数据挖掘项目--模型构建

# 数据划分
from sklearn.model_selection import train_test_split
random_state = 1115
X_train, X_test, y_train, y_test = train_test_split(X_cl, y, test_size=0.3, random_state=random_state)
 
# 归一化
from sklearn.preprocessing import StandardScaler
ss = StandardScaler()
X_train_std = ss.fit_transform(X_train)
X_test_std = ss.transform(X_test)

 

LR

from sklearn.linear_model import LogisticRegression
lr = LogisticRegression(C=0.05, penalty='l1')
lr.fit(X_train_std, y_train)

 

SVM

from sklearn.svm import SVC
# 线性 SVM
linear_svc = SVC(kernel='linear', probability=True)
linear_svc.fit(X_train_std, y_train)
# 多项式 SVM
poly_svc = SVC(kernel='poly', probability=True)
poly_svc.fit(X_train_std, y_train)

 

# 决策树

from sklearn.tree import DecisionTreeClassifier
dt = DecisionTreeClassifier(max_depth=8)
dt.fit(X_train_std, y_train)