Python建模步骤

#%%

#载⼊数据 、查看相关信息import pandas as pdimport numpy as np

from sklearn.preprocessing import LabelEncoderprint('第⼀步：加载、查看数据')

file_path = r'D:\rain\\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.indeximport 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_matrixconfmat = confusion_matrix(t_test,res)print(confmat)

#分类指标 https://blog.csdn.net/akadiao/article/details/787888from sklearn.metrics import classification_reportprint(classification_report(t_test,res))#%%

print('第五步：保存模型')

from sklearn.externals import joblib

joblib.dump(model,r'D:\rain\\201905data\\mymodel.model')#%%

print('第六步：加载新数据、使⽤模型')

file_path_do = r'D:\rain\\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:\rain\\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:\rain\\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')