next pylab update

Author: nborwankar

notebooks/.ipynb_checkpoints/D3. K-Means Clustering Analysis-checkpoint.ipynb

@@ -1,103 +1,64 @@
 {
  "cells": [
   {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Logistic Regression - Overview\n",
-    "===========\n",
-    "***\n",
-    "\n",
-    "###What are the odds that an event will happen? Answering yes/no questions.\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "<img src=\"files/images/b1fig1_nfloutcomes.png\" />"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "<img src=\"files/images/b1fig2_nfloutcomes_withline.png\" />"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "\n",
-    "<img src=\"files/images/standardSigmoidFunction.png\" />\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "\n",
-    "\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "A function that has the above shape is:\n",
-    "\n",
-    "\n",
-    "$$P(x) = \\frac{1}{1 + e^{b_0 + b_1x}}$$\n",
-    "\n",
-    "---\n",
-    "where P(x) is the probability of a score of x leading to a win.  \n",
-    "$b_0, b_1$ are parameters that we will estimate, so the curve fits our data.\n",
-    "\n",
-    "\n",
-    "\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Populating the interactive namespace from numpy and matplotlib\n",
+      "Coefficients:  [ 72.88279832  -0.08844242]\n",
+      "Intercept:  0.000210747768548\n",
+      "P-Values:  [  0.00000000e+000   0.00000000e+000   5.96972978e-203]\n",
+      "R-Squared:  0.656632624649\n"
+     ]
+    }
+   ],
    "source": [
-    "---\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"
+    "%pylab inline\n",
+    "import pylab as pl\n",
+    "import numpy as np\n",
+    "#from sklearn import datasets, linear_model\n",
+    "import pandas as pd\n",
+    "import statsmodels.api as sm\n",
+    "\n",
+    "# import the cleaned up dataset\n",
+    "df = pd.read_csv('../datasets/loanf.csv')\n",
+    "\n",
+    "intrate = df['Interest.Rate']\n",
+    "loanamt = df['Loan.Amount']\n",
+    "fico = df['FICO.Score']\n",
+    "\n",
+    "# reshape the data from a pandas Series to columns \n",
+    "# the dependent variable\n",
+    "y = np.matrix(intrate).transpose()\n",
+    "# the independent variables shaped as columns\n",
+    "x1 = np.matrix(fico).transpose()\n",
+    "x2 = np.matrix(loanamt).transpose()\n",
+    "\n",
+    "# put the two columns together to create an input matrix \n",
+    "# if we had n independent variables we would have n columns here\n",
+    "x = np.column_stack([x1,x2])\n",
+    "\n",
+    "# create a linear model and fit it to the data\n",
+    "X = sm.add_constant(x)\n",
+    "model = sm.OLS(y,X)\n",
+    "f = model.fit()\n",
+    "\n",
+    "print 'Coefficients: ', f.params[0:2]\n",
+    "print 'Intercept: ', f.params[2]\n",
+    "print 'P-Values: ', f.pvalues\n",
+    "print 'R-Squared: ', f.rsquared\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 1,
    "metadata": {
     "collapsed": false
    },
@@ -167,27 +128,15 @@
        "</script>"
       ],
       "text/plain": [
-       "<IPython.core.display.HTML at 0x109391790>"
+       "<IPython.core.display.HTML at 0x10931ba90>"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 1,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "\n",
-    "\n",
-    "\n",
-    "\n",
-    "\n",
-    "\n",
-    "\n",
-    "\n",
-    "\n",
-    "\n",
-    "\n",
-    "\n",
     "from IPython.core.display import HTML\n",
     "def css_styling():\n",
     "    styles = open(\"../styles/custom.css\", \"r\").read()\n",
@@ -197,7 +146,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "metadata": {
     "collapsed": false
    },