def train_forPMML(sparkUrl, dataForTrainPath, savePath):
# 取得模型存儲路徑
brp_path, model_path = get_model_save_path(savePath)
# 載入數據
sc = get_conf(sparkUrl, 'LSH_train', "8g")
df = load_sentence_data_frame(sc, dataForTrainPath)
# 開始訓練模型
brp = BucketedRandomProjectionLSH() \
.setBucketLength(BUCKET_LENGTH) \
.setNumHashTables(NUM_HASH_TABLES) \
.setInputCol("vector") \
.setOutputCol("hash")
# 流水線: 先提取特徵, 再訓練模型
pipeline = Pipeline(stages=[brp])
pipeline_model = pipeline.fit(df)
# 顯示大概結果
# pipeline_model.transform(df).show()
# 存儲模型至PMML
pmmlBuilder = PMMLBuilder(sc, df, pipeline_model)
pmmlBuilder.buildFile("~/pmmlModels/SM.pmml")
return
def testWorkflow(self):
df = self.sqlContext.read.csv(os.path.join(os.path.dirname(__file__), "resources/Iris.csv"), header = True, inferSchema = True)
formula = RFormula(formula = "Species ~ .")
classifier = DecisionTreeClassifier()
pipeline = Pipeline(stages = [formula, classifier])
pipelineModel = pipeline.fit(df)
pmmlBuilder = PMMLBuilder(self.sc, df, pipelineModel) \
.verify(df.sample(False, 0.1))
pmml = pmmlBuilder.build()
self.assertIsInstance(pmml, JavaObject)
pmmlByteArray = pmmlBuilder.buildByteArray()
self.assertIsInstance(pmmlByteArray, bytes)
pmmlString = pmmlByteArray.decode("UTF-8")
self.assertTrue("<PMML xmlns=\"http://www.dmg.org/PMML-4_3\" xmlns:data=\"http://jpmml.org/jpmml-model/InlineTable\" version=\"4.3\">" in pmmlString)
self.assertTrue("<VerificationFields>" in pmmlString)
pmmlBuilder = pmmlBuilder.putOption(classifier, "compact", False)
nonCompactFile = tempfile.NamedTemporaryFile(prefix = "pyspark2pmml-", suffix = ".pmml")
nonCompactPmmlPath = pmmlBuilder.buildFile(nonCompactFile.name)
pmmlBuilder = pmmlBuilder.putOption(classifier, "compact", True)
compactFile = tempfile.NamedTemporaryFile(prefix = "pyspark2pmml-", suffix = ".pmml")
compactPmmlPath = pmmlBuilder.buildFile(compactFile.name)
self.assertGreater(os.path.getsize(nonCompactPmmlPath), os.path.getsize(compactPmmlPath) + 100)
def save_pmml(self, pmml_dir: str) -> str:
try:
metadata_dir = f"{self.pipeline_dir}/metadata"
metadata_path = self.path(metadata_dir)
if self.fs.exists(metadata_path):
self.fs.delete(metadata_path)
if self.fs.exists(self.path(pmml_dir)):
self.fs.delete(self.path(pmml_dir))
self.sc.parallelize([self._metadata(self.stage_uids)],
1).saveAsTextFile(metadata_dir)
pipeline_model: PipelineModel = PipelineModel.load(
self.pipeline_dir)
pmml_builder = PMMLBuilder(self.spark, self.df, pipeline_model)
self.sc.parallelize([pmml_builder.buildByteArray()],
1).saveAsTextFile(pmml_dir)
except Exception as e:
raise PySparkLibError(e)
return pmml_dir
def testWorkflow(self):
df = self.sqlContext.read.csv(os.path.join(os.path.dirname(__file__),
"resources/Iris.csv"),
header=True,
inferSchema=True)
formula = RFormula(formula="Species ~ .")
classifier = DecisionTreeClassifier()
pipeline = Pipeline(stages=[formula, classifier])
pipelineModel = pipeline.fit(df)
pmmlBuilder = PMMLBuilder(self.sc, df, pipelineModel) \
.putOption(classifier, "compact", True)
pmmlBytes = pmmlBuilder.buildByteArray()
pmmlString = pmmlBytes.decode("UTF-8")
self.assertTrue(
pmmlString.find(
"<PMML xmlns=\"http://www.dmg.org/PMML-4_3\" version=\"4.3\">")
> -1)
class_index = StringIndexer(inputCol='class', outputCol='label')
vector = VectorAssembler(inputCols=feature_cols, outputCol='feature')
model = LinearSVC(featuresCol='feature', labelCol='label')
pipeline = Pipeline(stages=[class_index, vector, model])
pipeline = pipeline.fit(train)
if os.path.exists(MODEL_SAVE_PATH):
shutil.rmtree(MODEL_SAVE_PATH)
pipeline.write().overwrite().save(pipeline) # pipeline.save('/to/path')
load_pipeline = PipelineModel.load('pipeline')
test_predict = load_pipeline.transform(test)
evaluator = BinaryClassificationEvaluator(rawPredictionCol='rawPrediction',
labelCol='label')
print(evaluator.evaluate(test_predict, {evaluator.metricName: 'areaUnderROC'}))
print(evaluator.evaluate(test_predict, {evaluator.metricName: 'areaUnderPR'}))
origin_test_df = df.select(feature_cols)
predict_df = load_pipeline.transform(origin_test_df)
print(predict_df.show(20))
from pyspark2pmml import PMMLBuilder
sc = spark.sparkContext.getOrCreate()
pmmlBuilder = PMMLBuilder(sc, df,
load_pipeline).putOption(load_pipeline.stages[-1],
"compact", True)
pmmlBuilder.buildFile("LinearSVC.pmml")
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")
algosToRun = self._dataframe_context.get_algorithms_to_run()
algoSetting = [
x for x in algosToRun if x.get_algorithm_slug() == self._slug
][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))
numerical_columns = self._dataframe_helper.get_numeric_columns()
result_column = self._dataframe_context.get_result_column()
categorical_columns = [
x for x in categorical_columns if x != result_column
]
appType = self._dataframe_context.get_app_type()
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
levels = df.select(result_column).distinct().count()
appType = self._dataframe_context.get_app_type()
model_filepath = model_path + "/" + self._slug + "/model"
pmml_filepath = str(model_path) + "/" + str(
self._slug) + "/traindeModel.pmml"
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")
st = time.time()
pipeline = MLUtils.create_pyspark_ml_pipeline(numerical_columns,
categorical_columns,
result_column)
trainingData, validationData = MLUtils.get_training_and_validation_data(
df, result_column, 0.8) # indexed
labelIndexer = StringIndexer(inputCol=result_column, outputCol="label")
# OriginalTargetconverter = IndexToString(inputCol="label", outputCol="originalTargetColumn")
# Label Mapping and Inverse
labelIdx = labelIndexer.fit(trainingData)
labelMapping = {k: v for k, v in enumerate(labelIdx.labels)}
inverseLabelMapping = {
v: float(k)
for k, v in enumerate(labelIdx.labels)
}
if self._dataframe_context.get_trainerMode() == "autoML":
automl_enable = True
else:
automl_enable = False
clf = NaiveBayes()
if not algoSetting.is_hyperparameter_tuning_enabled():
algoParams = algoSetting.get_params_dict()
else:
algoParams = algoSetting.get_params_dict_hyperparameter()
print("=" * 100)
print(algoParams)
print("=" * 100)
clfParams = [prm.name for prm in clf.params]
algoParams = {
getattr(clf, k): v if isinstance(v, list) else [v]
for k, v in algoParams.items() if k in clfParams
}
#print("="*100)
#print("ALGOPARAMS - ",algoParams)
#print("="*100)
paramGrid = ParamGridBuilder()
# if not algoSetting.is_hyperparameter_tuning_enabled():
# for k,v in algoParams.items():
# if v == [None] * len(v):
# continue
# if k.name == 'thresholds':
# paramGrid = paramGrid.addGrid(k,v[0])
# else:
# paramGrid = paramGrid.addGrid(k,v)
# paramGrid = paramGrid.build()
# if not algoSetting.is_hyperparameter_tuning_enabled():
for k, v in algoParams.items():
print(k, v)
if v == [None] * len(v):
continue
paramGrid = paramGrid.addGrid(k, v)
paramGrid = paramGrid.build()
# else:
# for k,v in algoParams.items():
# print k.name, v
# if v[0] == [None] * len(v[0]):
# continue
# paramGrid = paramGrid.addGrid(k,v[0])
# paramGrid = paramGrid.build()
#print("="*143)
#print("PARAMGRID - ", paramGrid)
#print("="*143)
if len(paramGrid) > 1:
hyperParamInitParam = algoSetting.get_hyperparameter_params()
evaluationMetricDict = {
"name": hyperParamInitParam["evaluationMetric"]
}
evaluationMetricDict[
"displayName"] = GLOBALSETTINGS.SKLEARN_EVAL_METRIC_NAME_DISPLAY_MAP[
evaluationMetricDict["name"]]
else:
evaluationMetricDict = {
"name": GLOBALSETTINGS.CLASSIFICATION_MODEL_EVALUATION_METRIC
}
evaluationMetricDict[
"displayName"] = GLOBALSETTINGS.SKLEARN_EVAL_METRIC_NAME_DISPLAY_MAP[
evaluationMetricDict["name"]]
self._result_setter.set_hyper_parameter_results(self._slug, None)
if validationDict["name"] == "kFold":
numFold = int(validationDict["value"])
estimator = Pipeline(stages=[pipeline, labelIndexer, clf])
if algoSetting.is_hyperparameter_tuning_enabled():
modelFilepath = "/".join(model_filepath.split("/")[:-1])
pySparkHyperParameterResultObj = PySparkGridSearchResult(
estimator, paramGrid, appType, modelFilepath, levels,
evaluationMetricDict, trainingData, validationData,
numFold, self._targetLevel, labelMapping,
inverseLabelMapping, df)
resultArray = pySparkHyperParameterResultObj.train_and_save_classification_models(
)
self._result_setter.set_hyper_parameter_results(
self._slug, resultArray)
self._result_setter.set_metadata_parallel_coordinates(
self._slug, {
"ignoreList":
pySparkHyperParameterResultObj.get_ignore_list(),
"hideColumns":
pySparkHyperParameterResultObj.get_hide_columns(),
"metricColName":
pySparkHyperParameterResultObj.
get_comparison_metric_colname(),
"columnOrder":
pySparkHyperParameterResultObj.get_keep_columns()
})
bestModel = pySparkHyperParameterResultObj.getBestModel()
prediction = pySparkHyperParameterResultObj.getBestPrediction()
else:
if automl_enable:
paramGrid = (ParamGridBuilder().addGrid(
clf.smoothing, [1.0, 0.2]).build())
crossval = CrossValidator(
estimator=estimator,
estimatorParamMaps=paramGrid,
evaluator=BinaryClassificationEvaluator()
if levels == 2 else MulticlassClassificationEvaluator(),
numFolds=3 if numFold is None else
numFold) # use 3+ folds in practice
cvnb = crossval.fit(trainingData)
prediction = cvnb.transform(validationData)
bestModel = cvnb.bestModel
else:
train_test_ratio = float(
self._dataframe_context.get_train_test_split())
estimator = Pipeline(stages=[pipeline, labelIndexer, clf])
if algoSetting.is_hyperparameter_tuning_enabled():
modelFilepath = "/".join(model_filepath.split("/")[:-1])
pySparkHyperParameterResultObj = PySparkTrainTestResult(
estimator, paramGrid, appType, modelFilepath, levels,
evaluationMetricDict, trainingData, validationData,
train_test_ratio, self._targetLevel, labelMapping,
inverseLabelMapping, df)
resultArray = pySparkHyperParameterResultObj.train_and_save_classification_models(
)
self._result_setter.set_hyper_parameter_results(
self._slug, resultArray)
self._result_setter.set_metadata_parallel_coordinates(
self._slug, {
"ignoreList":
pySparkHyperParameterResultObj.get_ignore_list(),
"hideColumns":
pySparkHyperParameterResultObj.get_hide_columns(),
"metricColName":
pySparkHyperParameterResultObj.
get_comparison_metric_colname(),
"columnOrder":
pySparkHyperParameterResultObj.get_keep_columns()
})
bestModel = pySparkHyperParameterResultObj.getBestModel()
prediction = pySparkHyperParameterResultObj.getBestPrediction()
else:
tvs = TrainValidationSplit(
estimator=estimator,
estimatorParamMaps=paramGrid,
evaluator=BinaryClassificationEvaluator()
if levels == 2 else MulticlassClassificationEvaluator(),
trainRatio=train_test_ratio)
tvspnb = tvs.fit(trainingData)
prediction = tvspnb.transform(validationData)
bestModel = tvspnb.bestModel
modelmanagement_ = {
param[0].name: param[1]
for param in bestModel.stages[2].extractParamMap().items()
}
MLUtils.save_pipeline_or_model(bestModel, model_filepath)
predsAndLabels = prediction.select(['prediction',
'label']).rdd.map(tuple)
# label_classes = prediction.select("label").distinct().collect()
# label_classes = prediction.agg((F.collect_set('label').alias('label'))).first().asDict()['label']
#results = transformed.select(["prediction","label"])
# if len(label_classes) > 2:
# metrics = MulticlassMetrics(predsAndLabels) # accuracy of the model
# else:
# metrics = BinaryClassificationMetrics(predsAndLabels)
posLabel = inverseLabelMapping[self._targetLevel]
metrics = MulticlassMetrics(predsAndLabels)
trainingTime = time.time() - st
f1_score = metrics.fMeasure(inverseLabelMapping[self._targetLevel],
1.0)
precision = metrics.precision(inverseLabelMapping[self._targetLevel])
recall = metrics.recall(inverseLabelMapping[self._targetLevel])
accuracy = metrics.accuracy
print(f1_score, precision, recall, accuracy)
#gain chart implementation
def cal_prob_eval(x):
if len(x) == 1:
if x == posLabel:
return (float(x[1]))
else:
return (float(1 - x[1]))
else:
return (float(x[int(posLabel)]))
column_name = 'probability'
def y_prob_for_eval_udf():
return udf(lambda x: cal_prob_eval(x))
prediction = prediction.withColumn(
"y_prob_for_eval",
y_prob_for_eval_udf()(col(column_name)))
try:
pys_df = prediction.select(
['y_prob_for_eval', 'prediction', 'label'])
gain_lift_ks_obj = GainLiftKS(pys_df, 'y_prob_for_eval',
'prediction', 'label', posLabel,
self._spark)
gain_lift_KS_dataframe = gain_lift_ks_obj.Run().toPandas()
except:
try:
temp_df = pys_df.toPandas()
gain_lift_ks_obj = GainLiftKS(temp_df, 'y_prob_for_eval',
'prediction', 'label', posLabel,
self._spark)
gain_lift_KS_dataframe = gain_lift_ks_obj.Rank_Ordering()
except:
print("gain chant failed")
gain_lift_KS_dataframe = None
#feature_importance = MLUtils.calculate_sparkml_feature_importance(df, bestModel.stages[-1], categorical_columns, numerical_columns)
act_list = prediction.select('label').collect()
actual = [int(row.label) for row in act_list]
pred_list = prediction.select('prediction').collect()
predicted = [int(row.prediction) for row in pred_list]
prob_list = prediction.select('probability').collect()
probability = [list(row.probability) for row in prob_list]
# objs = {"trained_model":bestModel,"actual":prediction.select('label'),"predicted":prediction.select('prediction'),
# "probability":prediction.select('probability'),"feature_importance":None,
# "featureList":list(categorical_columns) + list(numerical_columns),"labelMapping":labelMapping}
objs = {
"trained_model": bestModel,
"actual": actual,
"predicted": predicted,
"probability": probability,
"feature_importance": None,
"featureList": list(categorical_columns) + list(numerical_columns),
"labelMapping": labelMapping
}
conf_mat_ar = metrics.confusionMatrix().toArray()
print(conf_mat_ar)
confusion_matrix = {}
for i in range(len(conf_mat_ar)):
confusion_matrix[labelMapping[i]] = {}
for j, val in enumerate(conf_mat_ar[i]):
confusion_matrix[labelMapping[i]][labelMapping[j]] = val
print(confusion_matrix) # accuracy of the model
'''ROC CURVE IMPLEMENTATION'''
y_prob = probability
y_score = predicted
y_test = actual
logLoss = log_loss(y_test, y_prob)
if levels <= 2:
positive_label_probs = []
for val in y_prob:
positive_label_probs.append(val[int(posLabel)])
roc_auc = roc_auc_score(y_test, y_score)
roc_data_dict = {
"y_score": y_score,
"y_test": y_test,
"positive_label_probs": positive_label_probs,
"y_prob": y_prob,
"positive_label": posLabel
}
roc_dataframe = pd.DataFrame({
"y_score":
y_score,
"y_test":
y_test,
"positive_label_probs":
positive_label_probs
})
#roc_dataframe.to_csv("binary_roc_data.csv")
fpr, tpr, thresholds = roc_curve(y_test,
positive_label_probs,
pos_label=posLabel)
roc_df = pd.DataFrame({
"FPR": fpr,
"TPR": tpr,
"thresholds": thresholds
})
roc_df["tpr-fpr"] = roc_df["TPR"] - roc_df["FPR"]
optimal_index = np.argmax(np.array(roc_df["tpr-fpr"]))
fpr_optimal_index = roc_df.loc[roc_df.index[optimal_index], "FPR"]
tpr_optimal_index = roc_df.loc[roc_df.index[optimal_index], "TPR"]
rounded_roc_df = roc_df.round({'FPR': 2, 'TPR': 4})
unique_fpr = rounded_roc_df["FPR"].unique()
final_roc_df = rounded_roc_df.groupby("FPR",
as_index=False)[["TPR"
]].mean()
endgame_roc_df = final_roc_df.round({'FPR': 2, 'TPR': 3})
elif levels > 2:
positive_label_probs = []
for val in y_prob:
positive_label_probs.append(val[int(posLabel)])
y_test_roc_multi = []
for val in y_test:
if val != posLabel:
val = posLabel + 1
y_test_roc_multi.append(val)
else:
y_test_roc_multi.append(val)
y_score_roc_multi = []
for val in y_score:
if val != posLabel:
val = posLabel + 1
y_score_roc_multi.append(val)
else:
y_score_roc_multi.append(val)
roc_auc = roc_auc_score(y_test_roc_multi, y_score_roc_multi)
fpr, tpr, thresholds = roc_curve(y_test_roc_multi,
positive_label_probs,
pos_label=posLabel)
roc_df = pd.DataFrame({
"FPR": fpr,
"TPR": tpr,
"thresholds": thresholds
})
roc_df["tpr-fpr"] = roc_df["TPR"] - roc_df["FPR"]
optimal_index = np.argmax(np.array(roc_df["tpr-fpr"]))
fpr_optimal_index = roc_df.loc[roc_df.index[optimal_index], "FPR"]
tpr_optimal_index = roc_df.loc[roc_df.index[optimal_index], "TPR"]
rounded_roc_df = roc_df.round({'FPR': 2, 'TPR': 4})
unique_fpr = rounded_roc_df["FPR"].unique()
final_roc_df = rounded_roc_df.groupby("FPR",
as_index=False)[["TPR"
]].mean()
endgame_roc_df = final_roc_df.round({'FPR': 2, 'TPR': 3})
# Calculating prediction_split
val_cnts = prediction.groupBy('label').count()
val_cnts = map(lambda row: row.asDict(), val_cnts.collect())
prediction_split = {}
total_nos = prediction.select('label').count()
for item in val_cnts:
print(labelMapping)
classname = labelMapping[item['label']]
prediction_split[classname] = round(
item['count'] * 100 / float(total_nos), 2)
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)
bestModel.save("/".join(modelFilepathArr))
runtime = round((time.time() - st_global), 2)
try:
print(pmml_filepath)
pmmlBuilder = PMMLBuilder(self._spark, trainingData,
bestModel).putOption(
clf, 'compact', True)
pmmlBuilder.buildFile(pmml_filepath)
pmmlfile = open(pmml_filepath, "r")
pmmlText = pmmlfile.read()
pmmlfile.close()
self._result_setter.update_pmml_object({self._slug: pmmlText})
except Exception as e:
print("PMML failed...", str(e))
pass
cat_cols = list(set(categorical_columns) - {result_column})
self._model_summary = MLModelSummary()
self._model_summary.set_algorithm_name("Naive Bayes")
self._model_summary.set_algorithm_display_name("Naive Bayes")
self._model_summary.set_slug(self._slug)
self._model_summary.set_training_time(runtime)
self._model_summary.set_confusion_matrix(confusion_matrix)
# self._model_summary.set_feature_importance(objs["feature_importance"])
self._model_summary.set_feature_list(objs["featureList"])
self._model_summary.set_model_accuracy(accuracy)
self._model_summary.set_training_time(round((time.time() - st), 2))
self._model_summary.set_precision_recall_stats([precision, recall])
self._model_summary.set_model_precision(precision)
self._model_summary.set_model_recall(recall)
self._model_summary.set_model_F1_score(f1_score)
self._model_summary.set_model_log_loss(logLoss)
self._model_summary.set_gain_lift_KS_data(gain_lift_KS_dataframe)
self._model_summary.set_AUC_score(roc_auc)
self._model_summary.set_target_variable(result_column)
self._model_summary.set_prediction_split(prediction_split)
self._model_summary.set_validation_method("KFold")
self._model_summary.set_level_map_dict(objs["labelMapping"])
# self._model_summary.set_model_features(list(set(x_train.columns)-set([result_column])))
self._model_summary.set_model_features(objs["featureList"])
self._model_summary.set_level_counts(
self._metaParser.get_unique_level_dict(
list(set(categorical_columns)) + [result_column]))
#self._model_summary.set_num_trees(objs['trained_model'].getNumTrees)
self._model_summary.set_num_rules(300)
self._model_summary.set_target_level(self._targetLevel)
if not algoSetting.is_hyperparameter_tuning_enabled():
modelDropDownObj = {
"name": self._model_summary.get_algorithm_name(),
"evaluationMetricValue": accuracy,
"evaluationMetricName": "accuracy",
"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": accuracy,
"evaluationMetricName": "accuracy",
"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()
}
self._model_management = MLModelSummary()
print(modelmanagement_)
self._model_management.set_job_type(
self._dataframe_context.get_job_name()) #Project name
self._model_management.set_training_status(
data="completed") # training status
self._model_management.set_target_level(
self._targetLevel) # target column value
self._model_management.set_training_time(runtime) # run time
self._model_management.set_model_accuracy(round(metrics.accuracy, 2))
# self._model_management.set_model_accuracy(round(metrics.accuracy_score(objs["actual"], objs["predicted"]),2))#accuracy
self._model_management.set_algorithm_name(
"NaiveBayes") #algorithm name
self._model_management.set_validation_method(
str(validationDict["displayName"]) + "(" +
str(validationDict["value"]) + ")") #validation method
self._model_management.set_target_variable(
result_column) #target column name
self._model_management.set_creation_date(data=str(
datetime.now().strftime('%b %d ,%Y %H:%M '))) #creation date
self._model_management.set_datasetName(self._datasetName)
self._model_management.set_model_type(data='classification')
self._model_management.set_var_smoothing(
data=int(modelmanagement_['smoothing']))
# self._model_management.set_no_of_independent_variables(df) #no of independent varables
modelManagementSummaryJson = [
["Project Name",
self._model_management.get_job_type()],
["Algorithm",
self._model_management.get_algorithm_name()],
["Training Status",
self._model_management.get_training_status()],
["Accuracy",
self._model_management.get_model_accuracy()],
["RunTime", self._model_management.get_training_time()],
#["Owner",None],
["Created On",
self._model_management.get_creation_date()]
]
modelManagementModelSettingsJson = [
["Training Dataset",
self._model_management.get_datasetName()],
["Target Column",
self._model_management.get_target_variable()],
["Target Column Value",
self._model_management.get_target_level()],
["Algorithm",
self._model_management.get_algorithm_name()],
[
"Model Validation",
self._model_management.get_validation_method()
],
["Model Type",
self._model_management.get_model_type()],
["Smoothing",
self._model_management.get_var_smoothing()],
#,["priors",self._model_management.get_priors()]
#,["var_smoothing",self._model_management.get_var_smoothing()]
]
nbOverviewCards = [
json.loads(CommonUtils.convert_python_object_to_json(cardObj))
for cardObj in MLUtils.create_model_management_card_overview(
self._model_management, modelManagementSummaryJson,
modelManagementModelSettingsJson)
]
nbPerformanceCards = [
json.loads(CommonUtils.convert_python_object_to_json(cardObj))
for cardObj in MLUtils.create_model_management_cards(
self._model_summary, endgame_roc_df)
]
nbDeploymentCards = [
json.loads(CommonUtils.convert_python_object_to_json(cardObj))
for cardObj in MLUtils.create_model_management_deploy_empty_card()
]
nbCards = [
json.loads(CommonUtils.convert_python_object_to_json(cardObj)) for
cardObj in MLUtils.create_model_summary_cards(self._model_summary)
]
NB_Overview_Node = NarrativesTree()
NB_Overview_Node.set_name("Overview")
NB_Performance_Node = NarrativesTree()
NB_Performance_Node.set_name("Performance")
NB_Deployment_Node = NarrativesTree()
NB_Deployment_Node.set_name("Deployment")
for card in nbOverviewCards:
NB_Overview_Node.add_a_card(card)
for card in nbPerformanceCards:
NB_Performance_Node.add_a_card(card)
for card in nbDeploymentCards:
NB_Deployment_Node.add_a_card(card)
for card in nbCards:
self._prediction_narrative.add_a_card(card)
self._result_setter.set_model_summary({
"naivebayes":
json.loads(
CommonUtils.convert_python_object_to_json(self._model_summary))
})
self._result_setter.set_naive_bayes_model_summary(modelSummaryJson)
self._result_setter.set_nb_cards(nbCards)
self._result_setter.set_nb_nodes(
[NB_Overview_Node, NB_Performance_Node, NB_Deployment_Node])
self._result_setter.set_nb_fail_card({
"Algorithm_Name": "Naive Bayes",
"success": "True"
})
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")
print("\n\n")
data = assembler.transform(df).select(['features', label_col]).withColumnRenamed(label_col, 'label')
data_java = _py2java(sc, data)
iso_class = sc._jvm.com.linkedin.relevance.isolationforest.IsolationForest
isolation = iso_class() \
.setNumEstimators(100) \
.setBootstrap(False) \
.setMaxFeatures(1.0) \
.setFeaturesCol("features") \
.setPredictionCol("predictedLabel") \
.setScoreCol("outlierScore") \
.setContamination(0.1) \
.setContaminationError(0.01 * 0.1) \
.setRandomSeed(1)
isolation_model = isolation.fit(data_java)
data_with_score = isolation_model.transform(data_java)
if os.path.exists(MODEL_SAVE_PATH):
shutil.rmtree(MODEL_SAVE_PATH)
isolation_model.write().overwrite().save(MODEL_SAVE_PATH)
print(data_with_score.show())
from pyspark2pmml import PMMLBuilder
sc = spark.sparkContext.getOrCreate()
pmmlBuilder = PMMLBuilder(sc, df, isolation_model).putOption(isolation_model, "compact", True)
pmmlBuilder.buildFile("isolation.pmml")
from pyspark.ml import Pipeline
from pyspark.ml.classification import DecisionTreeClassifier
from pyspark.ml.feature import RFormula
df = spark.read.csv("Iris.csv", header = True, inferSchema = True)
formula = RFormula(formula = "Species ~ .")
classifier = DecisionTreeClassifier()
pipeline = Pipeline(stages = [formula, classifier])
pipelineModel = pipeline.fit(df)
from pyspark2pmml import PMMLBuilder
pmmlBuilder = PMMLBuilder(sc, df, pipelineModel)
pmmlBuilder.buildFile("DecisionTreeIris.pmml")
conf = conf.setMaster("local")
sc = SparkContext(conf=conf)
# 加载sklearn的训练数据
iris = load_iris()
# 特征矩阵
features = pandas.DataFrame(iris.data, columns=iris.feature_names)
# 目标矩阵
targets = pandas.DataFrame(iris.target, columns=['Species'])
# 合并矩阵
merged = pandas.concat([features, targets], axis=1)
# 创建SparkSession
sess = SparkSession(sc)
# 创建spark DataFrame
raw_df = sess.createDataFrame(merged)
# 特征提取
fomula = RFormula(formula='Species ~ .')
# 创建LR分类器
lr = LogisticRegression()
# 流水线: 先提取特征, 再训练模型
pipeline = Pipeline(stages=[fomula, lr])
pipeline_model = pipeline.fit(raw_df)
# 导出PMML
pmmlBuilder = PMMLBuilder(sc, raw_df, pipeline_model)
pmmlBuilder.buildFile("lr.pmml")
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")
algosToRun = self._dataframe_context.get_algorithms_to_run()
algoSetting = [x for x in algosToRun if x.get_algorithm_slug()==self._slug][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))
numerical_columns = self._dataframe_helper.get_numeric_columns()
result_column = self._dataframe_context.get_result_column()
categorical_columns = [x for x in categorical_columns if x != result_column]
appType = self._dataframe_context.get_app_type()
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()
# 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
levels = df.select(result_column).distinct().count()
appType = self._dataframe_context.get_app_type()
model_filepath = model_path + "/" + self._slug + "/model"
pmml_filepath = str(model_path) + "/" + str(self._slug) + "/trainedModel.pmml"
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")
st = time.time()
pipeline = MLUtils.create_pyspark_ml_pipeline(numerical_columns, categorical_columns, result_column)
vectorFeats = pipeline.getStages()[-1].transform(df)
input_feats = len(vectorFeats.select('features').take(1)[0][0])
trainingData, validationData = MLUtils.get_training_and_validation_data(df, result_column, 0.8) # indexed
labelIndexer = StringIndexer(inputCol=result_column, outputCol="label")
# OriginalTargetconverter = IndexToString(inputCol="label", outputCol="originalTargetColumn")
# Label Mapping and Inverse
labelIdx = labelIndexer.fit(trainingData)
labelMapping = {k: v for k, v in enumerate(labelIdx.labels)}
inverseLabelMapping = {v: float(k) for k, v in enumerate(labelIdx.labels)}
clf = MultilayerPerceptronClassifier()
if not algoSetting.is_hyperparameter_tuning_enabled():
algoParams = algoSetting.get_params_dict()
else:
algoParams = algoSetting.get_params_dict_hyperparameter()
clfParams = [prm.name for prm in clf.params]
algoParams = {getattr(clf, k): v if isinstance(v, list) else [v] for k, v in algoParams.items() if
k in clfParams}
paramGrid = ParamGridBuilder()
layer_param_val = algoParams[getattr(clf, 'layers')]
for layer in layer_param_val:
layer.insert(0, input_feats)
layer.append(levels)
print('layer_param_val =', layer_param_val)
# if not algoSetting.is_hyperparameter_tuning_enabled():
# for k,v in algoParams.items():
# if k.name == 'layers':
# paramGrid = paramGrid.addGrid(k,layer_param_val)
# else:
# paramGrid = paramGrid.addGrid(k,v)
# paramGrid = paramGrid.build()
# else:
for k, v in algoParams.items():
if v == [None] * len(v):
continue
if k.name == 'layers':
paramGrid = paramGrid.addGrid(k, layer_param_val)
else:
paramGrid = paramGrid.addGrid(k, v)
paramGrid = paramGrid.build()
if len(paramGrid) > 1:
hyperParamInitParam = algoSetting.get_hyperparameter_params()
evaluationMetricDict = {"name": hyperParamInitParam["evaluationMetric"]}
evaluationMetricDict["displayName"] = GLOBALSETTINGS.SKLEARN_EVAL_METRIC_NAME_DISPLAY_MAP[
evaluationMetricDict["name"]]
else:
evaluationMetricDict = {"name": GLOBALSETTINGS.CLASSIFICATION_MODEL_EVALUATION_METRIC}
evaluationMetricDict["displayName"] = GLOBALSETTINGS.SKLEARN_EVAL_METRIC_NAME_DISPLAY_MAP[
evaluationMetricDict["name"]]
self._result_setter.set_hyper_parameter_results(self._slug, None)
if validationDict["name"] == "kFold":
numFold = int(validationDict["value"])
estimator = Pipeline(stages=[pipeline, labelIndexer, clf])
if algoSetting.is_hyperparameter_tuning_enabled():
modelFilepath = "/".join(model_filepath.split("/")[:-1])
pySparkHyperParameterResultObj = PySparkGridSearchResult(estimator, paramGrid, appType, modelFilepath,
levels,
evaluationMetricDict, trainingData,
validationData, numFold, self._targetLevel,
labelMapping, inverseLabelMapping,
df)
resultArray = pySparkHyperParameterResultObj.train_and_save_classification_models()
self._result_setter.set_hyper_parameter_results(self._slug, resultArray)
self._result_setter.set_metadata_parallel_coordinates(self._slug,
{
"ignoreList": pySparkHyperParameterResultObj.get_ignore_list(),
"hideColumns": pySparkHyperParameterResultObj.get_hide_columns(),
"metricColName": pySparkHyperParameterResultObj.get_comparison_metric_colname(),
"columnOrder": pySparkHyperParameterResultObj.get_keep_columns()})
bestModel = pySparkHyperParameterResultObj.getBestModel()
prediction = pySparkHyperParameterResultObj.getBestPrediction()
bestModelName = resultArray[0]["Model Id"]
else:
crossval = CrossValidator(estimator=estimator,
estimatorParamMaps=paramGrid,
evaluator=BinaryClassificationEvaluator() if levels == 2 else MulticlassClassificationEvaluator(),
numFolds=3 if numFold is None else numFold) # use 3+ folds in practice
cvrf = crossval.fit(trainingData)
prediction = cvrf.transform(validationData)
bestModel = cvrf.bestModel
bestModelName = "M" + "0" * (GLOBALSETTINGS.MODEL_NAME_MAX_LENGTH - 1) + "1"
else:
train_test_ratio = float(self._dataframe_context.get_train_test_split())
estimator = Pipeline(stages=[pipeline, labelIndexer, clf])
if algoSetting.is_hyperparameter_tuning_enabled():
modelFilepath = "/".join(model_filepath.split("/")[:-1])
pySparkHyperParameterResultObj = PySparkTrainTestResult(estimator, paramGrid, appType, modelFilepath,
levels,
evaluationMetricDict, trainingData,
validationData, train_test_ratio,
self._targetLevel, labelMapping,
inverseLabelMapping,
df)
resultArray = pySparkHyperParameterResultObj.train_and_save_classification_models()
self._result_setter.set_hyper_parameter_results(self._slug, resultArray)
self._result_setter.set_metadata_parallel_coordinates(self._slug,
{
"ignoreList": pySparkHyperParameterResultObj.get_ignore_list(),
"hideColumns": pySparkHyperParameterResultObj.get_hide_columns(),
"metricColName": pySparkHyperParameterResultObj.get_comparison_metric_colname(),
"columnOrder": pySparkHyperParameterResultObj.get_keep_columns()})
bestModel = pySparkHyperParameterResultObj.getBestModel()
prediction = pySparkHyperParameterResultObj.getBestPrediction()
bestModelName = resultArray[0]["Model Id"]
else:
tvs = TrainValidationSplit(estimator=estimator,
estimatorParamMaps=paramGrid,
evaluator=BinaryClassificationEvaluator() if levels == 2 else MulticlassClassificationEvaluator(),
trainRatio=train_test_ratio)
tvrf = tvs.fit(trainingData)
prediction = tvrf.transform(validationData)
bestModel = tvrf.bestModel
bestModelName = "M" + "0" * (GLOBALSETTINGS.MODEL_NAME_MAX_LENGTH - 1) + "1"
MLUtils.save_pipeline_or_model(bestModel,model_filepath)
predsAndLabels = prediction.select(['prediction', 'label']).rdd.map(tuple)
metrics = MulticlassMetrics(predsAndLabels)
posLabel = inverseLabelMapping[self._targetLevel]
conf_mat_ar = metrics.confusionMatrix().toArray()
print(conf_mat_ar)
confusion_matrix = {}
for i in range(len(conf_mat_ar)):
confusion_matrix[labelMapping[i]] = {}
for j, val in enumerate(conf_mat_ar[i]):
confusion_matrix[labelMapping[i]][labelMapping[j]] = val
print(confusion_matrix)
trainingTime = time.time() - st
f1_score = metrics.fMeasure(inverseLabelMapping[self._targetLevel], 1.0)
precision = metrics.precision(inverseLabelMapping[self._targetLevel])
recall = metrics.recall(inverseLabelMapping[self._targetLevel])
accuracy = metrics.accuracy
roc_auc = 'Undefined'
if levels == 2:
bin_metrics = BinaryClassificationMetrics(predsAndLabels)
roc_auc = bin_metrics.areaUnderROC
precision = metrics.precision(inverseLabelMapping[self._targetLevel])
recall = metrics.recall(inverseLabelMapping[self._targetLevel])
print(f1_score,precision,recall,accuracy)
#gain chart implementation
def cal_prob_eval(x):
if len(x) == 1:
if x == posLabel:
return(float(x[1]))
else:
return(float(1 - x[1]))
else:
return(float(x[int(posLabel)]))
column_name= 'probability'
def y_prob_for_eval_udf():
return udf(lambda x:cal_prob_eval(x))
prediction = prediction.withColumn("y_prob_for_eval", y_prob_for_eval_udf()(col(column_name)))
try:
pys_df = prediction.select(['y_prob_for_eval','prediction','label'])
gain_lift_ks_obj = GainLiftKS(pys_df, 'y_prob_for_eval', 'prediction', 'label', posLabel, self._spark)
gain_lift_KS_dataframe = gain_lift_ks_obj.Run().toPandas()
except:
try:
temp_df = pys_df.toPandas()
gain_lift_ks_obj = GainLiftKS(temp_df, 'y_prob_for_eval', 'prediction', 'label', posLabel, self._spark)
gain_lift_KS_dataframe = gain_lift_ks_obj.Rank_Ordering()
except:
print("gain chant failed")
gain_lift_KS_dataframe = None
objs = {"trained_model": bestModel, "actual": prediction.select('label'),
"predicted": prediction.select('prediction'),
"probability": prediction.select('probability'), "feature_importance": None,
"featureList": list(categorical_columns) + list(numerical_columns), "labelMapping": labelMapping}
# Calculating prediction_split
val_cnts = prediction.groupBy('label').count()
val_cnts = map(lambda row: row.asDict(), val_cnts.collect())
prediction_split = {}
total_nos = objs['actual'].count()
for item in val_cnts:
classname = labelMapping[item['label']]
prediction_split[classname] = round(item['count'] * 100 / float(total_nos), 2)
if not algoSetting.is_hyperparameter_tuning_enabled():
# modelName = "M" + "0" * (GLOBALSETTINGS.MODEL_NAME_MAX_LENGTH - 1) + "1"
modelFilepathArr = model_filepath.split("/")[:-1]
modelFilepathArr.append(bestModelName)
bestModel.save("/".join(modelFilepathArr))
runtime = round((time.time() - st_global), 2)
try:
print(pmml_filepath)
pmmlBuilder = PMMLBuilder(self._spark, trainingData, bestModel).putOption(clf, 'compact', True)
pmmlBuilder.buildFile(pmml_filepath)
pmmlfile = open(pmml_filepath, "r")
pmmlText = pmmlfile.read()
pmmlfile.close()
self._result_setter.update_pmml_object({self._slug: pmmlText})
except Exception as e:
print("PMML failed...", str(e))
pass
cat_cols = list(set(categorical_columns) - {result_column})
self._model_summary = MLModelSummary()
self._model_summary.set_algorithm_name("Spark ML Multilayer Perceptron")
self._model_summary.set_algorithm_display_name("Spark ML Multilayer Perceptron")
self._model_summary.set_slug(self._slug)
self._model_summary.set_training_time(runtime)
self._model_summary.set_confusion_matrix(confusion_matrix)
self._model_summary.set_feature_importance(objs["feature_importance"])
self._model_summary.set_feature_list(objs["featureList"])
self._model_summary.set_model_accuracy(accuracy)
self._model_summary.set_training_time(round((time.time() - st), 2))
self._model_summary.set_precision_recall_stats([precision, recall])
self._model_summary.set_model_precision(precision)
self._model_summary.set_model_recall(recall)
self._model_summary.set_target_variable(result_column)
self._model_summary.set_prediction_split(prediction_split)
self._model_summary.set_validation_method("KFold")
self._model_summary.set_level_map_dict(objs["labelMapping"])
self._model_summary.set_model_features(objs["featureList"])
self._model_summary.set_level_counts(
self._metaParser.get_unique_level_dict(list(set(categorical_columns)) + [result_column]))
self._model_summary.set_num_trees(None)
self._model_summary.set_num_rules(300)
self._model_summary.set_target_level(self._targetLevel)
modelManagementJson = {
"Model ID": "SPMLP-" + bestModelName,
"Project Name": self._dataframe_context.get_job_name(),
"Algorithm": self._model_summary.get_algorithm_name(),
"Status": 'Completed',
"Accuracy": accuracy,
"Runtime": runtime,
"Created On": "",
"Owner": "",
"Deployment": 0,
"Action": ''
}
# if not algoSetting.is_hyperparameter_tuning_enabled():
# modelDropDownObj = {
# "name": self._model_summary.get_algorithm_name(),
# "evaluationMetricValue": locals()[evaluationMetricDict["name"]], # accuracy
# "evaluationMetricName": evaluationMetricDict["displayName"], # accuracy
# "slug": self._model_summary.get_slug(),
# "Model Id": bestModelName
# }
# 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": accuracy, #locals()[evaluationMetricDict["name"]],
"evaluationMetricName": "accuracy", # evaluationMetricDict["name"],
"slug": self._model_summary.get_slug(),
"Model Id": bestModelName
}
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()
}
mlpcCards = [json.loads(CommonUtils.convert_python_object_to_json(cardObj)) for cardObj in
MLUtils.create_model_summary_cards(self._model_summary)]
for card in mlpcCards:
self._prediction_narrative.add_a_card(card)
self._result_setter.set_model_summary(
{"sparkperceptron": json.loads(CommonUtils.convert_python_object_to_json(self._model_summary))})
self._result_setter.set_spark_multilayer_perceptron_model_summary(modelSummaryJson)
self._result_setter.set_spark_multilayer_perceptron_management_summary(modelManagementJson)
self._result_setter.set_mlpc_cards(mlpcCards)
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")
abs_ = Abs(inputCol='random', outputCol='abs_feature')
vc=VectorAssembler(inputCols=['random','abs_feature'],outputCol="features")
lr=LogisticRegression()
lr.setLabelCol("bin_feature")
#
pipline = Pipeline(stages=[bin_, abs_,vc,lr])
model = pipline.fit(df)
bin_df = model.transform(df)
bin_df.show()
print('load model and save model')
print("---*-***--" * 20)
model.write().overwrite().save("./abs.model")
# save
# load pipmodel
models=PipelineModel.load('./abs.model')
models.transform(df).show()
## test pmml
from pyspark2pmml import PMMLBuilder
pmmlBuilder = PMMLBuilder(sc, df, model) \
.putOption(lr, "compact", True)
pmmlBuilder.buildFile("lr.pmml")