Python 建模步骤
2019-05-23 09:57:28来源:博客园 阅读 ()
#%% #载入数据 、查看相关信息 import pandas as pd import numpy as np from sklearn.preprocessing import LabelEncoder print('第一步:加载、查看数据') file_path = r'D:\train\201905data\liwang.csv' band_data = pd.read_csv(file_path,encoding='UTF-8') band_data.info() band_data.shape #%% # print('第二步:清洗、处理数据,某些数据可以使用数据库处理数据代替') #数据清洗:缺失值处理:丢去、 #查看缺失值 band_data.isnull().sum band_data = band_data.dropna() #band_data = band_data.drop(['state'],axis=1) # 去除空格 band_data['voice_mail_plan'] = band_data['voice_mail_plan'].map(lambda x: x.strip()) band_data['intl_plan'] = band_data['intl_plan'].map(lambda x: x.strip()) band_data['churned'] = band_data['churned'].map(lambda x: x.strip()) band_data['voice_mail_plan'] = band_data['voice_mail_plan'].map({'no':0, 'yes':1}) band_data.intl_plan = band_data.intl_plan.map({'no':0, 'yes':1}) for column in band_data.columns: if band_data[column].dtype == type(object): le = LabelEncoder() band_data[column] = le.fit_transform(band_data[column]) #band_data = band_data.drop(['phone_number'],axis=1) #band_data['churned'] = band_data['churned'].replace([' True.',' False.'],[1,0]) #band_data['intl_plan'] = band_data['intl_plan'].replace([' yes',' no'],[1,0]) #band_data['voice_mail_plan'] = band_data['voice_mail_plan'].replace([' yes',' no'],[1,0]) #%% # 模型 [重复、调优] print('第三步:选择、训练模型') x = band_data.drop(['churned'],axis=1) y = band_data['churned'] from sklearn import model_selection train,test,t_train,t_test = model_selection.train_test_split(x,y,test_size=0.3,random_state=1) from sklearn import tree model = tree.DecisionTreeClassifier(max_depth=2) model.fit(train,t_train) fea_res = pd.DataFrame(x.columns,columns=['features']) fea_res['importance'] = model.feature_importances_ t_name= band_data['churned'].value_counts() t_name.index import graphviz import os os.environ["PATH"] += os.pathsep + r'D:\software\developmentEnvironment\graphviz-2.38\release\bin' dot_data= tree.export_graphviz(model,out_file=None,feature_names=x.columns,max_depth=2, class_names=t_name.index.astype(str), filled=True, rounded=True, special_characters=False) graph = graphviz.Source(dot_data) #graph graph.render("dtr") #%% print('第四步:查看、分析模型') #结果预测 res = model.predict(test) #混淆矩阵 from sklearn.metrics import confusion_matrix confmat = confusion_matrix(t_test,res) print(confmat) #分类指标 https://blog.csdn.net/akadiao/article/details/78788864 from sklearn.metrics import classification_report print(classification_report(t_test,res)) #%% print('第五步:保存模型') from sklearn.externals import joblib joblib.dump(model,r'D:\train\201905data\mymodel.model') #%% print('第六步:加载新数据、使用模型') file_path_do = r'D:\train\201905data\do_liwang.csv' deal_data = pd.read_csv(file_path_do,encoding='UTF-8') #数据清洗:缺失值处理 deal_data = deal_data.dropna() deal_data['voice_mail_plan'] = deal_data['voice_mail_plan'].map(lambda x: x.strip()) deal_data['intl_plan'] = deal_data['intl_plan'].map(lambda x: x.strip()) deal_data['churned'] = deal_data['churned'].map(lambda x: x.strip()) deal_data['voice_mail_plan'] = deal_data['voice_mail_plan'].map({'no':0, 'yes':1}) deal_data.intl_plan = deal_data.intl_plan.map({'no':0, 'yes':1}) for column in deal_data.columns: if deal_data[column].dtype == type(object): le = LabelEncoder() deal_data[column] = le.fit_transform(deal_data[column]) #数据清洗 #加载模型 model_file_path = r'D:\train\201905data\mymodel.model' deal_model = joblib.load(model_file_path) #预测 res = deal_model.predict(deal_data.drop(['churned'],axis=1)) #%% print('第七步:执行模型,提供数据') result_file_path = r'D:\train\201905data\result_liwang.csv' deal_data.insert(1,'pre_result',res) deal_data[['state','pre_result']].to_csv(result_file_path,sep=',',index=True,encoding='UTF-8')
原文链接:https://www.cnblogs.com/zhongyf/p/10911223.html
如有疑问请与原作者联系
标签:
版权申明:本站文章部分自网络,如有侵权,请联系:west999com@outlook.com
特别注意:本站所有转载文章言论不代表本站观点,本站所提供的摄影照片,插画,设计作品,如需使用,请与原作者联系,版权归原作者所有
上一篇:python操作日志的封装
下一篇:函数递归
- python3基础之“术语表(2)” 2019-08-13
- python3 之 字符串编码小结(Unicode、utf-8、gbk、gb2312等 2019-08-13
- Python3安装impala 2019-08-13
- 小白如何入门 Python 爬虫? 2019-08-13
- python_字符串方法 2019-08-13
IDC资讯: 主机资讯 注册资讯 托管资讯 vps资讯 网站建设
网站运营: 建站经验 策划盈利 搜索优化 网站推广 免费资源
网络编程: Asp.Net编程 Asp编程 Php编程 Xml编程 Access Mssql Mysql 其它
服务器技术: Web服务器 Ftp服务器 Mail服务器 Dns服务器 安全防护
软件技巧: 其它软件 Word Excel Powerpoint Ghost Vista QQ空间 QQ FlashGet 迅雷
网页制作: FrontPages Dreamweaver Javascript css photoshop fireworks Flash