reverting

Author: kristychoi

4. K-means clustering and unsupervised learning.ipynb

@@ -20,29 +20,11 @@
   },
   {
    "cell_type": "code",
-<<<<<<< HEAD
-   "execution_count": 10,
-=======
    "execution_count": 27,
->>>>>>> origin/master
    "metadata": {
-    "collapsed": false
+    "collapsed": true
    },
-   "outputs": [
-    {
-     "ename": "ImportError",
-     "evalue": "No module named 'scipy'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[1;31mImportError\u001b[0m                               Traceback (most recent call last)",
-      "\u001b[1;32m<ipython-input-10-93ad81cdfd38>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m      4\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mmatplotlib\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpyplot\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mplt\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      5\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mmatplotlib\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mimage\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mmpimg\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 6\u001b[1;33m \u001b[1;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcluster\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mKMeans\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      7\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mutils\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mshuffle\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      8\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mtime\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mtime\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
-      "\u001b[1;32mc:\\users\\piyali\\python3\\lib\\site-packages\\sklearn\\__init__.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m     55\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     56\u001b[0m     \u001b[1;32mfrom\u001b[0m \u001b[1;33m.\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0m__check_build\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 57\u001b[1;33m     \u001b[1;32mfrom\u001b[0m \u001b[1;33m.\u001b[0m\u001b[0mbase\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mclone\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     58\u001b[0m     \u001b[0m__check_build\u001b[0m  \u001b[1;31m# avoid flakes unused variable error\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     59\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
-      "\u001b[1;32mc:\\users\\piyali\\python3\\lib\\site-packages\\sklearn\\base.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m      7\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      8\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mnumpy\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 9\u001b[1;33m \u001b[1;32mfrom\u001b[0m \u001b[0mscipy\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0msparse\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     10\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[1;33m.\u001b[0m\u001b[0mexternals\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0msix\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     11\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[1;33m.\u001b[0m\u001b[0mutils\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfixes\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0msignature\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
-      "\u001b[1;31mImportError\u001b[0m: No module named 'scipy'"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# useful packages\n",
     "import os\n",
@@ -136,11 +118,7 @@
   },
   {
    "cell_type": "code",
-<<<<<<< HEAD
-   "execution_count": 3,
-=======
    "execution_count": 28,
->>>>>>> origin/master
    "metadata": {
     "collapsed": false
    },
@@ -149,7 +127,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "['columbia.jpg', 'leo_bb.png', 'mario.png']\n"
+      "['leo_bb.png', 'mario.png']\n"
      ]
     }
    ],
@@ -179,8 +157,6 @@
      "text": [
       "Using image 0: path datasets/kmeans/imgs/leo_bb.png\n"
      ]
-<<<<<<< HEAD
-=======
     },
     {
      "data": {
@@ -191,11 +167,10 @@
      },
      "metadata": {},
      "output_type": "display_data"
->>>>>>> origin/master
     }
    ],
    "source": [
-    "img_path = os.path.join('datasets/kmeans/imgs/', imgs[1])\n",
+    "img_path = os.path.join('datasets/kmeans/imgs/', imgs[0])\n",
     "print('Using image 0: path {}'.format(img_path))\n",
     "\n",
     "img = mpimg.imread(img_path)\n",
@@ -217,11 +192,7 @@
   },
   {
    "cell_type": "code",
-<<<<<<< HEAD
-   "execution_count": 6,
-=======
    "execution_count": 30,
->>>>>>> origin/master
    "metadata": {
     "collapsed": false
    },
@@ -253,27 +224,11 @@
   },
   {
    "cell_type": "code",
-<<<<<<< HEAD
-   "execution_count": 8,
-=======
    "execution_count": 31,
->>>>>>> origin/master
    "metadata": {
-    "collapsed": false
+    "collapsed": true
    },
-   "outputs": [
-    {
-     "ename": "NameError",
-     "evalue": "name 'shuffle' is not defined",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "\u001b[1;32m<ipython-input-8-6ac900e80476>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[0mimg_reshaped\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreshape\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mimg\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mnum_pixels\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnum_channels\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[0mimg_sample\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mshuffle\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mimg_reshaped\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrandom_state\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
-      "\u001b[1;31mNameError\u001b[0m: name 'shuffle' is not defined"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "img_reshaped = np.reshape(img, (num_pixels, num_channels))\n",
     "img_sample = shuffle(img_reshaped, random_state=0)"
@@ -484,7 +439,7 @@
     "We can also use **penalization approaches**, where we use different criterion such as AIC (Akaike Information Criterion) or BIC (Bayesian Information Criterion) to keep the value of k under control. \n",
     "\n",
     "#### I. (d) What if we can’t cluster the data?\n",
-    "In the tutorial above, we try to classify each of our points into one of K clusters. But sometimes, maybe you are clustering based on a feature that is not so exclusive. For example, people usually enjoy more than one genre of music, or food. It would be pretty difficult to form a clustering system such that a person can be a fan of ice-cream or a fan of tiramisu but not both. Hence when we need to \"share\" members of clusters, we are doing something called **probabilistic clustering** or **fuzzy clustering**. "
+    "* In the tutorial above, we try to classify each of our points into one of K clusters. But sometimes, maybe you are clustering based on a feature that is not so exclusive. For example, people usually enjoy more than one genre of music, or food. It would be pretty difficult to form a clustering system such that a person can be a fan of ice-cream or a fan of tiramisu but not both. Hence when we need to \"share\" members of clusters, we are doing something called **probabilistic clustering** or **fuzzy clustering**. "
    ]
   },
   {