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()
tmpId = df[df.columns[0]][i2]
tmpVal = df[df.columns[1]][i2]
# tmpVal2= df[df.columns[2]][i2]
if tmpMainId == tmpId:
tmpFlag = True
print tmpVal
processDf[processDf.columns[tmpVal + 394]][i1] = 1
if tmpFlag == True and tmpMainId != tmpId:
tmpLastI2 = i2
break
print i1, i2
# outDf = pd.concat([dr._ansDataFrame, processDf], axis=1)
outDf = processDf
outDf.to_csv(_outputPathName, sep=',', encoding='utf-8')
# print dr._ansDataFrame
if __name__ == '__main__':
start = time.time()
oneHot()
elapsed = time.time() - start
print "elapsed:", elapsed , "sec"
musicAlarm()