Day22 复习

自行学习参考如何使用kaggle平台，写下使用注意点，并对下述比赛提交代码

# 导入必要的库
import numpy as np
import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
 
# 加载数据
train_data = pd.read_csv("train.csv")
test_data = pd.read_csv("test.csv")
 
# 数据预处理
def preprocess_data(df):
    # 填充缺失值
    df['Age'] = df['Age'].fillna(df['Age'].median())
    df['Fare'] = df['Fare'].fillna(df['Fare'].median())
    df['Embarked'] = df['Embarked'].fillna('S')
    
    # 特征工程
    df['Sex'] = df['Sex'].map({'female': 0, 'male': 1})
    df['Embarked'] = df['Embarked'].map({'S': 0, 'C': 1, 'Q': 2})
    
    # 选择特征
    features = ["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked"]
    return df[features]
 
# 预处理训练和测试数据
X = preprocess_data(train_data)
y = train_data["Survived"]
X_test = preprocess_data(test_data)
 
# 划分训练集和验证集
X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)
 
# 训练模型
model = RandomForestClassifier(n_estimators=100, max_depth=5, random_state=1)
model.fit(X_train, y_train)
 
# 验证集评估
val_predictions = model.predict(X_val)
print(f"Validation Accuracy: {accuracy_score(y_val, val_predictions):.4f}")
 
# 在测试集上预测
test_predictions = model.predict(X_test)
 
# 创建提交文件
output = pd.DataFrame({'PassengerId': test_data.PassengerId, 'Survived': test_predictions})
output.to_csv('submission.csv', index=False)
print("Submission file created!")

@浙大疏锦行