{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "pd.set_option('precision', 2)" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "titanic = pd.read_csv('titanic.csv')\n", "titanic.columns = ['name', 'survived', 'sex', 'age', 'klass']" ] }, { "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
namesurvivedsexageklass
0Allen, Miss. Elisabeth Waltonyesfemale29.001st
1Allison, Master. Hudson Trevoryesmale0.921st
2Allison, Miss. Helen Lorainenofemale2.001st
3Allison, Mr. Hudson Joshua Creinomale30.001st
4Allison, Mrs. Hudson J C (Bessinofemale25.001st
\n", "
" ], "text/plain": [ " name survived sex age klass\n", "0 Allen, Miss. Elisabeth Walton yes female 29.00 1st\n", "1 Allison, Master. Hudson Trevor yes male 0.92 1st\n", "2 Allison, Miss. Helen Loraine no female 2.00 1st\n", "3 Allison, Mr. Hudson Joshua Crei no male 30.00 1st\n", "4 Allison, Mrs. Hudson J C (Bessi no female 25.00 1st" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "titanic.head()" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "klass = [] # independent variable\n", "survived = [] # dependent variable\n", "\n", "for s, k in zip(titanic.survived, titanic.klass):\n", " \n", " if k == '1st': klass += [1]\n", " elif k == '2nd': klass += [2]\n", " else: klass += [3] \n", " \n", " if s == 'yes': survived += [1]\n", " else: survived += [0]" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "\n", "X = np.array(klass)\n", "y = np.array(survived)" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Shape of training set = (981, 1)\n", "Shape of testing set = (328, 1)\n" ] } ], "source": [ "from sklearn.model_selection import train_test_split\n", "\n", "X_train, X_test, y_train, y_test = train_test_split(X.reshape(-1, 1), y, random_state=0)\n", "\n", "print(f'Shape of training set = {X_train.shape}')\n", "print(f'Shape of testing set = {X_test.shape}')" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " X_train y_train X_test y_test\n", " 0 3 0 3 0\n", " 1 2 0 2 1\n", " 2 1 1 2 0\n", " 3 2 0 3 0\n", " 4 3 0 2 0\n", " 5 3 1 3 1\n", " 6 2 0 1 1\n", " 7 3 1 1 1\n", " 8 1 0 2 0\n", " 9 3 1 3 1\n", " 10 1 1 2 0\n" ] } ], "source": [ "print(' X_train y_train X_test y_test')\n", "\n", "for i in range(11):\n", " print(f'{i:3d}{X_train[i][0]:6d}{y_train[i]:9d}{X_test[i][0]:9d}{y_test[i]:8d}')" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "from sklearn.linear_model import LogisticRegression\n", "\n", "logistic_regression_model = LogisticRegression()\n", "logistic_regression_model.fit(X=X_train, y=y_train)\n", "\n", "predicted = logistic_regression_model.predict(X_test)\n", "expected = y_test" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "right predictions = 226\n", "wrong predictions = 102\n", "\n", "69% right\n" ] } ], "source": [ "right = 0\n", "wrong = 0\n", "\n", "for p, e in zip(predicted, expected):\n", " if p == e: right += 1\n", " else: wrong += 1\n", " \n", "print(f'right predictions = {right}')\n", "print(f'wrong predictions = {wrong}')\n", "print()\n", "print(f'{100*right/(right + wrong):.0f}% right')" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.7" } }, "nbformat": 4, "nbformat_minor": 4 }