from sklearn.model_selection import train_test_split
# 一般先取出X和y后再切割,有些情况会使用到未切割的,这时候X和y就可以用
X = data
y = train['Survived']
X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=0)
模型创建
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
# 默认参数逻辑回归模型
lr = LogisticRegression()
lr.fit(X_train, y_train)
# 查看训练集和测试集score值
print("Training set score: {:.2f}".format(lr.score(X_train, y_train)))
print("Testing set score: {:.2f}".format(lr.score(X_test, y_test)))
# 调整参数后的逻辑回归模型
lr2 = LogisticRegression(C=100)
lr2.fit(X_train, y_train)
print("Training set score: {:.2f}".format(lr2.score(X_train, y_train)))
print("Testing set score: {:.2f}".format(lr2.scor