{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "\n", "import pandas as pd\n", "\n", "from pandas import Series,DataFrame" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "collapsed": true }, "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
PythonEnMathPhysicChem
1001221052857
101741291611426
102971211222965
103141731201471
1041261328611617
1058534212166
10614265112483
10713614112286113
1081537124110102
1096330446958
110593811310916
1115518758126
1125397763745
1134214810797143
114701386968134
115471361132294
1163113762028
117148741344124
1181028113812832
11927111137022
1202893121684
12113643259719
12211170123858
12396103147868
12410104663149
1257759710831
12688614511655
12733741065046
12874282610076
1297618101126133
..................
170144124779282
1713698484380
17251143683474
17314911718141120
1748139146112122
17511510164629
17610714045148
17765436810918
1783110011049123
1792946695790
18014686182246
18171504090140
1824100147116110
1835587937834
18451091248782
185101181395051
18632127136124
187941613813149
1886510112312886
18943941029132
190681359428125
1913060982715
1928916101354
193104139972917
194529419991
195191021354140
19658100708264
19784971297613
19813115744114
199793795128116
\n", "

100 rows × 5 columns

\n", "
" ], "text/plain": [ " Python En Math Physic Chem\n", "100 122 10 5 28 57\n", "101 74 129 16 114 26\n", "102 97 121 122 29 65\n", "103 141 73 120 147 1\n", "104 126 132 86 116 17\n", "105 85 3 42 121 66\n", "106 142 65 1 124 83\n", "107 136 141 122 86 113\n", "108 15 37 124 110 102\n", "109 63 30 44 69 58\n", "110 59 38 113 109 16\n", "111 5 51 87 58 126\n", "112 53 97 76 37 45\n", "113 42 148 107 97 143\n", "114 70 138 69 68 134\n", "115 47 136 113 22 94\n", "116 31 137 6 20 28\n", "117 148 74 134 4 124\n", "118 102 81 138 128 32\n", "119 27 111 13 70 22\n", "120 28 93 121 68 4\n", "121 136 43 25 97 19\n", "122 111 70 12 38 58\n", "123 96 103 147 86 8\n", "124 10 10 46 63 149\n", "125 7 75 97 108 31\n", "126 88 6 145 116 55\n", "127 33 74 106 50 46\n", "128 74 28 26 100 76\n", "129 76 18 101 126 133\n", ".. ... ... ... ... ...\n", "170 144 124 77 92 82\n", "171 36 98 48 43 80\n", "172 51 143 68 34 74\n", "173 149 117 18 141 120\n", "174 8 139 146 112 122\n", "175 115 101 64 62 9\n", "176 10 7 140 45 148\n", "177 65 43 68 109 18\n", "178 31 100 110 49 123\n", "179 29 46 69 57 90\n", "180 146 86 18 22 46\n", "181 71 50 40 90 140\n", "182 4 100 147 116 110\n", "183 55 87 93 78 34\n", "184 5 109 124 87 82\n", "185 10 118 139 50 51\n", "186 32 12 71 36 124\n", "187 94 16 138 13 149\n", "188 65 101 123 128 86\n", "189 43 94 10 29 132\n", "190 68 135 94 28 125\n", "191 30 60 98 27 15\n", "192 89 16 10 135 4\n", "193 104 139 97 29 17\n", "194 5 29 41 99 91\n", "195 19 102 135 41 40\n", "196 58 100 70 82 64\n", "197 84 97 129 76 13\n", "198 131 15 7 44 114\n", "199 79 37 95 128 116\n", "\n", "[100 rows x 5 columns]" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = DataFrame(np.random.randint(0,150,size = (100,5)),index = np.arange(100,200),columns=['Python','En','Math','Physic','Chem'])\n", "df" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "Python False\n", "En False\n", "Math False\n", "Physic False\n", "Chem False\n", "dtype: bool" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# 判断DataFrame是否存在空数据\n", "df.isnull().any()" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "Python True\n", "En True\n", "Math True\n", "Physic True\n", "Chem True\n", "dtype: bool" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.notnull().all()" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "500" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "100*5" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [], "source": [ "for i in range(50):\n", " # 行索引\n", " index = np.random.randint(100,200,size =1)[0]\n", "\n", " cols = df.columns\n", "\n", " # 列索引\n", " col = np.random.choice(cols)\n", "\n", " df.loc[index,col] = None" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [], "source": [ "for i in range(20):\n", " # 行索引\n", " index = np.random.randint(100,200,size =1)[0]\n", "\n", " cols = df.columns\n", "\n", " # 列索引\n", " col = np.random.choice(cols)\n", "\n", "# not a number 不是一个数\n", " df.loc[index,col] = np.NAN" ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "collapsed": true }, "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
PythonEnMathPhysicChem
100122.010.05.028.057.0
101NaN129.016.0114.026.0
10297.0121.0122.029.065.0
103141.073.0120.0147.01.0
104126.0NaN86.0116.017.0
10585.0NaN42.0121.066.0
106142.065.01.0124.083.0
107136.0141.0NaN86.0113.0
10815.037.0124.0110.0102.0
10963.030.0NaN69.058.0
110NaNNaN113.0109.016.0
1115.051.087.058.0126.0
11253.097.076.037.045.0
11342.0148.0NaN97.0NaN
11470.0138.069.068.0134.0
115NaN136.0113.022.094.0
11631.0137.06.020.028.0
117148.074.0134.04.0124.0
118102.081.0138.0128.032.0
11927.0111.013.0NaN22.0
12028.093.0121.0NaN4.0
121136.0NaN25.097.019.0
122111.070.012.038.058.0
123NaN103.0147.086.08.0
12410.010.046.063.0149.0
1257.075.097.0108.031.0
12688.06.0NaNNaN55.0
12733.074.0106.050.046.0
12874.028.026.0100.076.0
12976.018.0101.0NaNNaN
..................
170144.0124.077.092.082.0
17136.098.0NaN43.080.0
17251.0NaN68.034.074.0
173149.0NaN18.0141.0NaN
1748.0139.0146.0112.0NaN
175115.0NaN64.062.09.0
176NaN7.0140.045.0148.0
177NaN43.068.0109.018.0
17831.0100.0NaN49.0123.0
17929.046.069.057.090.0
180146.086.018.022.046.0
18171.050.040.0NaN140.0
1824.0100.0147.0116.0110.0
18355.087.093.0NaN34.0
184NaN109.0124.087.082.0
18510.0118.0139.050.051.0
18632.012.071.036.0NaN
18794.0NaN138.013.0149.0
18865.0101.0123.0128.086.0
18943.094.0NaN29.0132.0
19068.0135.094.028.0125.0
19130.060.098.0NaN15.0
19289.016.010.0135.04.0
193104.0139.097.029.017.0
1945.029.041.099.0NaN
19519.0102.0135.041.040.0
19658.0NaN70.082.064.0
197NaN97.0129.076.013.0
198131.015.0NaN44.0114.0
19979.0NaN95.0128.0NaN
\n", "

100 rows × 5 columns

\n", "
" ], "text/plain": [ " Python En Math Physic Chem\n", "100 122.0 10.0 5.0 28.0 57.0\n", "101 NaN 129.0 16.0 114.0 26.0\n", "102 97.0 121.0 122.0 29.0 65.0\n", "103 141.0 73.0 120.0 147.0 1.0\n", "104 126.0 NaN 86.0 116.0 17.0\n", "105 85.0 NaN 42.0 121.0 66.0\n", "106 142.0 65.0 1.0 124.0 83.0\n", "107 136.0 141.0 NaN 86.0 113.0\n", "108 15.0 37.0 124.0 110.0 102.0\n", "109 63.0 30.0 NaN 69.0 58.0\n", "110 NaN NaN 113.0 109.0 16.0\n", "111 5.0 51.0 87.0 58.0 126.0\n", "112 53.0 97.0 76.0 37.0 45.0\n", "113 42.0 148.0 NaN 97.0 NaN\n", "114 70.0 138.0 69.0 68.0 134.0\n", "115 NaN 136.0 113.0 22.0 94.0\n", "116 31.0 137.0 6.0 20.0 28.0\n", "117 148.0 74.0 134.0 4.0 124.0\n", "118 102.0 81.0 138.0 128.0 32.0\n", "119 27.0 111.0 13.0 NaN 22.0\n", "120 28.0 93.0 121.0 NaN 4.0\n", "121 136.0 NaN 25.0 97.0 19.0\n", "122 111.0 70.0 12.0 38.0 58.0\n", "123 NaN 103.0 147.0 86.0 8.0\n", "124 10.0 10.0 46.0 63.0 149.0\n", "125 7.0 75.0 97.0 108.0 31.0\n", "126 88.0 6.0 NaN NaN 55.0\n", "127 33.0 74.0 106.0 50.0 46.0\n", "128 74.0 28.0 26.0 100.0 76.0\n", "129 76.0 18.0 101.0 NaN NaN\n", ".. ... ... ... ... ...\n", "170 144.0 124.0 77.0 92.0 82.0\n", "171 36.0 98.0 NaN 43.0 80.0\n", "172 51.0 NaN 68.0 34.0 74.0\n", "173 149.0 NaN 18.0 141.0 NaN\n", "174 8.0 139.0 146.0 112.0 NaN\n", "175 115.0 NaN 64.0 62.0 9.0\n", "176 NaN 7.0 140.0 45.0 148.0\n", "177 NaN 43.0 68.0 109.0 18.0\n", "178 31.0 100.0 NaN 49.0 123.0\n", "179 29.0 46.0 69.0 57.0 90.0\n", "180 146.0 86.0 18.0 22.0 46.0\n", "181 71.0 50.0 40.0 NaN 140.0\n", "182 4.0 100.0 147.0 116.0 110.0\n", "183 55.0 87.0 93.0 NaN 34.0\n", "184 NaN 109.0 124.0 87.0 82.0\n", "185 10.0 118.0 139.0 50.0 51.0\n", "186 32.0 12.0 71.0 36.0 NaN\n", "187 94.0 NaN 138.0 13.0 149.0\n", "188 65.0 101.0 123.0 128.0 86.0\n", "189 43.0 94.0 NaN 29.0 132.0\n", "190 68.0 135.0 94.0 28.0 125.0\n", "191 30.0 60.0 98.0 NaN 15.0\n", "192 89.0 16.0 10.0 135.0 4.0\n", "193 104.0 139.0 97.0 29.0 17.0\n", "194 5.0 29.0 41.0 99.0 NaN\n", "195 19.0 102.0 135.0 41.0 40.0\n", "196 58.0 NaN 70.0 82.0 64.0\n", "197 NaN 97.0 129.0 76.0 13.0\n", "198 131.0 15.0 NaN 44.0 114.0\n", "199 79.0 NaN 95.0 128.0 NaN\n", "\n", "[100 rows x 5 columns]" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df" ] }, { "cell_type": "code", "execution_count": 18, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "Python True\n", "En True\n", "Math True\n", "Physic True\n", "Chem True\n", "dtype: bool" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.isnull().any()" ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "Python 14\n", "En 14\n", "Math 15\n", "Physic 11\n", "Chem 13\n", "dtype: int64" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.isnull().sum()" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [], "source": [ "df2 = df.copy()" ] }, { "cell_type": "code", "execution_count": 24, "metadata": { "collapsed": true }, "outputs": [ { "data": { "text/plain": [ "Python 14\n", "En 14\n", "Math 15\n", "Physic 11\n", "Chem 13\n", "dtype: int64" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df2.isnull().sum()" ] }, { "cell_type": "code", "execution_count": 26, "metadata": { "collapsed": true }, "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
PythonEnMathPhysicChem
100122.010.05.028.057.0
101100.0129.016.0114.026.0
10297.0121.0122.029.065.0
103141.073.0120.0147.01.0
104126.0100.086.0116.017.0
10585.0100.042.0121.066.0
106142.065.01.0124.083.0
107136.0141.0100.086.0113.0
10815.037.0124.0110.0102.0
10963.030.0100.069.058.0
110100.0100.0113.0109.016.0
1115.051.087.058.0126.0
11253.097.076.037.045.0
11342.0148.0100.097.0100.0
11470.0138.069.068.0134.0
115100.0136.0113.022.094.0
11631.0137.06.020.028.0
117148.074.0134.04.0124.0
118102.081.0138.0128.032.0
11927.0111.013.0100.022.0
12028.093.0121.0100.04.0
121136.0100.025.097.019.0
122111.070.012.038.058.0
123100.0103.0147.086.08.0
12410.010.046.063.0149.0
1257.075.097.0108.031.0
12688.06.0100.0100.055.0
12733.074.0106.050.046.0
12874.028.026.0100.076.0
12976.018.0101.0100.0100.0
..................
170144.0124.077.092.082.0
17136.098.0100.043.080.0
17251.0100.068.034.074.0
173149.0100.018.0141.0100.0
1748.0139.0146.0112.0100.0
175115.0100.064.062.09.0
176100.07.0140.045.0148.0
177100.043.068.0109.018.0
17831.0100.0100.049.0123.0
17929.046.069.057.090.0
180146.086.018.022.046.0
18171.050.040.0100.0140.0
1824.0100.0147.0116.0110.0
18355.087.093.0100.034.0
184100.0109.0124.087.082.0
18510.0118.0139.050.051.0
18632.012.071.036.0100.0
18794.0100.0138.013.0149.0
18865.0101.0123.0128.086.0
18943.094.0100.029.0132.0
19068.0135.094.028.0125.0
19130.060.098.0100.015.0
19289.016.010.0135.04.0
193104.0139.097.029.017.0
1945.029.041.099.0100.0
19519.0102.0135.041.040.0
19658.0100.070.082.064.0
197100.097.0129.076.013.0
198131.015.0100.044.0114.0
19979.0100.095.0128.0100.0
\n", "

100 rows × 5 columns

\n", "
" ], "text/plain": [ " Python En Math Physic Chem\n", "100 122.0 10.0 5.0 28.0 57.0\n", "101 100.0 129.0 16.0 114.0 26.0\n", "102 97.0 121.0 122.0 29.0 65.0\n", "103 141.0 73.0 120.0 147.0 1.0\n", "104 126.0 100.0 86.0 116.0 17.0\n", "105 85.0 100.0 42.0 121.0 66.0\n", "106 142.0 65.0 1.0 124.0 83.0\n", "107 136.0 141.0 100.0 86.0 113.0\n", "108 15.0 37.0 124.0 110.0 102.0\n", "109 63.0 30.0 100.0 69.0 58.0\n", "110 100.0 100.0 113.0 109.0 16.0\n", "111 5.0 51.0 87.0 58.0 126.0\n", "112 53.0 97.0 76.0 37.0 45.0\n", "113 42.0 148.0 100.0 97.0 100.0\n", "114 70.0 138.0 69.0 68.0 134.0\n", "115 100.0 136.0 113.0 22.0 94.0\n", "116 31.0 137.0 6.0 20.0 28.0\n", "117 148.0 74.0 134.0 4.0 124.0\n", "118 102.0 81.0 138.0 128.0 32.0\n", "119 27.0 111.0 13.0 100.0 22.0\n", "120 28.0 93.0 121.0 100.0 4.0\n", "121 136.0 100.0 25.0 97.0 19.0\n", "122 111.0 70.0 12.0 38.0 58.0\n", "123 100.0 103.0 147.0 86.0 8.0\n", "124 10.0 10.0 46.0 63.0 149.0\n", "125 7.0 75.0 97.0 108.0 31.0\n", "126 88.0 6.0 100.0 100.0 55.0\n", "127 33.0 74.0 106.0 50.0 46.0\n", "128 74.0 28.0 26.0 100.0 76.0\n", "129 76.0 18.0 101.0 100.0 100.0\n", ".. ... ... ... ... ...\n", "170 144.0 124.0 77.0 92.0 82.0\n", "171 36.0 98.0 100.0 43.0 80.0\n", "172 51.0 100.0 68.0 34.0 74.0\n", "173 149.0 100.0 18.0 141.0 100.0\n", "174 8.0 139.0 146.0 112.0 100.0\n", "175 115.0 100.0 64.0 62.0 9.0\n", "176 100.0 7.0 140.0 45.0 148.0\n", "177 100.0 43.0 68.0 109.0 18.0\n", "178 31.0 100.0 100.0 49.0 123.0\n", "179 29.0 46.0 69.0 57.0 90.0\n", "180 146.0 86.0 18.0 22.0 46.0\n", "181 71.0 50.0 40.0 100.0 140.0\n", "182 4.0 100.0 147.0 116.0 110.0\n", "183 55.0 87.0 93.0 100.0 34.0\n", "184 100.0 109.0 124.0 87.0 82.0\n", "185 10.0 118.0 139.0 50.0 51.0\n", "186 32.0 12.0 71.0 36.0 100.0\n", "187 94.0 100.0 138.0 13.0 149.0\n", "188 65.0 101.0 123.0 128.0 86.0\n", "189 43.0 94.0 100.0 29.0 132.0\n", "190 68.0 135.0 94.0 28.0 125.0\n", "191 30.0 60.0 98.0 100.0 15.0\n", "192 89.0 16.0 10.0 135.0 4.0\n", "193 104.0 139.0 97.0 29.0 17.0\n", "194 5.0 29.0 41.0 99.0 100.0\n", "195 19.0 102.0 135.0 41.0 40.0\n", "196 58.0 100.0 70.0 82.0 64.0\n", "197 100.0 97.0 129.0 76.0 13.0\n", "198 131.0 15.0 100.0 44.0 114.0\n", "199 79.0 100.0 95.0 128.0 100.0\n", "\n", "[100 rows x 5 columns]" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# 固定值填充\n", "df2.fillna(value=100)" ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Python 71.662791\n", "En 75.627907\n", "Math 77.929412\n", "Physic 73.471910\n", "Chem 69.080460\n", "dtype: float64" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df2.mean()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 29, "metadata": { "collapsed": true }, "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
PythonEnMathPhysicChem
1001221052857
101711291611426
102971211222965
103141731201471
104126758611617
10585754212166
10614265112483
1071361417786113
1081537124110102
1096330776958
110717511310916
1115518758126
1125397763745
11342148779769
114701386968134
115711361132294
1163113762028
117148741344124
1181028113812832
11927111137322
1202893121734
12113675259719
12211170123858
12371103147868
12410104663149
1257759710831
126886777355
12733741065046
12874282610076
12976181017369
..................
170144124779282
1713698774380
1725175683474
173149751814169
174813914611269
1751157564629
17671714045148
17771436810918
178311007749123
1792946695790
18014686182246
18171504073140
1824100147116110
1835587937334
184711091248782
185101181395051
1863212713669
187947513813149
1886510112312886
18943947729132
190681359428125
1913060987315
1928916101354
193104139972917
194529419969
195191021354140
1965875708264
19771971297613
198131157744114
19979759512869
\n", "

100 rows × 5 columns

\n", "
" ], "text/plain": [ " Python En Math Physic Chem\n", "100 122 10 5 28 57\n", "101 71 129 16 114 26\n", "102 97 121 122 29 65\n", "103 141 73 120 147 1\n", "104 126 75 86 116 17\n", "105 85 75 42 121 66\n", "106 142 65 1 124 83\n", "107 136 141 77 86 113\n", "108 15 37 124 110 102\n", "109 63 30 77 69 58\n", "110 71 75 113 109 16\n", "111 5 51 87 58 126\n", "112 53 97 76 37 45\n", "113 42 148 77 97 69\n", "114 70 138 69 68 134\n", "115 71 136 113 22 94\n", "116 31 137 6 20 28\n", "117 148 74 134 4 124\n", "118 102 81 138 128 32\n", "119 27 111 13 73 22\n", "120 28 93 121 73 4\n", "121 136 75 25 97 19\n", "122 111 70 12 38 58\n", "123 71 103 147 86 8\n", "124 10 10 46 63 149\n", "125 7 75 97 108 31\n", "126 88 6 77 73 55\n", "127 33 74 106 50 46\n", "128 74 28 26 100 76\n", "129 76 18 101 73 69\n", ".. ... ... ... ... ...\n", "170 144 124 77 92 82\n", "171 36 98 77 43 80\n", "172 51 75 68 34 74\n", "173 149 75 18 141 69\n", "174 8 139 146 112 69\n", "175 115 75 64 62 9\n", "176 71 7 140 45 148\n", "177 71 43 68 109 18\n", "178 31 100 77 49 123\n", "179 29 46 69 57 90\n", "180 146 86 18 22 46\n", "181 71 50 40 73 140\n", "182 4 100 147 116 110\n", "183 55 87 93 73 34\n", "184 71 109 124 87 82\n", "185 10 118 139 50 51\n", "186 32 12 71 36 69\n", "187 94 75 138 13 149\n", "188 65 101 123 128 86\n", "189 43 94 77 29 132\n", "190 68 135 94 28 125\n", "191 30 60 98 73 15\n", "192 89 16 10 135 4\n", "193 104 139 97 29 17\n", "194 5 29 41 99 69\n", "195 19 102 135 41 40\n", "196 58 75 70 82 64\n", "197 71 97 129 76 13\n", "198 131 15 77 44 114\n", "199 79 75 95 128 69\n", "\n", "[100 rows x 5 columns]" ] }, "execution_count": 29, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# 均值\n", "df3 = df2.fillna(value=df2.mean())\n", "df3.astype(np.int16)" ] }, { "cell_type": "code", "execution_count": 31, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "array([ 6, 18, 1, 17, 19, 5, 17, 16, 13, 3])" ] }, "execution_count": 31, "metadata": {}, "output_type": "execute_result" } ], "source": [ "nd = np.random.randint(0,20,size = 10)\n", "nd" ] }, { "cell_type": "code", "execution_count": 33, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([ 1, 3, 5, 6, 13, 16, 17, 17, 18, 19])" ] }, "execution_count": 33, "metadata": {}, "output_type": "execute_result" } ], "source": [ "nd.sort()\n", "nd" ] }, { "cell_type": "code", "execution_count": 34, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "14.5" ] }, "execution_count": 34, "metadata": {}, "output_type": "execute_result" } ], "source": [ "(13 + 16)/2" ] }, { "cell_type": "code", "execution_count": 35, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "14.5" ] }, "execution_count": 35, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np.median(nd)" ] }, { "cell_type": "code", "execution_count": 36, "metadata": { "collapsed": true }, "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
PythonEnMathPhysicChem
100122.010.05.028.057.0
10168.0129.016.0114.026.0
10297.0121.0122.029.065.0
103141.073.0120.0147.01.0
104126.082.586.0116.017.0
10585.082.542.0121.066.0
106142.065.01.0124.083.0
107136.0141.086.086.0113.0
10815.037.0124.0110.0102.0
10963.030.086.069.058.0
11068.082.5113.0109.016.0
1115.051.087.058.0126.0
11253.097.076.037.045.0
11342.0148.086.097.065.0
11470.0138.069.068.0134.0
11568.0136.0113.022.094.0
11631.0137.06.020.028.0
117148.074.0134.04.0124.0
118102.081.0138.0128.032.0
11927.0111.013.069.022.0
12028.093.0121.069.04.0
121136.082.525.097.019.0
122111.070.012.038.058.0
12368.0103.0147.086.08.0
12410.010.046.063.0149.0
1257.075.097.0108.031.0
12688.06.086.069.055.0
12733.074.0106.050.046.0
12874.028.026.0100.076.0
12976.018.0101.069.065.0
..................
170144.0124.077.092.082.0
17136.098.086.043.080.0
17251.082.568.034.074.0
173149.082.518.0141.065.0
1748.0139.0146.0112.065.0
175115.082.564.062.09.0
17668.07.0140.045.0148.0
17768.043.068.0109.018.0
17831.0100.086.049.0123.0
17929.046.069.057.090.0
180146.086.018.022.046.0
18171.050.040.069.0140.0
1824.0100.0147.0116.0110.0
18355.087.093.069.034.0
18468.0109.0124.087.082.0
18510.0118.0139.050.051.0
18632.012.071.036.065.0
18794.082.5138.013.0149.0
18865.0101.0123.0128.086.0
18943.094.086.029.0132.0
19068.0135.094.028.0125.0
19130.060.098.069.015.0
19289.016.010.0135.04.0
193104.0139.097.029.017.0
1945.029.041.099.065.0
19519.0102.0135.041.040.0
19658.082.570.082.064.0
19768.097.0129.076.013.0
198131.015.086.044.0114.0
19979.082.595.0128.065.0
\n", "

100 rows × 5 columns

\n", "
" ], "text/plain": [ " Python En Math Physic Chem\n", "100 122.0 10.0 5.0 28.0 57.0\n", "101 68.0 129.0 16.0 114.0 26.0\n", "102 97.0 121.0 122.0 29.0 65.0\n", "103 141.0 73.0 120.0 147.0 1.0\n", "104 126.0 82.5 86.0 116.0 17.0\n", "105 85.0 82.5 42.0 121.0 66.0\n", "106 142.0 65.0 1.0 124.0 83.0\n", "107 136.0 141.0 86.0 86.0 113.0\n", "108 15.0 37.0 124.0 110.0 102.0\n", "109 63.0 30.0 86.0 69.0 58.0\n", "110 68.0 82.5 113.0 109.0 16.0\n", "111 5.0 51.0 87.0 58.0 126.0\n", "112 53.0 97.0 76.0 37.0 45.0\n", "113 42.0 148.0 86.0 97.0 65.0\n", "114 70.0 138.0 69.0 68.0 134.0\n", "115 68.0 136.0 113.0 22.0 94.0\n", "116 31.0 137.0 6.0 20.0 28.0\n", "117 148.0 74.0 134.0 4.0 124.0\n", "118 102.0 81.0 138.0 128.0 32.0\n", "119 27.0 111.0 13.0 69.0 22.0\n", "120 28.0 93.0 121.0 69.0 4.0\n", "121 136.0 82.5 25.0 97.0 19.0\n", "122 111.0 70.0 12.0 38.0 58.0\n", "123 68.0 103.0 147.0 86.0 8.0\n", "124 10.0 10.0 46.0 63.0 149.0\n", "125 7.0 75.0 97.0 108.0 31.0\n", "126 88.0 6.0 86.0 69.0 55.0\n", "127 33.0 74.0 106.0 50.0 46.0\n", "128 74.0 28.0 26.0 100.0 76.0\n", "129 76.0 18.0 101.0 69.0 65.0\n", ".. ... ... ... ... ...\n", "170 144.0 124.0 77.0 92.0 82.0\n", "171 36.0 98.0 86.0 43.0 80.0\n", "172 51.0 82.5 68.0 34.0 74.0\n", "173 149.0 82.5 18.0 141.0 65.0\n", "174 8.0 139.0 146.0 112.0 65.0\n", "175 115.0 82.5 64.0 62.0 9.0\n", "176 68.0 7.0 140.0 45.0 148.0\n", "177 68.0 43.0 68.0 109.0 18.0\n", "178 31.0 100.0 86.0 49.0 123.0\n", "179 29.0 46.0 69.0 57.0 90.0\n", "180 146.0 86.0 18.0 22.0 46.0\n", "181 71.0 50.0 40.0 69.0 140.0\n", "182 4.0 100.0 147.0 116.0 110.0\n", "183 55.0 87.0 93.0 69.0 34.0\n", "184 68.0 109.0 124.0 87.0 82.0\n", "185 10.0 118.0 139.0 50.0 51.0\n", "186 32.0 12.0 71.0 36.0 65.0\n", "187 94.0 82.5 138.0 13.0 149.0\n", "188 65.0 101.0 123.0 128.0 86.0\n", "189 43.0 94.0 86.0 29.0 132.0\n", "190 68.0 135.0 94.0 28.0 125.0\n", "191 30.0 60.0 98.0 69.0 15.0\n", "192 89.0 16.0 10.0 135.0 4.0\n", "193 104.0 139.0 97.0 29.0 17.0\n", "194 5.0 29.0 41.0 99.0 65.0\n", "195 19.0 102.0 135.0 41.0 40.0\n", "196 58.0 82.5 70.0 82.0 64.0\n", "197 68.0 97.0 129.0 76.0 13.0\n", "198 131.0 15.0 86.0 44.0 114.0\n", "199 79.0 82.5 95.0 128.0 65.0\n", "\n", "[100 rows x 5 columns]" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# 中位数填充\n", "df2.median()\n", "df4 = df2.fillna(df2.median())\n", "df4" ] }, { "cell_type": "code", "execution_count": 37, "metadata": { "collapsed": true }, "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
PythonEnMathPhysicChem
100122.010.05.028.057.0
101NaN129.016.0114.026.0
10297.0121.0122.029.065.0
103141.073.0120.0147.01.0
104126.0NaN86.0116.017.0
10585.0NaN42.0121.066.0
106142.065.01.0124.083.0
107136.0141.0NaN86.0113.0
10815.037.0124.0110.0102.0
10963.030.0NaN69.058.0
110NaNNaN113.0109.016.0
1115.051.087.058.0126.0
11253.097.076.037.045.0
11342.0148.0NaN97.0NaN
11470.0138.069.068.0134.0
115NaN136.0113.022.094.0
11631.0137.06.020.028.0
117148.074.0134.04.0124.0
118102.081.0138.0128.032.0
11927.0111.013.0NaN22.0
12028.093.0121.0NaN4.0
121136.0NaN25.097.019.0
122111.070.012.038.058.0
123NaN103.0147.086.08.0
12410.010.046.063.0149.0
1257.075.097.0108.031.0
12688.06.0NaNNaN55.0
12733.074.0106.050.046.0
12874.028.026.0100.076.0
12976.018.0101.0NaNNaN
..................
170144.0124.077.092.082.0
17136.098.0NaN43.080.0
17251.0NaN68.034.074.0
173149.0NaN18.0141.0NaN
1748.0139.0146.0112.0NaN
175115.0NaN64.062.09.0
176NaN7.0140.045.0148.0
177NaN43.068.0109.018.0
17831.0100.0NaN49.0123.0
17929.046.069.057.090.0
180146.086.018.022.046.0
18171.050.040.0NaN140.0
1824.0100.0147.0116.0110.0
18355.087.093.0NaN34.0
184NaN109.0124.087.082.0
18510.0118.0139.050.051.0
18632.012.071.036.0NaN
18794.0NaN138.013.0149.0
18865.0101.0123.0128.086.0
18943.094.0NaN29.0132.0
19068.0135.094.028.0125.0
19130.060.098.0NaN15.0
19289.016.010.0135.04.0
193104.0139.097.029.017.0
1945.029.041.099.0NaN
19519.0102.0135.041.040.0
19658.0NaN70.082.064.0
197NaN97.0129.076.013.0
198131.015.0NaN44.0114.0
19979.0NaN95.0128.0NaN
\n", "

100 rows × 5 columns

\n", "
" ], "text/plain": [ " Python En Math Physic Chem\n", "100 122.0 10.0 5.0 28.0 57.0\n", "101 NaN 129.0 16.0 114.0 26.0\n", "102 97.0 121.0 122.0 29.0 65.0\n", "103 141.0 73.0 120.0 147.0 1.0\n", "104 126.0 NaN 86.0 116.0 17.0\n", "105 85.0 NaN 42.0 121.0 66.0\n", "106 142.0 65.0 1.0 124.0 83.0\n", "107 136.0 141.0 NaN 86.0 113.0\n", "108 15.0 37.0 124.0 110.0 102.0\n", "109 63.0 30.0 NaN 69.0 58.0\n", "110 NaN NaN 113.0 109.0 16.0\n", "111 5.0 51.0 87.0 58.0 126.0\n", "112 53.0 97.0 76.0 37.0 45.0\n", "113 42.0 148.0 NaN 97.0 NaN\n", "114 70.0 138.0 69.0 68.0 134.0\n", "115 NaN 136.0 113.0 22.0 94.0\n", "116 31.0 137.0 6.0 20.0 28.0\n", "117 148.0 74.0 134.0 4.0 124.0\n", "118 102.0 81.0 138.0 128.0 32.0\n", "119 27.0 111.0 13.0 NaN 22.0\n", "120 28.0 93.0 121.0 NaN 4.0\n", "121 136.0 NaN 25.0 97.0 19.0\n", "122 111.0 70.0 12.0 38.0 58.0\n", "123 NaN 103.0 147.0 86.0 8.0\n", "124 10.0 10.0 46.0 63.0 149.0\n", "125 7.0 75.0 97.0 108.0 31.0\n", "126 88.0 6.0 NaN NaN 55.0\n", "127 33.0 74.0 106.0 50.0 46.0\n", "128 74.0 28.0 26.0 100.0 76.0\n", "129 76.0 18.0 101.0 NaN NaN\n", ".. ... ... ... ... ...\n", "170 144.0 124.0 77.0 92.0 82.0\n", "171 36.0 98.0 NaN 43.0 80.0\n", "172 51.0 NaN 68.0 34.0 74.0\n", "173 149.0 NaN 18.0 141.0 NaN\n", "174 8.0 139.0 146.0 112.0 NaN\n", "175 115.0 NaN 64.0 62.0 9.0\n", "176 NaN 7.0 140.0 45.0 148.0\n", "177 NaN 43.0 68.0 109.0 18.0\n", "178 31.0 100.0 NaN 49.0 123.0\n", "179 29.0 46.0 69.0 57.0 90.0\n", "180 146.0 86.0 18.0 22.0 46.0\n", "181 71.0 50.0 40.0 NaN 140.0\n", "182 4.0 100.0 147.0 116.0 110.0\n", "183 55.0 87.0 93.0 NaN 34.0\n", "184 NaN 109.0 124.0 87.0 82.0\n", "185 10.0 118.0 139.0 50.0 51.0\n", "186 32.0 12.0 71.0 36.0 NaN\n", "187 94.0 NaN 138.0 13.0 149.0\n", "188 65.0 101.0 123.0 128.0 86.0\n", "189 43.0 94.0 NaN 29.0 132.0\n", "190 68.0 135.0 94.0 28.0 125.0\n", "191 30.0 60.0 98.0 NaN 15.0\n", "192 89.0 16.0 10.0 135.0 4.0\n", "193 104.0 139.0 97.0 29.0 17.0\n", "194 5.0 29.0 41.0 99.0 NaN\n", "195 19.0 102.0 135.0 41.0 40.0\n", "196 58.0 NaN 70.0 82.0 64.0\n", "197 NaN 97.0 129.0 76.0 13.0\n", "198 131.0 15.0 NaN 44.0 114.0\n", "199 79.0 NaN 95.0 128.0 NaN\n", "\n", "[100 rows x 5 columns]" ] }, "execution_count": 37, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# 众数填充，数量最多的那个数\n", "df2" ] }, { "cell_type": "code", "execution_count": 42, "metadata": { "collapsed": true }, "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
PythonEnMathPhysicChem
100828999101125
101431109325
10256103566190
1034710014713899
1043846827544
10518111223126
106562610614139
10731377567144
10835471026063
109861265788149
11019140303533
11176151133
11231549111969
1136437502321
11472571381521
115551201043225
11696248922146
11763086489
11828461258274
119853970132111
12010990447439
121214810311465
12211029998057
123109888113571
12470103134121121
12551921172743
1266929759105
12765905214822
12841291711913
1292410010728139
..................
207012777241631
2071936192822
20721166154861
207347214011234
2074261081233233
207546130135124113
207633181363820
20771071112954119
207884551293787
20799550451984
2080124746514053
20812635149145127
20821921101389
20838410131714
208428741056889
20852393849788
2086861332612513
208721124401155
20882015353137
208996123123564
20902243927860
20911631176058
20926518131334
209369491094058
2094128461082111
20952659854149
209611147909266
209759773140104
2098102675119
209997197714348
\n", "

2000 rows × 5 columns

\n", "
" ], "text/plain": [ " Python En Math Physic Chem\n", "100 82 89 99 101 125\n", "101 4 31 109 32 5\n", "102 56 103 56 61 90\n", "103 47 100 147 138 99\n", "104 38 46 82 75 44\n", "105 18 11 122 3 126\n", "106 56 26 106 14 139\n", "107 3 137 75 67 144\n", "108 35 47 102 60 63\n", "109 86 126 57 88 149\n", "110 19 140 30 35 33\n", "111 76 1 5 11 33\n", "112 31 54 91 119 69\n", "113 64 37 50 23 21\n", "114 72 57 138 15 21\n", "115 55 120 104 32 25\n", "116 96 24 89 22 146\n", "117 63 0 8 64 89\n", "118 28 46 125 82 74\n", "119 85 39 70 132 111\n", "120 109 90 44 74 39\n", "121 2 148 103 114 65\n", "122 110 29 99 80 57\n", "123 109 88 81 135 71\n", "124 70 103 134 121 121\n", "125 51 92 117 27 43\n", "126 6 92 97 59 105\n", "127 65 90 52 148 22\n", "128 4 129 17 119 13\n", "129 24 100 107 28 139\n", "... ... ... ... ... ...\n", "2070 127 77 24 16 31\n", "2071 93 61 9 28 22\n", "2072 116 61 54 8 61\n", "2073 4 72 140 112 34\n", "2074 26 108 123 32 33\n", "2075 46 130 135 124 113\n", "2076 33 18 136 38 20\n", "2077 107 11 129 54 119\n", "2078 84 55 129 37 87\n", "2079 95 50 45 19 84\n", "2080 124 74 65 140 53\n", "2081 26 35 149 145 127\n", "2082 19 21 101 3 89\n", "2083 84 10 131 71 4\n", "2084 28 74 105 68 89\n", "2085 23 93 84 97 88\n", "2086 86 133 26 125 13\n", "2087 21 124 40 115 5\n", "2088 20 15 35 31 37\n", "2089 96 123 123 5 64\n", "2090 22 43 92 78 60\n", "2091 16 31 17 60 58\n", "2092 65 18 13 13 34\n", "2093 69 49 109 40 58\n", "2094 128 46 10 82 111\n", "2095 26 59 8 54 149\n", "2096 111 47 90 92 66\n", "2097 5 97 73 140 104\n", "2098 102 6 7 5 119\n", "2099 97 19 77 143 48\n", "\n", "[2000 rows x 5 columns]" ] }, "execution_count": 42, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = DataFrame(np.random.randint(0,150,size = (2000,5)),index = np.arange(100,2100),columns=['Python','En','Math','Physic','Chem'])\n", "df" ] }, { "cell_type": "code", "execution_count": 43, "metadata": {}, "outputs": [], "source": [ "for i in range(1000):\n", " # 行索引\n", " index = np.random.randint(100,2100,size =1)[0]\n", "\n", " cols = df.columns\n", "\n", " # 列索引\n", " col = np.random.choice(cols)\n", "\n", " df.loc[index,col] = None" ] }, { "cell_type": "code", "execution_count": 44, "metadata": { "collapsed": true }, "outputs": [ { "data": { "text/plain": [ "Python 190\n", "En 200\n", "Math 194\n", "Physic 189\n", "Chem 181\n", "dtype: int64" ] }, "execution_count": 44, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.isnull().sum()" ] }, { "cell_type": "code", "execution_count": 45, "metadata": { "collapsed": true }, "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", "
PythonEnMathPhysicChem
10082.089.099.0101.0125.0
1014.031.0109.032.05.0
10256.0103.056.0NaN90.0
10347.0100.0147.0138.099.0
10438.046.0NaN75.044.0
\n", "
" ], "text/plain": [ " Python En Math Physic Chem\n", "100 82.0 89.0 99.0 101.0 125.0\n", "101 4.0 31.0 109.0 32.0 5.0\n", "102 56.0 103.0 56.0 NaN 90.0\n", "103 47.0 100.0 147.0 138.0 99.0\n", "104 38.0 46.0 NaN 75.0 44.0" ] }, "execution_count": 45, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.head()" ] }, { "cell_type": "code", "execution_count": 46, "metadata": { "collapsed": true }, "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", "
PythonEnMathPhysicChem
209526.059.08.054.0149.0
2096NaN47.090.092.066.0
20975.097.073.0140.0104.0
2098102.06.07.05.0119.0
209997.019.077.0NaN48.0
\n", "
" ], "text/plain": [ " Python En Math Physic Chem\n", "2095 26.0 59.0 8.0 54.0 149.0\n", "2096 NaN 47.0 90.0 92.0 66.0\n", "2097 5.0 97.0 73.0 140.0 104.0\n", "2098 102.0 6.0 7.0 5.0 119.0\n", "2099 97.0 19.0 77.0 NaN 48.0" ] }, "execution_count": 46, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.tail()" ] }, { "cell_type": "code", "execution_count": 48, "metadata": { "collapsed": true }, "outputs": [ { "data": { "text/plain": [ "array([ 82., 4., 56., 47., 38., 18., 3., 35., 86., 19., 76.,\n", " 31., 64., 72., 55., 96., 63., 28., 85., 109., 2., 110.,\n", " 70., 51., 6., 65., 24., 48., 44., 11., 114., 129., 87.,\n", " 108., 125., nan, 140., 132., 91., 34., 54., 30., 12., 98.,\n", " 142., 79., 13., 77., 40., 139., 39., 81., 112., 36., 22.,\n", " 5., 120., 17., 127., 119., 59., 146., 89., 103., 8., 97.,\n", " 130., 73., 83., 122., 95., 100., 41., 21., 136., 80., 101.,\n", " 50., 27., 71., 16., 141., 126., 102., 145., 15., 52., 94.,\n", " 10., 33., 137., 9., 128., 88., 26., 84., 93., 1., 7.,\n", " 131., 107., 148., 0., 105., 66., 32., 115., 118., 58., 53.,\n", " 29., 42., 57., 62., 25., 60., 69., 133., 68., 20., 106.,\n", " 147., 78., 90., 124., 149., 92., 75., 117., 143., 99., 37.,\n", " 123., 45., 61., 121., 135., 138., 116., 14., 104., 74., 46.,\n", " 111., 23., 43., 49., 144., 113., 67., 134.])" ] }, "execution_count": 48, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# 去重之后的数据\n", "df['Python'].unique()" ] }, { "cell_type": "code", "execution_count": 49, "metadata": { "collapsed": true }, "outputs": [ { "data": { "text/plain": [ "143.0 20\n", "136.0 20\n", "102.0 19\n", "105.0 19\n", "26.0 19\n", "69.0 19\n", "31.0 18\n", "148.0 18\n", "75.0 18\n", "139.0 18\n", "1.0 18\n", "35.0 17\n", "140.0 17\n", "110.0 17\n", "125.0 17\n", "146.0 17\n", "141.0 17\n", "64.0 16\n", "30.0 16\n", "79.0 16\n", "73.0 16\n", "40.0 16\n", "10.0 15\n", "6.0 15\n", "65.0 15\n", "81.0 15\n", "28.0 15\n", "48.0 15\n", "92.0 15\n", "103.0 15\n", " ..\n", "104.0 9\n", "12.0 9\n", "116.0 9\n", "13.0 9\n", "59.0 9\n", "93.0 9\n", "124.0 9\n", "85.0 8\n", "135.0 8\n", "131.0 8\n", "68.0 8\n", "66.0 8\n", "62.0 8\n", "120.0 8\n", "17.0 8\n", "25.0 8\n", "145.0 7\n", "58.0 7\n", "134.0 7\n", "113.0 7\n", "123.0 7\n", "39.0 7\n", "34.0 7\n", "43.0 7\n", "74.0 6\n", "144.0 6\n", "132.0 6\n", "142.0 5\n", "67.0 5\n", "49.0 5\n", "Name: Python, Length: 150, dtype: int64" ] }, "execution_count": 49, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df['Python'].value_counts()" ] }, { "cell_type": "code", "execution_count": 53, "metadata": { "collapsed": true }, "outputs": [ { "data": { "text/plain": [ "8.0 21\n", "96.0 19\n", "118.0 19\n", "24.0 19\n", "43.0 19\n", "27.0 19\n", "19.0 19\n", "41.0 18\n", "0.0 18\n", "3.0 18\n", "52.0 18\n", "4.0 17\n", "137.0 17\n", "1.0 17\n", "101.0 17\n", "51.0 17\n", "39.0 17\n", "100.0 17\n", "127.0 17\n", "115.0 16\n", "33.0 16\n", "112.0 16\n", "92.0 16\n", "126.0 16\n", "133.0 15\n", "32.0 15\n", "89.0 15\n", "95.0 15\n", "36.0 15\n", "93.0 15\n", " ..\n", "12.0 9\n", "28.0 9\n", "106.0 9\n", "45.0 9\n", "80.0 9\n", "84.0 9\n", "58.0 9\n", "79.0 9\n", "71.0 9\n", "83.0 9\n", "142.0 9\n", "7.0 9\n", "6.0 8\n", "61.0 8\n", "149.0 8\n", "34.0 8\n", "20.0 8\n", "38.0 8\n", "130.0 8\n", "104.0 7\n", "120.0 7\n", "56.0 7\n", "146.0 7\n", "98.0 7\n", "134.0 6\n", "123.0 6\n", "35.0 6\n", "87.0 5\n", "42.0 5\n", "119.0 4\n", "Name: En, Length: 150, dtype: int64" ] }, "execution_count": 53, "metadata": {}, "output_type": "execute_result" } ], "source": [ "en = df['En'].value_counts()\n", "en" ] }, { "cell_type": "code", "execution_count": 54, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "8.0" ] }, "execution_count": 54, "metadata": {}, "output_type": "execute_result" } ], "source": [ "en.index[0]" ] }, { "cell_type": "code", "execution_count": 52, "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Python 75.0\n", "En 74.0\n", "Math 77.5\n", "Physic 73.0\n", "Chem 72.0\n", "dtype: float64 \n" ] } ], "source": [ "s = df.median()\n", "print(s,type(s))" ] }, { "cell_type": "code", "execution_count": 55, "metadata": {}, "outputs": [], "source": [ "zhongshu = []\n", "for col in df.columns:\n", " zhongshu.append(df[col].value_counts().index[0])" ] }, { "cell_type": "code", "execution_count": 57, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Python 143.0\n", "En 8.0\n", "Math 80.0\n", "Physic 31.0\n", "Chem 125.0\n", "dtype: float64" ] }, "execution_count": 57, "metadata": {}, "output_type": "execute_result" } ], "source": [ "s = Series(zhongshu,index = df.columns)\n", "s" ] }, { "cell_type": "code", "execution_count": 60, "metadata": { "collapsed": true }, "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
PythonEnMathPhysicChem
10082.089.099.0101.0125.0
1014.031.0109.032.05.0
10256.0103.056.031.090.0
10347.0100.0147.0138.099.0
10438.046.080.075.044.0
10518.011.0122.03.0126.0
10656.026.0106.014.0139.0
1073.0137.075.067.0144.0
10835.047.0102.060.063.0
10986.0126.080.088.0149.0
11019.0140.080.035.033.0
11176.08.05.011.033.0
11231.054.091.0119.069.0
11364.037.050.023.021.0
11472.057.0138.015.021.0
11555.0120.0104.032.025.0
11696.024.089.031.0146.0
11763.08.08.064.089.0
11828.08.0125.082.074.0
11985.039.070.0132.0111.0
120109.090.080.074.039.0
1212.08.0103.0114.065.0
122110.029.099.080.057.0
123109.088.081.0135.071.0
12470.0103.0134.0121.0121.0
12551.092.0117.031.043.0
1266.092.097.059.0105.0
12765.090.052.0148.022.0
1284.0129.017.0119.013.0
12924.0100.0107.028.0139.0
..................
2070127.077.024.016.0125.0
207193.061.09.028.022.0
2072116.061.054.08.061.0
20734.072.0140.031.034.0
2074143.0108.0123.032.033.0
207546.08.0135.0124.0113.0
2076143.018.0136.038.0125.0
2077143.011.0129.054.0119.0
207884.055.0129.037.087.0
207995.050.045.019.084.0
2080124.074.065.031.053.0
208126.035.0149.0145.0127.0
208219.021.0101.03.089.0
208384.08.0131.071.04.0
208428.074.0105.068.089.0
208523.093.084.097.088.0
208686.0133.026.0125.013.0
208721.0124.040.031.05.0
208820.015.035.031.037.0
208996.0123.0123.05.064.0
209022.043.092.078.060.0
209116.031.017.060.058.0
209265.018.013.013.034.0
209369.049.0109.040.058.0
2094128.046.010.082.0111.0
209526.059.08.054.0149.0
2096143.047.090.092.066.0
20975.097.073.0140.0104.0
2098102.06.07.05.0119.0
209997.019.077.031.048.0
\n", "

2000 rows × 5 columns

\n", "
" ], "text/plain": [ " Python En Math Physic Chem\n", "100 82.0 89.0 99.0 101.0 125.0\n", "101 4.0 31.0 109.0 32.0 5.0\n", "102 56.0 103.0 56.0 31.0 90.0\n", "103 47.0 100.0 147.0 138.0 99.0\n", "104 38.0 46.0 80.0 75.0 44.0\n", "105 18.0 11.0 122.0 3.0 126.0\n", "106 56.0 26.0 106.0 14.0 139.0\n", "107 3.0 137.0 75.0 67.0 144.0\n", "108 35.0 47.0 102.0 60.0 63.0\n", "109 86.0 126.0 80.0 88.0 149.0\n", "110 19.0 140.0 80.0 35.0 33.0\n", "111 76.0 8.0 5.0 11.0 33.0\n", "112 31.0 54.0 91.0 119.0 69.0\n", "113 64.0 37.0 50.0 23.0 21.0\n", "114 72.0 57.0 138.0 15.0 21.0\n", "115 55.0 120.0 104.0 32.0 25.0\n", "116 96.0 24.0 89.0 31.0 146.0\n", "117 63.0 8.0 8.0 64.0 89.0\n", "118 28.0 8.0 125.0 82.0 74.0\n", "119 85.0 39.0 70.0 132.0 111.0\n", "120 109.0 90.0 80.0 74.0 39.0\n", "121 2.0 8.0 103.0 114.0 65.0\n", "122 110.0 29.0 99.0 80.0 57.0\n", "123 109.0 88.0 81.0 135.0 71.0\n", "124 70.0 103.0 134.0 121.0 121.0\n", "125 51.0 92.0 117.0 31.0 43.0\n", "126 6.0 92.0 97.0 59.0 105.0\n", "127 65.0 90.0 52.0 148.0 22.0\n", "128 4.0 129.0 17.0 119.0 13.0\n", "129 24.0 100.0 107.0 28.0 139.0\n", "... ... ... ... ... ...\n", "2070 127.0 77.0 24.0 16.0 125.0\n", "2071 93.0 61.0 9.0 28.0 22.0\n", "2072 116.0 61.0 54.0 8.0 61.0\n", "2073 4.0 72.0 140.0 31.0 34.0\n", "2074 143.0 108.0 123.0 32.0 33.0\n", "2075 46.0 8.0 135.0 124.0 113.0\n", "2076 143.0 18.0 136.0 38.0 125.0\n", "2077 143.0 11.0 129.0 54.0 119.0\n", "2078 84.0 55.0 129.0 37.0 87.0\n", "2079 95.0 50.0 45.0 19.0 84.0\n", "2080 124.0 74.0 65.0 31.0 53.0\n", "2081 26.0 35.0 149.0 145.0 127.0\n", "2082 19.0 21.0 101.0 3.0 89.0\n", "2083 84.0 8.0 131.0 71.0 4.0\n", "2084 28.0 74.0 105.0 68.0 89.0\n", "2085 23.0 93.0 84.0 97.0 88.0\n", "2086 86.0 133.0 26.0 125.0 13.0\n", "2087 21.0 124.0 40.0 31.0 5.0\n", "2088 20.0 15.0 35.0 31.0 37.0\n", "2089 96.0 123.0 123.0 5.0 64.0\n", "2090 22.0 43.0 92.0 78.0 60.0\n", "2091 16.0 31.0 17.0 60.0 58.0\n", "2092 65.0 18.0 13.0 13.0 34.0\n", "2093 69.0 49.0 109.0 40.0 58.0\n", "2094 128.0 46.0 10.0 82.0 111.0\n", "2095 26.0 59.0 8.0 54.0 149.0\n", "2096 143.0 47.0 90.0 92.0 66.0\n", "2097 5.0 97.0 73.0 140.0 104.0\n", "2098 102.0 6.0 7.0 5.0 119.0\n", "2099 97.0 19.0 77.0 31.0 48.0\n", "\n", "[2000 rows x 5 columns]" ] }, "execution_count": 60, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df2 = df.fillna(s)\n", "df2" ] }, { "cell_type": "code", "execution_count": 61, "metadata": { "collapsed": true }, "outputs": [ { "data": { "text/plain": [ "Python 0\n", "En 0\n", "Math 0\n", "Physic 0\n", "Chem 0\n", "dtype: int64" ] }, "execution_count": 61, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df2.isnull().sum()" ] }, { "cell_type": "code", "execution_count": 62, "metadata": { "collapsed": true }, "outputs": [ { "data": { "text/plain": [ "Python 190\n", "En 200\n", "Math 194\n", "Physic 189\n", "Chem 181\n", "dtype: int64" ] }, "execution_count": 62, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.isnull().sum()" ] }, { "cell_type": "code", "execution_count": 65, "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", "
PythonEnMathPhysicChem
10082.089.099.0101.0125.0
1014.031.0109.032.05.0
10256.0103.056.0NaN90.0
10347.0100.0147.0138.099.0
10438.046.0NaN75.044.0
10518.011.0122.03.0126.0
10656.026.0106.014.0139.0
1073.0137.075.067.0144.0
10835.047.0102.060.063.0
10986.0126.0NaN88.0149.0
11019.0140.0NaN35.033.0
11176.0NaN5.011.033.0
11231.054.091.0119.069.0
11364.037.050.023.021.0
11472.057.0138.015.021.0
11555.0120.0104.032.025.0
11696.024.089.0NaN146.0
11763.0NaN8.064.089.0
11828.0NaN125.082.074.0
11985.039.070.0132.0111.0
\n", "
" ], "text/plain": [ " Python En Math Physic Chem\n", "100 82.0 89.0 99.0 101.0 125.0\n", "101 4.0 31.0 109.0 32.0 5.0\n", "102 56.0 103.0 56.0 NaN 90.0\n", "103 47.0 100.0 147.0 138.0 99.0\n", "104 38.0 46.0 NaN 75.0 44.0\n", "105 18.0 11.0 122.0 3.0 126.0\n", "106 56.0 26.0 106.0 14.0 139.0\n", "107 3.0 137.0 75.0 67.0 144.0\n", "108 35.0 47.0 102.0 60.0 63.0\n", "109 86.0 126.0 NaN 88.0 149.0\n", "110 19.0 140.0 NaN 35.0 33.0\n", "111 76.0 NaN 5.0 11.0 33.0\n", "112 31.0 54.0 91.0 119.0 69.0\n", "113 64.0 37.0 50.0 23.0 21.0\n", "114 72.0 57.0 138.0 15.0 21.0\n", "115 55.0 120.0 104.0 32.0 25.0\n", "116 96.0 24.0 89.0 NaN 146.0\n", "117 63.0 NaN 8.0 64.0 89.0\n", "118 28.0 NaN 125.0 82.0 74.0\n", "119 85.0 39.0 70.0 132.0 111.0" ] }, "execution_count": 65, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df3 = df.iloc[:20]\n", "df3" ] }, { "cell_type": "code", "execution_count": 70, "metadata": { "collapsed": true }, "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", "
PythonEnMathPhysicChem
10082.089.099.0101.0125.0
1014.031.0109.032.05.0
10256.0103.056.090.090.0
10347.0100.0147.0138.099.0
10438.046.075.075.044.0
10518.011.0122.03.0126.0
10656.026.0106.014.0139.0
1073.0137.075.067.0144.0
10835.047.0102.060.063.0
10986.0126.088.088.0149.0
11019.0140.035.035.033.0
11176.05.05.011.033.0
11231.054.091.0119.069.0
11364.037.050.023.021.0
11472.057.0138.015.021.0
11555.0120.0104.032.025.0
11696.024.089.0146.0146.0
11763.08.08.064.089.0
11828.0125.0125.082.074.0
11985.039.070.0132.0111.0
\n", "
" ], "text/plain": [ " Python En Math Physic Chem\n", "100 82.0 89.0 99.0 101.0 125.0\n", "101 4.0 31.0 109.0 32.0 5.0\n", "102 56.0 103.0 56.0 90.0 90.0\n", "103 47.0 100.0 147.0 138.0 99.0\n", "104 38.0 46.0 75.0 75.0 44.0\n", "105 18.0 11.0 122.0 3.0 126.0\n", "106 56.0 26.0 106.0 14.0 139.0\n", "107 3.0 137.0 75.0 67.0 144.0\n", "108 35.0 47.0 102.0 60.0 63.0\n", "109 86.0 126.0 88.0 88.0 149.0\n", "110 19.0 140.0 35.0 35.0 33.0\n", "111 76.0 5.0 5.0 11.0 33.0\n", "112 31.0 54.0 91.0 119.0 69.0\n", "113 64.0 37.0 50.0 23.0 21.0\n", "114 72.0 57.0 138.0 15.0 21.0\n", "115 55.0 120.0 104.0 32.0 25.0\n", "116 96.0 24.0 89.0 146.0 146.0\n", "117 63.0 8.0 8.0 64.0 89.0\n", "118 28.0 125.0 125.0 82.0 74.0\n", "119 85.0 39.0 70.0 132.0 111.0" ] }, "execution_count": 70, "metadata": {}, "output_type": "execute_result" } ], "source": [ "'''method : {'backfill', 'bfill', 'pad', 'ffill', None}, default None\n", " Method to use for filling holes in reindexed Series\n", " pad / ffill: propagate last valid observation forward to next valid\n", " backfill / bfill: use NEXT valid observation to fill gap'''\n", "df3.fillna(method='bfill',axis = 1)" ] }, { "cell_type": "code", "execution_count": 71, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(2000, 5)" ] }, "execution_count": 71, "metadata": {}, "output_type": "execute_result" } ], "source": [ "#数据量足够大，空数据比较少，直接删除\n", "df.shape" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "df.dro" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.5" } }, "nbformat": 4, "nbformat_minor": 2 }