From 055cd52cd3ba2d7646113c70318f2ff3727830b2 Mon Sep 17 00:00:00 2001
From: Donne Martin <donne.martin@gmail.com>
Date: Fri, 20 Mar 2015 11:35:25 -0400
Subject: [PATCH] Added Random Forest Predicting section.

---
 kaggle/titanic.ipynb | 150 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 150 insertions(+)

diff --git a/kaggle/titanic.ipynb b/kaggle/titanic.ipynb
index 8f00a2e..aeb246e 100644
--- a/kaggle/titanic.ipynb
+++ b/kaggle/titanic.ipynb
@@ -2402,6 +2402,156 @@
      "metadata": {},
      "outputs": [],
      "prompt_number": 39
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "## Random Forest: Predicting"
+     ]
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "Read the test data:"
+     ]
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "df_test = pd.read_csv('../data/titanic/test.csv')\n",
+      "df_test.head(3)"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [
+      {
+       "html": [
+        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\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",
+        "  </tbody>\n",
+        "</table>\n",
+        "</div>"
+       ],
+       "metadata": {},
+       "output_type": "pyout",
+       "prompt_number": 40,
+       "text": [
+        "   PassengerId  Pclass                              Name     Sex   Age  SibSp  \\\n",
+        "0          892       3                  Kelly, Mr. James    male  34.5      0   \n",
+        "1          893       3  Wilkes, Mrs. James (Ellen Needs)  female  47.0      1   \n",
+        "2          894       2         Myles, Mr. Thomas Francis    male  62.0      0   \n",
+        "\n",
+        "   Parch  Ticket    Fare Cabin Embarked  \n",
+        "0      0  330911  7.8292   NaN        Q  \n",
+        "1      0  363272  7.0000   NaN        S  \n",
+        "2      0  240276  9.6875   NaN        Q  "
+       ]
+      }
+     ],
+     "prompt_number": 40
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "Note the test data does not contain the column 'Survived', we'll use our trained model to predict these values."
+     ]
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "df_test = clean_data(df_test, drop_passenger_id=False)\n",
+      "test_data = df_test.values"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [],
+     "prompt_number": 41
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "Take the decision trees and run it on the test data:"
+     ]
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "# Test data (features), skip the first column 'PassengerId'\n",
+      "test_input = test_data[0::, 1::]\n",
+      "\n",
+      "# Predict the Survival values for the test data\n",
+      "output = forest.predict(test_input)"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [],
+     "prompt_number": 42
     }
    ],
    "metadata": {}