有关Flatiron数据科学训练营技术面试的问题

import pandas as pd
from sklearn.impute import SimpleImputer

# 创建一个示例数据集
data = {'A': [1, 2, None, 4], 'B': [5, None, 7, 8]}
df = pd.DataFrame(data)

# 使用均值插补缺失值
imputer = SimpleImputer(strategy='mean')
df_imputed = pd.DataFrame(imputer.fit_transform(df), columns=df.columns)
print(df_imputed)

from sklearn.linear_model import Ridge, Lasso
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error

# 假设X和y是你的特征和目标变量
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 使用Ridge回归防止过拟合
ridge_model = Ridge(alpha=1.0)
ridge_model.fit(X_train, y_train)
y_pred_ridge = ridge_model.predict(X_test)
print("Ridge MSE:", mean_squared_error(y_test, y_pred_ridge))

# 使用Lasso回归防止过拟合
lasso_model = Lasso(alpha=0.1)
lasso_model.fit(X_train, y_train)
y_pred_lasso = lasso_model.predict(X_test)
print("Lasso MSE:", mean_squared_error(y_test, y_pred_lasso))

from sklearn.preprocessing import StandardScaler, PolynomialFeatures

# 特征缩放
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

# 多项式特征生成
poly = PolynomialFeatures(degree=2)
X_poly = poly.fit_transform(X_scaled)