testPath = _basePath + "001_test_tobe.csv"
# 1. read data
dr = DataReader()
dr.readInCSV(path, "train")
newX, newY = dr._trainDataFrame, dr._ansDataFrame
if doTestFlag == True:
dr.readInCSV(testPath, "test")
newX = dr._testDataFrame
#newX = pd.DataFrame(newX[newX.columns[0]])
print newX
# 2. stratify 60 % data and train location only
# newX, newY = stratifyData(dr._trainDataFrame, dr._ansDataFrame, 0.4)
# 3. get all best model from newX
# fab = ModelFactory()
# fab._gridSearchFlag = True
# fab._n_iter_search = 500
# fab._expInfo = "001_location_only"
# fab.getAllModels(newX, newY)
# 4. test all data, output 3 ans as features
modelPath = _basePath + "(Xgboost)_(2016-02-03_18_39_14).model"
tmpOutPath = _basePath + "001_submission_2.csv"
tmpClf = loadModel(modelPath)
log(tmpClf.predict_proba(newX))
#outDf = pd.concat([newX, pd.DataFrame(tmpClf.predict_proba(newX))], axis=1)
outDf = pd.DataFrame(tmpClf.predict_proba(newX))
outDf.to_csv(tmpOutPath, sep=',', encoding='utf-8')
musicAlarm()
# 4. test all data, output 3 ans as features
# D:\Kaggle\Telstra\004_one_hot_resource_type\(Xgboost)_(2016-02-06_11_14_31).model
# D:\Kaggle\Telstra\004_one_hot_resource_type\(Random_Forest)_(2016-02-06_11_24_09).model
# D:\Kaggle\Telstra\004_one_hot_resource_type\(Extra_Trees)_(2016-02-06_11_30_52).model
# D:\Kaggle\Telstra\004_one_hot_resource_type\(K_NN)_(2016-02-06_11_40_10).model
modelFolder = _basePath + "models" + Config.osSep + "stacked" + Config.osSep
clfNameList = []
clfNameList.append("Extra_Trees")
clfNameList.append("K_NN")
clfNameList.append("Random_Forest")
clfNameList.append("Xgboost")
clfNameList.append("Logistic_Regression")
testCsv = _basePath + "010_train_tobe.csv"
dr = DataReader()
newX, testY = dr.cvtPathListToDfList(testCsv, "train")
for curModel in clfNameList:
modelPath = modelFolder + str(getMatchNameModelPath(modelFolder, curModel))
tmpOutPath = _basePath + expNo + "_blender" + curModel + "_train.csv"
tmpClf = loadModel( modelPath)
log(tmpClf.predict_proba(newX))
#outDf = pd.concat([newX, pd.DataFrame(tmpClf.predict_proba(newX))], axis=1)
outDf = pd.DataFrame(tmpClf.predict_proba(newX))
outDf.to_csv(tmpOutPath, sep=',', encoding='utf-8')
#musicAlarm()
