python学习:两个py文件间的函数调用

　　本例子是测试一些数据分析模型的R值,R值越接近1,表明该模型越适合分析该数据集.

　　本例子是在集成开发环境Aptana Studio 3 中创建 一个dataAnaly ,然后创建modelTest.py调用modelChose.py中的函数;在modelTest.py中需要import modelChose

　　格式:from 模块名 import 函数名1,函数名2....

'''

Created on 2015-1-19



@author: xuzhengzhu

'''

#input files

import xlrd,openpyxl

import pandas as pd

from sklearn import cross_validation

from dataAnaly import modelChose

from sklearn.metrics import r2_score

import numpy as np



file=pd.ExcelFile('e:\\report.xlsx')

data=file.parse('Sheet1')

n=len(data)

#init data

x=data[['myjg','tjg']]

y=data['byjg']

models=['linear_model.SGDRegressor','GradientBoostingRegressor','RandomForestRegressor','AdaBoostRegressor','BaggingRegressor','linear_model.LinearRegression','linear_model.LogisticRegression','svm.svr','svm.NuSVR']

m=len(models)

k=10

R2=np.zeros(k)

z=2

count=0

modelCount=0   

#lookup get model object 

for modelCount in range(m-1):

    clf=modelChose.modelChose(models[modelCount])

    R2=np.zeros(k)

    count=0

    #lookup folds

    for train_index,test_index in cross_validation.KFold(n-z,n_folds=k):

        x_train,x_test=x.ix[train_index],x.ix[test_index]

        y_train,y_test=y[train_index],y[test_index]

        clf.fit(x_train,y_train)

        y_predict=clf.predict(x_test);

        r2=r2_score(y_test,y_predict)

        #print 'computed %d time(s) and R square is:%f ' %(count+1,r2)

        R2[count]=r2

        count+=1



    print 'model choose is :',models[modelCount],'the mean of R2 is :',np.mean(R2)

    y_validation = clf.predict(x.ix[(n-z):n])

    r2_val=r2_score(y.ix[(n-z):n],y_validation)

    print 'model choose is :',models[modelCount],'the validation ser R square is :%f ',r2_val

    #print pd.DataFrame({'y_true':y.ix[(n-z):n,],'y_validation':y_validation})

    modelCount+=1

modelTest.py

'''

Created on 2015-1-19

@author: xuzhengzhu

'''

from sklearn.ensemble import BaggingRegressor

from sklearn.ensemble import AdaBoostRegressor

from sklearn.ensemble import RandomForestRegressor

from sklearn.ensemble import GradientBoostingRegressor

from sklearn import linear_model

from sklearn.svm import SVR

from sklearn.svm import NuSVR



def modelChose(modelName):       

    if(cmp(modelName,'linear_model.SGDRegressor')==0):

            #print modelName

            clf = linear_model.SGDRegressor()

            return clf

    elif  (cmp(modelName,'GradientBoostingRegressor')==0):

            #print modelName

            clf = GradientBoostingRegressor()

            return clf

    elif (cmp(modelName,'RandomForestRegressor')==0):

            #print modelName

            clf = RandomForestRegressor()

            return clf

    elif (cmp(modelName,'AdaBoostRegressor')==0):

            #print modelName

            clf = AdaBoostRegressor()

            return clf

    elif (cmp(modelName,'BaggingRegressor')==0):

            #print modelName

            clf = BaggingRegressor()

            return clf

    elif (cmp(modelName,'linear_model.LinearRegression')==0):

            #print modelName

            clf = linear_model.LinearRegression()

            return clf

    elif (cmp(modelName,'linear_model.LogisticRegression')==0):

            #print modelName

            clf = linear_model.LogisticRegression()

            return clf

    elif  (cmp(modelName,'svm.svr')==0):

            #print modelName

            clf = SVR()

            return clf

    elif  (cmp(modelName,'svm.NuSVR')==0):

            #print modelName

            clf = NuSVR()

            return clf

    else: 

            #print modelName,count,'dddd',models[count]

            return 1

    

modelChose.py

 

测试结果:

model choose is : linear_model.SGDRegressor the mean of R2 is : -4.40149514377e+158
model choose is : linear_model.SGDRegressor the validation ser R square is :%f  -1.69950873171e+175
model choose is : GradientBoostingRegressor the mean of R2 is : 0.06842532769
model choose is : GradientBoostingRegressor the validation ser R square is :%f  -0.706828939678
model choose is : RandomForestRegressor the mean of R2 is : 0.0656454293629
model choose is : RandomForestRegressor the validation ser R square is :%f  -1.62440546968
model choose is : AdaBoostRegressor the mean of R2 is : 0.0678670360111
model choose is : AdaBoostRegressor the validation ser R square is :%f  -0.743162901308
model choose is : BaggingRegressor the mean of R2 is : 0.0913739612188
model choose is : BaggingRegressor the validation ser R square is :%f  -1.11141498216
model choose is : linear_model.LinearRegression the mean of R2 is : 0.0976952970181
model choose is : linear_model.LinearRegression the validation ser R square is :%f  -15.3631379961
model choose is : linear_model.LogisticRegression the mean of R2 is : -0.224099722992
model choose is : linear_model.LogisticRegression the validation ser R square is :%f  0.588585017836
model choose is : svm.svr the mean of R2 is : -0.243679440381
model choose is : svm.svr the validation ser R square is :%f  -1.21033155027