Session 4 added

Author: Shreya Gupta

.gitignore

@@ -102,3 +102,8 @@ venv.bak/
 
 # mypy
 .mypy_cache/
+
+
+
+#temporarily
+Session 4 Part 1.2 K-means clustering sklearn-Copy1.ipynb

Session 3 Part 1.1 - Logistic Regression Intuition.ipynb

@@ -4,6 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "\n",
     "## Agenda\n",
     "\n",
     "1. Refresh your memory on how to do linear regression in scikit-learn\n",

Session 4 Part 1.1 K-Means Clustering from scratch.ipynb

@@ -0,0 +1,157 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "# K-Means Clustering\n",
+    "\n",
+    "# Importing the libraries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Importing the cars.csv dataset\n",
+    "\n",
+    "#print first 10 rows of X\n",
+    "\n",
+    "\n",
+    "#construct X\n",
+    "\n",
+    "\n",
+    "# X = pd.DataFrame(X)\n",
+    "# X = X.convert_objects(convert_numeric=True)\n",
+    "\n",
+    "#allot column names to X"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#print first 5 rows of X"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#describe X"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Eliminating null values"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Using the elbow method to find  the optimal number of clusters\n",
+    "\n",
+    "#import kmeans \n",
+    "\n",
+    "\n",
+    "wcss = []\n",
+    "for i in range(1,11):\n",
+    "    #initialise k means instance\n",
+    "    \n",
+    "    #fit the data\n",
+    "    \n",
+    "    \n",
+    "    wcss.append(kmeans.inertia_)\n",
+    "    \n",
+    "#plot cluster vs wcss"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "# Applying k-means to the cars dataset\n",
+    "kmeans = KMeans(n_clusters=3,init='k-means++',max_iter=300,n_init=10,random_state=0) \n",
+    "y_kmeans = kmeans.fit_predict(X)\n",
+    "\n",
+    "X = X.as_matrix(columns=None)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_kmeans"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Visualising the clusters\n",
+    "plt.scatter(X[y_kmeans == 0, 0], X[y_kmeans == 0,1],s=100,c='red',label='US')\n",
+    "plt.scatter(X[y_kmeans == 1, 0], X[y_kmeans == 1,1],s=100,c='blue',label='Japan')\n",
+    "plt.scatter(X[y_kmeans == 2, 0], X[y_kmeans == 2,1],s=100,c='green',label='Europe')\n",
+    "plt.scatter(kmeans.cluster_centers_[:,0],kmeans.cluster_centers_[:,1],s=300,c='yellow',label='Centroids')\n",
+    "plt.title('Clusters of car brands')\n",
+    "plt.legend()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}