上传一些sklearn的小实践

import numpy as np
import joblib
from imblearn.over_sampling import RandomOverSampler
train_X = np.load(r"/home/renhaitao/code/train_rhtX.npy")
train_y = np.load(r"/home/renhaitao/code/train_rhty.npy")
test_X = np.load(r"/home/renhaitao/code/test_rhtX.npy")
test_y = np.load(r"/home/renhaitao/code/test_rhty.npy")
ros = RandomOverSampler(random_state=0)
train_X, train_y = ros.fit_resample(train_X, train_y)
# 数据集来源环境自己改

def svm():
    from sklearn.pipeline import Pipeline
    from sklearn.preprocessing import StandardScaler
    from sklearn.svm import LinearSVC
    svm_clf = Pipeline([
        ("scaler", StandardScaler()),
        ("linear_svc", LinearSVC(max_iter=1000, C=0.5, loss="hinge"))
    ])
    return svm_clf


def rf():
    from sklearn.ensemble import RandomForestClassifier
    rnd_clf = RandomForestClassifier(max_depth=50, n_estimators=500, n_jobs=50, max_features='sqrt')
    return rnd_clf


def lr():
    from sklearn.linear_model import LogisticRegression
    lr_clf = LogisticRegression(penalty='l2', max_iter=500, n_jobs=200, C=0.5, solver='sag')
    return lr_clf


def lrcv():
    from sklearn.linear_model import LogisticRegressionCV
    lr_clf = LogisticRegressionCV(penalty='l2', max_iter=500, n_jobs=200, C=0.5, solver='sag',cv=5)
    return lr_clf


def knn():
    from sklearn.neighbors import KNeighborsClassifier
    knn_clf = KNeighborsClassifier(n_neighbors=20, n_jobs=50)
    return knn_clf


def vc():
    from sklearn.ensemble import VotingClassifier
    vc_lr = lr()
    vc_rf = rf()
    vc_svm = svm()
    vc_clf = VotingClassifier(
        estimators=[('lr', vc_lr), ('rf', vc_rf), ('svc', vc_svm)],
        voting='hard'
    )
    return vc_clf


print(train_y.shape)
print("调用模型")
model = vc()
print("开始训练")
model.fit(train_X, train_y)
print("训练结束")
joblib.dump(model, 'vc.model')
print(model.score(train_X, train_y))
print(model.score(test_X, test_y))