一段数据挖掘示例

[python]代码库

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression

#导入数据集
data = pd.read_csv('data.csv')

#分割训练集和测试集
X = data.iloc[:, :-1]
y = data.iloc[:, -1]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

#模型训练
model = LinearRegression()
model.fit(X_train, y_train)

#预测结果
y_pred = model.predict(X_test)

#评估模型性能
score = model.score(X_test, y_test)
print(score)