def main():
print("Tesing the performance of RandomForest...")
# Load data
X, y = decision_tree.load_data()
# Split data randomly, train set rate 70%
X_train, X_test, y_train, y_test = decision_tree.train_test_split(
X, y, random_state=40)
# Train model
rf = RandomForest()
rf.fit(X_train, y_train, n_samples=300, max_depth=3, n_estimators=20)
# Model evaluation
y_hat = rf.predict(X_test)
acc = decision_tree.get_acc(y_test, y_hat)
print("Accuracy is %.3f" % acc)
def pushTrainTreeButton(ui):
# 按下创建决策树按钮
# 提示加载数据
ui.tipBrowser.append("start loading train data...")
load_tree_file = str(ui.trainTreeLine.text())
dt_gui.columns, data = dt.load_data(load_tree_file)
train_columns = dt_gui.columns[:]
dt_gui.tree = dt.build_tree(data, train_columns)
print(dt_gui.tree)
# 显示决策树
tree_content_list = []
dt.tree_content(dt_gui.tree, dt_gui.columns, tree_content_list)
ui.treeShow.setText("") # 先清空
tree_str = ""
for l in tree_content_list:
tree_str += (l + "\n")
ui.treeShow.setText(tree_str)
# 提示创建成功
ui.tipBrowser.append("train tree success")
print("完成决策树训练")
from sklearn.linear_model import LogisticRegression as lr
from sklearn.metrics import accuracy_score
import numpy as np
from decision_tree import load_data
if __name__ == '__main__':
print(
"Tutorial: Training a logistic regression to detect phishing websites")
# Load the training data
train_inputs, train_outputs, test_inputs, test_outputs = load_data()
print("Training data loaded.")
# Create a logistic regression classifier model using scikit-learn
classifier = lr()
print("Logistic regression classifier created.")
print("Beginning model training.")
# Train the logistic regression classifier
classifier.fit(train_inputs, train_outputs)
print("Model training completed.")
# Use the trained classifier to make predictions on the test data
predictions = classifier.predict(test_inputs)
print("Predictions on testing data computed.")
# Print the accuracy (percentage of phishing websites correctly predicted)
accuracy = 100.0 * accuracy_score(test_outputs, predictions)
print("The accuracy of your logistic regression on testing data is: " +