【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分类

分类

KNN

K=5

朴素贝叶斯

如果有联合概率分布，就是生成模型，如果没有，就是判别模型

决策树

对于上面的例子






剪枝
对于某些数据不均衡的情况，可以剪枝

支持向量机（SVM）

集成-随机森林

集成-Adaboost

提升法：每个模型都是根据前一个模型训练的结果
最大的影响是权重，而不是顺序



![在这里插入图片描述](https://img-blog.csdnimg.cn/9679d3b8926842e1a2fe9a23c94e472b.png

代码

#sl:false:minimaxscaler,true:standerdscalar
#le:last_evaluation,
#cr:False:LabelEncoding,True:OneHotEncoding
def hr_preprocessing(dn=False,ta=False,pn=False,hn=False,vol=False,risk=False,cr=False,lower_d=False,ld_n=1):
    df=pd.read_csv(r'C:\Users\wenxiaoyu_intern\Documents\用户画像\shengji.csv')
    #1.清洗数据
    df=df.fillna(0)
    # #2.得到标注
    # label=df["shengji_type"]
    # df=df.drop("shengji_type",axis=1)
    
    #df=df[df["date_nums"<1000][df["vol"]>0]]
    #3.特征选择
    #4.特征处理
    scaler_lst=[dn,ta,pn,hn,vol,risk]
    column_list=["date_nums","total_amount","plan_nums","holding_plan_nums","vol","risk"]
    for i in range(len(scaler_lst)):
        if not scaler_lst[i]:
            df[column_list[i]]=\
            MinMaxScaler().fit_transform(df[column_list[i]].values.reshape(-1,1)).reshape(1,-1)[0]
        else:
            df[column_list[i]]=\
            StandardScaler().fit_transform(df[column_list[i]].values.reshape(-1,1)).reshape(1,-1)[0] 
    scaler_list=[cr]
    column_list=["client_rfm"]
    for i in range(len(scaler_list)):
        
        if not scaler_list[i]:
            if column_list[i]=="client_rfm":
                df[column_list[i]]=[map_client_rfm(s) for s in df["client_rfm"].values]
            else:
                df[column_list[i]]=\
                LabelEncoder().fit_transform(df[column_list[i]].values.reshape(-1,1)).reshape(1,-1)[0]
            df[column_list[i]]=\
            MinMaxScaler().fit_transform(df[column_list[i]].values.reshape(-1,1)).reshape(1,-1)[0]
        else:
            df=pd.get_dummies(df,columns=[column_list[0]])
    if lower_d:
        #return LinearDiscriminantAnalysis(n_components=ld_n)
        return PCA(n_components=ld_n).fit_transform(df.values)
    return df
def map_client_rfm(s):
    return dict([("sleep",0),("lost",1),("decline",2),("normal",3),("active",4),("new",5),("vip",6)]).get(s,0)

from sklearn.model_selection import train_test_split
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
features_list=["date_nums","total_amount","plan_nums","holding_plan_nums","vol","risk"]
label_list=["shengji_type"]
#df=hr_preprocessing(True,cr=False)
df=hr_preprocessing(dn=True,ta=True,pn=True,hn=True,vol=True,risk=True)
features=df[features_list]
label=df[label_list]
f_v=features.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)

import pydotplus


def hr_modeling(features, label):
    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.externals.six import StringIO
    import os

    os.environ["PATH"] += os.pathsep+"D:/Program/Graphviz/bin/"
    # 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()))
    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))
            dot_data = export_graphviz(clf, out_file=None,feature_names=f_names,class_names=['NL','L'],filled=True,rounded=True,special_characters=True)
            graph=pydotplus.graph_from_dot_data(dot_data)
            graph.write_pdf("dt_tree.pdf")

    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
    # 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()))
    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))