def test_prediction_scores(self):
y_test_predicted = self.clf.predict(self.X_test)
assert_equal(len(y_test_predicted), self.X_test.shape[0])
# check performance
assert_greater(accuracy_score(self.y_test, y_test_predicted),
self.accuracy_floor)
# test utility function
evaluate_print('averaging', self.y_test, y_test_predicted)
X, y, test_size=0.4, random_state=random_state)
# initialize a group of clfs
classifiers = [
DecisionTreeClassifier(random_state=random_state),
LogisticRegression(random_state=random_state),
KNeighborsClassifier(),
RandomForestClassifier(random_state=random_state),
GradientBoostingClassifier(random_state=random_state)
]
clf_names = ['DT', 'LR', 'KNN', 'RF', 'GBDT']
# evaluate individual classifiers
for i, clf in enumerate(classifiers):
clf.fit(X_train, y_train)
y_test_predict = clf.predict(X_test)
evaluate_print(clf_names[i] + ' | ', y_test, y_test_predict)
print()
# build a Stacking model and evaluate
clf = Stacking(classifiers,
n_folds=4,
shuffle_data=False,
keep_original=True,
use_proba=False,
random_state=random_state)
clf.fit(X_train, y_train)
y_test_predict = clf.predict(X_test)
evaluate_print('Stacking | ', y_test, y_test_predict)
random_state = 42
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4,
random_state=random_state)
# initialize a group of clfs
classifiers = [DecisionTreeClassifier(random_state=random_state),
LogisticRegression(random_state=random_state),
KNeighborsClassifier(),
RandomForestClassifier(random_state=random_state),
GradientBoostingClassifier(random_state=random_state)]
# fit and predict by individual classifiers
clf = DecisionTreeClassifier(random_state=random_state)
clf.fit(X_train, y_train)
evaluate_print('Decision Tree |', y_test, clf.predict(X_test))
clf = LogisticRegression(random_state=random_state)
clf.fit(X_train, y_train)
evaluate_print('Logistic Regression |', y_test, clf.predict(X_test))
clf = KNeighborsClassifier()
clf.fit(X_train, y_train)
evaluate_print('K Neighbors |', y_test, clf.predict(X_test))
clf = GradientBoostingClassifier(random_state=random_state)
clf.fit(X_train, y_train)
evaluate_print('Gradient Boosting |', y_test, clf.predict(X_test))
clf = RandomForestClassifier(random_state=random_state)
clf.fit(X_train, y_train)
import warnings
warnings.filterwarnings("ignore")
if __name__ == "__main__":
# Define data file and read X and y
random_state = 42
X, y = load_breast_cancer(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.4, random_state=random_state)
# fit and predict by individual classifiers
clf = DecisionTreeClassifier(random_state=random_state)
clf.fit(X_train, y_train)
evaluate_print('Decision Tree |', y_test, clf.predict(X_test))
clf = LogisticRegression(random_state=random_state)
clf.fit(X_train, y_train)
evaluate_print('Logistic Regression |', y_test, clf.predict(X_test))
clf = KNeighborsClassifier()
clf.fit(X_train, y_train)
evaluate_print('K Neighbors |', y_test, clf.predict(X_test))
clf = GradientBoostingClassifier(random_state=random_state)
clf.fit(X_train, y_train)
evaluate_print('Gradient Boosting |', y_test, clf.predict(X_test))
clf = RandomForestClassifier(random_state=random_state)
clf.fit(X_train, y_train)
