Pipeline for PCA

Author: mGalarnyk

Sklearn/PCA/PCA_MNIST_Logistic_Regression_Speeding_Machine_Learning.ipynb renamed to Sklearn/PCA/PCA_MNIST_PCA_MachineLearningNoPipeline.ipynb

@@ -16,19 +16,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 6,
+   "metadata": {},
    "outputs": [],
    "source": [
+    "from sklearn.datasets import fetch_mldata\n",
+    "\n",
     "# Change data_home to wherever to where you want to download your data\n",
     "mnist = fetch_mldata('MNIST original', data_home='~/Desktop/alternativeData')"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -46,7 +46,7 @@
        " 'target': array([ 0.,  0.,  0., ...,  9.,  9.,  9.])}"
       ]
      },
-     "execution_count": 46,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -57,7 +57,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -66,7 +66,7 @@
        "(70000, 784)"
       ]
      },
-     "execution_count": 47,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -78,7 +78,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -87,7 +87,7 @@
        "(70000,)"
       ]
      },
-     "execution_count": 48,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -106,12 +106,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 11,
+   "metadata": {},
    "outputs": [],
    "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "\n",
     "# test_size: what proportion of original data is used for test set\n",
     "train_img, test_img, train_lbl, test_lbl = train_test_split(\n",
     "    mnist.data, mnist.target, test_size=1/7.0, random_state=0)"
@@ -140,15 +140,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/mgalarny/anaconda2/lib/python2.7/site-packages/sklearn/utils/validation.py:444: DataConversionWarning: Data with input dtype uint8 was converted to float64 by StandardScaler.\n",
+      "  warnings.warn(msg, DataConversionWarning)\n"
+     ]
+    }
+   ],
    "source": [
     "from sklearn.preprocessing import StandardScaler\n",
     "scaler = StandardScaler()\n",
-    "train_img = scaler.fit_transform(train_img)\n",
+    "scaler.fit(train_img)\n",
+    "train_img = scaler.transform(train_img)\n",
     "test_img = scaler.transform(test_img)"
    ]
   },
@@ -168,7 +176,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": 13,
    "metadata": {
     "collapsed": true
    },
@@ -186,7 +194,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 14,
    "metadata": {
     "collapsed": true
    },
@@ -204,7 +212,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
@@ -214,7 +222,7 @@
        "  svd_solver='auto', tol=0.0, whiten=False)"
       ]
      },
-     "execution_count": 53,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -232,7 +240,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": 16,
    "metadata": {
     "collapsed": true
    },
@@ -258,7 +266,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 55,
+   "execution_count": 17,
    "metadata": {
     "collapsed": true
    },
@@ -276,7 +284,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 56,
+   "execution_count": 18,
    "metadata": {
     "collapsed": true
    },
@@ -304,7 +312,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 57,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [
     {
@@ -316,7 +324,7 @@
        "          verbose=0, warm_start=False)"
       ]
      },
-     "execution_count": 57,
+     "execution_count": 19,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -341,7 +349,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 58,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [
     {
@@ -350,7 +358,7 @@
        "array([ 1.])"
       ]
      },
-     "execution_count": 58,
+     "execution_count": 20,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -363,7 +371,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 59,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [
     {
@@ -372,7 +380,7 @@
        "array([ 1.,  9.,  2.,  2.,  7.,  1.,  8.,  3.,  3.,  7.])"
       ]
      },
-     "execution_count": 59,
+     "execution_count": 21,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -405,7 +413,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 60,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [
     {
@@ -420,15 +428,6 @@
     "score = logisticRegr.score(test_img, test_lbl)\n",
     "print(score)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {