Last active
February 16, 2022 04:48
-
-
Save vimaloctavius/598496314325e3e820451a4a9a02610e to your computer and use it in GitHub Desktop.
Titanic.ipynb
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "nbformat": 4, | |
| "nbformat_minor": 0, | |
| "metadata": { | |
| "colab": { | |
| "name": "Titanic.ipynb", | |
| "provenance": [], | |
| "collapsed_sections": [], | |
| "mount_file_id": "1hrRubWz4nfYtQIhFLqm3YRYh6SK-5QSM", | |
| "authorship_tag": "ABX9TyPm3V+PgeBayXjlcX1B1jrS", | |
| "include_colab_link": true | |
| }, | |
| "kernelspec": { | |
| "name": "python3", | |
| "display_name": "Python 3" | |
| }, | |
| "language_info": { | |
| "name": "python" | |
| } | |
| }, | |
| "cells": [ | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "view-in-github", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "<a href=\"https://colab.research.google.com/gist/vimaloctavius/598496314325e3e820451a4a9a02610e/titanic.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "Ir2FPypJx-Fs" | |
| }, | |
| "source": [ | |
| "**Machine Learning** Algorithms to predict who survived the Titanic based on independent Xs like Age, Gender, Parent or Child etc...\n", | |
| "\n" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "zPRyfLeucVSL" | |
| }, | |
| "source": [ | |
| "# Not all libraries maybe used...copied as a standard template for my use, not quite efficient for sure ;-)\n", | |
| "\n", | |
| "# Pandas is a software library written for the Python programming language for data manipulation and analysis.\n", | |
| "import pandas as pd\n", | |
| "# NumPy is a library for the Python programming language, adding support for large, multi-dimensional arrays and matrices, along with a large collection of high-level mathematical functions to operate on these arrays\n", | |
| "import numpy as np\n", | |
| "# Matplotlib is a plotting library for python and pyplot gives us a MatLab like plotting framework. We will use this in our plotter function to plot data.\n", | |
| "import matplotlib.pyplot as plt\n", | |
| "#Seaborn is a Python data visualization library based on matplotlib. It provides a high-level interface for drawing attractive and informative statistical graphics\n", | |
| "import seaborn as sns\n", | |
| "# Preprocessing allows us to standarsize our data\n", | |
| "from sklearn import preprocessing\n", | |
| "# Allows us to split our data into training and testing data\n", | |
| "from sklearn.model_selection import train_test_split\n", | |
| "# Allows us to test parameters of classification algorithms and find the best one\n", | |
| "from sklearn.model_selection import GridSearchCV\n", | |
| "# Logistic Regression classification algorithm\n", | |
| "from sklearn.linear_model import LogisticRegression\n", | |
| "# Support Vector Machine classification algorithm\n", | |
| "from sklearn.svm import SVC\n", | |
| "# Decision Tree classification algorithm\n", | |
| "from sklearn.tree import DecisionTreeClassifier\n", | |
| "# K Nearest Neighbors classification algorithm\n", | |
| "from sklearn.neighbors import KNeighborsClassifier" | |
| ], | |
| "execution_count": null, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "Vf8hqw3Aj70f" | |
| }, | |
| "source": [ | |
| "import itertools\n", | |
| "import numpy as np\n", | |
| "import matplotlib.pyplot as plt\n", | |
| "from matplotlib.ticker import NullFormatter\n", | |
| "import pandas as pd\n", | |
| "import numpy as np\n", | |
| "import matplotlib.ticker as ticker\n", | |
| "from sklearn import preprocessing\n", | |
| "%matplotlib inline\n", | |
| "from sklearn.metrics import jaccard_score\n", | |
| "from sklearn.metrics import log_loss\n", | |
| "from sklearn.metrics import classification_report\n", | |
| "from sklearn.model_selection import train_test_split\n", | |
| "from sklearn.neighbors import KNeighborsClassifier\n", | |
| "from sklearn import metrics\n", | |
| "from sklearn.tree import DecisionTreeClassifier\n", | |
| "from sklearn.metrics import accuracy_score\n", | |
| "import sklearn.metrics as metrics\n", | |
| "from sklearn import svm\n", | |
| "import pylab as pl\n", | |
| "import scipy.optimize as opt\n", | |
| "from sklearn import preprocessing\n", | |
| "from sklearn.svm import SVC\n", | |
| "from sklearn.linear_model import LogisticRegression\n", | |
| "from sklearn.metrics import confusion_matrix\n", | |
| "from sklearn.metrics import jaccard_score\n", | |
| "from sklearn.metrics import f1_score\n", | |
| "from sklearn.metrics import log_loss" | |
| ], | |
| "execution_count": null, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "BuafV5SLkXou" | |
| }, | |
| "source": [ | |
| "# Data Prep, feature engineering" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 496 | |
| }, | |
| "id": "Kz_K8E_gq9vK", | |
| "outputId": "cc63b445-d814-4447-9562-32fc8bf33211" | |
| }, | |
| "source": [ | |
| "train_data = pd.read_csv('/content/drive/MyDrive/Books/Kaggle/train.csv')\n", | |
| "train_data.head()" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/html": [ | |
| "<div>\n", | |
| "<style scoped>\n", | |
| " .dataframe tbody tr th:only-of-type {\n", | |
| " vertical-align: middle;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe tbody tr th {\n", | |
| " vertical-align: top;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe thead th {\n", | |
| " text-align: right;\n", | |
| " }\n", | |
| "</style>\n", | |
| "<table border=\"1\" class=\"dataframe\">\n", | |
| " <thead>\n", | |
| " <tr style=\"text-align: right;\">\n", | |
| " <th></th>\n", | |
| " <th>PassengerId</th>\n", | |
| " <th>Survived</th>\n", | |
| " <th>Pclass</th>\n", | |
| " <th>Name</th>\n", | |
| " <th>Sex</th>\n", | |
| " <th>Age</th>\n", | |
| " <th>SibSp</th>\n", | |
| " <th>Parch</th>\n", | |
| " <th>Ticket</th>\n", | |
| " <th>Fare</th>\n", | |
| " <th>Cabin</th>\n", | |
| " <th>Embarked</th>\n", | |
| " </tr>\n", | |
| " </thead>\n", | |
| " <tbody>\n", | |
| " <tr>\n", | |
| " <th>0</th>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>3</td>\n", | |
| " <td>Braund, Mr. Owen Harris</td>\n", | |
| " <td>male</td>\n", | |
| " <td>22.0</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>A/5 21171</td>\n", | |
| " <td>7.2500</td>\n", | |
| " <td>NaN</td>\n", | |
| " <td>S</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>1</th>\n", | |
| " <td>2</td>\n", | |
| " <td>1</td>\n", | |
| " <td>1</td>\n", | |
| " <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n", | |
| " <td>female</td>\n", | |
| " <td>38.0</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>PC 17599</td>\n", | |
| " <td>71.2833</td>\n", | |
| " <td>C85</td>\n", | |
| " <td>C</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>2</th>\n", | |
| " <td>3</td>\n", | |
| " <td>1</td>\n", | |
| " <td>3</td>\n", | |
| " <td>Heikkinen, Miss. Laina</td>\n", | |
| " <td>female</td>\n", | |
| " <td>26.0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>STON/O2. 3101282</td>\n", | |
| " <td>7.9250</td>\n", | |
| " <td>NaN</td>\n", | |
| " <td>S</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>3</th>\n", | |
| " <td>4</td>\n", | |
| " <td>1</td>\n", | |
| " <td>1</td>\n", | |
| " <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n", | |
| " <td>female</td>\n", | |
| " <td>35.0</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>113803</td>\n", | |
| " <td>53.1000</td>\n", | |
| " <td>C123</td>\n", | |
| " <td>S</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>4</th>\n", | |
| " <td>5</td>\n", | |
| " <td>0</td>\n", | |
| " <td>3</td>\n", | |
| " <td>Allen, Mr. William Henry</td>\n", | |
| " <td>male</td>\n", | |
| " <td>35.0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>373450</td>\n", | |
| " <td>8.0500</td>\n", | |
| " <td>NaN</td>\n", | |
| " <td>S</td>\n", | |
| " </tr>\n", | |
| " </tbody>\n", | |
| "</table>\n", | |
| "</div>" | |
| ], | |
| "text/plain": [ | |
| " PassengerId Survived Pclass ... Fare Cabin Embarked\n", | |
| "0 1 0 3 ... 7.2500 NaN S\n", | |
| "1 2 1 1 ... 71.2833 C85 C\n", | |
| "2 3 1 3 ... 7.9250 NaN S\n", | |
| "3 4 1 1 ... 53.1000 C123 S\n", | |
| "4 5 0 3 ... 8.0500 NaN S\n", | |
| "\n", | |
| "[5 rows x 12 columns]" | |
| ] | |
| }, | |
| "metadata": {}, | |
| "execution_count": 11 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "8Bvye_8r0Cm4" | |
| }, | |
| "source": [ | |
| "test_data = pd.read_csv('/content/drive/MyDrive/Books/Kaggle/test.csv')" | |
| ], | |
| "execution_count": null, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 445 | |
| }, | |
| "id": "4-GE0AMn0Zr7", | |
| "outputId": "066a9bd5-a2bb-480a-c08c-c8cc5f93c86f" | |
| }, | |
| "source": [ | |
| "test_data.head()" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/html": [ | |
| "<div>\n", | |
| "<style scoped>\n", | |
| " .dataframe tbody tr th:only-of-type {\n", | |
| " vertical-align: middle;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe tbody tr th {\n", | |
| " vertical-align: top;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe thead th {\n", | |
| " text-align: right;\n", | |
| " }\n", | |
| "</style>\n", | |
| "<table border=\"1\" class=\"dataframe\">\n", | |
| " <thead>\n", | |
| " <tr style=\"text-align: right;\">\n", | |
| " <th></th>\n", | |
| " <th>PassengerId</th>\n", | |
| " <th>Pclass</th>\n", | |
| " <th>Name</th>\n", | |
| " <th>Sex</th>\n", | |
| " <th>Age</th>\n", | |
| " <th>SibSp</th>\n", | |
| " <th>Parch</th>\n", | |
| " <th>Ticket</th>\n", | |
| " <th>Fare</th>\n", | |
| " <th>Cabin</th>\n", | |
| " <th>Embarked</th>\n", | |
| " </tr>\n", | |
| " </thead>\n", | |
| " <tbody>\n", | |
| " <tr>\n", | |
| " <th>0</th>\n", | |
| " <td>892</td>\n", | |
| " <td>3</td>\n", | |
| " <td>Kelly, Mr. James</td>\n", | |
| " <td>male</td>\n", | |
| " <td>34.5</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>330911</td>\n", | |
| " <td>7.8292</td>\n", | |
| " <td>NaN</td>\n", | |
| " <td>Q</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>1</th>\n", | |
| " <td>893</td>\n", | |
| " <td>3</td>\n", | |
| " <td>Wilkes, Mrs. James (Ellen Needs)</td>\n", | |
| " <td>female</td>\n", | |
| " <td>47.0</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>363272</td>\n", | |
| " <td>7.0000</td>\n", | |
| " <td>NaN</td>\n", | |
| " <td>S</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>2</th>\n", | |
| " <td>894</td>\n", | |
| " <td>2</td>\n", | |
| " <td>Myles, Mr. Thomas Francis</td>\n", | |
| " <td>male</td>\n", | |
| " <td>62.0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>240276</td>\n", | |
| " <td>9.6875</td>\n", | |
| " <td>NaN</td>\n", | |
| " <td>Q</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>3</th>\n", | |
| " <td>895</td>\n", | |
| " <td>3</td>\n", | |
| " <td>Wirz, Mr. Albert</td>\n", | |
| " <td>male</td>\n", | |
| " <td>27.0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>315154</td>\n", | |
| " <td>8.6625</td>\n", | |
| " <td>NaN</td>\n", | |
| " <td>S</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>4</th>\n", | |
| " <td>896</td>\n", | |
| " <td>3</td>\n", | |
| " <td>Hirvonen, Mrs. Alexander (Helga E Lindqvist)</td>\n", | |
| " <td>female</td>\n", | |
| " <td>22.0</td>\n", | |
| " <td>1</td>\n", | |
| " <td>1</td>\n", | |
| " <td>3101298</td>\n", | |
| " <td>12.2875</td>\n", | |
| " <td>NaN</td>\n", | |
| " <td>S</td>\n", | |
| " </tr>\n", | |
| " </tbody>\n", | |
| "</table>\n", | |
| "</div>" | |
| ], | |
| "text/plain": [ | |
| " PassengerId Pclass ... Cabin Embarked\n", | |
| "0 892 3 ... NaN Q\n", | |
| "1 893 3 ... NaN S\n", | |
| "2 894 2 ... NaN Q\n", | |
| "3 895 3 ... NaN S\n", | |
| "4 896 3 ... NaN S\n", | |
| "\n", | |
| "[5 rows x 11 columns]" | |
| ] | |
| }, | |
| "metadata": {}, | |
| "execution_count": 13 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 419 | |
| }, | |
| "id": "w5JKIG1d2OD8", | |
| "outputId": "fb4f699a-e766-4043-e581-6d7f52698a52" | |
| }, | |
| "source": [ | |
| "features = [\"Pclass\",\"Sex\",\"SibSp\",\"Parch\"]\n", | |
| "X = pd.get_dummies(train_data[features])\n", | |
| "X" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/html": [ | |
| "<div>\n", | |
| "<style scoped>\n", | |
| " .dataframe tbody tr th:only-of-type {\n", | |
| " vertical-align: middle;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe tbody tr th {\n", | |
| " vertical-align: top;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe thead th {\n", | |
| " text-align: right;\n", | |
| " }\n", | |
| "</style>\n", | |
| "<table border=\"1\" class=\"dataframe\">\n", | |
| " <thead>\n", | |
| " <tr style=\"text-align: right;\">\n", | |
| " <th></th>\n", | |
| " <th>Pclass</th>\n", | |
| " <th>SibSp</th>\n", | |
| " <th>Parch</th>\n", | |
| " <th>Sex_female</th>\n", | |
| " <th>Sex_male</th>\n", | |
| " </tr>\n", | |
| " </thead>\n", | |
| " <tbody>\n", | |
| " <tr>\n", | |
| " <th>0</th>\n", | |
| " <td>3</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>1</th>\n", | |
| " <td>1</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>2</th>\n", | |
| " <td>3</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>3</th>\n", | |
| " <td>1</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>4</th>\n", | |
| " <td>3</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>...</th>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>886</th>\n", | |
| " <td>2</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>887</th>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>888</th>\n", | |
| " <td>3</td>\n", | |
| " <td>1</td>\n", | |
| " <td>2</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>889</th>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>890</th>\n", | |
| " <td>3</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " </tbody>\n", | |
| "</table>\n", | |
| "<p>891 rows × 5 columns</p>\n", | |
| "</div>" | |
| ], | |
| "text/plain": [ | |
| " Pclass SibSp Parch Sex_female Sex_male\n", | |
| "0 3 1 0 0 1\n", | |
| "1 1 1 0 1 0\n", | |
| "2 3 0 0 1 0\n", | |
| "3 1 1 0 1 0\n", | |
| "4 3 0 0 0 1\n", | |
| ".. ... ... ... ... ...\n", | |
| "886 2 0 0 0 1\n", | |
| "887 1 0 0 1 0\n", | |
| "888 3 1 2 1 0\n", | |
| "889 1 0 0 0 1\n", | |
| "890 3 0 0 0 1\n", | |
| "\n", | |
| "[891 rows x 5 columns]" | |
| ] | |
| }, | |
| "metadata": {}, | |
| "execution_count": 16 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "Fz8gjEfC3TJA" | |
| }, | |
| "source": [ | |
| "y = train_data[\"Survived\"]" | |
| ], | |
| "execution_count": null, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "colab": { | |
| "base_uri": "https://localhost:8080/" | |
| }, | |
| "id": "mIUeIzUkvpsK", | |
| "outputId": "8acfa7a7-d531-4f02-86e1-53f61fb12387" | |
| }, | |
| "source": [ | |
| "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2)\n", | |
| "print(\"Train set:\", X_train.shape, y_train.shape)\n", | |
| "print(\"Test set:\", X_test.shape, y_test.shape)" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "stream", | |
| "name": "stdout", | |
| "text": [ | |
| "Train set: (712, 5) (712,)\n", | |
| "Test set: (179, 5) (179,)\n" | |
| ] | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 419 | |
| }, | |
| "id": "sgMkyY8lfejD", | |
| "outputId": "accc2782-6c5c-4a90-85af-9ebc8b0a2d20" | |
| }, | |
| "source": [ | |
| "X_train" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/html": [ | |
| "<div>\n", | |
| "<style scoped>\n", | |
| " .dataframe tbody tr th:only-of-type {\n", | |
| " vertical-align: middle;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe tbody tr th {\n", | |
| " vertical-align: top;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe thead th {\n", | |
| " text-align: right;\n", | |
| " }\n", | |
| "</style>\n", | |
| "<table border=\"1\" class=\"dataframe\">\n", | |
| " <thead>\n", | |
| " <tr style=\"text-align: right;\">\n", | |
| " <th></th>\n", | |
| " <th>Pclass</th>\n", | |
| " <th>SibSp</th>\n", | |
| " <th>Parch</th>\n", | |
| " <th>Sex_female</th>\n", | |
| " <th>Sex_male</th>\n", | |
| " </tr>\n", | |
| " </thead>\n", | |
| " <tbody>\n", | |
| " <tr>\n", | |
| " <th>790</th>\n", | |
| " <td>3</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>467</th>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>431</th>\n", | |
| " <td>3</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>710</th>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>608</th>\n", | |
| " <td>2</td>\n", | |
| " <td>1</td>\n", | |
| " <td>2</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>...</th>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>536</th>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>198</th>\n", | |
| " <td>3</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>876</th>\n", | |
| " <td>3</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>7</th>\n", | |
| " <td>3</td>\n", | |
| " <td>3</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>558</th>\n", | |
| " <td>1</td>\n", | |
| " <td>1</td>\n", | |
| " <td>1</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " </tbody>\n", | |
| "</table>\n", | |
| "<p>712 rows × 5 columns</p>\n", | |
| "</div>" | |
| ], | |
| "text/plain": [ | |
| " Pclass SibSp Parch Sex_female Sex_male\n", | |
| "790 3 0 0 0 1\n", | |
| "467 1 0 0 0 1\n", | |
| "431 3 1 0 1 0\n", | |
| "710 1 0 0 1 0\n", | |
| "608 2 1 2 1 0\n", | |
| ".. ... ... ... ... ...\n", | |
| "536 1 0 0 0 1\n", | |
| "198 3 0 0 1 0\n", | |
| "876 3 0 0 0 1\n", | |
| "7 3 3 1 0 1\n", | |
| "558 1 1 1 1 0\n", | |
| "\n", | |
| "[712 rows x 5 columns]" | |
| ] | |
| }, | |
| "metadata": {}, | |
| "execution_count": 19 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "colab": { | |
| "base_uri": "https://localhost:8080/" | |
| }, | |
| "id": "buLIdU0gfj4s", | |
| "outputId": "00ee284f-6191-4f2a-ef96-f998cbb4b0b3" | |
| }, | |
| "source": [ | |
| "y_train" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "790 0\n", | |
| "467 0\n", | |
| "431 1\n", | |
| "710 1\n", | |
| "608 1\n", | |
| " ..\n", | |
| "536 0\n", | |
| "198 1\n", | |
| "876 0\n", | |
| "7 0\n", | |
| "558 1\n", | |
| "Name: Survived, Length: 712, dtype: int64" | |
| ] | |
| }, | |
| "metadata": {}, | |
| "execution_count": 20 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 419 | |
| }, | |
| "id": "Rc_LaOgTfulO", | |
| "outputId": "839e33f5-ce19-49d0-888b-c415150e350c" | |
| }, | |
| "source": [ | |
| "X_test" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/html": [ | |
| "<div>\n", | |
| "<style scoped>\n", | |
| " .dataframe tbody tr th:only-of-type {\n", | |
| " vertical-align: middle;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe tbody tr th {\n", | |
| " vertical-align: top;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe thead th {\n", | |
| " text-align: right;\n", | |
| " }\n", | |
| "</style>\n", | |
| "<table border=\"1\" class=\"dataframe\">\n", | |
| " <thead>\n", | |
| " <tr style=\"text-align: right;\">\n", | |
| " <th></th>\n", | |
| " <th>Pclass</th>\n", | |
| " <th>SibSp</th>\n", | |
| " <th>Parch</th>\n", | |
| " <th>Sex_female</th>\n", | |
| " <th>Sex_male</th>\n", | |
| " </tr>\n", | |
| " </thead>\n", | |
| " <tbody>\n", | |
| " <tr>\n", | |
| " <th>177</th>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>846</th>\n", | |
| " <td>3</td>\n", | |
| " <td>8</td>\n", | |
| " <td>2</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>69</th>\n", | |
| " <td>3</td>\n", | |
| " <td>2</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>682</th>\n", | |
| " <td>3</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>569</th>\n", | |
| " <td>3</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>...</th>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>797</th>\n", | |
| " <td>3</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>91</th>\n", | |
| " <td>3</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>312</th>\n", | |
| " <td>2</td>\n", | |
| " <td>1</td>\n", | |
| " <td>1</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>540</th>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>2</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>135</th>\n", | |
| " <td>2</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " </tbody>\n", | |
| "</table>\n", | |
| "<p>179 rows × 5 columns</p>\n", | |
| "</div>" | |
| ], | |
| "text/plain": [ | |
| " Pclass SibSp Parch Sex_female Sex_male\n", | |
| "177 1 0 0 1 0\n", | |
| "846 3 8 2 0 1\n", | |
| "69 3 2 0 0 1\n", | |
| "682 3 0 0 0 1\n", | |
| "569 3 0 0 0 1\n", | |
| ".. ... ... ... ... ...\n", | |
| "797 3 0 0 1 0\n", | |
| "91 3 0 0 0 1\n", | |
| "312 2 1 1 1 0\n", | |
| "540 1 0 2 1 0\n", | |
| "135 2 0 0 0 1\n", | |
| "\n", | |
| "[179 rows x 5 columns]" | |
| ] | |
| }, | |
| "metadata": {}, | |
| "execution_count": 21 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "colab": { | |
| "base_uri": "https://localhost:8080/" | |
| }, | |
| "id": "0WXYNTkQf5Ed", | |
| "outputId": "f6d45b4b-c55e-4531-cb61-984b4caef909" | |
| }, | |
| "source": [ | |
| "y_test" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "177 0\n", | |
| "846 0\n", | |
| "69 0\n", | |
| "682 0\n", | |
| "569 1\n", | |
| " ..\n", | |
| "797 1\n", | |
| "91 0\n", | |
| "312 0\n", | |
| "540 1\n", | |
| "135 0\n", | |
| "Name: Survived, Length: 179, dtype: int64" | |
| ] | |
| }, | |
| "metadata": {}, | |
| "execution_count": 39 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "hBx-ubkJiqRU" | |
| }, | |
| "source": [ | |
| "# KNN" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "colab": { | |
| "base_uri": "https://localhost:8080/" | |
| }, | |
| "id": "yvJUFFc4kKMe", | |
| "outputId": "d3b6c3e8-af69-419b-9b31-87114f576df6" | |
| }, | |
| "source": [ | |
| " j = 10\n", | |
| " for i in range(1,j):\n", | |
| " \n", | |
| " KNN_model = KNeighborsClassifier(n_neighbors = i).fit(X_train,y_train)\n", | |
| " yhat_Knn = KNN_model.predict(X_test)\n", | |
| " acc_sc= (metrics.accuracy_score(y_test, yhat_Knn))\n", | |
| " print('Neighbour {} with acuracy {}'. format(i, acc_sc))" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "stream", | |
| "name": "stdout", | |
| "text": [ | |
| "Neighbour 1 with acuracy 0.8268156424581006\n", | |
| "Neighbour 2 with acuracy 0.8212290502793296\n", | |
| "Neighbour 3 with acuracy 0.8491620111731844\n", | |
| "Neighbour 4 with acuracy 0.7988826815642458\n", | |
| "Neighbour 5 with acuracy 0.8156424581005587\n", | |
| "Neighbour 6 with acuracy 0.7988826815642458\n", | |
| "Neighbour 7 with acuracy 0.7988826815642458\n", | |
| "Neighbour 8 with acuracy 0.770949720670391\n", | |
| "Neighbour 9 with acuracy 0.776536312849162\n" | |
| ] | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "colab": { | |
| "base_uri": "https://localhost:8080/" | |
| }, | |
| "id": "QIa1stDYkPXN", | |
| "outputId": "0141ca07-8d3d-40a8-804e-7dd8240f5090" | |
| }, | |
| "source": [ | |
| "k=3\n", | |
| "neigh = KNeighborsClassifier(n_neighbors = k).fit(X_train, y_train)\n", | |
| "yhat_knn2 = neigh.predict(X_test)\n", | |
| "jc_knn = jaccard_score(y_test,yhat_knn2,pos_label=1)\n", | |
| "print(classification_report(y_test,yhat_knn2))" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "stream", | |
| "name": "stdout", | |
| "text": [ | |
| " precision recall f1-score support\n", | |
| "\n", | |
| " 0 0.86 0.91 0.89 114\n", | |
| " 1 0.83 0.74 0.78 65\n", | |
| "\n", | |
| " accuracy 0.85 179\n", | |
| " macro avg 0.84 0.83 0.83 179\n", | |
| "weighted avg 0.85 0.85 0.85 179\n", | |
| "\n" | |
| ] | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "colab": { | |
| "base_uri": "https://localhost:8080/" | |
| }, | |
| "id": "1rzG-Lur5LyA", | |
| "outputId": "7bd17f43-d14a-48f4-ea6a-4574623e9f71" | |
| }, | |
| "source": [ | |
| "yhat_knn2" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "array([1, 0, 0, 0, 0, 0, 1, 1, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 1, 0, 0,\n", | |
| " 1, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0,\n", | |
| " 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 1, 1, 0,\n", | |
| " 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", | |
| " 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0,\n", | |
| " 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 0,\n", | |
| " 1, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 1, 0,\n", | |
| " 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 1, 0,\n", | |
| " 1, 1, 0])" | |
| ] | |
| }, | |
| "metadata": {}, | |
| "execution_count": 25 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "xzEYpgMYki7e" | |
| }, | |
| "source": [ | |
| "# Decision Tree" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "634bo44Pkpbe" | |
| }, | |
| "source": [ | |
| "dtree = DecisionTreeClassifier(criterion = \"entropy\", max_depth = 4)\n", | |
| "dtree.fit(X_train, y_train)\n", | |
| "predtree = dtree.predict(X_test)" | |
| ], | |
| "execution_count": null, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "TvUGfAgxktGz", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/" | |
| }, | |
| "outputId": "a8608f0b-efa2-4853-d0fb-65420439ef65" | |
| }, | |
| "source": [ | |
| "print(\"Decision tree accuracy :\",metrics.accuracy_score(y_test,predtree) )" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "stream", | |
| "name": "stdout", | |
| "text": [ | |
| "Decision tree accuracy : 0.7988826815642458\n" | |
| ] | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "DuwbjSWNkvi8", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/" | |
| }, | |
| "outputId": "1803af04-d187-4be3-b539-877b1d3ebc1b" | |
| }, | |
| "source": [ | |
| "jc_dtree = jaccard_score(y_test,predtree,pos_label=1)\n", | |
| "jc_dtree" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "0.5135135135135135" | |
| ] | |
| }, | |
| "metadata": {}, | |
| "execution_count": 29 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "KKPtCry6k1aI" | |
| }, | |
| "source": [ | |
| "# Support Vector Machine" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "PiqrHW3Pk8HB", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/" | |
| }, | |
| "outputId": "7917b010-6d47-4cb4-c3a9-546fddf76a9c" | |
| }, | |
| "source": [ | |
| "clf = svm.SVC(kernel = \"rbf\")\n", | |
| "clf.fit(X_train,y_train)\n", | |
| "SVC()" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "SVC()" | |
| ] | |
| }, | |
| "metadata": {}, | |
| "execution_count": 30 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "U2sCf3Sfk_w8" | |
| }, | |
| "source": [ | |
| "yhat_svm = clf.predict(X_test)" | |
| ], | |
| "execution_count": null, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "_A1n_j4rlCEK", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/" | |
| }, | |
| "outputId": "d4a6e626-9977-4132-f627-23d99ebda77f" | |
| }, | |
| "source": [ | |
| "jc_svm = jaccard_score(y_test,yhat_svm,pos_label=1)\n", | |
| "jc_svm" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "0.56" | |
| ] | |
| }, | |
| "metadata": {}, | |
| "execution_count": 33 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "ecs67HO3lPpK", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/" | |
| }, | |
| "outputId": "6aa0f19a-e486-4e90-c95e-17d8dd7f9cea" | |
| }, | |
| "source": [ | |
| "print(classification_report(y_test,yhat_svm))" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "stream", | |
| "name": "stdout", | |
| "text": [ | |
| " precision recall f1-score support\n", | |
| "\n", | |
| " 0 0.82 0.91 0.86 114\n", | |
| " 1 0.81 0.65 0.72 65\n", | |
| "\n", | |
| " accuracy 0.82 179\n", | |
| " macro avg 0.81 0.78 0.79 179\n", | |
| "weighted avg 0.81 0.82 0.81 179\n", | |
| "\n" | |
| ] | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "ofRd5X0Llpme" | |
| }, | |
| "source": [ | |
| "# Logistic Regression" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "gn_e0j9AlxFw" | |
| }, | |
| "source": [ | |
| "LR = LogisticRegression(C = 0.01, solver = \"liblinear\").fit(X_train, y_train)\n", | |
| "yhat_LR = LR.predict(X_test)" | |
| ], | |
| "execution_count": null, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "zSqqIz68lyAJ", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/" | |
| }, | |
| "outputId": "c079f8ed-b43f-49e8-8536-d1fb43df374f" | |
| }, | |
| "source": [ | |
| "jc_logreg = jaccard_score(y_test,yhat_LR,pos_label=1)\n", | |
| "jc_logreg" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "0.4444444444444444" | |
| ] | |
| }, | |
| "metadata": {}, | |
| "execution_count": 37 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "wHL-dK2fl1sT", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/" | |
| }, | |
| "outputId": "fdf6a948-486b-4fee-bde3-487d4685e565" | |
| }, | |
| "source": [ | |
| "print(classification_report(y_test,yhat_LR))" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "stream", | |
| "name": "stdout", | |
| "text": [ | |
| " precision recall f1-score support\n", | |
| "\n", | |
| " 0 0.76 0.94 0.84 114\n", | |
| " 1 0.82 0.49 0.62 65\n", | |
| "\n", | |
| " accuracy 0.78 179\n", | |
| " macro avg 0.79 0.72 0.73 179\n", | |
| "weighted avg 0.78 0.78 0.76 179\n", | |
| "\n" | |
| ] | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "v7XCkutSl9KZ" | |
| }, | |
| "source": [ | |
| "# Prediction, Output" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 419 | |
| }, | |
| "id": "J9-stXcJk9kc", | |
| "outputId": "4e8bdeab-3780-4a2e-e8a4-73cd0f4dff57" | |
| }, | |
| "source": [ | |
| "X2 = pd.get_dummies(test_data[features])\n", | |
| "X2" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/html": [ | |
| "<div>\n", | |
| "<style scoped>\n", | |
| " .dataframe tbody tr th:only-of-type {\n", | |
| " vertical-align: middle;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe tbody tr th {\n", | |
| " vertical-align: top;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe thead th {\n", | |
| " text-align: right;\n", | |
| " }\n", | |
| "</style>\n", | |
| "<table border=\"1\" class=\"dataframe\">\n", | |
| " <thead>\n", | |
| " <tr style=\"text-align: right;\">\n", | |
| " <th></th>\n", | |
| " <th>Pclass</th>\n", | |
| " <th>SibSp</th>\n", | |
| " <th>Parch</th>\n", | |
| " <th>Sex_female</th>\n", | |
| " <th>Sex_male</th>\n", | |
| " </tr>\n", | |
| " </thead>\n", | |
| " <tbody>\n", | |
| " <tr>\n", | |
| " <th>0</th>\n", | |
| " <td>3</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>1</th>\n", | |
| " <td>3</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>2</th>\n", | |
| " <td>2</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>3</th>\n", | |
| " <td>3</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>4</th>\n", | |
| " <td>3</td>\n", | |
| " <td>1</td>\n", | |
| " <td>1</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>...</th>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>413</th>\n", | |
| " <td>3</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>414</th>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>415</th>\n", | |
| " <td>3</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>416</th>\n", | |
| " <td>3</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>417</th>\n", | |
| " <td>3</td>\n", | |
| " <td>1</td>\n", | |
| " <td>1</td>\n", | |
| " <td>0</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " </tbody>\n", | |
| "</table>\n", | |
| "<p>418 rows × 5 columns</p>\n", | |
| "</div>" | |
| ], | |
| "text/plain": [ | |
| " Pclass SibSp Parch Sex_female Sex_male\n", | |
| "0 3 0 0 0 1\n", | |
| "1 3 1 0 1 0\n", | |
| "2 2 0 0 0 1\n", | |
| "3 3 0 0 0 1\n", | |
| "4 3 1 1 1 0\n", | |
| ".. ... ... ... ... ...\n", | |
| "413 3 0 0 0 1\n", | |
| "414 1 0 0 1 0\n", | |
| "415 3 0 0 0 1\n", | |
| "416 3 0 0 0 1\n", | |
| "417 3 1 1 0 1\n", | |
| "\n", | |
| "[418 rows x 5 columns]" | |
| ] | |
| }, | |
| "metadata": {}, | |
| "execution_count": 42 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "colab": { | |
| "base_uri": "https://localhost:8080/" | |
| }, | |
| "id": "jE54Sw8alaoJ", | |
| "outputId": "5d8f1e2b-c649-4e16-9290-6a45e03e21a2" | |
| }, | |
| "source": [ | |
| "yhat_Knn3 = neigh.predict(X2)\n", | |
| "yhat_Knn3" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "array([0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 1, 1,\n", | |
| " 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 1, 0, 0, 1,\n", | |
| " 1, 0, 0, 0, 1, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1,\n", | |
| " 1, 0, 0, 1, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 1, 1,\n", | |
| " 1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", | |
| " 0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0,\n", | |
| " 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1,\n", | |
| " 0, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1,\n", | |
| " 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1,\n", | |
| " 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0,\n", | |
| " 1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0, 1, 1, 1, 1,\n", | |
| " 0, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0,\n", | |
| " 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0,\n", | |
| " 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1,\n", | |
| " 0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0,\n", | |
| " 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 1, 0,\n", | |
| " 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 0,\n", | |
| " 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1,\n", | |
| " 0, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 1, 0, 1, 0, 0, 0])" | |
| ] | |
| }, | |
| "metadata": {}, | |
| "execution_count": 44 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "cQjxHSTmmHb6" | |
| }, | |
| "source": [ | |
| "#yhat_knn2 seems best with neighbor3 with .8491 accuracy\n", | |
| "output = pd.DataFrame\\\n", | |
| "({'PassengeId':test_data.PassengerId,'Survivor':yhat_Knn3})\n" | |
| ], | |
| "execution_count": null, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 419 | |
| }, | |
| "id": "-D5As-ipmQ2Y", | |
| "outputId": "b8698673-9248-4b29-ae19-efe2e14db7ea" | |
| }, | |
| "source": [ | |
| "output" | |
| ], | |
| "execution_count": null, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/html": [ | |
| "<div>\n", | |
| "<style scoped>\n", | |
| " .dataframe tbody tr th:only-of-type {\n", | |
| " vertical-align: middle;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe tbody tr th {\n", | |
| " vertical-align: top;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe thead th {\n", | |
| " text-align: right;\n", | |
| " }\n", | |
| "</style>\n", | |
| "<table border=\"1\" class=\"dataframe\">\n", | |
| " <thead>\n", | |
| " <tr style=\"text-align: right;\">\n", | |
| " <th></th>\n", | |
| " <th>PassengeId</th>\n", | |
| " <th>Survivor</th>\n", | |
| " </tr>\n", | |
| " </thead>\n", | |
| " <tbody>\n", | |
| " <tr>\n", | |
| " <th>0</th>\n", | |
| " <td>892</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>1</th>\n", | |
| " <td>893</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>2</th>\n", | |
| " <td>894</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>3</th>\n", | |
| " <td>895</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>4</th>\n", | |
| " <td>896</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>...</th>\n", | |
| " <td>...</td>\n", | |
| " <td>...</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>413</th>\n", | |
| " <td>1305</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>414</th>\n", | |
| " <td>1306</td>\n", | |
| " <td>1</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>415</th>\n", | |
| " <td>1307</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>416</th>\n", | |
| " <td>1308</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>417</th>\n", | |
| " <td>1309</td>\n", | |
| " <td>0</td>\n", | |
| " </tr>\n", | |
| " </tbody>\n", | |
| "</table>\n", | |
| "<p>418 rows × 2 columns</p>\n", | |
| "</div>" | |
| ], | |
| "text/plain": [ | |
| " PassengeId Survivor\n", | |
| "0 892 0\n", | |
| "1 893 1\n", | |
| "2 894 0\n", | |
| "3 895 0\n", | |
| "4 896 0\n", | |
| ".. ... ...\n", | |
| "413 1305 0\n", | |
| "414 1306 1\n", | |
| "415 1307 0\n", | |
| "416 1308 0\n", | |
| "417 1309 0\n", | |
| "\n", | |
| "[418 rows x 2 columns]" | |
| ] | |
| }, | |
| "metadata": {}, | |
| "execution_count": 47 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "z4IH1qe8mVgB" | |
| }, | |
| "source": [ | |
| "output.to_csv('/content/drive/MyDrive/Books/Kaggle/prediction.csv',index=False)" | |
| ], | |
| "execution_count": null, | |
| "outputs": [] | |
| } | |
| ] | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment