class dataTransform:
def __init__(self):
self.goodDataPath = "Training_Raw_files_validated/Good_Raw"
self.logger = App_logger()
def replaceMissingWithNull(self):
log_file = open("Training_Logs/dataTransformLog.txt", 'a+')
try:
onlyfiles = [f for f in listdir(self.goodDataPath)]
for file in onlyfiles:
csv = pandas.read_csv(self.goodDataPath + "/" + file)
csv.fillna('NULL', inplace=True)
csv.to_csv(self.goodDataPath + "/" + file, index=None, header=True)
self.logger.log(log_file, " %s: File Transformed successfully!!" % file)
except Exception as e:
self.logger.log(log_file, "Data Transformation failed because:: %s" % e)
log_file.close()
log_file.close()
class Prediction:
def __init__(self, path):
self.file_object = open("Prediction_Logs/Prediction_Log.txt", 'a+')
self.log_writer = App_logger()
if path is not None:
self.pred_data_val = Prediction_data_validation(path)
def predictFromModel(self):
try:
self.pred_data_val.deletePredictionFile()
self.log_writer.log(self.file_object, 'Start of Prediction')
data_getter = Data_Getter_Prediction(self.file_object,
self.log_writer)
data = data_getter.get_data()
preprocessor = Preprocessor(self.file_object, self.log_writer)
is_null_present = preprocessor.is_null_present(data)
if (is_null_present):
data = preprocessor.impute_missing_values(data)
cols_to_drop = preprocessor.get_columns_with_zero_std_deviation(
data)
data = preprocessor.remove_columns(data, cols_to_drop)
file_loader = File_operation(self.file_object, self.log_writer)
model = file_loader.load_model('my_model')
X, y = preprocessor.separate_label_feature(data, 'Calories')
result = list(model.predict(X.values))
result = pd.Series(result, name='Predictions')
path = "Prediction_Output_File/Predictions.csv"
result.to_csv("Prediction_Output_File/Predictions.csv",
header=True,
mode='a+')
self.log_writer.log(self.file_object, 'End of Prediction')
except Exception as ex:
self.log_writer.log(
self.file_object,
'Error occured while running the prediction!! Error:: %s' % ex)
raise ex
return path, result.head().to_json(orient="records")
class trainModel:
def __init__(self):
self.log_writer = App_logger()
self.file_object = open("Training_Logs/ModelTrainingLog.txt", 'a+')
def trainingModel(self):
self.log_writer.log(self.file_object, 'Start of Training')
try:
data_getter = Data_Getter(self.file_object, self.log_writer)
data = data_getter.get_data()
preprocessor = Preprocessor(self.file_object, self.log_writer)
X, Y = preprocessor.separate_label_feature(
data, label_column_name='Calories')
is_null_present = preprocessor.is_null_present(X)
if (is_null_present):
X = preprocessor.impute_missing_values(X)
cols_to_drop = preprocessor.get_columns_with_zero_std_deviation(X)
X = preprocessor.remove_columns(X, cols_to_drop)
x_train, x_test, y_train, y_test = train_test_split(
X, Y, test_size=1 / 3, random_state=355)
model_finder = Model_Finder(self.file_object, self.log_writer)
best_model_name, best_model = model_finder.get_best_model(
x_train, y_train, x_test, y_test)
file_op = File_operation(self.file_object, self.log_writer)
save_model = file_op.save_model(best_model, best_model_name)
self.log_writer.log(self.file_object, 'Successful End of Training')
self.file_object.close()
except Exception:
self.log_writer.log(self.file_object,
'Unsuccessful End of Training')
self.file_object.close()
raise Exception
class dBOperation:
def __init__(self):
self.path = 'Prediction_Database/'
self.badFilePath = "Prediction_Raw_Files_Validated/Bad_Raw"
self.goodFilePath = "Prediction_Raw_Files_Validated/Good_Raw"
self.logger = App_logger()
def dataBaseConnection(self, DatabaseName):
try:
conn = sqlite3.connect(self.path + DatabaseName + '.db')
file = open("Prediction_Logs/DataBaseConnectionLog.txt", 'a+')
self.logger.log(file, "Opened %s database successfully" % DatabaseName)
file.close()
except ConnectionError:
file = open("Prediction_Logs/DataBaseConnectionLog.txt", 'a+')
self.logger.log(file, "Error while connecting to database: %s" % ConnectionError)
file.close()
raise ConnectionError
return conn
def createTableDb(self, DatabaseName, column_names):
try:
conn = self.dataBaseConnection(DatabaseName)
conn.execute('DROP TABLE IF EXISTS Good_Raw_Data;')
for key in column_names.keys():
type = column_names[key]
try:
conn.execute(
'ALTER TABLE Good_Raw_Data ADD COLUMN "{column_name}" {dataType}'.format(column_name=key,
dataType=type))
except:
conn.execute(
'CREATE TABLE Good_Raw_Data ({column_name} {dataType})'.format(column_name=key, dataType=type))
conn.close()
file = open("Prediction_Logs/DbTableCreateLog.txt", 'a+')
self.logger.log(file, "Tables created successfully!!")
file.close()
file = open("Prediction_Logs/DataBaseConnectionLog.txt", 'a+')
self.logger.log(file, "Closed %s database successfully" % DatabaseName)
file.close()
except Exception as e:
file = open("Prediction_Logs/DbTableCreateLog.txt", 'a+')
self.logger.log(file, "Error while creating table: %s " % e)
file.close()
conn.close()
file = open("Prediction_Logs/DataBaseConnectionLog.txt", 'a+')
self.logger.log(file, "Closed %s database successfully" % DatabaseName)
file.close()
raise e
def insertIntoTableGoodData(self, Database):
conn = self.dataBaseConnection(Database)
goodFilePath = self.goodFilePath
badFilePath = self.badFilePath
onlyfiles = [f for f in os.listdir(goodFilePath)]
log_file = open("Prediction_Logs/DbInsertLog.txt", 'a+')
for file in onlyfiles:
try:
with open(goodFilePath + '/' + file, "r") as f:
next(f)
reader = csv.reader(f, delimiter="\n")
for line in enumerate(reader):
for list_ in (line[1]):
try:
conn.execute('INSERT INTO Good_Raw_Data values ({values})'.format(values=(list_)))
self.logger.log(log_file, " %s: File loaded successfully!!" % file)
conn.commit()
except Exception as e:
raise e
except Exception as e:
conn.rollback()
self.logger.log(log_file, "Error while creating table: %s " % e)
shutil.move(goodFilePath + '/' + file, badFilePath)
self.logger.log(log_file, "File Moved Successfully %s" % file)
log_file.close()
conn.close()
raise e
conn.close()
log_file.close()
def selectingDatafromtableintocsv(self, Database):
self.fileFromDb = 'Prediction_FileFromDB/'
self.fileName = 'InputFile.csv'
log_file = open("Prediction_Logs/ExportToCsv.txt", 'a+')
try:
conn = self.dataBaseConnection(Database)
sqlSelect = "SELECT * FROM Good_Raw_Data"
cursor = conn.cursor()
cursor.execute(sqlSelect)
results = cursor.fetchall()
headers = [i[0] for i in cursor.description]
if not os.path.isdir(self.fileFromDb):
os.makedirs(self.fileFromDb)
csvFile = csv.writer(open(self.fileFromDb + self.fileName, 'w', newline=''), delimiter=',',
lineterminator='\r\n', quoting=csv.QUOTE_ALL, escapechar='\\')
csvFile.writerow(headers)
csvFile.writerows(results)
self.logger.log(log_file, "File exported successfully!!!")
except Exception as e:
self.logger.log(log_file, "File exporting failed. Error : %s" % e)
raise e
class pred_validation:
def __init__(self, path):
self.raw_data = Prediction_data_validation(path)
self.dataTransform = dataTransformationPredict()
self.dBOperation = dBOperation()
self.file_object = open("Prediction_Logs/Prediction_Log.txt", 'a+')
self.log_writer = App_logger()
def prediction_validation(self):
try:
self.log_writer.log(self.file_object, 'Start of Validation on files for prediction!!')
LengthOfDateStampInFile, noofcolumns, column_names = self.raw_data.valuesFromSchema()
regex = self.raw_data.manualRegexCreation()
self.raw_data.validateFileNameRaw(regex, LengthOfDateStampInFile)
self.raw_data.validateColumnLength(noofcolumns)
self.raw_data.validateMissingValuesInWholeColumn()
self.log_writer.log(self.file_object, "Raw Data Validation Complete!!")
self.log_writer.log(self.file_object, ("Starting Data Transforamtion!!"))
self.dataTransform.replaceMissingWithNull()
self.log_writer.log(self.file_object, "DataTransformation Completed!!!")
self.log_writer.log(self.file_object,
"Creating Prediction_Database and tables on the basis of given schema!!!")
self.dBOperation.createTableDb('Prediction', column_names)
self.log_writer.log(self.file_object, "Table creation Completed!!")
self.log_writer.log(self.file_object, "Insertion of Data into Table started!!!!")
self.dBOperation.insertIntoTableGoodData('Prediction')
self.log_writer.log(self.file_object, "Insertion in Table completed!!!")
self.log_writer.log(self.file_object, "Deleting Good Data Folder!!!")
self.raw_data.deleteExistingGoodDataTrainingFolder()
self.log_writer.log(self.file_object, "Good_Data folder deleted!!!")
self.log_writer.log(self.file_object, "Moving bad files to Archive and deleting Bad_Data folder!!!")
self.raw_data.moveBadFilesToArchiveBad()
self.log_writer.log(self.file_object, "Bad files moved to archive!! Bad folder Deleted!!")
self.log_writer.log(self.file_object, "Validation Operation completed!!")
self.log_writer.log(self.file_object, "Extracting csv file from table")
self.dBOperation.selectingDatafromtableintocsv('Prediction')
except Exception as e:
raise e
class Raw_Data_validation:
def __init__(self, path):
self.Batch_Directory = path
self.schema_path = 'schema_training.json'
self.logger = App_logger()
def valuesFromSchema(self):
try:
with open(self.schema_path, 'r') as f:
dic = json.load(f)
f.close()
pattern = dic['SampleFileName']
LengthOfDateStampInFile = dic['LengthOfDateStampInFile']
column_names = dic['ColName']
NumberofColumns = dic['NumberofColumns']
file = open("Training_Logs/valuesfromSchemaValidationLog.txt",
'a+')
message = "LengthOfDateStampInFile:: %s" % LengthOfDateStampInFile + "\t" + "NumberofColumns:: %s" % NumberofColumns + "\n"
self.logger.log(file, message)
file.close()
except ValueError:
file = open("Training_Logs/valuesfromSchemaValidationLog.txt",
'a+')
self.logger.log(
file, "ValueError:Value not found inside schema_training.json")
file.close()
raise ValueError
except KeyError:
file = open("Training_Logs/valuesfromSchemaValidationLog.txt",
'a+')
self.logger.log(file,
"KeyError:Key value error incorrect key passed")
file.close()
raise KeyError
except Exception as e:
file = open("Training_Logs/valuesfromSchemaValidationLog.txt",
'a+')
self.logger.log(file, str(e))
file.close()
raise e
return LengthOfDateStampInFile, column_names, NumberofColumns
def manualRegexCreation(self):
regex = "['data']+['\_'']+[\d]+\.csv"
return regex
def createDirectoryForGoodBadRawData(self):
try:
path = os.path.join("Training_Raw_files_validated/", "Good_Raw/")
if not os.path.isdir(path):
os.makedirs(path)
path = os.path.join("Training_Raw_files_validated/", "Bad_Raw/")
if not os.path.isdir(path):
os.makedirs(path)
except OSError as ex:
file = open("Training_Logs/GeneralLog.txt", 'a+')
self.logger.log(file, "Error while creating Directory %s:" % ex)
file.close()
raise OSError
def deleteExistingGoodDataTrainingFolder(self):
try:
path = 'Training_Raw_files_validated/'
if os.path.isdir(path + 'Good_Raw/'):
shutil.rmtree(path + 'Good_Raw/')
file = open("Training_Logs/GeneralLog.txt", 'a+')
self.logger.log(file,
"GoodRaw directory deleted successfully!!!")
file.close()
except OSError as s:
file = open("Training_Logs/GeneralLog.txt", 'a+')
self.logger.log(file, "Error while Deleting Directory : %s" % s)
file.close()
raise OSError
def deleteExistingBadDataTrainingFolder(self):
try:
path = 'Training_Raw_files_validated/'
if os.path.isdir(path + 'Bad_Raw/'):
shutil.rmtree(path + 'Bad_Raw/')
file = open("Training_Logs/GeneralLog.txt", 'a+')
self.logger.log(
file,
"BadRaw directory deleted before starting validation!!!")
file.close()
except OSError as s:
file = open("Training_Logs/GeneralLog.txt", 'a+')
self.logger.log(file, "Error while Deleting Directory : %s" % s)
file.close()
raise OSError
def moveBadFilesToArchiveBad(self):
now = datetime.now()
date = now.date()
time = now.strftime("%H%M%S")
try:
source = 'Training_Raw_files_validated/Bad_Raw/'
if os.path.isdir(source):
path = "TrainingArchiveBadData"
if not os.path.isdir(path):
os.makedirs(path)
dest = 'TrainingArchiveBadData/BadData_' + str(
date) + "_" + str(time)
if not os.path.isdir(dest):
os.makedirs(dest)
files = os.listdir(source)
for f in files:
if f not in os.listdir(dest):
shutil.move(source + f, dest)
file = open("Training_Logs/GeneralLog.txt", 'a+')
self.logger.log(file, "Bad files moved to archive")
path = 'Training_Raw_files_validated/'
if os.path.isdir(path + 'Bad_Raw/'):
shutil.rmtree(path + 'Bad_Raw/')
self.logger.log(file,
"Bad Raw Data Folder Deleted successfully!!")
file.close()
except Exception as e:
file = open("Training_Logs/GeneralLog.txt", 'a+')
self.logger.log(file,
"Error while moving bad files to archive:: %s" % e)
file.close()
raise e
def validateFileNameRaw(self, regex, LengthOfDateStampInFile):
self.deleteExistingBadDataTrainingFolder()
self.deleteExistingGoodDataTrainingFolder()
self.createDirectoryForGoodBadRawData()
onlyfiles = [f for f in os.listdir(self.Batch_Directory)]
try:
f = open("Training_Logs/nameValidationLog.txt", 'a+')
for filename in onlyfiles:
if (re.match(regex, filename)):
splitAtDot = re.split('.csv', filename)
splitAtDot = (re.split('_', splitAtDot[0]))
if len(splitAtDot[1]) == LengthOfDateStampInFile:
shutil.copy("Training_Batch_files/" + filename,
"Training_Raw_Files_Validated/Good_Raw")
self.logger.log(
f,
"Valid File name!! File moved to GoodRaw Folder :: %s"
% filename)
else:
shutil.copy("Training_Batch_files/" + filename,
"Training_Raw_Files_Validated/Bad_Raw")
self.logger.log(
f,
"Invalid File Name!! File moved to Bad Raw Folder :: %s"
% filename)
else:
shutil.copy("Training_Batch_files/" + filename,
"Training_Raw_Files_Validated/Bad_Raw")
self.logger.log(
f,
"Invalid File Name!! File moved to Bad Raw Folder :: %s"
% filename)
f.close()
except Exception as e:
f = open("Training_Logs/nameValidationLog.txt", 'a+')
self.logger.log(f,
"Error occured while validating FileName %s" % e)
f.close()
raise e
def validateColumnLength(self, NumberofColumns):
try:
f = open("Training_Logs/columnValidationLog.txt", 'a+')
self.logger.log(f, "Column Length Validation Started!!")
for file in listdir('Training_Raw_files_validated/Good_Raw/'):
csv = pd.read_csv("Training_Raw_files_validated/Good_Raw/" +
file)
if csv.shape[1] == NumberofColumns:
pass
else:
shutil.move(
"Training_Raw_files_validated/Good_Raw/" + file,
"Training_Raw_files_validated/Bad_Raw")
self.logger.log(
f,
"Invalid Column Length for the file!! File moved to Bad Raw Folder :: %s"
% file)
self.logger.log(f, "Column Length Validation Completed!!")
except OSError:
f = open("Training_Logs/columnValidationLog.txt", 'a+')
self.logger.log(
f, "Error Occured while moving the file :: %s" % OSError)
f.close()
raise OSError
except Exception as e:
f = open("Training_Logs/columnValidationLog.txt", 'a+')
self.logger.log(f, "Error Occured:: %s" % e)
f.close()
raise e
f.close()
def validateMissingValuesInWholeColumn(self):
try:
f = open("Training_Logs/missingValuesInColumn.txt", 'a+')
self.logger.log(f, "Missing Values Validation Started!!")
for file in listdir('Training_Raw_files_validated/Good_Raw/'):
csv = pd.read_csv("Training_Raw_files_validated/Good_Raw/" +
file)
count = 0
for columns in csv:
if (len(csv[columns]) - csv[columns].count()) == len(
csv[columns]):
count += 1
shutil.move(
"Training_Raw_files_validated/Good_Raw/" + file,
"Training_Raw_files_validated/Bad_Raw")
self.logger.log(
f,
"Invalid Column Length for the file!! File moved to Bad Raw Folder :: %s"
% file)
break
if count == 0:
csv.rename(columns={"Unnamed: 0": "Wafer"}, inplace=True)
csv.to_csv("Training_Raw_files_validated/Good_Raw/" + file,
index=None,
header=True)
except OSError:
f = open("Training_Logs/missingValuesInColumn.txt", 'a+')
self.logger.log(
f, "Error Occured while moving the file :: %s" % OSError)
f.close()
raise OSError
except Exception as e:
f = open("Training_Logs/missingValuesInColumn.txt", 'a+')
self.logger.log(f, "Error Occured:: %s" % e)
f.close()
raise e
f.close()