From 3fcbc8364f3e32416ebe7b37c8aa9efdd53d847d Mon Sep 17 00:00:00 2001
From: Donne Martin <donne.martin@gmail.com>
Date: Fri, 20 Mar 2015 11:33:41 -0400
Subject: [PATCH] Added Random Forest training section.

---
 kaggle/titanic.ipynb | 50 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 50 insertions(+)

diff --git a/kaggle/titanic.ipynb b/kaggle/titanic.ipynb
index f6b5ab6..8f00a2e 100644
--- a/kaggle/titanic.ipynb
+++ b/kaggle/titanic.ipynb
@@ -2352,6 +2352,56 @@
      "metadata": {},
      "outputs": [],
      "prompt_number": 37
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "## Random Forest: Training"
+     ]
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "Create the random forest object:"
+     ]
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "forest = RandomForestClassifier(n_estimators=100)"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [],
+     "prompt_number": 38
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "Fit the training data and create the decision trees:"
+     ]
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "# Training data (features), skip the first column 'Survived'\n",
+      "training_input = train_data[0::, 1::]\n",
+      "\n",
+      "# 'Survived' column values\n",
+      "target_values = train_data[0::, 0]\n",
+      "\n",
+      "# Fit the model to our training data\n",
+      "forest = forest.fit(training_input, target_values)"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [],
+     "prompt_number": 39
     }
    ],
    "metadata": {}