【数据分析入门】python数据分析-分析建模机器学习监督学习中的回归

本文链接：https://blog.youkuaiyun.com/weixin_39348931/article/details/125643994

文章目录

回归
代码

回归

在这里插入图片描述

线性回归

在这里插入图片描述

在这里插入图片描述

岭回归，lasso回归通过控制参数的规模

分类-逻辑回归

在这里插入图片描述

分类-人工神经网络

在这里插入图片描述

一条线代表一个参数

在这里插入图片描述

回归树与提升树

在这里插入图片描述

代码

    from sklearn.model_selection import train_test_split
    fv = features.values
    f_names = features.columns.values
    l_v = label.values
    X_tt, X_validation, Y_tt, Y_validation = train_test_split(
        f_v, l_v, test_size=0.2)
    X_train, X_test, Y_train, Y_test = train_test_split(
        X_tt, Y_tt, test_size=0.25)
    from sklearn.neighbors import NearestNeighbors, KNeighborsClassifier
    from sklearn.metrics import accuracy_score, recall_score, f1_score
    from sklearn.naive_bayes import GaussianNB, BernoulliNB
    from sklearn.tree import DecisionTreeClassifier, export_graphviz
    from sklearn.svm import SVC
    from sklearn.ensemble import AdaBoostClassifier
    from sklearn.linear_model import LogisticRegression
    from sklearn.ensemble import GradientBoostingClassifier
    # 贝叶斯，在离散属性下，有更好的表现，对特征有更高的要求
    models = []
    models.append(("KNN",KNeighborsClassifier(n_neighbors=5)))
    models.append(("GaussianNB",GaussianNB()))
    models.append(("BernoulliNB", BernoulliNB()))
    models.append(("DecisionTree", DecisionTreeClassifier()))
    #models.append(("svm", SVC(C=10000)))
    #models.append(("adaboost", AdaBoostClassifier(base_estimator=SVC(),n_estimators=10000,)))
    models.append(("logisiticRegression",LogisticRegression()))
    models.append(("GBDT",GradientBoostingClassifier()))
    for clf_name, clf in models:
        clf.fit(x_train, y_train)
        xy_lst = [(x_train, y_train), (x_validation,
                                       y_validation), (x_test, y_test)]
        for i in range(len(xy_lst)):
            X_part = xy_lst[i][0]
            Y_part = xy_lst[i][1]
            Y_pred = clf.predict(X_part)
            print(i)
            print(clf_name, "ACT:", accuracy_score(Y_part, Y_pred))
            print(clf_name, "REC:", recall_score(Y_part, Y_pred))
            print(clf_name, "F:", f1_score(Y_part, Y_pred))

def regr_test(features,label):
    from sklearn.linear_model import LinearRegression,Ridge,Lasso
    #regr = LinearRegression()
    #regr = Ridge(alpha=0.1)
    regr=Lasso(alpha=0.1)
    regr.fit(features.values,label.values)
    Y_pred = regr.predict(features.values)
    regr.coef_
    from sklearn.metrics import mean_squared_error
    mean_squared_error(Y_pred,label.values)

def main():
    features,label=hr_preprocessing()
    regr_test(df,label)