import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score

# 加载数据集
data = pd.read_csv('spirit_airlines_data.csv')

# 预处理数据
# 这一步包括清理、处理缺失值和特征工程
processed_data = preprocess_data(data)

# 将数据分成训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(processed_data.drop('delayed', axis=1), processed_data['delayed'], test_size=0.2, random_state=42)

# 训练模型
model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

# 进行预测
predictions = model.predict(X_test)

# 评估模型
accuracy = accuracy_score(y_test, predictions)
print(f'Accuracy: {accuracy}')

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score

# Load the dataset
data = pd.read_csv('spirit_airlines_data.csv')

# Preprocess the data
# This step would include cleaning, handling missing values, and feature engineering
processed_data = preprocess_data(data)

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(processed_data.drop('delayed', axis=1), processed_data['delayed'], test_size=0.2, random_state=42)

# Train the model
model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

# Make predictions
predictions = model.predict(X_test)

# Evaluate the model
accuracy = accuracy_score(y_test, predictions)
print(f'Accuracy: {accuracy}')