回归

回归：线性回归、岭回归、Lasso回归、Logistic回归（常用作分类器）

回归树与提升树

Gradient Boosting Decision Tree（GBDT）

import pandas as pd
import numpy as np
from sklearn.preprocessing import MinMaxScaler,StandardScaler
from sklearn.preprocessing import LabelEncoder,OneHotEncoder
from sklearn.preprocessing import Normalizer
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.decomposition import PCA
def hr_preprocessing(sl=False,le=False,npr=False,amh=False,tsc=False,wa=False,pl5=False,dp=False,slr=False,lower_d=False,ld_n=1):
    df=pd.read_csv("HR.csv")  #读入数据
    #1.清洗数据
    df=df.dropna(subset=["satisfaction_level","last_evaluation"])
    df=df[df["satisfaction_level"]<=1][df["salary"]!="nme"]
    #2.得到标注
    label=df["left"]
    df=df.drop("left",axis=1)  #axis=1以列删除
    #3.特征选择
    #4.特征处理:标准化，归一化
    scaler_lst=[sl,le,npr,amh,tsc,wa,pl5]
    column_lst=["satisfaction_level","last_evaluation","number_project",\
               "average_monthly_hours","time_spend_company","Work_accident",\
                           "promotion_last_5years"]
    for i in range(len(scaler_lst)):
        if not scaler_lst[i]:
            df[column_lst[i]]=\
             MinMaxScaler().fit_transform(df[column_lst[i]].values.reshape(-1,1)).reshape(1,-1)[0]
            #reshape(-1,1)列，reshape(1,-1)[0]二维向量取第零个
        else:
            df[column_lst[i]]=\
             StandardScaler().fit_transform(df[column_lst[i]].values.reshape(-1,1)).reshape(1,-1)[0]
    scaler_lst=[slr,dp]
    column_lst=["salary","department"]
    for i in range(len(scaler_lst)):
        if not scaler_lst[i]:
            if column_lst[i]=="salary":
                df[column_lst[i]]=[map_salary(s) for s in df["salary"].values]
            else:
                df[column_lst[i]]=LabelEncoder().fit_transform(df[column_lst[i]])
            df[column_lst[i]]=MinMaxScaler().fit_transform(df[column_lst[i]].values.reshape(-1,1)).reshape(1,-1)[0]#再归一化或标准化也可不进行
        else:
            df=pd.get_dummies(df,columns=[column_lst[i]])  #pandas提供的独热
    if lower_d:
        #return LinearDiscriminantAnalysis(n_components=ld_n)
        #LDA这里的n_components不能大于标注的类的个数,有限值，改用无限制的PCA方法
        return PCA(n_components=ld_n).fit_transform(df.values),label
    
    return df,label
#由于LabelEncoder会默认按英文字母排序，为了让low为0，medium为1，high为2，需自定义
d=dict([("low",0),("medium",1),("high",2)])
def map_salary(s):
    return d.get(s,0)  #如果没有找到就返回0，默认是低收入人群 
def regr_test(features,label):
    print("x",features)
    print("y",label)
    from sklearn.linear_model import LinearRegression,Ridge,Lasso#线性回归，岭回归，Lasso回归
    regr=LinearRegression()  #线性回归
    #regr=Ridge(alpha=0.8)   #岭回归
    #regr=Lasso(alpha=0.001)  #Lasso回归
    regr.fit(features.values,label.values)
    y_pred=regr.predict(features.values)
    print("Coef",regr.coef_)   #显示模型估计的参数
    from sklearn.metrics import mean_squared_error
    print("MSE",mean_squared_error(y_pred,label.values)) #评价模型的误差
def hr_modeling(features,label):
    #切分训练集和验证集(测试集)
    from sklearn.model_selection import train_test_split
    f_v=features.values  #原先的数据是DataFrame,装换为数值，得到特征值
    f_names=features.columns.values  #得到特征名称
    l_v=label.values
    x_tt,x_validation,y_tt,y_validation=train_test_split(f_v,l_v,test_size=0.2)
    #将训练集再切分为训练集和测试集
    x_train,x_test,y_train,y_test=train_test_split(x_tt,y_tt,test_size=0.25)
    #引入评价指标
    from sklearn.metrics import accuracy_score,recall_score,f1_score
    from sklearn.linear_model import LogisticRegression
    from sklearn.ensemble import GradientBoostingClassifier
    models=[]
    models.append(("LogisticRegression",LogisticRegression()))#Logistic回归,常用作分类器
    models.append(("GBDT",GradientBoostingClassifier(max_depth=6,n_estimators=100)))  #回归树和提升树
    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]  #为遍历中的第0部分
            y_part=xy_lst[i][1]  #为遍历中的第1部分
            y_pred=clf.predict(x_part)
            print(i)  #i是下标，0表示训练集，1表示验证集，2表示测试集
            print(clf_name,"ACC:",accuracy_score(y_part,y_pred))
            print(clf_name,"REC:",recall_score(y_part,y_pred))
            print(clf_name,"F-score:",f1_score(y_part,y_pred))
def main():
    features,label=hr_preprocessing()
    regr_test(features[["number_project","average_monthly_hours"]],features["last_evaluation"])
    hr_modeling(features,label)
if __name__=="__main__":
    main()