def main():
print("-- Classification Tree --")
data = datasets.load_iris()
X = data.data
y = data.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)
clf = ClassificationTree(max_features=2)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print("Our DTClassifier Accuracy:", accuracy)
clf = tree.DecisionTreeClassifier()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print("sklearn DTClassifier Accuracy:", accuracy)
def main():
print('-- Classification Tree')
data = datasets.load_iris()
X = data.data
y = data.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)
clf = ClassificationTree()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print('Accuracy: ', accuracy)
dt = DecisionTreeClassifier()
dt.fit(X_train, y_train)
y_val = dt.predict(X_test)
acc = accuracy_score(y_test, y_val)
print('sklearn score:', acc)
# dataset.append(Instance( [ncfr, dur, dfl, a3fl, a1fl, gr], [target] ))
except Exception as e:
pass
model = ClassificationTree()
X = standardize(X)
# X = RobustScaler(quantile_range=(25, 75)).fit_transform(X)
# X = MinMaxScaler().fit_transform(X)
# # # print y
datasets = k_fold_cross_validation_sets(X, y, 3)
for data in datasets:
X_train, X_test, y_train, y_test = data
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
print(accuracy_score(y_test, y_pred))
# print accuracy_score(y_test, y_pred)
mse = mean_squared_error(y_test, y_pred)
print("Mean Squared Error:", mse)
# print (model.predict(np.array([[178, 0, 1000, 936]])))
print(model.predict(np.array([[178, 0, 1000, 936, 855, 237000000, 0]])))
# model.print_tree()
filename = 'finalized_model.pikle'
pickle.dump(model, open(filename, 'wb'))
model_a = pickle.load(open(filename, 'rb'))
# print (model_a.predict(np.array([[178, 0, 1000, 936, 855, 237000000, 0]])))
random_forest.fit(X_train, y_train)
print "\tSupport Vector Machine"
support_vector_machine.fit(X_train, rescaled_y_train)
# .........
# PREDICT
# .........
y_pred = {}
y_pred["Adaboost"] = adaboost.predict(X_test)
y_pred["Naive Bayes"] = naive_bayes.predict(X_test)
y_pred["K Nearest Neighbors"] = knn.predict(X_test, X_train, y_train)
y_pred["Logistic Regression"] = logistic_regression.predict(X_test)
y_pred["LDA"] = lda.predict(X_test)
y_pred["Multilayer Perceptron"] = mlp.predict(X_test)
y_pred["Perceptron"] = perceptron.predict(X_test)
y_pred["Decision Tree"] = decision_tree.predict(X_test)
y_pred["Random Forest"] = random_forest.predict(X_test)
y_pred["Support Vector Machine"] = support_vector_machine.predict(X_test)
# ..........
# ACCURACY
# ..........
print
print "Accuracy:"
for clf in y_pred:
if clf == "Adaboost" or clf == "Support Vector Machine":
print "\t%-23s: %.5f" % (clf,
accuracy_score(rescaled_y_test, y_pred[clf]))
else:
print "\t%-23s: %.5f" % (clf, accuracy_score(y_test, y_pred[clf]))
print
# .........
# PREDICT
# .........
y_pred = {}
y_pred["Adaboost"] = adaboost.predict(X_test)
y_pred["Gradient Boosting"] = gbc.predict(X_test)
y_pred["Naive Bayes"] = naive_bayes.predict(X_test)
y_pred["K Nearest Neighbors"] = knn.predict(X_test, X_train, y_train)
y_pred["Logistic Regression"] = logistic_regression.predict(X_test)
y_pred["LDA"] = lda.predict(X_test)
y_pred["Multilayer Perceptron"] = mlp.predict(X_test)
y_pred["Perceptron"] = perceptron.predict(X_test)
y_pred["Decision Tree"] = decision_tree.predict(X_test)
y_pred["Random Forest"] = random_forest.predict(X_test)
y_pred["Support Vector Machine"] = support_vector_machine.predict(X_test)
y_pred["XGBoost"] = xgboost.predict(X_test)
# ..........
# ACCURACY
# ..........
print ("Accuracy:")
for clf in y_pred:
if clf == "Adaboost" or clf == "Support Vector Machine":
print ("\t%-23s: %.5f" %(clf, accuracy_score(rescaled_y_test, y_pred[clf])))
else:
print ("\t%-23s: %.5f" %(clf, accuracy_score(y_test, y_pred[clf])))