{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "collapsed": true }, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "# import seaborn as sns\n", "# import matplotlib.pyplot as plt\n", "import os\n", "from sklearn.model_selection import train_test_split\n", "\n", "# plt.style.use('seaborn-colorblind')\n", "# %matplotlib inline\n", "#from feature_cleaning import rare_values as ra" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Load Dataset" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "collapsed": true }, "outputs": [], "source": [ "use_cols = [\n", " 'Pclass', 'Sex', 'Age', 'Fare', 'SibSp',\n", " 'Survived'\n", "]\n", "\n", "data = pd.read_csv('./data/titanic.csv', usecols=use_cols)\n" ] }, { "cell_type": "code", "execution_count": 3, "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", "
SurvivedPclassSexAgeSibSpFare
003male22.017.2500
111female38.0171.2833
213female26.007.9250
\n", "
" ], "text/plain": [ " Survived Pclass Sex Age SibSp Fare\n", "0 0 3 male 22.0 1 7.2500\n", "1 1 1 female 38.0 1 71.2833\n", "2 1 3 female 26.0 0 7.9250" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data.head(3)" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "((623, 6), (268, 6))" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Note that we include target variable in the X_train \n", "# because we need it to supervise our discretization\n", "# this is not the standard way of using train-test-split\n", "X_train, X_test, y_train, y_test = train_test_split(data, data.Survived, test_size=0.3,\n", " random_state=0)\n", "X_train.shape, X_test.shape" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Normalization - Standardization (Z-score scaling)\n", "\n", "removes the mean and scales the data to unit variance.
z = (X - X.mean) / std" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Survived Pclass Sex Age SibSp Fare Fare_zscore\n", "857 1 1 male 51.0 0 26.5500 -0.122530\n", "52 1 1 female 49.0 1 76.7292 0.918124\n", "386 0 3 male 1.0 5 46.9000 0.299503\n", "124 0 1 male 54.0 0 77.2875 0.929702\n", "578 0 3 female NaN 1 14.4583 -0.373297\n", "549 1 2 male 8.0 1 36.7500 0.089005\n" ] } ], "source": [ "# add the new created feature\n", "from sklearn.preprocessing import StandardScaler\n", "ss = StandardScaler().fit(X_train[['Fare']])\n", "X_train_copy = X_train.copy(deep=True)\n", "X_train_copy['Fare_zscore'] = ss.transform(X_train_copy[['Fare']])\n", "print(X_train_copy.head(6))" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "5.916437306188636e-17\n", "1.0008035356861\n" ] } ], "source": [ "# check if it is with mean=0 std=1\n", "print(X_train_copy['Fare_zscore'].mean())\n", "print(X_train_copy['Fare_zscore'].std())\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Min-Max scaling\n", "transforms features by scaling each feature to a given range. Default to [0,1].
X_scaled = (X - X.min / (X.max - X.min)" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Survived Pclass Sex Age SibSp Fare Fare_minmax\n", "857 1 1 male 51.0 0 26.5500 0.051822\n", "52 1 1 female 49.0 1 76.7292 0.149765\n", "386 0 3 male 1.0 5 46.9000 0.091543\n", "124 0 1 male 54.0 0 77.2875 0.150855\n", "578 0 3 female NaN 1 14.4583 0.028221\n", "549 1 2 male 8.0 1 36.7500 0.071731\n" ] } ], "source": [ "# add the new created feature\n", "from sklearn.preprocessing import MinMaxScaler\n", "mms = MinMaxScaler().fit(X_train[['Fare']])\n", "X_train_copy = X_train.copy(deep=True)\n", "X_train_copy['Fare_minmax'] = mms.transform(X_train_copy[['Fare']])\n", "print(X_train_copy.head(6))" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "1.0\n", "0.0\n" ] } ], "source": [ "# check the range of Fare_minmax\n", "print(X_train_copy['Fare_minmax'].max())\n", "print(X_train_copy['Fare_minmax'].min())" ] }, { "cell_type": "markdown", "metadata": { "collapsed": true }, "source": [ "## Robust scaling\n", "removes the median and scales the data according to the quantile range (defaults to IQR)
X_scaled = (X - X.median) / IQR" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Survived Pclass Sex Age SibSp Fare Fare_robust\n", "857 1 1 male 51.0 0 26.5500 0.492275\n", "52 1 1 female 49.0 1 76.7292 2.630973\n", "386 0 3 male 1.0 5 46.9000 1.359616\n", "124 0 1 male 54.0 0 77.2875 2.654768\n", "578 0 3 female NaN 1 14.4583 -0.023088\n", "549 1 2 male 8.0 1 36.7500 0.927011\n" ] } ], "source": [ "# add the new created feature\n", "from sklearn.preprocessing import RobustScaler\n", "rs = RobustScaler().fit(X_train[['Fare']])\n", "X_train_copy = X_train.copy(deep=True)\n", "X_train_copy['Fare_robust'] = rs.transform(X_train_copy[['Fare']])\n", "print(X_train_copy.head(6))" ] } ], "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": "3.6.1" } }, "nbformat": 4, "nbformat_minor": 2 }