[python] 机器学习随机森林算法RandomForestRegressor

叁歲伎倆 2022-02-15 15:55 535阅读 0赞

## 前言 ##

随机森林Python版本有很可以调用的库，使用随机森林非常方便，主要用到以下的库

**sklearn**

Scikit learn 也简称 [sklearn][], 是机器学习领域当中最知名的 python 模块之一.

Sklearn 包含了很多种机器学习的方式:

*  Classification 分类
 *  Regression 回归
 *  Clustering 非监督分类
 *  Dimensionality reduction 数据降维
 *  Model Selection 模型选择
 *  Preprocessing 数据预处理

快速入门：[传送门][Link 1]

**numpy**

numpy（Numerical Python）提供了python对多维数组对象的支持：ndarray，具有矢量运算能力，快速、节省空间。numpy支持高级大量的维度数组与矩阵运算，此外也针对数组运算提供大量的数学函数库。

![这里写图片描述][SouthEast]

numpy快速入门:[ 传送门][Link 2]

**pandas**

pandas 是基于 Numpy 构建的含有更高级数据结构和工具的数据分析包 类似于 Numpy 的核心是 ndarray，pandas 也是围绕着 Series 和 DataFrame 两个核心数据结构展开的 。Series 和 DataFrame 分别对应于一维的序列和二维的表结构。

pandas使用教程：[传送门][Link 3]

### RandomForestRegressor 基础 ###

1.导入模块，创建模型

import matplotlib.pyplot as plt #可视化图形库
    import numpy as np    #numpy多维数值操作库
    import pandas as pd    #pandas数据分析库
    from sklearn import datasets, cross_validation, ensemble #sklearn机器学习库

2.引入数据，对数据进行分集

'''
        加载用于回归问题的数据集
    
        :return: 一个元组，用于回归问题。元组元素依次为：训练样本集、测试样本集、训练样本集对应的值、测试样本集对应的值
        '''
        diabetes = datasets.load_diabetes()  # 使用 scikit-learn 自带的一个糖尿病病人的数据集
        return cross_validation.train_test_split(diabetes.data, diabetes.target,
                                                 test_size=0.25, random_state=0)  # 拆分成训练集和测试集，测试集大小为原始数据集大小的 1/4

3.模型预测

'''
        测试 RandomForestRegressor 的用法
    
        :param data:  可变参数。它是一个元组，这里要求其元素依次为：训练样本集、测试样本集、训练样本的          值、测试样本的值
        :return: None
        '''
        X_train, X_test, y_train, y_test = data
        regr = ensemble.RandomForestRegressor()
        regr.fit(X_train, y_train)
        print("Traing Score:%f" % regr.score(X_train, y_train))
        print("Testing Score:%f" % regr.score(X_test, y_test))

训练集：0.89 测试集 ：0.24

![20190424175513353.png][]

更多使用参考：[链接][Link 4]

### Demo ###

自定义数据拓展模型

# -*- coding: UTF-8 -*-
    import pandas as pd
    import numpy as np
    from sklearn.ensemble import RandomForestRegressor
    from sklearn.cross_validation import train_test_split
    from sklearn.decomposition import PCA
    from sklearn import preprocessing
    from sklearn.externals import joblib
    # 各指数计算
    # PCA降维
    def pcachange(pcadata):
        global MType
        pcadata1 = pcadata.fillna(0)
        pca = PCA(n_components=1)
        data_new = pca.fit_transform(pcadata1)
        print pcadata1.columns, pca.explained_variance_ratio_
        joblib.dump(pca, unicode('D:/pca/' +  str(MType) + '.m', 'utf-8'))
        minmax_scaler = preprocessing.MinMaxScaler(feature_range=(0, 100))
        joblib.dump(pca, unicode('D:/minmax/' + str(MType) + '.m', 'utf-8'))
        data_minmax = minmax_scaler.fit_transform(data_new)
        return data_minmax
    
    #分组计算
    def cal_zs(input_features):
        for col in input_features:
            'print(data[col])'
        data_output = data[col]
        data_output1 = pcachange(data_output)
        data_output2 = pd.DataFrame(data_output1)
        return data_output2
    
    #整个预处理过程
    def preprocess(data_raw):
        global MType
        MType = 0
        info = data_raw.iloc[:,0:12]
        #diannei = data_raw.iloc[:,22:89]
        ylsale =data_raw.iloc[:,-2]
        sale =data_raw.iloc[:,-1]
    
        ls_features = [['t130403','t130201','t130200','t130204','t130207','t130102','t130103','t130105','t130106','t130104','t130101']]
    
        xzl_features = [['t200103','t200104']]
    
        yl_features = [['t180201','t180400','t180402','t180403','t180209','t180205','t180202','t180210','t180203',
                        't180103','t180106','t180105','t180104','t180110','t180107','t180102','t180111','t180101','t180100','t120201','t120202','t120101','t120102']]
    
        cy_features = [['t110101','t110102','t110103','t110200','t110301','t110303','t110302']]
    
        fw_features = [['t230224','t230212','t230206','t230213','t230230','t230223','t230129','t230112','t230125','t230107','t230126','t230100','t230103','t230108']]
    
        jy_features = [[ 't160103', 't160104', 't160105']]
    
        jj_features = [
            ['t800000', 't800001', 't800010', 't800011', 't800012', 't800013', 't800014', 't800020', 't800030', 't800031',
             't800032', 't800035', 't800036', 't800037', 't8_0_19', 't8_0_29', 't8_0_39', 't8_0_49', 't8_10_29', 't8_10_39',
             't8_10_49', 't8_20_39', 't8_20_49', 't8_30_49']]
    
        MType = MType + 1
        lszs = cal_zs(ls_features)
        MType = MType + 1
        xzlzs = cal_zs(xzl_features)
        MType = MType + 1
        ylzs = cal_zs(yl_features)
        MType = MType + 1
        cyzs = cal_zs(cy_features)
        MType = MType + 1
        fwzs = cal_zs(fw_features)
        MType = MType + 1
        jyzs = cal_zs(jy_features)
        MType = MType + 1
        jjzs = cal_zs(jj_features)
    
        lszs.columns = ['lszs']
        xzlzs.columns = ['xzlzs']
        ylzs.columns = ['ylzs']
        cyzs.columns = ['cyzs']
        jyzs.columns = ['jyzs']
        jjzs.columns = ['jjzs']
        ls = data_raw[['t130403','t130201','t130200','t130204','t130207','t130102','t130103','t130105','t130106','t130104','t130101']]
        cy = data_raw[['t110101','t110102','t110103','t110200','t110301','t110303','t110302']]
        fw = data_raw[['t230224','t230212','t230206','t230213','t230230','t230223','t230129','t230112','t230125','t230107','t230126','t230100','t230103','t230108']]
        yl = data_raw[['t180201', 't180400', 't180402', 't180403', 't180209', 't180205', 't180202', 't180210', 't180203',
                        't180103', 't180106', 't180105', 't180104', 't180110', 't180107', 't180102', 't180111', 't180101',
                        't180100', 't120201', 't120202', 't120101', 't120102']]
        jj = data_raw[['t800000', 't800001', 't800010', 't800011', 't800012', 't800013', 't800014', 't800020', 't800030', 't800031',
             't800032','t800035','t800036', 't800037', 't8_0_19', 't8_0_29', 't8_0_39', 't8_0_49', 't8_10_29', 't8_10_39',
             't8_10_49', 't8_20_39', 't8_20_49', 't8_30_49']]
    
        data_pre = pd.concat([info,lszs,xzlzs,ylzs,jyzs,ls,cy,cyzs,fw,fwzs,jjzs,jj,yl,ylsale,sale],axis = 1)
        return data_pre
    
    
    filepath =  u'D:/data/f1.csv'
    labelpath = u'D:/data/f2.csv'
    data = pd.read_csv(filepath, header=0, sep=',',na_values='NULL')
    label = pd.read_csv(labelpath, header=0, sep=',')
    
    
    data2 = preprocess(data)
    x_labels = data2.columns[12:-2]
    x_labels_t = np.array(x_labels).T
    print x_labels
    
    
    # 销量分等级
    def cat_sale(inputdata):
        y1 = inputdata.iloc[:, -1]  # 销量
        inputdata['salecat'] = pd.qcut(y1, 10, labels=[1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
        inputdata['salecat'] = inputdata['salecat'].astype(int)
        return inputdata
    
    
    # 随机森林算法
    def rt_method(x_train, y_train, x_test, y_test):
        global CityIndex,CityName
    
        x_train1 = x_train.iloc[:, 12:]
        info_train = x_train.iloc[:, 0:12]
        info_train1 = info_train.reset_index(drop=True)
        rf0 = RandomForestRegressor(n_estimators=100, max_features='sqrt',oob_score=True)
    
        x_test1 = x_test.iloc[:, 12:]
        #rf0.fit(x_test1, y_test)
        rf0.fit(x_train1, y_train)
        y1 = rf0.predict(x_train1)
        y_train_pred = pd.DataFrame(y1, columns=['cat_pred'])
        y_train1 = y_train.reset_index(drop=True)
    
    
        info_test = x_test.iloc[:, 0:12]
        info_test1 = info_test.reset_index(drop=True)
        y2 = rf0.predict(x_test1)
        y_test_pred = pd.DataFrame(y2, columns=['cat_pred'])
        y_test1 = y_test.reset_index(drop=True)
    
        result_train = pd.concat([info_train1, y_train_pred, y_train1], axis=1)
        result_train1 = result_train.rename(columns={'salecat': 'cat_true'})
        result_train1['PCV'] = result_train1['cat_pred'] * 10
        result_train1.to_csv(unicode('D:/train.csv','utf-8'), index=False, sep=',')
    
        result_test = pd.concat([info_test1, y_test_pred, y_test1], axis=1)
        result_test1 = result_test.rename(columns={'salecat': 'cat_true'})
        result_test1['PCV'] = result_test1['cat_pred'] * 10
        result_test1.to_csv(unicode('D:/test.csv','utf-8'), index=False, sep=',')
    
        r1 = result_train1.cat_pred.corr(result_train1.cat_true)
        r2 = result_test1.cat_pred.corr(result_test1.cat_true)
        print r1, r2
    
        result.loc[CityIndex, ['train_R']] = r1
        result.loc[CityIndex, ['test_R']] = r2
    
    
        importances = rf0.feature_importances_
    
        df_ipt = pd.DataFrame(importances, columns=["feature_importance"])
        feature_imp["feature_importance"] = df_ipt
        return rf0
    
    global CityName,CityIndex
    CityIndex = 0
    feature_imp = pd.DataFrame(data=[])
    feature_imp['feature'] = x_labels_t
    result = pd.DataFrame(data=[], index=[], columns=['city', 'train_R', 'test_R', 'num'])
    data3 = cat_sale(data)
    X = data3.iloc[:, 0:-2]
    Y = data3['salecat']
    Y = Y.fillna(1)
    X1 = X.fillna(0)  # 用0填充空值
    X2 = X1.replace('t', 1)  # 用1填充t值
    X_train, X_test, Y_train, Y_test = train_test_split(X2, Y, test_size=0.3, random_state=42)
    rf = rt_method(X_train, Y_train, X_test, Y_test)
    joblib.dump(rf, unicode('D:/data/model/0116/ly/全国.m', 'utf-8'))
    
    '''for city, ctdata in data3.groupby(['city_name']):
        print city, CityIndex
        CityName = city
    
        result.loc[CityIndex, ['city']] = city
    
        n = ctdata.iloc[:, 0].size  # 行数
        if n > 20:
            X = ctdata.iloc[:, 0:-2]
            Y = ctdata['salecat']
            Y = Y.fillna(1)
    
            X1 = X.fillna(0)  # 用0填充空值
            X2 = X1.replace('t', 1)  # 用1填充t值
            X_train, X_test, Y_train, Y_test = train_test_split(X2, Y, test_size=0.3, random_state=42)
            try:
                rf = rt_method(X_train, Y_train, X_test, Y_test)
                joblib.dump(rf, unicode('D:/data/model/0115/ly/' + str(CityName) + '.m', 'utf-8'))
    
            except:
                print ('wrong')
    
        else:
            print n
        result.loc[CityIndex, ['num']] = n
        CityIndex = CityIndex + 1'''
    
    feature_imp1 = pd.merge(label, feature_imp, on='feature',how = 'right')
    
    result.to_csv(u'D:/R.csv', index=False, sep=',',encoding = 'gbk')
    feature_imp1.to_csv(u'D:/变量重要性.csv', index=False, sep=',',encoding = 'gbk')

[sklearn]: https://link.jianshu.com?t=http://scikit-learn.org/stable/
[Link 1]: https://www.jianshu.com/p/cd5a929bec33
[SouthEast]: /images/20220215/a98683d0180b422da63ff8f71ccd2d1a.png
[Link 2]: https://blog.csdn.net/cxmscb/article/details/54583415
[Link 3]: https://blog.csdn.net/qq_38251616/article/details/79775789
[20190424175513353.png]: /images/20220215/c53410d3069d46e8a5222de23241694d.png
[Link 4]: https://blog.csdn.net/mr_muli/article/details/84796955