Updating based on new sklearn API

03-linear-and-logistic-regression.ipynb

@@ -6,7 +6,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Lab 04: Linear and logistic regressions"
+    "# Lab 03: Linear and logistic regressions"
    ]
   },
   {
@@ -21,9 +21,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "import pandas as pd\n",
@@ -46,9 +44,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "# load the regression task data\n",
@@ -59,9 +55,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "# Load the data into X and y data arrays\n",
@@ -87,22 +81,18 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "# set up folds for cross_validation\n",
     "from sklearn import model_selection\n",
-    "folds_regr = model_selection.KFold(y_regr.size, n_folds=10, shuffle=True)"
+    "folds_regr = model_selection.KFold(n_splits=10, shuffle=True)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "def cross_validate_regr(design_matrix, labels, regressor, cv_folds):\n",
@@ -144,9 +134,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "from sklearn import linear_model\n",
@@ -207,9 +195,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "# TODO"
@@ -227,22 +213,18 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "# Set up folds for cross_validation\n",
     "from sklearn import model_selection\n",
-    "folds_clf = model_selection.StratifiedKFold(y_clf, n_folds=10, shuffle=True)"
+    "folds_clf = model_selection.StratifiedKFold(n_splits=10, shuffle=True)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "def cross_validate_clf(design_matrix, labels, classifier, cv_folds):\n",
@@ -285,9 +267,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "from sklearn import linear_model\n",
@@ -312,9 +292,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "fpr_logreg, tpr_logreg, thresholds = # TODO\n",
@@ -347,9 +325,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "from sklearn import preprocessing\n",
@@ -380,9 +356,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "fpr_logreg_scaled, tpr_logreg_scaled, thresholds = # TODO\n",
@@ -414,9 +388,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "def cross_validate_clf_with_scaling(design_matrix, labels, classifier, cv_folds):\n",
@@ -456,9 +428,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "clf = linear_model.LogisticRegression(C=1e6) \n",
@@ -476,9 +446,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "fpr_logreg_scaled_, tpr_logreg_scaled_, thresholds = # TODO\n",