Remove random printouts so run to run output is the same.

Author: rrlyman

p115_l1_l2_regularization.py

@@ -69,7 +69,7 @@
 
 from sklearn.linear_model import LogisticRegression
 
-lr = LogisticRegression(penalty='l1', C=0.1)
+lr = LogisticRegression(penalty='l1', C=0.1, random_state=0)
 lr.fit(X_train_std, y_train)
 print('Training accuracy-l1 regularization:', lr.score(X_train_std, y_train))
 print('Test accuracy-l1 regularization:', lr.score(X_test_std, y_test))
@@ -79,7 +79,7 @@
 print('\t{}'.format(lr.coef_))
 
 
-lr = LogisticRegression(penalty='l2', C=0.1)
+lr = LogisticRegression(penalty='l2', C=0.1, random_state=0)
 lr.fit(X_train_std, y_train)
 print('Training accuracy-l2 regularization:', lr.score(X_train_std, y_train))
 print('Test accuracy-l2 regularization:', lr.score(X_test_std, y_test))

p186_grid_search.py

@@ -61,7 +61,7 @@
     gs = gs.fit(X_train, y_train)
 
     print('Support Vector Machine Grid Search best score: {}'.format(gs.best_score_))
-    print('Support Vector Machine Grid Search best params: {}'.format(gs.best_params_))
+    print('Support Vector Machine Grid Search best params: {}'.format(sorted(gs.best_params_.items())))
 
     clf = gs.best_estimator_
     clf.fit(X_train, y_train)

p189_nested_cross_validation.py

@@ -85,8 +85,7 @@
 
         gs = gs.fit(X_train, y_train)
         print('Support Vector Machine Grid Search best score: {}'.format(gs.best_score_))
-        print('Support Vector Machine Grid Search best params: {}\n'.format(gs.best_params_))
-
+        print('Support Vector Machine Grid Search best params: {}'.format(sorted(gs.best_params_.items())))
         from sklearn.tree import DecisionTreeClassifier
         gs = GridSearchCV(estimator=DecisionTreeClassifier(random_state=0), 
                                     param_grid=[{'max_depth': [1, 2, 3, 4, 5, 6, 7, None]}], 

p193_model_precision_recall.py

@@ -93,6 +93,5 @@
                                     n_jobs=-1)
     gs = gs.fit(X_train, y_train)
     print('\nGrid Search f1 scoring best score: {}'.format(gs.best_score_))
-    print('Grid Search f1 scoring best params: {}'.format(gs.best_params_))
-
+    print('Grid Search f1 scoring best params: {}'.format(sorted(gs.best_params_.items())))
     print ('\n########################### No Errors ####################################')

p206_majority_vote_classifier.py

@@ -48,7 +48,7 @@
 from sklearn.base import clone
 from sklearn.pipeline import _name_estimators
 import numpy as np       
-import ocr_utils
+import ocr_utils 
 from sklearn.cross_validation import train_test_split
 from sklearn.cross_validation import cross_val_score
 from sklearn.linear_model import LogisticRegression
@@ -326,9 +326,9 @@ def get_params(self, deep=True):
 grid.fit(X_train, y_train)
 
 for params, mean_score, scores in grid.grid_scores_:
-    print("%0.3f+/-%0.2f %r"
-            % (mean_score, scores.std() / 2, params))
-print('\nBest parameters: %s' % grid.best_params_)
-print('Best Accuracy: %.2f' % grid.best_score_)
+    print("%0.6f+/-%0.6f %r"
+            % (mean_score, scores.std() / 2, sorted(params.items())))
+print('\nBest parameters: %s' % sorted(grid.best_params_.items()))
+print('Best Accuracy: %.6f' % grid.best_score_)
 
 print ('\n########################### No Errors ####################################')

p44_adaline_sgd.py

@@ -163,7 +163,7 @@ def predict(self, X):
 X_std = np.copy(X)
 X_std[:,0] = (X[:,0] - X[:,0].mean()) / X[:,0].std()
 X_std[:,1] = (X[:,1] - X[:,1].mean()) / X[:,1].std()
-ada = AdalineSGD(n_iter=15, eta=0.01)
+ada = AdalineSGD(n_iter=15, eta=0.01, random_state = 1)
 ada.fit(X_std, y)
 
 ocr_utils.plot_decision_regions(X=X_std,