The first attack Titanic: Machine Learning from Disaster for Competition

titanic.ipynb

{
  "cells": [
    {
      "metadata": {
        "collapsed": true,
        "trusted": true
      },
      "cell_type": "code",
      "source": "import pandas as pd\nimport numpy as np\nfrom sklearn import tree",
      "execution_count": 1,
      "outputs": []
    },
    {
      "metadata": {
        "collapsed": true,
        "trusted": true
      },
      "cell_type": "code",
      "source": "gender_map = {'female': 0, 'male': 1}\nfeature_fields = ['Pclass', 'Sex', 'Age', 'Fare']",
      "execution_count": 2,
      "outputs": []
    },
    {
      "metadata": {
        "collapsed": true,
        "scrolled": true,
        "trusted": true
      },
      "cell_type": "code",
      "source": "train_df = pd.read_csv('data/train.csv')\ntest_df  = pd.read_csv('data/test.csv')",
      "execution_count": 3,
      "outputs": []
    },
    {
      "metadata": {
        "collapsed": true,
        "trusted": true
      },
      "cell_type": "code",
      "source": "train_df['Sex'] = train_df['Sex'].map(gender_map).astype(int)\ntrain_df['Age'] = train_df['Age'].fillna(train_df['Age'].median())",
      "execution_count": 4,
      "outputs": []
    },
    {
      "metadata": {
        "collapsed": true,
        "trusted": true
      },
      "cell_type": "code",
      "source": "test_df['Sex'] = test_df['Sex'].map(gender_map).astype(int)\ntest_df['Age'] = test_df['Age'].fillna(test_df['Age'].median())\ntest_df['Fare'] = test_df['Fare'].fillna(test_df['Fare'].median())",
      "execution_count": 5,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": true
      },
      "cell_type": "code",
      "source": "target = train_df['Survived'].values\nfeatures = train_df[feature_fields].values\ntest_features = test_df[feature_fields].values",
      "execution_count": 6,
      "outputs": []
    },
    {
      "metadata": {
        "collapsed": true,
        "trusted": true
      },
      "cell_type": "code",
      "source": "dec_tree = tree.DecisionTreeClassifier(min_samples_split=4)\ndec_tree = dec_tree.fit(features, target)",
      "execution_count": 7,
      "outputs": []
    },
    {
      "metadata": {
        "collapsed": true,
        "trusted": true
      },
      "cell_type": "code",
      "source": "prediction = dec_tree.predict(test_features)",
      "execution_count": 8,
      "outputs": []
    },
    {
      "metadata": {
        "collapsed": true,
        "trusted": true
      },
      "cell_type": "code",
      "source": "pindex = test_df['PassengerId'].values\nsolution = pd.DataFrame(prediction, pindex, columns = ['Survived'])\nsolution.to_csv('solution.csv', index_label = 'PassengerId')",
      "execution_count": 9,
      "outputs": []
    }
  ],
  "metadata": {
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3",
      "language": "python"
    },
    "language_info": {
      "name": "python",
      "version": "3.6.3",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "gist": {
      "id": "43147125b888f512e15f733eca5d077e",
      "data": {
        "description": "The first attack Titanic: Machine Learning from Disaster for Competition",
        "public": true
      }
    },
    "_draft": {
      "nbviewer_url": "https://gist.github.com/43147125b888f512e15f733eca5d077e"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}