testPath = _basePath + expInfo + "_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
# 3. get all best model from newX
fab = ModelFactory()
fab._gridSearchFlag = True
fab._n_iter_search = 30
fab._expInfo = expInfo
fab.getAllModels(newX, newY)
# 4. test all data, output 3 ans as features
#D:\Kaggle\Telstra\002_blending\(Xgboost)_(2016-02-03_20_09_03).model
#D:\Kaggle\Telstra\002_blending\(Random_Forest)_(2016-02-03_20_16_16).model
#D:\Kaggle\Telstra\002_blending\(Extra_Trees)_(2016-02-03_20_21_58).model
#D:\Kaggle\Telstra\002_blending\(K_NN)_(2016-02-03_20_32_22).model
# modelPath = _basePath+"(K_NN)_(2016-02-03_20_32_22).model"
# tmpOutPath = _basePath + "002_submission_1_K_NN.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))
expNo = "011"
expInfo = expNo + "_remove_one_hot"
_basePath = Config.FolderBasePath + expInfo + Config.osSep
path = _basePath + expNo + "_train_tobe.csv"
testPath = _basePath + expNo + "_test_tobe.csv"
dr = DataReader()
dr.readInCSV( path, "train")
newX, newY = dr._trainDataFrame, dr._ansDataFrame
# Get all best model from newX
fab = ModelFactory()
fab._gridSearchFlag = True
# fab._subFolderName = "stacked"
fab._n_iter_search = 100
fab._expInfo = expInfo
fab.getAllModels(newX, newY)
# Test all data
modelList = ["Xgboost","Random_Forest","Extra_Trees", "K_NN", "Logistic_Regression"]
# featureList = ["event_type", "log_feature", "resource_type", "severity_type"]
# for tmpFeature in featureList:
modelFolder = _basePath + "models" + Config.osSep
for tmpModel in modelList:
curModel = tmpModel
dr = DataReader()
newX = dr.cvtPathListToDfList(testPath, "test")
# 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
# 3. get all best model from newX
fab = ModelFactory()
fab._gridSearchFlag = True
fab._n_iter_search = 30
fab._expInfo = expInfo
fab.getAllModels(newX, newY)
# 4. test all data, output 3 ans as features
#D:\Kaggle\Telstra\002_blending\(Xgboost)_(2016-02-03_20_09_03).model
#D:\Kaggle\Telstra\002_blending\(Random_Forest)_(2016-02-03_20_16_16).model
#D:\Kaggle\Telstra\002_blending\(Extra_Trees)_(2016-02-03_20_21_58).model
#D:\Kaggle\Telstra\002_blending\(K_NN)_(2016-02-03_20_32_22).model
# modelPath = _basePath+"(K_NN)_(2016-02-03_20_32_22).model"
# tmpOutPath = _basePath + "002_submission_1_K_NN.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))
def exp():
expInfo = "location_only\\"
_basePath = Config.FolderBasePath + expInfo
doTestFlag = False
path = _basePath + "train.csv"
testPath = _basePath + "test10.csv"
# 1. read data
dr = DataReader()
dr.readInCSV(path, "train")
if doTestFlag == True:
dr.readInCSV(testPath, "test")
# 2. run models
#print dr._trainDataFrame.as_matrix
fab = ModelFactory()
fab._gridSearchFlag = True
fab._n_iter_search = 10
fab._expInfo = "location_only"
X = dr._trainDataFrame
Y = dr._ansDataFrame
#fab.getRandomForestClf(X, Y)
#fab.getAllModels(dr._trainDataFrame, dr._ansDataFrame)
# log( "xgb start")
# param = {'max_depth':10, 'n_estimators':300 , 'num_class':3, 'learning_rate':0.05, 'objective':'multi:softprob'}
# num_round = 5
#gbm = xgb.XGBClassifier(max_depth=10, n_estimators=300, learning_rate=0.05, objective='multi:softprob').fit(dr._trainDataFrame, dr._ansDataFrame)
#testResult = gbm.predict_proba(dr._testDataFrame)
#print testResult
# gbm = xgb.XGBClassifier(max_depth=10, n_estimators=300, learning_rate=0.05, objective='multi:softprob')
# scores = cross_val_score(rfClf, dr._trainDataFrame, dr._ansDataFrame, n_jobs = -1)
# log( "xgboost Validation Precision: ", scores.mean() )
#xgbCv = xgb.cv(param, xgb.DMatrix(dr._trainDataFrame, dr._ansDataFrame), num_round, nfold=5,metrics={'error'}, seed = 0)
#gbTrain = gbm.fit(dr._trainDataFrame, dr._ansDataFrame)
#joblib.dump(gbTrain, xgbModelPath)
#clf = joblib.load( xgbModelPath )
#clf.predict_proba(dr._testDataFrame)
#xgb.save(gbm, xgbModelPath)
#print xgbCv
#print "xgb end"
#gbm = joblib.load( xgbModelPath )
#finalClf = gbm
if doTestFlag == True:
print finalClf.predict_proba(dr._testDataFrame)
# featureImportance =[]
# for i in range(0,len(finalClf.feature_importances_)):
# if i != len(dr._trainDataFrame.columns):
# if (dr._trainDataFrame.columns[i]).find("_one_hot") == -1:
# featureImportance.append( [dr._trainDataFrame.columns[i] , finalClf.feature_importances_[i]] )
#
# print featureImportance
# featureImportance.sort(lambda x, y: cmp(x[1], y[1]), reverse=True)
# print featureImportance
if doTestFlag == True:
return finalClf.predict_proba(dr._testDataFrame)
expNo = "012"
expInfo = expNo + "_rf_chk_important"
_basePath = Config.FolderBasePath + expInfo + Config.osSep
path = _basePath + expNo + "_train_asis.csv"
testPath = _basePath + expNo + "_test_asis.csv"
dr = DataReader()
dr.readInCSV(path, "train")
newX, newY = dr._trainDataFrame, dr._ansDataFrame
# Get all best model from newX
fab = ModelFactory()
fab._gridSearchFlag = True
# fab._subFolderName = "stacked"
fab._n_iter_search = 250
fab._expInfo = expInfo
# fab.getAllModels(newX, newY)
finalClf = fab.getRandomForestClf(newX, newY)
featureImportance = []
for i in range(0, len(finalClf.feature_importances_)):
if i != len(dr._trainDataFrame.columns):
# if (dr._trainDataFrame.columns[i]).find("_one_hot") == -1:
featureImportance.append([dr._trainDataFrame.columns[i], finalClf.feature_importances_[i]])
# log( featureImportance)
featureImportance.sort(lambda x, y: cmp(x[1], y[1]), reverse=True)
log(featureImportance)
trainNewX = dr._ansDataFrame
clfList = ["xgboost", "rf","extra_tree",]
fab = ModelFactory()
fab._gridSearchFlag = True
dfUpper = pd.DataFrame()
dfTestUpper = pd.DataFrame()
eachClfLoopTimes = 3
iter_search_times = 1
for tmpClfName in clfList:
for i in range(0,eachClfLoopTimes):
fab._subFolderName = tmpClfName
fab._n_iter_search = iter_search_times
fab._expInfo = expInfo
if tmpClfName == "rf":
clf = fab.getRandomForestClf(train_fold_1, train_fold_label_1)
elif tmpClfName == "knn":
clf = fab.getKnnClf(train_fold_1, train_fold_label_1)
elif tmpClfName == "extra_tree":
clf = fab.getExtraTressClf(train_fold_1, train_fold_label_1)
elif tmpClfName == "xgboost":
clf = fab.getXgboostClf(train_fold_1, train_fold_label_1)
if tmpClfName == "xgboost":
predictResult = clf.predict(xgb.DMatrix(train_fold_2))
predictTestResult = clf.predict(xgb.DMatrix(test_fold_2))
else:
predictResult = clf.predict_proba(train_fold_2)
"rf",
"extra_tree",
]
fab = ModelFactory()
fab._gridSearchFlag = True
dfUpper = pd.DataFrame()
dfTestUpper = pd.DataFrame()
eachClfLoopTimes = 3
iter_search_times = 1
for tmpClfName in clfList:
for i in range(0, eachClfLoopTimes):
fab._subFolderName = tmpClfName
fab._n_iter_search = iter_search_times
fab._expInfo = expInfo
if tmpClfName == "rf":
clf = fab.getRandomForestClf(train_fold_1, train_fold_label_1)
elif tmpClfName == "knn":
clf = fab.getKnnClf(train_fold_1, train_fold_label_1)
elif tmpClfName == "extra_tree":
clf = fab.getExtraTressClf(train_fold_1, train_fold_label_1)
elif tmpClfName == "xgboost":
clf = fab.getXgboostClf(train_fold_1, train_fold_label_1)
if tmpClfName == "xgboost":
predictResult = clf.predict(xgb.DMatrix(train_fold_2))
predictTestResult = clf.predict(xgb.DMatrix(test_fold_2))
else:
predictResult = clf.predict_proba(train_fold_2)
def exp():
expInfo = "location_only\\"
_basePath = Config.FolderBasePath + expInfo
doTestFlag = False
path = _basePath + "train.csv"
testPath = _basePath + "test10.csv"
# 1. read data
dr = DataReader()
dr.readInCSV( path, "train")
if doTestFlag == True:
dr.readInCSV(testPath , "test")
# 2. run models
#print dr._trainDataFrame.as_matrix
fab = ModelFactory()
fab._gridSearchFlag = True
fab._n_iter_search = 10
fab._expInfo = "location_only"
X = dr._trainDataFrame
Y = dr._ansDataFrame
#fab.getRandomForestClf(X, Y)
#fab.getAllModels(dr._trainDataFrame, dr._ansDataFrame)
# log( "xgb start")
# param = {'max_depth':10, 'n_estimators':300 , 'num_class':3, 'learning_rate':0.05, 'objective':'multi:softprob'}
# num_round = 5
#gbm = xgb.XGBClassifier(max_depth=10, n_estimators=300, learning_rate=0.05, objective='multi:softprob').fit(dr._trainDataFrame, dr._ansDataFrame)
#testResult = gbm.predict_proba(dr._testDataFrame)
#print testResult
# gbm = xgb.XGBClassifier(max_depth=10, n_estimators=300, learning_rate=0.05, objective='multi:softprob')
# scores = cross_val_score(rfClf, dr._trainDataFrame, dr._ansDataFrame, n_jobs = -1)
# log( "xgboost Validation Precision: ", scores.mean() )
#xgbCv = xgb.cv(param, xgb.DMatrix(dr._trainDataFrame, dr._ansDataFrame), num_round, nfold=5,metrics={'error'}, seed = 0)
#gbTrain = gbm.fit(dr._trainDataFrame, dr._ansDataFrame)
#joblib.dump(gbTrain, xgbModelPath)
#clf = joblib.load( xgbModelPath )
#clf.predict_proba(dr._testDataFrame)
#xgb.save(gbm, xgbModelPath)
#print xgbCv
#print "xgb end"
#gbm = joblib.load( xgbModelPath )
#finalClf = gbm
if doTestFlag == True:
print finalClf.predict_proba(dr._testDataFrame)
# featureImportance =[]
# for i in range(0,len(finalClf.feature_importances_)):
# if i != len(dr._trainDataFrame.columns):
# if (dr._trainDataFrame.columns[i]).find("_one_hot") == -1:
# featureImportance.append( [dr._trainDataFrame.columns[i] , finalClf.feature_importances_[i]] )
#
# print featureImportance
# featureImportance.sort(lambda x, y: cmp(x[1], y[1]), reverse=True)
# print featureImportance
if doTestFlag == True:
return finalClf.predict_proba(dr._testDataFrame)
