机器学习中的Python问题及解决策略

import numpy as np
import pandas as pd

# 计算平均值
data = np.array([1, 2, 3, np.nan, 5])
mean_value = np.mean(data)
print(mean_value)

# 填充缺失值
data = pd.Series([1, 2, 3, np.nan, 5])
data = data.fillna(0)
print(data)

from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score

# 将数据划分为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 使用决策树模型进行训练和预测
model = DecisionTreeClassifier()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)

# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print(accuracy)

from sklearn.feature_selection import SelectKBest, f_regression

# 选择最佳的K个特征
selector = SelectKBest(score_func=f_regression, k=5)
X_new = selector.fit_transfORM(X, y)

# 打印选择的特征
selected_features = selector.get_support(indices=True)
print(selected_features)