|
| 1 | +{ |
| 2 | + "nbformat": 4, |
| 3 | + "nbformat_minor": 0, |
| 4 | + "metadata": { |
| 5 | + "colab": { |
| 6 | + "name": "Introduction-To-Data-PreProcessing.ipynb", |
| 7 | + "provenance": [] |
| 8 | + }, |
| 9 | + "kernelspec": { |
| 10 | + "name": "python3", |
| 11 | + "display_name": "Python 3" |
| 12 | + } |
| 13 | + }, |
| 14 | + "cells": [ |
| 15 | + { |
| 16 | + "cell_type": "code", |
| 17 | + "metadata": { |
| 18 | + "id": "n5SffVH7WyKD", |
| 19 | + "colab_type": "code", |
| 20 | + "colab": {} |
| 21 | + }, |
| 22 | + "source": [ |
| 23 | + "%matplotlib inline\n", |
| 24 | + "import pandas as pd\n", |
| 25 | + "import numpy as np\n", |
| 26 | + "import matplotlib.pyplot as plt\n" |
| 27 | + ], |
| 28 | + "execution_count": 0, |
| 29 | + "outputs": [] |
| 30 | + }, |
| 31 | + { |
| 32 | + "cell_type": "code", |
| 33 | + "metadata": { |
| 34 | + "id": "hTx7f0phZFIR", |
| 35 | + "colab_type": "code", |
| 36 | + "colab": {} |
| 37 | + }, |
| 38 | + "source": [ |
| 39 | + "from google.colab import drive \n", |
| 40 | + "drive.mount('/mntDrive') \n", |
| 41 | + "!ls \"/mntDrive/My Drive/Colab Notebooks\"\n" |
| 42 | + ], |
| 43 | + "execution_count": 0, |
| 44 | + "outputs": [] |
| 45 | + }, |
| 46 | + { |
| 47 | + "cell_type": "markdown", |
| 48 | + "metadata": { |
| 49 | + "id": "02ESSs6qZqXn", |
| 50 | + "colab_type": "text" |
| 51 | + }, |
| 52 | + "source": [ |
| 53 | + "" |
| 54 | + ] |
| 55 | + }, |
| 56 | + { |
| 57 | + "cell_type": "code", |
| 58 | + "metadata": { |
| 59 | + "id": "H9cAjsktYGkV", |
| 60 | + "colab_type": "code", |
| 61 | + "colab": {} |
| 62 | + }, |
| 63 | + "source": [ |
| 64 | + "df=pd.read_csv('/mntDrive/My Drive/Colab Notebooks/pima1.csv')" |
| 65 | + ], |
| 66 | + "execution_count": 0, |
| 67 | + "outputs": [] |
| 68 | + }, |
| 69 | + { |
| 70 | + "cell_type": "code", |
| 71 | + "metadata": { |
| 72 | + "id": "2MUSOJOrZPmW", |
| 73 | + "colab_type": "code", |
| 74 | + "colab": {} |
| 75 | + }, |
| 76 | + "source": [ |
| 77 | + "df" |
| 78 | + ], |
| 79 | + "execution_count": 0, |
| 80 | + "outputs": [] |
| 81 | + }, |
| 82 | + { |
| 83 | + "cell_type": "code", |
| 84 | + "metadata": { |
| 85 | + "id": "9GryFGuFZ0kt", |
| 86 | + "colab_type": "code", |
| 87 | + "colab": {} |
| 88 | + }, |
| 89 | + "source": [ |
| 90 | + "df.at[0, 'pregnancy'] = 200 #Changing the value in a particular cell" |
| 91 | + ], |
| 92 | + "execution_count": 0, |
| 93 | + "outputs": [] |
| 94 | + }, |
| 95 | + { |
| 96 | + "cell_type": "code", |
| 97 | + "metadata": { |
| 98 | + "id": "RJX9BEBFcgh7", |
| 99 | + "colab_type": "code", |
| 100 | + "colab": {} |
| 101 | + }, |
| 102 | + "source": [ |
| 103 | + "df.head()" |
| 104 | + ], |
| 105 | + "execution_count": 0, |
| 106 | + "outputs": [] |
| 107 | + }, |
| 108 | + { |
| 109 | + "cell_type": "code", |
| 110 | + "metadata": { |
| 111 | + "id": "gwZmEHtJebme", |
| 112 | + "colab_type": "code", |
| 113 | + "colab": {} |
| 114 | + }, |
| 115 | + "source": [ |
| 116 | + "#Checking for outliers (Method 1)\n", |
| 117 | + "plt.boxplot(df['pregnancy'])\n", |
| 118 | + "plt.show" |
| 119 | + ], |
| 120 | + "execution_count": 0, |
| 121 | + "outputs": [] |
| 122 | + }, |
| 123 | + { |
| 124 | + "cell_type": "code", |
| 125 | + "metadata": { |
| 126 | + "id": "2-8jcSDcg49x", |
| 127 | + "colab_type": "code", |
| 128 | + "colab": {} |
| 129 | + }, |
| 130 | + "source": [ |
| 131 | + "#Method 2\n", |
| 132 | + "Q1, Q3 = df.quantile(0.25), df.quantile(0.75)\n", |
| 133 | + "IQR = Q3 - Q1\n", |
| 134 | + "print(Q1)\n", |
| 135 | + "print(Q3)\n", |
| 136 | + "print(IQR)" |
| 137 | + ], |
| 138 | + "execution_count": 0, |
| 139 | + "outputs": [] |
| 140 | + }, |
| 141 | + { |
| 142 | + "cell_type": "code", |
| 143 | + "metadata": { |
| 144 | + "id": "rYOgxaKuidx0", |
| 145 | + "colab_type": "code", |
| 146 | + "colab": {} |
| 147 | + }, |
| 148 | + "source": [ |
| 149 | + "lower, upper = Q1 - (1.5*IQR), Q3 + (1.5*IQR)\n", |
| 150 | + "print((df<lower) | (df>upper))" |
| 151 | + ], |
| 152 | + "execution_count": 0, |
| 153 | + "outputs": [] |
| 154 | + }, |
| 155 | + { |
| 156 | + "cell_type": "code", |
| 157 | + "metadata": { |
| 158 | + "id": "F8Yp4E8_ixNt", |
| 159 | + "colab_type": "code", |
| 160 | + "colab": {} |
| 161 | + }, |
| 162 | + "source": [ |
| 163 | + "" |
| 164 | + ], |
| 165 | + "execution_count": 0, |
| 166 | + "outputs": [] |
| 167 | + } |
| 168 | + ] |
| 169 | +} |
0 commit comments