Updated joblib import to sklearn 0.23

ml1/2_5_2_Decision_Tree_Model.ipynb

@@ -74,7 +74,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -124,25 +124,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=3,\n",
-       "            max_features=None, max_leaf_nodes=None,\n",
-       "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
-       "            min_samples_leaf=1, min_samples_split=2,\n",
-       "            min_weight_fraction_leaf=0.0, presort=False, random_state=1,\n",
-       "            splitter='best')"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "from sklearn.tree import DecisionTreeClassifier\n",
     "import numpy as np\n",
@@ -161,24 +145,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Prediction  [1 0 1 1 1 0 0 1 0 2 0 0 1 2 0 1 2 2 1 1 0 0 2 0 0 2 1 1 2 2 2 2 0 0 1 1 0\n",
-      " 1 2 1 2 0 2 0 1 0 2 1 0 2 2 0 0 2 0 0 0 2 2 0 1 0 1 0 1 1 1 1 1 0 1 0 1 2\n",
-      " 0 0 0 0 2 2 0 1 1 2 1 0 0 2 1 1 0 1 1 0 2 1 2 1 2 0 1 0 0 0 2 1 2 1 2 1 2\n",
-      " 0]\n",
-      "Expected  [1 0 1 1 1 0 0 1 0 2 0 0 1 2 0 1 2 2 1 1 0 0 2 0 0 2 1 1 2 2 2 2 0 0 1 1 0\n",
-      " 1 2 1 2 0 2 0 1 0 2 1 0 2 2 0 0 2 0 0 0 2 2 0 1 0 1 0 1 1 1 1 1 0 1 0 1 2\n",
-      " 0 0 0 0 2 2 0 1 1 2 1 0 0 1 1 1 0 1 1 0 2 2 2 1 2 0 1 0 0 0 2 1 2 1 2 1 2\n",
-      " 0]\n"
-     ]
-    }
-   ],
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "print(\"Prediction \", model.predict(x_train))\n",
     "print(\"Expected \", y_train)"
@@ -193,26 +162,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Predicted probabilities [[0.         0.97368421 0.02631579]\n",
-      " [1.         0.         0.        ]\n",
-      " [0.         0.97368421 0.02631579]\n",
-      " [0.         0.97368421 0.02631579]\n",
-      " [0.         0.97368421 0.02631579]\n",
-      " [1.         0.         0.        ]\n",
-      " [1.         0.         0.        ]\n",
-      " [0.         0.97368421 0.02631579]\n",
-      " [1.         0.         0.        ]\n",
-      " [0.         0.         1.        ]]\n"
-     ]
-    }
-   ],
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "# Print the \n",
     "print(\"Predicted probabilities\", model.predict_proba(x_train[:10]))"
@@ -220,17 +172,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Accuracy in training 0.9821428571428571\n"
-     ]
-    }
-   ],
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "# Evaluate Accuracy in training\n",
     "\n",
@@ -241,17 +185,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Accuracy in testing  0.9210526315789473\n"
-     ]
-    }
-   ],
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "# Now we evaluate error in testing\n",
     "y_test_pred = model.predict(x_test)\n",
@@ -273,24 +209,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "ename": "ModuleNotFoundError",
-     "evalue": "No module named 'pydotplus'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-7-1bf5ec7fb043>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mIPython\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdisplay\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mImage\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexternals\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msix\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mStringIO\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0;32mimport\u001b[0m \u001b[0mpydotplus\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mpydot\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      4\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0mdot_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mStringIO\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'pydotplus'"
-     ]
-    }
-   ],
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "from IPython.display import Image \n",
-    "from sklearn.externals.six import StringIO\n",
+    "from six import StringIO\n",
     "import pydotplus as pydot\n",
     "\n",
     "dot_data = StringIO()  \n",
@@ -529,6 +453,15 @@
   }
  ],
  "metadata": {
+  "datacleaner": {
+   "position": {
+    "top": "50px"
+   },
+   "python": {
+    "varRefreshCmd": "try:\n    print(_datacleaner.dataframe_metadata())\nexcept:\n    print([])"
+   },
+   "window_display": false
+  },
   "kernelspec": {
    "display_name": "Python 3",
    "language": "python",
@@ -544,7 +477,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.1"
+   "version": "3.7.9"
   },
   "latex_envs": {
    "LaTeX_envs_menu_present": true,

ml1/2_7_Model_Persistence.ipynb

@@ -117,7 +117,7 @@
    "outputs": [],
    "source": [
     "# save model\n",
-    "from sklearn.externals import joblib\n",
+    "import joblib\n",
     "joblib.dump(model, 'filename.pkl') \n",
     "\n",
     "#load model\n",
@@ -151,6 +151,15 @@
   }
  ],
  "metadata": {
+  "datacleaner": {
+   "position": {
+    "top": "50px"
+   },
+   "python": {
+    "varRefreshCmd": "try:\n    print(_datacleaner.dataframe_metadata())\nexcept:\n    print([])"
+   },
+   "window_display": false
+  },
   "kernelspec": {
    "display_name": "Python 3",
    "language": "python",
@@ -166,7 +175,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.7"
+   "version": "3.7.9"
   },
   "latex_envs": {
    "LaTeX_envs_menu_present": true,

ml1/util_knn.py

@@ -2,6 +2,7 @@ import numpy as np
 import matplotlib.pyplot as plt
 from matplotlib.colors import ListedColormap
 from sklearn import neighbors, datasets
+import seaborn as sns
 from sklearn.neighbors import KNeighborsClassifier
 
 # Taken from http://scikit-learn.org/stable/auto_examples/neighbors/plot_classification.html
@@ -19,9 +20,9 @@ def plot_classification_iris():
     h = .02  # step size in the mesh
     n_neighbors = 15
 
-    # Create color maps
-    cmap_light = ListedColormap(['#FFAAAA', '#AAFFAA', '#AAAAFF'])
-    cmap_bold = ListedColormap(['#FF0000', '#00FF00', '#0000FF'])
+  # Create color maps
+    cmap_light = ListedColormap(['orange', 'cyan', 'cornflowerblue'])
+    cmap_bold = ['darkorange', 'c', 'darkblue']
 
     for weights in ['uniform', 'distance']:
         # we create an instance of Neighbours Classifier and fit the data.
@@ -29,7 +30,7 @@ def plot_classification_iris():
         clf.fit(X, y)
 
         # Plot the decision boundary. For that, we will assign a color to each
-        # point in the mesh [x_min, m_max]x[y_min, y_max].
+        # point in the mesh [x_min, x_max]x[y_min, y_max].
         x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
         y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
         xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
@@ -38,14 +39,17 @@ def plot_classification_iris():
 
         # Put the result into a color plot
         Z = Z.reshape(xx.shape)
-        plt.figure()
-        plt.pcolormesh(xx, yy, Z, cmap=cmap_light)
+        plt.figure(figsize=(8, 6))
+        plt.contourf(xx, yy, Z, cmap=cmap_light)
 
         # Plot also the training points
-        plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold)
+        sns.scatterplot(x=X[:, 0], y=X[:, 1], hue=iris.target_names[y],
+                        palette=cmap_bold, alpha=1.0, edgecolor="black")
         plt.xlim(xx.min(), xx.max())
         plt.ylim(yy.min(), yy.max())
         plt.title("3-Class classification (k = %i, weights = '%s')"
-                % (n_neighbors, weights))
+                  % (n_neighbors, weights))
+        plt.xlabel(iris.feature_names[0])
+        plt.ylabel(iris.feature_names[1])
 
-    plt.show()
+plt.show()