def Train(self):
st_global = time.time()
CommonUtils.create_update_and_save_progress_message(self._dataframe_context,self._scriptWeightDict,self._scriptStages,self._slug,"initialization","info",display=True,emptyBin=False,customMsg=None,weightKey="total")
appType = self._dataframe_context.get_app_type()
algosToRun = self._dataframe_context.get_algorithms_to_run()
algoSetting = filter(lambda x:x.get_algorithm_slug()==self._slug,algosToRun)[0]
categorical_columns = self._dataframe_helper.get_string_columns()
uid_col = self._dataframe_context.get_uid_column()
if self._metaParser.check_column_isin_ignored_suggestion(uid_col):
categorical_columns = list(set(categorical_columns) - {uid_col})
allDateCols = self._dataframe_context.get_date_columns()
categorical_columns = list(set(categorical_columns)-set(allDateCols))
print categorical_columns
result_column = self._dataframe_context.get_result_column()
numerical_columns = self._dataframe_helper.get_numeric_columns()
numerical_columns = [x for x in numerical_columns if x != result_column]
model_path = self._dataframe_context.get_model_path()
if model_path.startswith("file"):
model_path = model_path[7:]
validationDict = self._dataframe_context.get_validation_dict()
print "model_path",model_path
pipeline_filepath = "file://"+str(model_path)+"/"+str(self._slug)+"/pipeline/"
model_filepath = "file://"+str(model_path)+"/"+str(self._slug)+"/model"
pmml_filepath = "file://"+str(model_path)+"/"+str(self._slug)+"/modelPmml"
df = self._data_frame
if self._mlEnv == "spark":
pipeline = MLUtils.create_pyspark_ml_pipeline(numerical_columns,categorical_columns,result_column,algoType="regression")
pipelineModel = pipeline.fit(df)
indexed = pipelineModel.transform(df)
featureMapping = sorted((attr["idx"], attr["name"]) for attr in (chain(*indexed.schema["features"].metadata["ml_attr"]["attrs"].values())))
# print indexed.select([result_column,"features"]).show(5)
MLUtils.save_pipeline_or_model(pipelineModel,pipeline_filepath)
# OriginalTargetconverter = IndexToString(inputCol="label", outputCol="originalTargetColumn")
dtreer = DecisionTreeRegressor(labelCol=result_column, featuresCol='features',predictionCol="prediction")
if validationDict["name"] == "kFold":
defaultSplit = GLOBALSETTINGS.DEFAULT_VALIDATION_OBJECT["value"]
numFold = int(validationDict["value"])
if numFold == 0:
numFold = 3
trainingData,validationData = indexed.randomSplit([defaultSplit,1-defaultSplit], seed=12345)
paramGrid = ParamGridBuilder()\
.addGrid(dtreer.regParam, [0.1, 0.01]) \
.addGrid(dtreer.fitIntercept, [False, True])\
.addGrid(dtreer.elasticNetParam, [0.0, 0.5, 1.0])\
.build()
crossval = CrossValidator(estimator=dtreer,
estimatorParamMaps=paramGrid,
evaluator=RegressionEvaluator(predictionCol="prediction", labelCol=result_column),
numFolds=numFold)
st = time.time()
cvModel = crossval.fit(indexed)
trainingTime = time.time()-st
print "cvModel training takes",trainingTime
bestModel = cvModel.bestModel
elif validationDict["name"] == "trainAndtest":
trainingData,validationData = indexed.randomSplit([float(validationDict["value"]),1-float(validationDict["value"])], seed=12345)
st = time.time()
fit = dtreer.fit(trainingData)
trainingTime = time.time()-st
print "time to train",trainingTime
bestModel = fit
featureImportance = bestModel.featureImportances
print featureImportance,type(featureImportance)
# print featureImportance[0],len(featureImportance[1],len(featureImportance[2]))
print len(featureMapping)
featuresArray = [(name, featureImportance[idx]) for idx, name in featureMapping]
print featuresArray
MLUtils.save_pipeline_or_model(bestModel,model_filepath)
transformed = bestModel.transform(validationData)
transformed = transformed.withColumn(result_column,transformed[result_column].cast(DoubleType()))
transformed = transformed.select([result_column,"prediction",transformed[result_column]-transformed["prediction"]])
transformed = transformed.withColumnRenamed(transformed.columns[-1],"difference")
transformed = transformed.select([result_column,"prediction","difference",FN.abs(transformed["difference"])*100/transformed[result_column]])
transformed = transformed.withColumnRenamed(transformed.columns[-1],"mape")
sampleData = None
nrows = transformed.count()
if nrows > 100:
sampleData = transformed.sample(False, float(100)/nrows, seed=420)
else:
sampleData = transformed
print sampleData.show()
evaluator = RegressionEvaluator(predictionCol="prediction",labelCol=result_column)
metrics = {}
metrics["r2"] = evaluator.evaluate(transformed,{evaluator.metricName: "r2"})
metrics["rmse"] = evaluator.evaluate(transformed,{evaluator.metricName: "rmse"})
metrics["mse"] = evaluator.evaluate(transformed,{evaluator.metricName: "mse"})
metrics["mae"] = evaluator.evaluate(transformed,{evaluator.metricName: "mae"})
runtime = round((time.time() - st_global),2)
# print transformed.count()
mapeDf = transformed.select("mape")
# print mapeDf.show()
mapeStats = MLUtils.get_mape_stats(mapeDf,"mape")
mapeStatsArr = mapeStats.items()
mapeStatsArr = sorted(mapeStatsArr,key=lambda x:int(x[0]))
# print mapeStatsArr
quantileDf = transformed.select("prediction")
# print quantileDf.show()
quantileSummaryDict = MLUtils.get_quantile_summary(quantileDf,"prediction")
quantileSummaryArr = quantileSummaryDict.items()
quantileSummaryArr = sorted(quantileSummaryArr,key=lambda x:int(x[0]))
# print quantileSummaryArr
self._model_summary.set_model_type("regression")
self._model_summary.set_algorithm_name("dtree Regression")
self._model_summary.set_algorithm_display_name("Decision Tree Regression")
self._model_summary.set_slug(self._slug)
self._model_summary.set_training_time(runtime)
self._model_summary.set_training_time(trainingTime)
self._model_summary.set_target_variable(result_column)
self._model_summary.set_validation_method(validationDict["displayName"])
self._model_summary.set_model_evaluation_metrics(metrics)
self._model_summary.set_model_params(bestEstimator.get_params())
self._model_summary.set_quantile_summary(quantileSummaryArr)
self._model_summary.set_mape_stats(mapeStatsArr)
self._model_summary.set_sample_data(sampleData.toPandas().to_dict())
self._model_summary.set_feature_importance(featureImportance)
# print CommonUtils.convert_python_object_to_json(self._model_summary)
elif self._mlEnv == "sklearn":
model_filepath = model_path+"/"+self._slug+"/model.pkl"
x_train,x_test,y_train,y_test = self._dataframe_helper.get_train_test_data()
x_train = MLUtils.create_dummy_columns(x_train,[x for x in categorical_columns if x != result_column])
x_test = MLUtils.create_dummy_columns(x_test,[x for x in categorical_columns if x != result_column])
x_test = MLUtils.fill_missing_columns(x_test,x_train.columns,result_column)
st = time.time()
est = DecisionTreeRegressor()
CommonUtils.create_update_and_save_progress_message(self._dataframe_context,self._scriptWeightDict,self._scriptStages,self._slug,"training","info",display=True,emptyBin=False,customMsg=None,weightKey="total")
if algoSetting.is_hyperparameter_tuning_enabled():
hyperParamInitParam = algoSetting.get_hyperparameter_params()
evaluationMetricDict = {"name":hyperParamInitParam["evaluationMetric"]}
evaluationMetricDict["displayName"] = GLOBALSETTINGS.SKLEARN_EVAL_METRIC_NAME_DISPLAY_MAP[evaluationMetricDict["name"]]
hyperParamAlgoName = algoSetting.get_hyperparameter_algo_name()
params_grid = algoSetting.get_params_dict_hyperparameter()
params_grid = {k:v for k,v in params_grid.items() if k in est.get_params()}
print params_grid
if hyperParamAlgoName == "gridsearchcv":
estGrid = GridSearchCV(est,params_grid)
gridParams = estGrid.get_params()
hyperParamInitParam = {k:v for k,v in hyperParamInitParam.items() if k in gridParams}
estGrid.set_params(**hyperParamInitParam)
estGrid.fit(x_train,y_train)
bestEstimator = estGrid.best_estimator_
modelFilepath = "/".join(model_filepath.split("/")[:-1])
sklearnHyperParameterResultObj = SklearnGridSearchResult(estGrid.cv_results_,est,x_train,x_test,y_train,y_test,appType,modelFilepath,evaluationMetricDict=evaluationMetricDict)
resultArray = sklearnHyperParameterResultObj.train_and_save_models()
self._result_setter.set_hyper_parameter_results(self._slug,resultArray)
self._result_setter.set_metadata_parallel_coordinates(self._slug,{"ignoreList":sklearnHyperParameterResultObj.get_ignore_list(),"hideColumns":sklearnHyperParameterResultObj.get_hide_columns(),"metricColName":sklearnHyperParameterResultObj.get_comparison_metric_colname(),"columnOrder":sklearnHyperParameterResultObj.get_keep_columns()})
elif hyperParamAlgoName == "randomsearchcv":
estRand = RandomizedSearchCV(est,params_grid)
estRand.set_params(**hyperParamInitParam)
bestEstimator = None
else:
evaluationMetricDict = {"name":GLOBALSETTINGS.REGRESSION_MODEL_EVALUATION_METRIC}
evaluationMetricDict["displayName"] = GLOBALSETTINGS.SKLEARN_EVAL_METRIC_NAME_DISPLAY_MAP[evaluationMetricDict["name"]]
algoParams = algoSetting.get_params_dict()
algoParams = {k:v for k,v in algoParams.items() if k in est.get_params().keys()}
est.set_params(**algoParams)
self._result_setter.set_hyper_parameter_results(self._slug,None)
if validationDict["name"] == "kFold":
defaultSplit = GLOBALSETTINGS.DEFAULT_VALIDATION_OBJECT["value"]
numFold = int(validationDict["value"])
if numFold == 0:
numFold = 3
kFoldClass = SkleanrKFoldResult(numFold,est,x_train,x_test,y_train,y_test,appType,evaluationMetricDict=evaluationMetricDict)
kFoldClass.train_and_save_result()
kFoldOutput = kFoldClass.get_kfold_result()
bestEstimator = kFoldClass.get_best_estimator()
elif validationDict["name"] == "trainAndtest":
est.fit(x_train, y_train)
bestEstimator = est
trainingTime = time.time()-st
y_score = bestEstimator.predict(x_test)
try:
y_prob = bestEstimator.predict_proba(x_test)
except:
y_prob = [0]*len(y_score)
featureImportance={}
objs = {"trained_model":bestEstimator,"actual":y_test,"predicted":y_score,"probability":y_prob,"feature_importance":featureImportance,"featureList":list(x_train.columns),"labelMapping":{}}
featureImportance = objs["trained_model"].feature_importances_
featuresArray = [(col_name, featureImportance[idx]) for idx, col_name in enumerate(x_train.columns)]
if not algoSetting.is_hyperparameter_tuning_enabled():
modelName = "M"+"0"*(GLOBALSETTINGS.MODEL_NAME_MAX_LENGTH-1)+"1"
modelFilepathArr = model_filepath.split("/")[:-1]
modelFilepathArr.append(modelName+".pkl")
joblib.dump(objs["trained_model"],"/".join(modelFilepathArr))
metrics = {}
metrics["r2"] = r2_score(y_test, y_score)
metrics["mse"] = mean_squared_error(y_test, y_score)
metrics["mae"] = mean_absolute_error(y_test, y_score)
metrics["rmse"] = sqrt(metrics["mse"])
transformed = pd.DataFrame({"prediction":y_score,result_column:y_test})
transformed["difference"] = transformed[result_column] - transformed["prediction"]
transformed["mape"] = np.abs(transformed["difference"])*100/transformed[result_column]
sampleData = None
nrows = transformed.shape[0]
if nrows > 100:
sampleData = transformed.sample(n=100,random_state=420)
else:
sampleData = transformed
print sampleData.head()
mapeCountArr = pd.cut(transformed["mape"],GLOBALSETTINGS.MAPEBINS).value_counts().to_dict().items()
mapeStatsArr = [(str(idx),dictObj) for idx,dictObj in enumerate(sorted([{"count":x[1],"splitRange":(x[0].left,x[0].right)} for x in mapeCountArr],key = lambda x:x["splitRange"][0]))]
predictionColSummary = transformed["prediction"].describe().to_dict()
quantileBins = [predictionColSummary["min"],predictionColSummary["25%"],predictionColSummary["50%"],predictionColSummary["75%"],predictionColSummary["max"]]
print quantileBins
quantileBins = sorted(list(set(quantileBins)))
transformed["quantileBinId"] = pd.cut(transformed["prediction"],quantileBins)
quantileDf = transformed.groupby("quantileBinId").agg({"prediction":[np.sum,np.mean,np.size]}).reset_index()
quantileDf.columns = ["prediction","sum","mean","count"]
print quantileDf
quantileArr = quantileDf.T.to_dict().items()
quantileSummaryArr = [(obj[0],{"splitRange":(obj[1]["prediction"].left,obj[1]["prediction"].right),"count":obj[1]["count"],"mean":obj[1]["mean"],"sum":obj[1]["sum"]}) for obj in quantileArr]
print quantileSummaryArr
runtime = round((time.time() - st_global),2)
self._model_summary.set_model_type("regression")
self._model_summary.set_algorithm_name("DTREE Regression")
self._model_summary.set_algorithm_display_name("Decision Tree Regression")
self._model_summary.set_slug(self._slug)
self._model_summary.set_training_time(runtime)
self._model_summary.set_training_time(trainingTime)
self._model_summary.set_target_variable(result_column)
self._model_summary.set_validation_method(validationDict["displayName"])
self._model_summary.set_model_evaluation_metrics(metrics)
self._model_summary.set_model_params(bestEstimator.get_params())
self._model_summary.set_quantile_summary(quantileSummaryArr)
self._model_summary.set_mape_stats(mapeStatsArr)
self._model_summary.set_sample_data(sampleData.to_dict())
self._model_summary.set_feature_importance(featuresArray)
self._model_summary.set_feature_list(list(x_train.columns))
try:
pmml_filepath = str(model_path)+"/"+str(self._slug)+"/traindeModel.pmml"
modelPmmlPipeline = PMMLPipeline([
("pretrained-estimator", objs["trained_model"])
])
modelPmmlPipeline.target_field = result_column
modelPmmlPipeline.active_fields = np.array([col for col in x_train.columns if col != result_column])
sklearn2pmml(modelPmmlPipeline, pmml_filepath, with_repr = True)
pmmlfile = open(pmml_filepath,"r")
pmmlText = pmmlfile.read()
pmmlfile.close()
self._result_setter.update_pmml_object({self._slug:pmmlText})
except:
pass
if not algoSetting.is_hyperparameter_tuning_enabled():
modelDropDownObj = {
"name":self._model_summary.get_algorithm_name(),
"evaluationMetricValue":self._model_summary.get_model_accuracy(),
"evaluationMetricName":"r2",
"slug":self._model_summary.get_slug(),
"Model Id":modelName
}
modelSummaryJson = {
"dropdown":modelDropDownObj,
"levelcount":self._model_summary.get_level_counts(),
"modelFeatureList":self._model_summary.get_feature_list(),
"levelMapping":self._model_summary.get_level_map_dict(),
"slug":self._model_summary.get_slug(),
"name":self._model_summary.get_algorithm_name()
}
else:
modelDropDownObj = {
"name":self._model_summary.get_algorithm_name(),
"evaluationMetricValue":resultArray[0]["R-Squared"],
"evaluationMetricName":"r2",
"slug":self._model_summary.get_slug(),
"Model Id":resultArray[0]["Model Id"]
}
modelSummaryJson = {
"dropdown":modelDropDownObj,
"levelcount":self._model_summary.get_level_counts(),
"modelFeatureList":self._model_summary.get_feature_list(),
"levelMapping":self._model_summary.get_level_map_dict(),
"slug":self._model_summary.get_slug(),
"name":self._model_summary.get_algorithm_name()
}
dtreerCards = [json.loads(CommonUtils.convert_python_object_to_json(cardObj)) for cardObj in MLUtils.create_model_summary_cards(self._model_summary)]
for card in dtreerCards:
self._prediction_narrative.add_a_card(card)
self._result_setter.set_model_summary({"dtreeregression":json.loads(CommonUtils.convert_python_object_to_json(self._model_summary))})
self._result_setter.set_dtree_regression_model_summart(modelSummaryJson)
self._result_setter.set_dtreer_cards(dtreerCards)
CommonUtils.create_update_and_save_progress_message(self._dataframe_context,self._scriptWeightDict,self._scriptStages,self._slug,"completion","info",display=True,emptyBin=False,customMsg=None,weightKey="total")
def Train(self):
st_global = time.time()
algosToRun = self._dataframe_context.get_algorithms_to_run()
algoSetting = filter(lambda x:x["algorithmSlug"]==GLOBALSETTINGS.MODEL_SLUG_MAPPING["generalizedlinearregression"],algosToRun)[0]
categorical_columns = self._dataframe_helper.get_string_columns()
uid_col = self._dataframe_context.get_uid_column()
if self._metaParser.check_column_isin_ignored_suggestion(uid_col):
categorical_columns = list(set(categorical_columns) - {uid_col})
allDateCols = self._dataframe_context.get_date_columns()
categorical_columns = list(set(categorical_columns)-set(allDateCols))
print categorical_columns
result_column = self._dataframe_context.get_result_column()
numerical_columns = self._dataframe_helper.get_numeric_columns()
numerical_columns = [x for x in numerical_columns if x != result_column]
model_path = self._dataframe_context.get_model_path()
if model_path.startswith("file"):
model_path = model_path[7:]
validationDict = self._dataframe_context.get_validation_dict()
print "model_path",model_path
pipeline_filepath = "file://"+str(model_path)+"/"+str(self._slug)+"/pipeline/"
model_filepath = "file://"+str(model_path)+"/"+str(self._slug)+"/model"
pmml_filepath = "file://"+str(model_path)+"/"+str(self._slug)+"/modelPmml"
df = self._data_frame
pipeline = MLUtils.create_pyspark_ml_pipeline(numerical_columns,categorical_columns,result_column,algoType="regression")
pipelineModel = pipeline.fit(df)
indexed = pipelineModel.transform(df)
featureMapping = sorted((attr["idx"], attr["name"]) for attr in (chain(*indexed.schema["features"].metadata["ml_attr"]["attrs"].values())))
# print indexed.select([result_column,"features"]).show(5)
MLUtils.save_pipeline_or_model(pipelineModel,pipeline_filepath)
glinr = GeneralizedLinearRegression(labelCol=result_column, featuresCol='features',predictionCol="prediction")
if validationDict["name"] == "kFold":
defaultSplit = GLOBALSETTINGS.DEFAULT_VALIDATION_OBJECT["value"]
numFold = int(validationDict["value"])
if numFold == 0:
numFold = 3
trainingData,validationData = indexed.randomSplit([defaultSplit,1-defaultSplit], seed=12345)
paramGrid = ParamGridBuilder()\
.addGrid(glinr.regParam, [0.1, 0.01]) \
.addGrid(glinr.fitIntercept, [False, True])\
.build()
crossval = CrossValidator(estimator=glinr,
estimatorParamMaps=paramGrid,
evaluator=RegressionEvaluator(predictionCol="prediction", labelCol=result_column),
numFolds=numFold)
st = time.time()
cvModel = crossval.fit(indexed)
trainingTime = time.time()-st
print "cvModel training takes",trainingTime
bestModel = cvModel.bestModel
elif validationDict["name"] == "trainAndtest":
trainingData,validationData = indexed.randomSplit([float(validationDict["value"]),1-float(validationDict["value"])], seed=12345)
st = time.time()
fit = glinr.fit(trainingData)
trainingTime = time.time()-st
print "time to train",trainingTime
bestModel = fit
print bestModel.explainParams()
print bestModel.extractParamMap()
print bestModel.params
print 'Best Param (regParam): ', bestModel._java_obj.getRegParam()
print 'Best Param (MaxIter): ', bestModel._java_obj.getMaxIter()
# modelPmmlPipeline = PMMLPipeline([
# ("pretrained-estimator", objs["trained_model"])
# ])
# try:
# modelPmmlPipeline.target_field = result_column
# modelPmmlPipeline.active_fields = np.array([col for col in x_train.columns if col != result_column])
# sklearn2pmml(modelPmmlPipeline, pmml_filepath, with_repr = True)
# pmmlfile = open(pmml_filepath,"r")
# pmmlText = pmmlfile.read()
# pmmlfile.close()
# self._result_setter.update_pmml_object({self._slug:pmmlText})
# except:
# pass
coefficientsArray = [(name, bestModel.coefficients[idx]) for idx, name in featureMapping]
MLUtils.save_pipeline_or_model(bestModel,model_filepath)
transformed = bestModel.transform(validationData)
transformed = transformed.withColumn(result_column,transformed[result_column].cast(DoubleType()))
transformed = transformed.select([result_column,"prediction",transformed[result_column]-transformed["prediction"]])
transformed = transformed.withColumnRenamed(transformed.columns[-1],"difference")
transformed = transformed.select([result_column,"prediction","difference",FN.abs(transformed["difference"])*100/transformed[result_column]])
transformed = transformed.withColumnRenamed(transformed.columns[-1],"mape")
sampleData = None
nrows = transformed.count()
if nrows > 100:
sampleData = transformed.sample(False, float(100)/nrows, seed=420)
else:
sampleData = transformed
print sampleData.show()
evaluator = RegressionEvaluator(predictionCol="prediction",labelCol=result_column)
metrics = {}
metrics["r2"] = evaluator.evaluate(transformed,{evaluator.metricName: "r2"})
metrics["rmse"] = evaluator.evaluate(transformed,{evaluator.metricName: "rmse"})
metrics["mse"] = evaluator.evaluate(transformed,{evaluator.metricName: "mse"})
metrics["mae"] = evaluator.evaluate(transformed,{evaluator.metricName: "mae"})
runtime = round((time.time() - st_global),2)
# print transformed.count()
mapeDf = transformed.select("mape")
# print mapeDf.show()
mapeStats = MLUtils.get_mape_stats(mapeDf,"mape")
mapeStatsArr = mapeStats.items()
mapeStatsArr = sorted(mapeStatsArr,key=lambda x:int(x[0]))
# print mapeStatsArr
quantileDf = transformed.select("prediction")
# print quantileDf.show()
quantileSummaryDict = MLUtils.get_quantile_summary(quantileDf,"prediction")
quantileSummaryArr = quantileSummaryDict.items()
quantileSummaryArr = sorted(quantileSummaryArr,key=lambda x:int(x[0]))
# print quantileSummaryArr
self._model_summary.set_model_type("regression")
self._model_summary.set_algorithm_name("Generalized Linear Regression")
self._model_summary.set_algorithm_display_name("Generalized Linear Regression")
self._model_summary.set_slug(self._slug)
self._model_summary.set_training_time(runtime)
self._model_summary.set_training_time(trainingTime)
self._model_summary.set_target_variable(result_column)
self._model_summary.set_validation_method(validationDict["displayName"])
self._model_summary.set_model_evaluation_metrics(metrics)
self._model_summary.set_model_params(bestEstimator.get_params())
self._model_summary.set_quantile_summary(quantileSummaryArr)
self._model_summary.set_mape_stats(mapeStatsArr)
self._model_summary.set_sample_data(sampleData.toPandas().to_dict())
self._model_summary.set_coefficinets_array(coefficientsArray)
self._model_summary.set_feature_list(list(x_train.columns))
# print CommonUtils.convert_python_object_to_json(self._model_summary)
modelSummaryJson = {
"dropdown":{
"name":self._model_summary.get_algorithm_name(),
"accuracy":CommonUtils.round_sig(self._model_summary.get_model_evaluation_metrics()["r2"]),
"slug":self._model_summary.get_slug()
},
"levelcount":self._model_summary.get_level_counts(),
"modelFeatureList":self._model_summary.get_feature_list(),
"levelMapping":self._model_summary.get_level_map_dict()
}
glinrCards = [json.loads(CommonUtils.convert_python_object_to_json(cardObj)) for cardObj in MLUtils.create_model_summary_cards(self._model_summary)]
for card in glinrCards:
self._prediction_narrative.add_a_card(card)
self._result_setter.set_model_summary({"generalizedlinearregression":json.loads(CommonUtils.convert_python_object_to_json(self._model_summary))})
self._result_setter.set_generalized_linear_regression_model_summary(modelSummaryJson)
self._result_setter.set_glinr_cards(glinrCards)