class SupportVectorMachineScript(object):
def __init__(self,
data_frame,
df_helper,
df_context,
spark,
prediction_narrative,
result_setter,
meta_parser,
mlEnvironment="sklearn"):
self._metaParser = meta_parser
self._prediction_narrative = prediction_narrative
self._result_setter = result_setter
self._data_frame = data_frame
self._dataframe_helper = df_helper
self._dataframe_context = df_context
self._ignoreMsg = self._dataframe_context.get_message_ignore()
self._spark = spark
self._model_summary = {
"confusion_matrix": {},
"precision_recall_stats": {},
"FrequencySummary": {},
"ChiSquare": {}
}
self._score_summary = {}
self._model_slug_map = GLOBALSETTINGS.MODEL_SLUG_MAPPING
self._slug = self._model_slug_map["svm"]
self._targetLevel = self._dataframe_context.get_target_level_for_model(
)
self._completionStatus = self._dataframe_context.get_completion_status(
)
print(self._completionStatus, "initial completion status")
self._analysisName = self._slug
self._messageURL = self._dataframe_context.get_message_url()
self._scriptWeightDict = self._dataframe_context.get_ml_model_training_weight(
)
self._mlEnv = mlEnvironment
self._scriptStages = {
"initialization": {
"summary": "Initialized the SVM Scripts",
"weight": 4
},
"training": {
"summary": "SVM Model Training Started",
"weight": 2
},
"completion": {
"summary": "SVM Model Training Finished",
"weight": 4
},
}
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))
print(categorical_columns)
numerical_columns = self._dataframe_helper.get_numeric_columns()
result_column = self._dataframe_context.get_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":
pass
elif self._mlEnv == "sklearn":
model_filepath = model_path + "/" + self._slug + "/model.pkl"
pmml_filepath = str(model_path) + "/" + str(
self._slug) + "/traindeModel.pmml"
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)
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()
levels = df[result_column].unique()
clf = SVC(kernel='linear', probability=True)
labelEncoder = preprocessing.LabelEncoder()
labelEncoder.fit(np.concatenate([y_train, y_test]))
y_train = pd.Series(labelEncoder.transform(y_train))
y_test = labelEncoder.transform(y_test)
classes = labelEncoder.classes_
transformed = labelEncoder.transform(classes)
labelMapping = dict(list(zip(transformed, classes)))
inverseLabelMapping = dict(list(zip(classes, transformed)))
posLabel = inverseLabelMapping[self._targetLevel]
appType = self._dataframe_context.get_app_type()
print(appType, labelMapping, inverseLabelMapping, posLabel,
self._targetLevel)
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 list(params_grid.items())
if k in clf.get_params()
}
print(params_grid)
if hyperParamAlgoName == "gridsearchcv":
clfGrid = GridSearchCV(clf, params_grid)
gridParams = clfGrid.get_params()
hyperParamInitParam = {
k: v
for k, v in list(hyperParamInitParam.items())
if k in gridParams
}
clfGrid.set_params(**hyperParamInitParam)
#clfGrid.fit(x_train,y_train)
grid_param = {}
grid_param['params'] = ParameterGrid(params_grid)
#bestEstimator = clfGrid.best_estimator_
modelFilepath = "/".join(model_filepath.split("/")[:-1])
sklearnHyperParameterResultObj = SklearnGridSearchResult(
grid_param, clf, x_train, x_test, y_train, y_test,
appType, modelFilepath, levels, posLabel,
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":
clfRand = RandomizedSearchCV(clf, params_grid)
clfRand.set_params(**hyperParamInitParam)
bestEstimator = None
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)
algoParams = algoSetting.get_params_dict()
algoParams = {
k: v
for k, v in list(algoParams.items())
if k in list(clf.get_params().keys())
}
clf.set_params(**algoParams)
print("!" * 50)
print(clf.get_params())
print("!" * 50)
if validationDict["name"] == "kFold":
defaultSplit = GLOBALSETTINGS.DEFAULT_VALIDATION_OBJECT[
"value"]
numFold = int(validationDict["value"])
if numFold == 0:
numFold = 3
kFoldClass = SkleanrKFoldResult(
numFold,
clf,
x_train,
x_test,
y_train,
y_test,
appType,
levels,
posLabel,
evaluationMetricDict=evaluationMetricDict)
kFoldClass.train_and_save_result()
kFoldOutput = kFoldClass.get_kfold_result()
bestEstimator = kFoldClass.get_best_estimator()
elif validationDict["name"] == "trainAndtest":
clf.fit(x_train, y_train)
bestEstimator = clf
# clf.fit(x_train, y_train)
# bestEstimator = clf
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)
# overall_precision_recall = MLUtils.calculate_overall_precision_recall(y_test,y_score,targetLevel = self._targetLevel)
# print overall_precision_recall
accuracy = metrics.accuracy_score(y_test, y_score)
if len(levels) <= 2:
precision = metrics.precision_score(y_test,
y_score,
pos_label=posLabel,
average="binary")
recall = metrics.recall_score(y_test,
y_score,
pos_label=posLabel,
average="binary")
auc = metrics.roc_auc_score(y_test, y_score)
elif len(levels) > 2:
precision = metrics.precision_score(y_test,
y_score,
pos_label=posLabel,
average="macro")
recall = metrics.recall_score(y_test,
y_score,
pos_label=posLabel,
average="macro")
# auc = metrics.roc_auc_score(y_test,y_score,average="weighted")
auc = None
y_score = labelEncoder.inverse_transform(y_score)
y_test = labelEncoder.inverse_transform(y_test)
featureImportance = {}
feature_importance = dict(
sorted(zip(x_train.columns,
bestEstimator.feature_importances_),
key=lambda x: x[1],
reverse=True))
for k, v in feature_importance.items():
feature_importance[k] = CommonUtils.round_sig(v)
objs = {
"trained_model": bestEstimator,
"actual": y_test,
"predicted": y_score,
"probability": y_prob,
"feature_importance": feature_importance,
"featureList": list(x_train.columns),
"labelMapping": labelMapping
}
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))
runtime = round((time.time() - st_global), 2)
try:
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
cat_cols = list(set(categorical_columns) - {result_column})
overall_precision_recall = MLUtils.calculate_overall_precision_recall(
objs["actual"], objs["predicted"], targetLevel=self._targetLevel)
self._model_summary = MLModelSummary()
self._model_summary.set_algorithm_name("Svm")
self._model_summary.set_algorithm_display_name(
"Support Vector Machine")
self._model_summary.set_slug(self._slug)
self._model_summary.set_training_time(runtime)
self._model_summary.set_confusion_matrix(
MLUtils.calculate_confusion_matrix(objs["actual"],
objs["predicted"]))
self._model_summary.set_feature_importance(objs["feature_importance"])
self._model_summary.set_feature_list(objs["featureList"])
self._model_summary.set_model_accuracy(
round(metrics.accuracy_score(objs["actual"], objs["predicted"]),
2))
self._model_summary.set_training_time(round((time.time() - st), 2))
self._model_summary.set_precision_recall_stats(
overall_precision_recall["classwise_stats"])
self._model_summary.set_model_precision(
overall_precision_recall["precision"])
self._model_summary.set_model_recall(
overall_precision_recall["recall"])
self._model_summary.set_target_variable(result_column)
self._model_summary.set_prediction_split(
overall_precision_recall["prediction_split"])
self._model_summary.set_validation_method("Train and Test")
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(
[col for col in x_train.columns if col != result_column])
self._model_summary.set_level_counts(
self._metaParser.get_unique_level_dict(
list(set(categorical_columns))))
self._model_summary.set_num_trees(100)
self._model_summary.set_num_rules(300)
if not algoSetting.is_hyperparameter_tuning_enabled():
modelDropDownObj = {
"name": self._model_summary.get_algorithm_name(),
"evaluationMetricValue":
self._model_summary.get_model_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": resultArray[0]["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()
}
svmCards = [
json.loads(CommonUtils.convert_python_object_to_json(cardObj)) for
cardObj in MLUtils.create_model_summary_cards(self._model_summary)
]
for card in svmCards:
self._prediction_narrative.add_a_card(card)
self._result_setter.set_model_summary({
"svm":
json.loads(
CommonUtils.convert_python_object_to_json(self._model_summary))
})
self._result_setter.set_svm_model_summary(modelSummaryJson)
self._result_setter.set_rf_cards(svmCards)
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")
# DataWriter.write_dict_as_json(self._spark, {"modelSummary":json.dumps(self._model_summary)}, summary_filepath)
# print self._model_summary
# CommonUtils.write_to_file(summary_filepath,json.dumps({"modelSummary":self._model_summary}))
def Predict(self):
self._scriptWeightDict = self._dataframe_context.get_ml_model_prediction_weight(
)
self._scriptStages = {
"initialization": {
"summary": "Initialized the Random Forest Scripts",
"weight": 2
},
"prediction": {
"summary": "Random Forest Model Prediction Finished",
"weight": 2
},
"frequency": {
"summary": "descriptive analysis finished",
"weight": 2
},
"chisquare": {
"summary": "chi Square analysis finished",
"weight": 4
},
"completion": {
"summary": "all analysis finished",
"weight": 4
},
}
self._completionStatus += old_div(
self._scriptWeightDict[self._analysisName]["total"] *
self._scriptStages["initialization"]["weight"], 10)
progressMessage = CommonUtils.create_progress_message_object(self._analysisName,\
"initialization",\
"info",\
self._scriptStages["initialization"]["summary"],\
self._completionStatus,\
self._completionStatus)
CommonUtils.save_progress_message(self._messageURL,
progressMessage,
ignore=self._ignoreMsg)
self._dataframe_context.update_completion_status(
self._completionStatus)
# Match with the level_counts and then clean the data
dataSanity = True
level_counts_train = self._dataframe_context.get_level_count_dict()
cat_cols = self._dataframe_helper.get_string_columns()
# level_counts_score = CommonUtils.get_level_count_dict(self._data_frame,cat_cols,self._dataframe_context.get_column_separator(),output_type="dict")
# if level_counts_train != {}:
# for key in level_counts_train:
# if key in level_counts_score:
# if level_counts_train[key] != level_counts_score[key]:
# dataSanity = False
# else:
# dataSanity = False
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()
test_data_path = self._dataframe_context.get_input_file()
if self._mlEnv == "spark":
pass
elif self._mlEnv == "sklearn":
score_data_path = self._dataframe_context.get_score_path(
) + "/data.csv"
if score_data_path.startswith("file"):
score_data_path = score_data_path[7:]
trained_model_path = self._dataframe_context.get_model_path()
trained_model_path += "/" + self._dataframe_context.get_model_for_scoring(
) + ".pkl"
if trained_model_path.startswith("file"):
trained_model_path = trained_model_path[7:]
score_summary_path = self._dataframe_context.get_score_path(
) + "/Summary/summary.json"
if score_summary_path.startswith("file"):
score_summary_path = score_summary_path[7:]
trained_model = joblib.load(trained_model_path)
# pandas_df = self._data_frame.toPandas()
df = self._data_frame.toPandas()
model_columns = self._dataframe_context.get_model_features()
pandas_df = MLUtils.create_dummy_columns(
df, [x for x in categorical_columns if x != result_column])
pandas_df = MLUtils.fill_missing_columns(pandas_df, model_columns,
result_column)
if uid_col:
pandas_df = pandas_df[[
x for x in pandas_df.columns if x != uid_col
]]
y_score = trained_model.predict(pandas_df)
y_prob = trained_model.predict_proba(pandas_df)
y_prob = MLUtils.calculate_predicted_probability(y_prob)
y_prob = list([round(x, 2) for x in y_prob])
score = {
"predicted_class": y_score,
"predicted_probability": y_prob
}
df["predicted_class"] = score["predicted_class"]
labelMappingDict = self._dataframe_context.get_label_map()
df["predicted_class"] = df["predicted_class"].apply(
lambda x: labelMappingDict[x] if x != None else "NA")
df["predicted_probability"] = score["predicted_probability"]
self._score_summary[
"prediction_split"] = MLUtils.calculate_scored_probability_stats(
df)
self._score_summary["result_column"] = result_column
if result_column in df.columns:
df.drop(result_column, axis=1, inplace=True)
df = df.rename(index=str, columns={"predicted_class": result_column})
df.to_csv(score_data_path, header=True, index=False)
uidCol = self._dataframe_context.get_uid_column()
if uidCol == None:
uidCols = self._metaParser.get_suggested_uid_columns()
if len(uidCols) > 0:
uidCol = uidCols[0]
uidTableData = []
predictedClasses = list(df[result_column].unique())
if uidCol:
if uidCol in df.columns:
for level in predictedClasses:
levelDf = df[df[result_column] == level]
levelDf = levelDf[[
uidCol, "predicted_probability", result_column
]]
levelDf.sort_values(by="predicted_probability",
ascending=False,
inplace=True)
levelDf["predicted_probability"] = levelDf[
"predicted_probability"].apply(
lambda x: humanize.apnumber(x * 100) + "%"
if x * 100 >= 10 else str(int(x * 100)) + "%")
uidTableData.append(levelDf[:5])
uidTableData = pd.concat(uidTableData)
uidTableData = [list(arr) for arr in list(uidTableData.values)]
uidTableData = [[uidCol, "Probability", result_column]
] + uidTableData
uidTable = TableData()
uidTable.set_table_width(25)
uidTable.set_table_data(uidTableData)
uidTable.set_table_type("normalHideColumn")
self._result_setter.set_unique_identifier_table(
json.loads(
CommonUtils.convert_python_object_to_json(uidTable)))
self._completionStatus += old_div(
self._scriptWeightDict[self._analysisName]["total"] *
self._scriptStages["prediction"]["weight"], 10)
progressMessage = CommonUtils.create_progress_message_object(self._analysisName,\
"prediction",\
"info",\
self._scriptStages["prediction"]["summary"],\
self._completionStatus,\
self._completionStatus)
CommonUtils.save_progress_message(self._messageURL,
progressMessage,
ignore=self._ignoreMsg)
self._dataframe_context.update_completion_status(
self._completionStatus)
# CommonUtils.write_to_file(score_summary_path,json.dumps({"scoreSummary":self._score_summary}))
print("STARTING DIMENSION ANALYSIS ...")
columns_to_keep = []
columns_to_drop = []
# considercolumnstype = self._dataframe_context.get_score_consider_columns_type()
# considercolumns = self._dataframe_context.get_score_consider_columns()
# if considercolumnstype != None:
# if considercolumns != None:
# if considercolumnstype == ["excluding"]:
# columns_to_drop = considercolumns
# elif considercolumnstype == ["including"]:
# columns_to_keep = considercolumns
columns_to_keep = self._dataframe_context.get_score_consider_columns()
if len(columns_to_keep) > 0:
columns_to_drop = list(set(df.columns) - set(columns_to_keep))
else:
columns_to_drop += ["predicted_probability"]
columns_to_drop = [
x for x in columns_to_drop
if x in df.columns and x != result_column
]
print("columns_to_drop", columns_to_drop)
df.drop(columns_to_drop, axis=1, inplace=True)
resultColLevelCount = dict(df[result_column].value_counts())
# self._metaParser.update_level_counts(result_column,resultColLevelCount)
self._metaParser.update_column_dict(
result_column, {
"LevelCount": resultColLevelCount,
"numberOfUniqueValues": len(list(resultColLevelCount.keys()))
})
self._dataframe_context.set_story_on_scored_data(True)
SQLctx = SQLContext(sparkContext=self._spark.sparkContext,
sparkSession=self._spark)
spark_scored_df = SQLctx.createDataFrame(df)
# spark_scored_df.write.csv(score_data_path+"/data",mode="overwrite",header=True)
# TODO update metadata for the newly created dataframe
self._dataframe_context.update_consider_columns(columns_to_keep)
df_helper = DataFrameHelper(spark_scored_df, self._dataframe_context,
self._metaParser)
df_helper.set_params()
spark_scored_df = df_helper.get_data_frame()
# try:
# fs = time.time()
# narratives_file = self._dataframe_context.get_score_path()+"/narratives/FreqDimension/data.json"
# if narratives_file.startswith("file"):
# narratives_file = narratives_file[7:]
# result_file = self._dataframe_context.get_score_path()+"/results/FreqDimension/data.json"
# if result_file.startswith("file"):
# result_file = result_file[7:]
# init_freq_dim = FreqDimensions(df, df_helper, self._dataframe_context,scriptWeight=self._scriptWeightDict,analysisName=self._analysisName)
# df_freq_dimension_obj = init_freq_dim.test_all(dimension_columns=[result_column])
# df_freq_dimension_result = CommonUtils.as_dict(df_freq_dimension_obj)
# narratives_obj = DimensionColumnNarrative(result_column, df_helper, self._dataframe_context, df_freq_dimension_obj,self._result_setter,self._prediction_narrative,scriptWeight=self._scriptWeightDict,analysisName=self._analysisName)
# narratives = CommonUtils.as_dict(narratives_obj)
#
# print "Frequency Analysis Done in ", time.time() - fs, " seconds."
# self._completionStatus += self._scriptWeightDict[self._analysisName]["total"]*self._scriptStages["frequency"]["weight"]/10
# progressMessage = CommonUtils.create_progress_message_object(self._analysisName,\
# "frequency",\
# "info",\
# self._scriptStages["frequency"]["summary"],\
# self._completionStatus,\
# self._completionStatus)
# CommonUtils.save_progress_message(self._messageURL,progressMessage,ignore=self._ignoreMsg)
# self._dataframe_context.update_completion_status(self._completionStatus)
# print "Frequency ",self._completionStatus
# except:
# print "Frequency Analysis Failed "
#
# try:
# fs = time.time()
# narratives_file = self._dataframe_context.get_score_path()+"/narratives/ChiSquare/data.json"
# if narratives_file.startswith("file"):
# narratives_file = narratives_file[7:]
# result_file = self._dataframe_context.get_score_path()+"/results/ChiSquare/data.json"
# if result_file.startswith("file"):
# result_file = result_file[7:]
# init_chisquare_obj = ChiSquare(df, df_helper, self._dataframe_context,scriptWeight=self._scriptWeightDict,analysisName=self._analysisName)
# df_chisquare_obj = init_chisquare_obj.test_all(dimension_columns= [result_column])
# df_chisquare_result = CommonUtils.as_dict(df_chisquare_obj)
# chisquare_narratives = CommonUtils.as_dict(ChiSquareNarratives(df_helper, df_chisquare_obj, self._dataframe_context,df,self._prediction_narrative,self._result_setter,scriptWeight=self._scriptWeightDict,analysisName=self._analysisName))
# except:
# print "ChiSquare Analysis Failed "
if len(predictedClasses) >= 2:
try:
fs = time.time()
df_decision_tree_obj = DecisionTrees(
spark_scored_df,
df_helper,
self._dataframe_context,
self._spark,
self._metaParser,
scriptWeight=self._scriptWeightDict,
analysisName=self._analysisName).test_all(
dimension_columns=[result_column])
narratives_obj = CommonUtils.as_dict(
DecisionTreeNarrative(result_column,
df_decision_tree_obj,
self._dataframe_helper,
self._dataframe_context,
self._metaParser,
self._result_setter,
story_narrative=None,
analysisName=self._analysisName,
scriptWeight=self._scriptWeightDict))
print(narratives_obj)
except:
print("DecisionTree Analysis Failed ")
else:
data_dict = {
"npred": len(predictedClasses),
"nactual": len(list(labelMappingDict.values()))
}
if data_dict["nactual"] > 2:
levelCountDict[predictedClasses[0]] = resultColLevelCount[
predictedClasses[0]]
levelCountDict["Others"] = sum([
v for k, v in list(resultColLevelCount.items())
if k != predictedClasses[0]
])
else:
levelCountDict = resultColLevelCount
otherClass = list(
set(labelMappingDict.values()) - set(predictedClasses))[0]
levelCountDict[otherClass] = 0
print(levelCountDict)
total = float(
sum([x for x in list(levelCountDict.values()) if x != None]))
levelCountTuple = [({
"name":
k,
"count":
v,
"percentage":
humanize.apnumber(old_div(v * 100, total)) +
"%" if old_div(v * 100, total) >= 10 else
str(int(old_div(v * 100, total))) + "%"
}) for k, v in list(levelCountDict.items()) if v != None]
levelCountTuple = sorted(levelCountTuple,
key=lambda x: x["count"],
reverse=True)
data_dict["blockSplitter"] = "|~NEWBLOCK~|"
data_dict["targetcol"] = result_column
data_dict["nlevel"] = len(list(levelCountDict.keys()))
data_dict["topLevel"] = levelCountTuple[0]
data_dict["secondLevel"] = levelCountTuple[1]
maincardSummary = NarrativesUtils.get_template_output(
"/apps/", 'scorewithoutdtree.html', data_dict)
main_card = NormalCard()
main_card_data = []
main_card_narrative = NarrativesUtils.block_splitter(
maincardSummary, "|~NEWBLOCK~|")
main_card_data += main_card_narrative
chartData = NormalChartData([levelCountDict]).get_data()
chartJson = ChartJson(data=chartData)
chartJson.set_title(result_column)
chartJson.set_chart_type("donut")
mainCardChart = C3ChartData(data=chartJson)
mainCardChart.set_width_percent(33)
main_card_data.append(mainCardChart)
uidTable = self._result_setter.get_unique_identifier_table()
if uidTable != None:
main_card_data.append(uidTable)
main_card.set_card_data(main_card_data)
main_card.set_card_name(
"Predicting Key Drivers of {}".format(result_column))
self._result_setter.set_score_dtree_cards([main_card], {})
class DTREERegressionModelScript:
def __init__(self, data_frame, df_helper,df_context, spark, prediction_narrative, result_setter,meta_parser,mlEnvironment="sklearn"):
self._metaParser = meta_parser
self._prediction_narrative = prediction_narrative
self._result_setter = result_setter
self._data_frame = data_frame
self._dataframe_helper = df_helper
self._dataframe_context = df_context
self._spark = spark
self._model_summary = MLModelSummary()
self._score_summary = {}
self._slug = GLOBALSETTINGS.MODEL_SLUG_MAPPING["dtreeregression"]
self._analysisName = "dtreeRegression"
self._dataframe_context.set_analysis_name(self._analysisName)
self._mlEnv = mlEnvironment
self._completionStatus = self._dataframe_context.get_completion_status()
print self._completionStatus,"initial completion status"
self._messageURL = self._dataframe_context.get_message_url()
self._scriptWeightDict = self._dataframe_context.get_ml_model_training_weight()
self._ignoreMsg = self._dataframe_context.get_message_ignore()
self._scriptStages = {
"initialization":{
"summary":"Initialized the Decision Tree Regression Scripts",
"weight":4
},
"training":{
"summary":"Decision Tree Regression Model Training Started",
"weight":2
},
"completion":{
"summary":"Decision Tree Regression Model Training Finished",
"weight":4
},
}
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 Predict(self):
self._scriptWeightDict = self._dataframe_context.get_ml_model_prediction_weight()
self._scriptStages = {
"initialization":{
"summary":"Initialized the Decision Tree Regression Scripts",
"weight":2
},
"predictionStart":{
"summary":"Decision Tree Regression Model Prediction Started",
"weight":2
},
"predictionFinished":{
"summary":"Decision Tree Regression Model Prediction Finished",
"weight":6
}
}
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")
SQLctx = SQLContext(sparkContext=self._spark.sparkContext, sparkSession=self._spark)
dataSanity = True
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()
test_data_path = self._dataframe_context.get_input_file()
if self._mlEnv == "spark":
score_data_path = self._dataframe_context.get_score_path()+"/data.csv"
trained_model_path = "file://" + self._dataframe_context.get_model_path()
trained_model_path += "/model"
pipeline_path = "/".join(trained_model_path.split("/")[:-1])+"/pipeline"
print "trained_model_path",trained_model_path
print "pipeline_path",pipeline_path
print "score_data_path",score_data_path
pipelineModel = MLUtils.load_pipeline(pipeline_path)
trained_model = MLUtils.load_dtree_regresssion_pyspark_model(trained_model_path)
df = self._data_frame
indexed = pipelineModel.transform(df)
transformed = trained_model.transform(indexed)
if result_column in transformed.columns:
transformed = transformed.withColumnRenamed(result_column,"originalLabel")
transformed = transformed.withColumnRenamed("prediction",result_column)
pandas_scored_df = transformed.select(list(set(self._data_frame.columns+[result_column]))).toPandas()
if score_data_path.startswith("file"):
score_data_path = score_data_path[7:]
pandas_scored_df.to_csv(score_data_path,header=True,index=False)
print "STARTING Measure ANALYSIS ..."
columns_to_keep = []
columns_to_drop = []
columns_to_keep = self._dataframe_context.get_score_consider_columns()
if len(columns_to_keep) > 0:
columns_to_drop = list(set(df.columns)-set(columns_to_keep))
else:
columns_to_drop += ["predicted_probability"]
columns_to_drop = [x for x in columns_to_drop if x in df.columns and x != result_column]
print "columns_to_drop",columns_to_drop
spark_scored_df = transformed.select(list(set(columns_to_keep+[result_column])))
elif self._mlEnv == "sklearn":
CommonUtils.create_update_and_save_progress_message(self._dataframe_context,self._scriptWeightDict,self._scriptStages,self._slug,"predictionStart","info",display=True,emptyBin=False,customMsg=None,weightKey="total")
score_data_path = self._dataframe_context.get_score_path()+"/data.csv"
trained_model_path = "file://" + self._dataframe_context.get_model_path()
trained_model_path += "/"+self._dataframe_context.get_model_for_scoring()+".pkl"
print "trained_model_path",trained_model_path
print "score_data_path",score_data_path
if trained_model_path.startswith("file"):
trained_model_path = trained_model_path[7:]
trained_model = joblib.load(trained_model_path)
model_columns = self._dataframe_context.get_model_features()
print "model_columns",model_columns
df = self._data_frame.toPandas()
# pandas_df = MLUtils.factorize_columns(df,[x for x in categorical_columns if x != result_column])
pandas_df = MLUtils.create_dummy_columns(df,[x for x in categorical_columns if x != result_column])
pandas_df = MLUtils.fill_missing_columns(pandas_df,model_columns,result_column)
if uid_col:
pandas_df = pandas_df[[x for x in pandas_df.columns if x != uid_col]]
y_score = trained_model.predict(pandas_df)
scoreKpiArray = MLUtils.get_scored_data_summary(y_score)
kpiCard = NormalCard()
kpiCardData = [KpiData(data=x) for x in scoreKpiArray]
kpiCard.set_card_data(kpiCardData)
kpiCard.set_cente_alignment(True)
print CommonUtils.convert_python_object_to_json(kpiCard)
self._result_setter.set_kpi_card_regression_score(kpiCard)
pandas_df[result_column] = y_score
df[result_column] = y_score
df.to_csv(score_data_path,header=True,index=False)
CommonUtils.create_update_and_save_progress_message(self._dataframe_context,self._scriptWeightDict,self._scriptStages,self._slug,"predictionFinished","info",display=True,emptyBin=False,customMsg=None,weightKey="total")
print "STARTING Measure ANALYSIS ..."
columns_to_keep = []
columns_to_drop = []
columns_to_keep = self._dataframe_context.get_score_consider_columns()
if len(columns_to_keep) > 0:
columns_to_drop = list(set(df.columns)-set(columns_to_keep))
else:
columns_to_drop += ["predicted_probability"]
columns_to_drop = [x for x in columns_to_drop if x in df.columns and x != result_column]
print "columns_to_drop",columns_to_drop
pandas_scored_df = df[list(set(columns_to_keep+[result_column]))]
spark_scored_df = SQLctx.createDataFrame(pandas_scored_df)
# spark_scored_df.write.csv(score_data_path+"/data",mode="overwrite",header=True)
# TODO update metadata for the newly created dataframe
self._dataframe_context.update_consider_columns(columns_to_keep)
print spark_scored_df.printSchema()
df_helper = DataFrameHelper(spark_scored_df, self._dataframe_context,self._metaParser)
df_helper.set_params()
df = df_helper.get_data_frame()
# self._dataframe_context.set_dont_send_message(True)
try:
fs = time.time()
descr_stats_obj = DescriptiveStatsScript(df, df_helper, self._dataframe_context, self._result_setter, self._spark,self._prediction_narrative,scriptWeight=self._scriptWeightDict,analysisName="Descriptive analysis")
descr_stats_obj.Run()
print "DescriptiveStats Analysis Done in ", time.time() - fs, " seconds."
except:
print "Frequency Analysis Failed "
# try:
# fs = time.time()
# df_helper.fill_na_dimension_nulls()
# df = df_helper.get_data_frame()
# dt_reg = DecisionTreeRegressionScript(df, df_helper, self._dataframe_context, self._result_setter, self._spark,self._prediction_narrative,self._metaParser,scriptWeight=self._scriptWeightDict,analysisName="Predictive modeling")
# dt_reg.Run()
# print "DecisionTrees Analysis Done in ", time.time() - fs, " seconds."
# except:
# print "DTREE FAILED"
try:
fs = time.time()
two_way_obj = TwoWayAnovaScript(df, df_helper, self._dataframe_context, self._result_setter, self._spark,self._prediction_narrative,self._metaParser,scriptWeight=self._scriptWeightDict,analysisName="Measure vs. Dimension")
two_way_obj.Run()
print "OneWayAnova Analysis Done in ", time.time() - fs, " seconds."
except:
print "Anova Analysis Failed"
class NaiveBayesPysparkScript(object):
def __init__(self,
data_frame,
df_helper,
df_context,
spark,
prediction_narrative,
result_setter,
meta_parser,
mlEnvironment="pyspark"):
self._metaParser = meta_parser
self._prediction_narrative = prediction_narrative
self._result_setter = result_setter
self._data_frame = data_frame
self._dataframe_helper = df_helper
self._dataframe_context = df_context
self._ignoreMsg = self._dataframe_context.get_message_ignore()
self._spark = spark
self._model_summary = MLModelSummary()
self._score_summary = {}
self._slug = GLOBALSETTINGS.MODEL_SLUG_MAPPING["naive bayes"]
self._datasetName = CommonUtils.get_dataset_name(
self._dataframe_context.CSV_FILE)
self._targetLevel = self._dataframe_context.get_target_level_for_model(
)
self._targetLevel = self._dataframe_context.get_target_level_for_model(
)
self._completionStatus = self._dataframe_context.get_completion_status(
)
print(self._completionStatus, "initial completion status")
self._analysisName = self._slug
self._messageURL = self._dataframe_context.get_message_url()
self._scriptWeightDict = self._dataframe_context.get_ml_model_training_weight(
)
self._mlEnv = mlEnvironment
# self._classifier = "nb"
self._scriptStages = {
"initialization": {
"summary": "Initialized the Naive Bayes Scripts",
"weight": 4
},
"training": {
"summary": "Naive Bayes Model Training Started",
"weight": 2
},
"completion": {
"summary": "Naive Bayes Model Training Finished",
"weight": 4
},
}
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")
def Predict(self):
self._scriptWeightDict = self._dataframe_context.get_ml_model_prediction_weight(
)
self._scriptStages = {
"initialization": {
"summary": "Initialized the Naive Bayes Scripts",
"weight": 2
},
"prediction": {
"summary": "Spark ML Naive Bayes Model Prediction Finished",
"weight": 2
},
"frequency": {
"summary": "descriptive analysis finished",
"weight": 2
},
"chisquare": {
"summary": "chi Square analysis finished",
"weight": 4
},
"completion": {
"summary": "all analysis finished",
"weight": 4
},
}
self._completionStatus += self._scriptWeightDict[self._analysisName][
"total"] * self._scriptStages["initialization"]["weight"] / 10
progressMessage = CommonUtils.create_progress_message_object(self._analysisName,\
"initialization",\
"info",\
self._scriptStages["initialization"]["summary"],\
self._completionStatus,\
self._completionStatus)
CommonUtils.save_progress_message(self._messageURL, progressMessage)
self._dataframe_context.update_completion_status(
self._completionStatus)
SQLctx = SQLContext(sparkContext=self._spark.sparkContext,
sparkSession=self._spark)
dataSanity = True
level_counts_train = self._dataframe_context.get_level_count_dict()
categorical_columns = self._dataframe_helper.get_string_columns()
numerical_columns = self._dataframe_helper.get_numeric_columns()
time_dimension_columns = self._dataframe_helper.get_timestamp_columns()
result_column = self._dataframe_context.get_result_column()
categorical_columns = [
x for x in categorical_columns if x != result_column
]
level_counts_score = CommonUtils.get_level_count_dict(
self._data_frame,
categorical_columns,
self._dataframe_context.get_column_separator(),
output_type="dict",
dataType="spark")
for key in level_counts_train:
if key in level_counts_score:
if level_counts_train[key] != level_counts_score[key]:
dataSanity = False
else:
dataSanity = False
test_data_path = self._dataframe_context.get_input_file()
score_data_path = self._dataframe_context.get_score_path(
) + "/data.csv"
trained_model_path = self._dataframe_context.get_model_path()
trained_model_path = "/".join(
trained_model_path.split("/")[:-1]
) + "/" + self._slug + "/" + self._dataframe_context.get_model_for_scoring(
)
# score_summary_path = self._dataframe_context.get_score_path()+"/Summary/summary.json"
pipelineModel = MLUtils.load_pipeline(trained_model_path)
df = self._data_frame
transformed = pipelineModel.transform(df)
label_indexer_dict = MLUtils.read_string_indexer_mapping(
trained_model_path, SQLctx)
prediction_to_levels = udf(lambda x: label_indexer_dict[x],
StringType())
transformed = transformed.withColumn(
result_column, prediction_to_levels(transformed.prediction))
if "probability" in transformed.columns:
probability_dataframe = transformed.select(
[result_column, "probability"]).toPandas()
probability_dataframe = probability_dataframe.rename(
index=str, columns={result_column: "predicted_class"})
probability_dataframe[
"predicted_probability"] = probability_dataframe[
"probability"].apply(lambda x: max(x))
self._score_summary[
"prediction_split"] = MLUtils.calculate_scored_probability_stats(
probability_dataframe)
self._score_summary["result_column"] = result_column
scored_dataframe = transformed.select(
categorical_columns + time_dimension_columns +
numerical_columns + [result_column, "probability"]).toPandas()
scored_dataframe['predicted_probability'] = probability_dataframe[
"predicted_probability"].values
# scored_dataframe = scored_dataframe.rename(index=str, columns={"predicted_probability": "probability"})
else:
self._score_summary["prediction_split"] = []
self._score_summary["result_column"] = result_column
scored_dataframe = transformed.select(categorical_columns +
time_dimension_columns +
numerical_columns +
[result_column]).toPandas()
labelMappingDict = self._dataframe_context.get_label_map()
if score_data_path.startswith("file"):
score_data_path = score_data_path[7:]
scored_dataframe.to_csv(score_data_path, header=True, index=False)
uidCol = self._dataframe_context.get_uid_column()
if uidCol == None:
uidCols = self._metaParser.get_suggested_uid_columns()
if len(uidCols) > 0:
uidCol = uidCols[0]
uidTableData = []
predictedClasses = list(scored_dataframe[result_column].unique())
if uidCol:
if uidCol in df.columns:
for level in predictedClasses:
levelDf = scored_dataframe[scored_dataframe[result_column]
== level]
levelDf = levelDf[[
uidCol, "predicted_probability", result_column
]]
levelDf.sort_values(by="predicted_probability",
ascending=False,
inplace=True)
levelDf["predicted_probability"] = levelDf[
"predicted_probability"].apply(
lambda x: humanize.apnumber(x * 100) + "%"
if x * 100 >= 10 else str(int(x * 100)) + "%")
uidTableData.append(levelDf[:5])
uidTableData = pd.concat(uidTableData)
uidTableData = [list(arr) for arr in list(uidTableData.values)]
uidTableData = [[uidCol, "Probability", result_column]
] + uidTableData
uidTable = TableData()
uidTable.set_table_width(25)
uidTable.set_table_data(uidTableData)
uidTable.set_table_type("normalHideColumn")
self._result_setter.set_unique_identifier_table(
json.loads(
CommonUtils.convert_python_object_to_json(uidTable)))
self._completionStatus += self._scriptWeightDict[self._analysisName][
"total"] * self._scriptStages["prediction"]["weight"] / 10
progressMessage = CommonUtils.create_progress_message_object(self._analysisName,\
"prediction",\
"info",\
self._scriptStages["prediction"]["summary"],\
self._completionStatus,\
self._completionStatus)
CommonUtils.save_progress_message(self._messageURL, progressMessage)
self._dataframe_context.update_completion_status(
self._completionStatus)
print("STARTING DIMENSION ANALYSIS ...")
columns_to_keep = []
columns_to_drop = []
columns_to_keep = self._dataframe_context.get_score_consider_columns()
if len(columns_to_keep) > 0:
columns_to_drop = list(set(df.columns) - set(columns_to_keep))
else:
columns_to_drop += ["predicted_probability"]
scored_df = transformed.select(categorical_columns +
time_dimension_columns +
numerical_columns + [result_column])
columns_to_drop = [
x for x in columns_to_drop if x in scored_df.columns
]
modified_df = scored_df.select(
[x for x in scored_df.columns if x not in columns_to_drop])
resultColLevelCount = dict(
modified_df.groupby(result_column).count().collect())
self._metaParser.update_column_dict(
result_column, {
"LevelCount": resultColLevelCount,
"numberOfUniqueValues": len(resultColLevelCount.keys())
})
self._dataframe_context.set_story_on_scored_data(True)
self._dataframe_context.update_consider_columns(columns_to_keep)
df_helper = DataFrameHelper(modified_df, self._dataframe_context,
self._metaParser)
df_helper.set_params()
spark_scored_df = df_helper.get_data_frame()
if len(predictedClasses) >= 2:
try:
fs = time.time()
df_decision_tree_obj = DecisionTrees(
spark_scored_df,
df_helper,
self._dataframe_context,
self._spark,
self._metaParser,
scriptWeight=self._scriptWeightDict,
analysisName=self._analysisName).test_all(
dimension_columns=[result_column])
narratives_obj = CommonUtils.as_dict(
DecisionTreeNarrative(result_column,
df_decision_tree_obj,
self._dataframe_helper,
self._dataframe_context,
self._metaParser,
self._result_setter,
story_narrative=None,
analysisName=self._analysisName,
scriptWeight=self._scriptWeightDict))
print(narratives_obj)
except Exception as e:
print("DecisionTree Analysis Failed ", str(e))
else:
data_dict = {
"npred": len(predictedClasses),
"nactual": len(labelMappingDict.values())
}
if data_dict["nactual"] > 2:
levelCountDict[predictedClasses[0]] = resultColLevelCount[
predictedClasses[0]]
levelCountDict["Others"] = sum([
v for k, v in resultColLevelCount.items()
if k != predictedClasses[0]
])
else:
levelCountDict = resultColLevelCount
otherClass = list(
set(labelMappingDict.values()) - set(predictedClasses))[0]
levelCountDict[otherClass] = 0
print(levelCountDict)
total = float(
sum([x for x in levelCountDict.values() if x != None]))
levelCountTuple = [({
"name":
k,
"count":
v,
"percentage":
humanize.apnumber(v * 100 / total) + "%"
}) for k, v in levelCountDict.items() if v != None]
levelCountTuple = sorted(levelCountTuple,
key=lambda x: x["count"],
reverse=True)
data_dict["blockSplitter"] = "|~NEWBLOCK~|"
data_dict["targetcol"] = result_column
data_dict["nlevel"] = len(levelCountDict.keys())
data_dict["topLevel"] = levelCountTuple[0]
data_dict["secondLevel"] = levelCountTuple[1]
maincardSummary = NarrativesUtils.get_template_output(
"/apps/", 'scorewithoutdtree.html', data_dict)
main_card = NormalCard()
main_card_data = []
main_card_narrative = NarrativesUtils.block_splitter(
maincardSummary, "|~NEWBLOCK~|")
main_card_data += main_card_narrative
chartData = NormalChartData([levelCountDict]).get_data()
chartJson = ChartJson(data=chartData)
chartJson.set_title(result_column)
chartJson.set_chart_type("donut")
mainCardChart = C3ChartData(data=chartJson)
mainCardChart.set_width_percent(33)
main_card_data.append(mainCardChart)
uidTable = self._result_setter.get_unique_identifier_table()
if uidTable != None:
main_card_data.append(uidTable)
main_card.set_card_data(main_card_data)
main_card.set_card_name(
"Predicting Key Drivers of {}".format(result_column))
self._result_setter.set_score_dtree_cards([main_card], {})