.005623\n", "88) f.25858.2.0 0.005613\n", "89) f.25867.2.0 0.005604\n", "90) f.20434.0.0 0.005582\n", "91) f.25802.2.0 0.005574\n", "92) f.25862.2.0 0.005559\n", "93) f.25786.2.0 0.005524\n", "94) f.25834.2.0 0.005515\n", "95) f.25830.2.0 0.005507\n", "96) f.25824.2.0 0.005487\n", "97) f.25826.2.0 0.005472\n", "98) f.25907.2.0 0.005437\n", "99) f.25892.2.0 0.005396\n", "100) f.25785.2.0 0.005393\n", "101) f.25789.2.0 0.005373\n", "102) f.25863.2.0 0.005367\n", "103) f.25015.2.0 0.005364\n", "104) f.25817.2.0 0.005348\n", "105) f.25023.2.0 0.005312\n", "106) f.25856.2.0 0.005306\n", "107) f.25793.2.0 0.005299\n", "108) f.25885.2.0 0.005299\n", "109) f.25796.2.0 0.005296\n", "110) f.25838.2.0 0.005289\n", "111) f.25908.2.0 0.005278\n", "112) f.25909.2.0 0.005263\n", "113) f.25799.2.0 0.005252\n", "114) f.25784.2.0 0.005241\n", "115) f.25880.2.0 0.005235\n", "116) f.25898.2.0 0.005219\n", "117) f.25906.2.0 0.005206\n", "118) f.25875.2.0 0.005186\n", "119) f.25893.2.0 0.005129\n", "120) f.25788.2.0 0.005116\n", "121) f.25014.2.0 0.005026\n", "122) f.25850.2.0 0.005021\n", "123) f.25848.2.0 0.004987\n", "124) f.25808.2.0 0.004986\n", "125) f.25807.2.0 0.004938\n", "126) f.25913.2.0 0.004938\n", "127) f.25011.2.0 0.004923\n", "128) f.25791.2.0 0.004899\n", "129) f.25910.2.0 0.004869\n", "130) f.25905.2.0 0.004864\n", "131) f.25915.2.0 0.004858\n", "132) f.25871.2.0 0.004851\n", "133) f.25783.2.0 0.004850\n", "134) f.25803.2.0 0.004812\n", "135) f.25853.2.0 0.004782\n", "136) f.20433.0.0 0.004764\n", "137) f.25018.2.0 0.004761\n", "138) f.25895.2.0 0.004758\n", "139) f.25859.2.0 0.004739\n", "140) f.25839.2.0 0.004737\n", "141) f.25917.2.0 0.004737\n", "142) f.25865.2.0 0.004733\n", "143) f.25013.2.0 0.004731\n", "144) f.25825.2.0 0.004680\n", "145) f.25896.2.0 0.004636\n", "146) f.25820.2.0 0.004629\n", "147) f.25902.2.0 0.004582\n", "148) f.25811.2.0 0.004568\n", "149) f.25903.2.0 0.004504\n", "150) f.25918.2.0 0.004469\n", "151) f.25868.2.0 0.004423\n", "152) f.25016.2.0 0.004411\n", "153) f.25873.2.0 0.004385\n", "154) f.25916.2.0 0.004378\n", "155) f.25894.2.0 0.004373\n", "156) f.25835.2.0 0.004303\n", "157) f.25852.2.0 0.004234\n", "158) f.20450.0.0 0.004033\n", "159) f.20511.0.0 0.002246\n", "160) f.1160.0.0 0.002146\n", "161) f.20438.0.0 0.002057\n", "162) f.20514.0.0 0.001998\n", "163) f.20519.0.0 0.001989\n", "164) f.2100.0.0 0.001958\n", "165) f.1558.0.0 0.001862\n", "166) f.20508.0.0 0.001555\n", "167) f.20536.0.0 0.001438\n", "168) f.1548.0.0 0.001095\n", "169) f.20518.0.0 0.001048\n", "170) f.20500.0.0 0.000990\n", "171) f.20116.0.0 0.000977\n", "172) f.6142.0.0 0.000893\n", "173) f.21000.0.0 0.000870\n", "174) f.20441.0.0 0.000363\n", "175) f.20449.0.0 0.000331\n", "176) f.31.0.0 0.000312\n", "177) f.20435.0.0 0.000258\n", "178) f.20446.0.0 0.000180\n" ] } ], "source": [ "feat_labels = data.columns[1:]\n", "importances = forest.feature_importances_\n", "indices = np.argsort(importances)[::-1]\n", "for f in range(data_X.shape[1]):\n", " print(\"%2d) %-*s %f\" % (f + 1, 60, feat_labels[indices[f]], importances[indices[f]]))" ] }, { "cell_type": "code", "execution_count": 61, "id": "e0c20e77", "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import train_test_split\n", "X_train,X_test,y_train,y_test = train_test_split(data_X,y,test_size=0.3,stratify=y,random_state=0)" ] }, { "cell_type": "code", "execution_count": 62, "id": "139860f3", "metadata": {}, "outputs": [], "source": [ "train_feature1=X_train.iloc[:,[33,158,131,21,144,89,111,100,99,126,36,135,136,145,38,86,52,76,85,44,79,176,94,118,93,171,103,22,67,84,169,69,8,25]]" ] }, { "cell_type": "code", "execution_count": 63, "id": "1c58af61", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
f.25019.2.0f.25901.2.0f.25874.2.0f.21003.0.0f.25887.2.0f.25832.2.0f.25854.2.0f.25843.2.0f.25842.2.0f.25869.2.0...f.25836.2.0f.25914.2.0f.25846.2.0f.4620.0.0f.25810.2.0f.25827.2.0f.25912.2.0f.25812.2.0f.20450.0.0f.25011.2.0
730.3628220.557500.3404390.0344830.4307380.4911730.5702700.4311660.3318610.525925...0.4487290.3578890.6615990.0090181.0000000.6361710.4929390.6939101.00.383818
410.7736390.048750.4957950.2758620.4295750.2125520.3210340.3614200.4016930.474198...0.5651260.3173000.4299870.0010020.1767720.2105560.2804550.5386321.00.339703
1750.6565190.115000.3168840.6551720.3974410.1024360.1884430.2509790.2652780.000000...0.2446990.5229100.1879960.0020040.1769000.4674900.4976330.2708030.00.341939
1790.3173350.173750.3787260.7586210.3236730.0986550.3530580.3316740.3964170.477559...0.3960260.0826890.0952300.0030060.2730780.3024200.0132940.6607361.00.147388
990.6830230.272500.3549350.1724140.5099820.3224430.9660950.4111230.2822091.000000...0.4152730.5989630.4693190.0040080.5534520.6601200.6561040.7635741.00.532222
..................................................................
520.5981380.508750.4085560.0689660.5624990.5787190.7069970.4968880.5167960.367848...0.3029030.6787110.3988230.0040080.4300120.5246150.5132000.6010681.00.349055
1120.6214180.470000.3782250.1724140.1931450.5024020.8658280.2791050.2956550.460900...0.4420060.8469880.0544410.1492990.4501870.6416810.4851550.2733651.00.474080
650.5702010.286250.1562840.6551720.3158700.3629440.3585170.2010050.1718970.298971...0.1266950.2143520.2272580.0290580.3141740.2693730.1534380.3888971.00.147184
670.6891120.221250.5134860.3448280.3104580.2128160.3852480.0584460.1435150.251587...0.2480160.2861530.1694330.0070140.3494220.2805460.0798200.3136981.00.150234
1010.8259310.056250.5333910.2758620.5914530.7009740.8765220.7875340.7855820.921121...0.4217200.4653370.6783210.0090180.6745470.6617700.4818340.7325141.00.496036
\n", "

145 rows × 34 columns

\n", "
" ], "text/plain": [ " f.25019.2.0 f.25901.2.0 f.25874.2.0 f.21003.0.0 f.25887.2.0 \\\n", "73 0.362822 0.55750 0.340439 0.034483 0.430738 \n", "41 0.773639 0.04875 0.495795 0.275862 0.429575 \n", "175 0.656519 0.11500 0.316884 0.655172 0.397441 \n", "179 0.317335 0.17375 0.378726 0.758621 0.323673 \n", "99 0.683023 0.27250 0.354935 0.172414 0.509982 \n", ".. ... ... ... ... ... \n", "52 0.598138 0.50875 0.408556 0.068966 0.562499 \n", "112 0.621418 0.47000 0.378225 0.172414 0.193145 \n", "65 0.570201 0.28625 0.156284 0.655172 0.315870 \n", "67 0.689112 0.22125 0.513486 0.344828 0.310458 \n", "101 0.825931 0.05625 0.533391 0.275862 0.591453 \n", "\n", " f.25832.2.0 f.25854.2.0 f.25843.2.0 f.25842.2.0 f.25869.2.0 ... \\\n", "73 0.491173 0.570270 0.431166 0.331861 0.525925 ... \n", "41 0.212552 0.321034 0.361420 0.401693 0.474198 ... \n", "175 0.102436 0.188443 0.250979 0.265278 0.000000 ... \n", "179 0.098655 0.353058 0.331674 0.396417 0.477559 ... \n", "99 0.322443 0.966095 0.411123 0.282209 1.000000 ... \n", ".. ... ... ... ... ... ... \n", "52 0.578719 0.706997 0.496888 0.516796 0.367848 ... \n", "112 0.502402 0.865828 0.279105 0.295655 0.460900 ... \n", "65 0.362944 0.358517 0.201005 0.171897 0.298971 ... \n", "67 0.212816 0.385248 0.058446 0.143515 0.251587 ... \n", "101 0.700974 0.876522 0.787534 0.785582 0.921121 ... \n", "\n", " f.25836.2.0 f.25914.2.0 f.25846.2.0 f.4620.0.0 f.25810.2.0 \\\n", "73 0.448729 0.357889 0.661599 0.009018 1.000000 \n", "41 0.565126 0.317300 0.429987 0.001002 0.176772 \n", "175 0.244699 0.522910 0.187996 0.002004 0.176900 \n", "179 0.396026 0.082689 0.095230 0.003006 0.273078 \n", "99 0.415273 0.598963 0.469319 0.004008 0.553452 \n", ".. ... ... ... ... ... \n", "52 0.302903 0.678711 0.398823 0.004008 0.430012 \n", "112 0.442006 0.846988 0.054441 0.149299 0.450187 \n", "65 0.126695 0.214352 0.227258 0.029058 0.314174 \n", "67 0.248016 0.286153 0.169433 0.007014 0.349422 \n", "101 0.421720 0.465337 0.678321 0.009018 0.674547 \n", "\n", " f.25827.2.0 f.25912.2.0 f.25812.2.0 f.20450.0.0 f.25011.2.0 \n", "73 0.636171 0.492939 0.693910 1.0 0.383818 \n", "41 0.210556 0.280455 0.538632 1.0 0.339703 \n", "175 0.467490 0.497633 0.270803 0.0 0.341939 \n", "179 0.302420 0.013294 0.660736 1.0 0.147388 \n", "99 0.660120 0.656104 0.763574 1.0 0.532222 \n", ".. ... ... ... ... ... \n", "52 0.524615 0.513200 0.601068 1.0 0.349055 \n", "112 0.641681 0.485155 0.273365 1.0 0.474080 \n", "65 0.269373 0.153438 0.388897 1.0 0.147184 \n", "67 0.280546 0.079820 0.313698 1.0 0.150234 \n", "101 0.661770 0.481834 0.732514 1.0 0.496036 \n", "\n", "[145 rows x 34 columns]" ] }, "execution_count": 63, "metadata": {}, "output_type": "execute_result" } ], "source": [ "train_feature1" ] }, { "cell_type": "code", "execution_count": 64, "id": "d159d223", "metadata": {}, "outputs": [], "source": [ "from sklearn.svm import SVC" ] }, { "cell_type": "code", "execution_count": 65, "id": "9578863c", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "SVC(kernel='linear')" ] }, "execution_count": 65, "metadata": {}, "output_type": "execute_result" } ], "source": [ "svmc = SVC(kernel=\"linear\")\n", "svmc.fit(train_feature1,y_train) " ] }, { "cell_type": "code", "execution_count": 66, "id": "2af8a744", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.8482758620689655" ] }, "execution_count": 66, "metadata": {}, "output_type": "execute_result" } ], "source": [ "svmc.score(train_feature1,y_train)" ] }, { "cell_type": "code", "execution_count": 67, "id": "8e626a72", "metadata": {}, "outputs": [], "source": [ "test_feature1=X_test.iloc[:,[33,158,131,21,144,89,111,100,99,126,36,135,136,145,38,86,52,76,85,44,79,176,94,118,93,171,103,22,67,84,169,69,8,25]]" ] }, { "cell_type": "code", "execution_count": 68, "id": "9f0ea6e0", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
f.25019.2.0f.25901.2.0f.25874.2.0f.21003.0.0f.25887.2.0f.25832.2.0f.25854.2.0f.25843.2.0f.25842.2.0f.25869.2.0...f.25836.2.0f.25914.2.0f.25846.2.0f.4620.0.0f.25810.2.0f.25827.2.0f.25912.2.0f.25812.2.0f.20450.0.0f.25011.2.0
2010.5447710.131250.1116920.7241380.3146540.0594880.2405570.0837290.1232430.014197...0.0830600.1280780.0041420.0000000.0771670.4789570.2566670.2075921.00.129498
370.3348850.446250.4665960.8620690.2381240.5613330.3327350.4884750.4103980.290024...0.1205390.0818640.1296840.0290580.3610930.0337370.2165850.4008861.00.204513
1180.3864610.000000.3392170.6551720.2135460.4292110.2800630.3679820.3499260.106301...0.1135290.1597940.1117190.0050100.2268050.1653230.1498320.3285581.00.161822
1050.3198420.250000.6474240.3793100.3254420.4574170.3154330.5466130.5069220.534553...0.5423580.2758820.7280750.0040080.4621590.8074010.1504960.7525101.00.188860
1770.5540830.311250.4053750.4137930.6317090.6336860.4445700.5426750.5842690.470313...0.5700630.3432560.5205300.0030060.4892520.4291260.0582520.4116090.00.368977
..................................................................
950.4885390.086250.6332100.7241380.2418370.5084260.5725670.5154140.5726930.525001...0.5648590.5035390.5234370.0090180.4150210.4047180.5389490.3325080.00.333401
840.6987820.686250.5177150.5862070.4551780.3665940.3699690.3161770.2758120.425971...0.3040970.5370870.3740190.0050100.6027330.5252590.4405310.4835161.00.388900
50.0000000.000000.3396581.0000000.1048820.2983250.3220900.2927970.3728330.128872...0.3161940.2734070.3520500.0090180.3300620.1342000.3718780.5639661.00.159789
210.5530090.460000.6442570.5517240.3529230.2556960.2655650.6227710.8770160.520724...0.5792180.4561420.4466040.0010020.3736180.6259000.4336830.5878001.00.293556
700.5906160.250000.4837010.1379310.5047490.3594040.6963360.5138650.5801750.253836...0.2626020.3091960.2655670.0511020.1631920.1990500.4344230.3020991.00.276682
\n", "

63 rows × 34 columns

\n", "
" ], "text/plain": [ " f.25019.2.0 f.25901.2.0 f.25874.2.0 f.21003.0.0 f.25887.2.0 \\\n", "201 0.544771 0.13125 0.111692 0.724138 0.314654 \n", "37 0.334885 0.44625 0.466596 0.862069 0.238124 \n", "118 0.386461 0.00000 0.339217 0.655172 0.213546 \n", "105 0.319842 0.25000 0.647424 0.379310 0.325442 \n", "177 0.554083 0.31125 0.405375 0.413793 0.631709 \n", ".. ... ... ... ... ... \n", "95 0.488539 0.08625 0.633210 0.724138 0.241837 \n", "84 0.698782 0.68625 0.517715 0.586207 0.455178 \n", "5 0.000000 0.00000 0.339658 1.000000 0.104882 \n", "21 0.553009 0.46000 0.644257 0.551724 0.352923 \n", "70 0.590616 0.25000 0.483701 0.137931 0.504749 \n", "\n", " f.25832.2.0 f.25854.2.0 f.25843.2.0 f.25842.2.0 f.25869.2.0 ... \\\n", "201 0.059488 0.240557 0.083729 0.123243 0.014197 ... \n", "37 0.561333 0.332735 0.488475 0.410398 0.290024 ... \n", "118 0.429211 0.280063 0.367982 0.349926 0.106301 ... \n", "105 0.457417 0.315433 0.546613 0.506922 0.534553 ... \n", "177 0.633686 0.444570 0.542675 0.584269 0.470313 ... \n", ".. ... ... ... ... ... ... \n", "95 0.508426 0.572567 0.515414 0.572693 0.525001 ... \n", "84 0.366594 0.369969 0.316177 0.275812 0.425971 ... \n", "5 0.298325 0.322090 0.292797 0.372833 0.128872 ... \n", "21 0.255696 0.265565 0.622771 0.877016 0.520724 ... \n", "70 0.359404 0.696336 0.513865 0.580175 0.253836 ... \n", "\n", " f.25836.2.0 f.25914.2.0 f.25846.2.0 f.4620.0.0 f.25810.2.0 \\\n", "201 0.083060 0.128078 0.004142 0.000000 0.077167 \n", "37 0.120539 0.081864 0.129684 0.029058 0.361093 \n", "118 0.113529 0.159794 0.111719 0.005010 0.226805 \n", "105 0.542358 0.275882 0.728075 0.004008 0.462159 \n", "177 0.570063 0.343256 0.520530 0.003006 0.489252 \n", ".. ... ... ... ... ... \n", "95 0.564859 0.503539 0.523437 0.009018 0.415021 \n", "84 0.304097 0.537087 0.374019 0.005010 0.602733 \n", "5 0.316194 0.273407 0.352050 0.009018 0.330062 \n", "21 0.579218 0.456142 0.446604 0.001002 0.373618 \n", "70 0.262602 0.309196 0.265567 0.051102 0.163192 \n", "\n", " f.25827.2.0 f.25912.2.0 f.25812.2.0 f.20450.0.0 f.25011.2.0 \n", "201 0.478957 0.256667 0.207592 1.0 0.129498 \n", "37 0.033737 0.216585 0.400886 1.0 0.204513 \n", "118 0.165323 0.149832 0.328558 1.0 0.161822 \n", "105 0.807401 0.150496 0.752510 1.0 0.188860 \n", "177 0.429126 0.058252 0.411609 0.0 0.368977 \n", ".. ... ... ... ... ... \n", "95 0.404718 0.538949 0.332508 0.0 0.333401 \n", "84 0.525259 0.440531 0.483516 1.0 0.388900 \n", "5 0.134200 0.371878 0.563966 1.0 0.159789 \n", "21 0.625900 0.433683 0.587800 1.0 0.293556 \n", "70 0.199050 0.434423 0.302099 1.0 0.276682 \n", "\n", "[63 rows x 34 columns]" ] }, "execution_count": 68, "metadata": {}, "output_type": "execute_result" } ], "source": [ "test_feature1" ] }, { "cell_type": "code", "execution_count": 69, "id": "9fd457a0", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.7777777777777778" ] }, "execution_count": 69, "metadata": {}, "output_type": "execute_result" } ], "source": [ "svmc.score(test_feature1,y_test)" ] }, { "cell_type": "code", "execution_count": 70, "id": "df559065", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " precision recall f1-score support\n", "\n", " 0 0.76 0.70 0.73 27\n", " 1 0.79 0.83 0.81 36\n", "\n", " accuracy 0.78 63\n", " macro avg 0.77 0.77 0.77 63\n", "weighted avg 0.78 0.78 0.78 63\n", "\n" ] } ], "source": [ "from sklearn.metrics import classification_report\n", "y_true = y_test #测试集标签\n", "y_pred = svmc.predict(test_feature1)#测试集预测值\n", "target_names = ['0', '1']#写入你标签的类别名，有几个就写几个\n", "print(classification_report(y_true, y_pred, target_names=target_names))" ] }, { "cell_type": "code", "execution_count": 71, "id": "4d7c395c", "metadata": {}, "outputs": [], "source": [ "from sklearn.metrics import confusion_matrix\n", "tn, fp, fn, tp = confusion_matrix(y_true,y_pred).ravel()" ] }, { "cell_type": "code", "execution_count": 72, "id": "b1116ed1", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.7777777777777778" ] }, "execution_count": 72, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ACC=(tp+tn)/(tp+fn+fp+tn)\n", "ACC" ] }, { "cell_type": "code", "execution_count": 73, "id": "8d5f4843", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.8333333333333334" ] }, "execution_count": 73, "metadata": {}, "output_type": "execute_result" } ], "source": [ "TPR = tp/(tp+fn)\n", "TPR" ] }, { "cell_type": "code", "execution_count": 74, "id": "c679f23a", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.7037037037037037" ] }, "execution_count": 74, "metadata": {}, "output_type": "execute_result" } ], "source": [ "TNR = tn/(tn+fp)\n", "TNR" ] }, { "cell_type": "code", "execution_count": 75, "id": "4afc37ee", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.7894736842105263" ] }, "execution_count": 75, "metadata": {}, "output_type": "execute_result" } ], "source": [ "PPV = tp/(tp+fp)\n", "PPV" ] }, { "cell_type": "code", "execution_count": 76, "id": "aff04de4", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.76" ] }, "execution_count": 76, "metadata": {}, "output_type": "execute_result" } ], "source": [ "NPV = tn/(tn+fn)\n", "NPV" ] }, { "cell_type": "code", "execution_count": 87, "id": "066a0516", "metadata": {}, "outputs": [], "source": [ "#sklearn的调用，绘制ROC曲线，AUC就是ROC 曲线下的面积，通常情况下数值介于0.5-1之间，可以评价分类器的好坏，数值越大说明越好。\n", "from sklearn.metrics import roc_curve as ROC\n", "import matplotlib.pyplot as plt\n", "#导入模型，测试集\n", "def roc_auc_score_plot(svmc,test_feature1,y_test):\n", "\tFPR, Recall, thresholds = ROC(y_test,svmc.decision_function(test_feature1),pos_label=1)\n", "\tarea = roc_auc_score(y_test,svmc.decision_function(test_feature1))#计算auc的值\n", "\tplt.figure()\n", "\tplt.plot(FPR, Recall, color='red',\n", " label='ROC curve (area = %0.2f)' % area)\n", "\tplt.plot([0, 1], [0, 1], color='black', linestyle='--')\n", "\tplt.xlim([-0.05, 1.05])\n", "\tplt.ylim([-0.05, 1.05])\n", "\tplt.xlabel('False Positive Rate')\n", "\tplt.ylabel('Recall')\n", "\tplt.title('Receiver operating characteristic example')\n", "\tplt.legend(loc=\"lower right\")\n", "\tplt.savefig('./img_test.svg', dpi=300)\n", "\tplt.show()" ] }, { "cell_type": "code", "execution_count": 88, "id": "d56016ee", "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "from sklearn.metrics import roc_auc_score\n", "roc_auc_score_plot(svmc,test_feature1,y_test)" ] }, { "cell_type": "code", "execution_count": 79, "id": "765abcda", "metadata": {}, "outputs": [], "source": [ "import matplotlib.pyplot as pl\n", "from sklearn import metrics\n", "# 相关库\n", "\n", "def plot_matrix(y_true, y_pred, labels_name, title=None, thresh=0.8, axis_labels=None):\n", "# 利用sklearn中的函数生成混淆矩阵并归一化\n", " cm = metrics.confusion_matrix(y_true, y_pred, labels=labels_name, sample_weight=None) # 生成混淆矩阵 \n", " cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis] # 归一化\n", "\n", "# 画图，如果希望改变颜色风格，可以改变此部分的cmap=pl.get_cmap('Blues')处\n", " pl.imshow(cm, interpolation='nearest', cmap=pl.get_cmap('Blues'))\n", " pl.colorbar() # 绘制图例\n", "\n", "# 图像标题\n", " if title is not None:\n", " pl.title(title)\n", "# 绘制坐标\n", " num_local = np.array(range(len(labels_name)))\n", " if axis_labels is None:\n", " axis_labels = labels_name\n", " pl.xticks(num_local, axis_labels) # 将标签印在x轴坐标上， 并倾斜45度\n", " pl.yticks(num_local, axis_labels) # 将标签印在y轴坐标上\n", " pl.ylabel('True label')\n", " pl.xlabel('Predicted label')\n", "\n", "# 将百分比打印在相应的格子内，大于thresh的用白字，小于的用黑字\n", " for i in range(np.shape(cm)[0]):\n", " for j in range(np.shape(cm)[1]):\n", " if int(cm[i][j] * 100 + 0.5) > 0:\n", " pl.text(j, i, format(int(cm[i][j] * 100 + 0.5), 'd') + '%',\n", " ha=\"center\", va=\"center\",\n", " color=\"white\" if cm[i][j] > thresh else \"black\") #y_true, y_pred果要更改颜色风格，需要同时更改此行\n", "# 显示\n", " pl.show()" ] }, { "cell_type": "code", "execution_count": 80, "id": "a8b45f63", "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plot_matrix(y_true, y_pred, [0, 1],\n", " axis_labels=['Non-Attempters', 'Attempters'])" ] }, { "cell_type": "code", "execution_count": null, "id": "e37ad572", "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 }