def __init__(self, path, execution_id):
self.Batch_Directory = path
self.execution_id = execution_id
self.collection_name = "strength_schema_prediction" #code added by Avnish yadav
self.database_name = "Wafer-sys" #code added by Avnish yadav
self.logger_db_writer = App_LoggerDB(
execution_id=execution_id) #code added by Avnish yadav
self.mongdb = MongodbOperation()
self.az_blob_mgt = AzureBlobManagement()
self.good_directory_path = "good-raw-file-prediction-validated"
self.bad_directory_path = "bad-raw-file-prediction-validated"
def __init__(self, log_database, log_collection, execution_id):
self.log_database = log_database
self.log_collection = log_collection
self.execution_id = execution_id
self.mongoDBObject = MongodbOperation()
self.log_db_writer = App_LoggerDB(execution_id=execution_id)
self.az_blob_mgt = AzureBlobManagement()
def __init__(self, execution_id):
#self.file_object = file_object
#self.logger_object = logger_object
self.log_database="strength_training_log"
self.log_collection="stg-training_main_log"
self.execution_id=execution_id
self.log_db_writer=App_LoggerDB(execution_id=execution_id)
self.mongoDBObject = MongodbOperation()
self.az_blob_mgt=AzureBlobManagement()
def __init__(self, log_database, log_collection, execution_id):
#self.file_object = file_object
#self.logger_object = logger_object
self.execution_id = execution_id
self.log_db_writer = App_LoggerDB(execution_id=execution_id)
self.log_database = log_database
self.log_collection = log_collection
self.az_blob_mgt = AzureBlobManagement()
self.mongoDBObject = MongodbOperation()
self.clf = RandomForestClassifier()
self.xgb = XGBClassifier(objective='binary:logistic')
class App_LoggerDB:
def __init__(self, execution_id):
self.mongoDBObject = MongodbOperation()
self.azureBlobObject = AzureBlobManagement()
self.execution_id = execution_id
pass
def log(self, database_name, collection_name, log_message):
try:
self.now = datetime.now()
self.date = self.now.date()
self.current_time = self.now.strftime("%H:%M:%S")
log = {
'Log_updated_date': self.now,
'Log_update_time': self.current_time,
'Log_message': log_message,
'execution_id': self.execution_id
}
res = self.mongoDBObject.insertRecordInCollection(
database_name, collection_name, log)
if res > 0:
return True
else:
log = {
'Log_updated_date': [self.now],
'Log_update_time': [self.current_time],
'Log_message': [log_message],
'execution_id': self.execution_id
}
self.azureBlobObject.saveDataFrametoCSV("db-fail-log",
"log_" + self.execution_id,
pd.DataFrame(log),
mode="a+",
header=True)
return True
except Exception as e:
log = {
'Log_updated_date': [self.now],
'Log_update_time': [self.current_time],
'Log_message': [log_message],
'execution_id': self.execution_id
}
log["Log_message"][0] = log["Log_message"][0] + str(e)
self.azureBlobObject.saveDataFrametoCSV("db-fail-log",
"log_" + self.execution_id,
pd.DataFrame(log),
mode="a+",
header=True)
def __init__(self, log_database, log_collection, execution_id):
#self.file_object = file_object
#self.logger_object = logger_object
self.execution_id = execution_id
self.log_db_writer = App_LoggerDB(execution_id=execution_id)
self.log_database = log_database
self.log_collection = log_collection
self.az_blob_mgt = AzureBlobManagement()
self.mongoDBObject = MongodbOperation()
self.linearReg = LinearRegression()
self.RandomForestReg = RandomForestRegressor()
self.DecisionTreeReg = DecisionTreeRegressor()
self.XGBoostReg = XGBRegressor()
self.AdaboostReg = AdaBoostRegressor()
self.svm = SVC()
def index():
if request.method == 'POST':
searchString = request.form['content'].replace(
" ", "") # obtaining the search string entered in the form
print(searchString)
try:
print("entered try Block")
mongodb = MongodbOperation()
#dbConn = pymongo.MongoClient("mongodb://localhost:27017/") # opening a connection to Mongo
#db = dbConn['crawlerDB'] # connecting to the database called crawlerDB
a = mongodb.getDataBaseClientObject()
#reviews=mongodb.checkExistingCollection(searchString,database='crawlerDB')
#print(reviews)
#reviews = db[searchString].find({}) # searching the collection with the name same as the keyword
reviews = -1
print("entered if block")
if reviews > 0: # if there is a collection with searched keyword and it has records in it
return render_template(
'results.html',
reviews=reviews) # show the results to user
else:
print('entered else block')
flipkart_url = "https://www.flipkart.com/search?q=" + searchString # preparing the URL to search the product on flipkart
uClient = uReq(
flipkart_url) # requesting the webpage from the internet
flipkartPage = uClient.read() # reading the webpage
uClient.close() # closing the connection to the web server
flipkart_html = bs(
flipkartPage, "html.parser") # parsing the webpage as HTML
bigboxes = flipkart_html.findAll(
"div", {"class": "_1AtVbE col-12-12"}
) # seacrhing for appropriate tag to redirect to the product link
del bigboxes[
0:
3] # the first 3 members of the list do not contain relevant information, hence deleting them.
box = bigboxes[0] # taking the first iteration (for demo)
productLink = "https://www.flipkart.com" + box.div.div.div.a[
'href'] # extracting the actual product link
prodRes = requests.get(
productLink) # getting the product page from server
prod_html = bs(
prodRes.text,
"html.parser") # parsing the product page as HTML
commentboxes = prod_html.find_all('div', {
'class': "_16PBlm"
}) # finding the HTML section containing the customer comments
#table = db[searchString] # creating a collection with the same name as search string. Tables and Collections are analogous.
a = mongodb.getDataBaseClientObject()
database1 = mongodb.createDatabase(a, "crawlerDB")
table1 = mongodb.createCollectionInDatabase(
database1, searchString)
#filename = searchString+".csv" # filename to save the details
#fw = open(filename, "w") # creating a local file to save the details
#headers = "Product, Customer Name, Rating, Heading, Comment \n" # providing the heading of the columns
#fw.write(headers) # writing first the headers to file
reviews = [] # initializing an empty list for reviews
# iterating over the comment section to get the details of customer and their comments
for commentbox in commentboxes:
try:
name = commentbox.div.div.find_all(
'p', {'class': '_2sc7ZR _2V5EHH'})[0].text
except:
name = 'No Name'
try:
rating = commentbox.div.div.div.div.text
except:
rating = 'No Rating'
try:
commentHead = commentbox.div.div.div.p.text
except:
commentHead = 'No Comment Heading'
try:
comtag = commentbox.div.div.find_all(
'div', {'class': ''})
custComment = comtag[0].div.text
except:
custComment = 'No Customer Comment'
#fw.write(searchString+","+name.replace(",", ":")+","+rating + "," + commentHead.replace(",", ":") + "," + custComment.replace(",", ":") + "\n")
mydict = {
"Product": searchString,
"Name": name,
"Rating": rating,
"CommentHead": commentHead,
"Comment": custComment
} # saving that detail to a dictionary
#x = table.insert_one(mydict) #insertig the dictionary containing the rview comments to the collection
x = mongodb.createOneRecord(searchString, mydict)
reviews.append(
mydict) # appending the comments to the review list
return render_template(
'results.html',
reviews=reviews) # showing the review to the user
except Exception as e:
print(e)
return 'something is wrong'
#return render_template('results.html')
else:
return render_template('index.html')
#client = pymongo.MongoClient("mongodb+srv://{0}:{1}@cluster0.tpqna.mongodb.net/Projectdb?retryWrites=true&w=majority")
client = pymongo.MongoClient("mongodb+srv://test:[email protected]/Projectdb?retryWrites=true&w=majority")
db = client.get_database('Wafer-sys')
mydb = client['Wafer-sys']
mycol = mydb["schema-training"]
#records = db.new1_db
#a=records.count_documents({})
#print(a)
""" for testing the class function"""
a=MongodbOperation()
#c=a.getDataBaseClientObject()
#d=a.createDatabase(c,'newentry')
#e=a.createCollectionInDatabase(d,'values')
record={"Sensor - 3":" float "}
record1={"name":"sherwyn"}
record3={"name":"leena","rollno": 3223,"dept": "plsql"}
record4={"name":"sangetha","rollno": 13223,"dept": "12plsql"}
#data1 = [{"code":"2","sum":"10"},{"local":"20"}]
#df = pd.DataFrame(data1)
#g=a.checkExistingCollection("values", d)
#print(g)
#d=a.checkDatabase(c,'Projectdb')
class Prediction_Data_validation:
"""
This class shall be used for handling all the validation done on the Raw Prediction Data!!.
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
def __init__(self, path, execution_id):
self.Batch_Directory = path
self.execution_id = execution_id
self.collection_name = "strength_schema_prediction" #code added by Avnish yadav
self.database_name = "Wafer-sys" #code added by Avnish yadav
self.logger_db_writer = App_LoggerDB(
execution_id=execution_id) #code added by Avnish yadav
self.mongdb = MongodbOperation()
self.az_blob_mgt = AzureBlobManagement()
self.good_directory_path = "good-raw-file-prediction-validated"
self.bad_directory_path = "bad-raw-file-prediction-validated"
def valuesFromSchema(self):
"""
Method Name: valuesFromSchema
Description: This method extracts all the relevant information from the pre-defined "Schema" file.
Output: LengthOfDateStampInFile, LengthOfTimeStampInFile, column_names, Number of Columns
On Failure: Raise ValueError,KeyError,Exception
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
log_database = "strength_prediction_log"
log_collection = "values_from_schema_validation"
try:
log_database = "wafer_prediction_log"
log_collection = "values_from_schema_validation"
df_schema_training = self.mongdb.getDataFrameofCollection(
self.database_name, self.collection_name)
dic = {}
[
dic.update({i: df_schema_training.loc[0, i]})
for i in df_schema_training.columns
]
del df_schema_training
#with open(self.schema_path, 'r') as f:
# dic = json.load(f)
# f.close()
pattern = dic['SampleFileName']
LengthOfDateStampInFile = dic['LengthOfDateStampInFile']
LengthOfTimeStampInFile = dic['LengthOfTimeStampInFile']
column_names = dic['ColName']
NumberofColumns = dic['NumberofColumns']
#file = open("Training_Logs/valuesfromSchemaValidationLog.txt", 'a+')
message = "LengthOfDateStampInFile:: %s" % LengthOfDateStampInFile + "\t" + "LengthOfTimeStampInFile:: %s" % LengthOfTimeStampInFile + "\t " + "NumberofColumns:: %s" % NumberofColumns + "\n"
self.logger_db_writer.log(log_database, log_collection, message)
#file.close()
except ValueError:
self.logger_db_writer.log(
log_database, log_collection,
"KeyError:Key value error incorrect key passed")
raise ValueError
except KeyError:
self.logger_db_writer.log(
log_database, log_collection,
"KeyError:Key value error incorrect key passed")
raise KeyError
except Exception as e:
self.logger_db_writer.log(log_database, log_collection, str(e))
raise e
return LengthOfDateStampInFile, LengthOfTimeStampInFile, column_names, NumberofColumns
def manualRegexCreation(self):
"""
Method Name: manualRegexCreation
Description: This method contains a manually defined regex based on the "FileName" given in "Schema" file.
This Regex is used to validate the filename of the prediction data.
Output: Regex pattern
On Failure: None
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
regex = "['cement_strength']+['\_'']+[\d_]+[\d]+\.csv"
return regex
def createDirectoryForGoodBadRawData(self):
"""
Method Name: createDirectoryForGoodBadRawData
Description: This method creates directories to store the Good Data and Bad Data
after validating the prediction data.
Output: None
On Failure: OSError
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
log_database = "strength_prediction_log"
log_collection = "general_log"
try:
log_database = "strength_prediction_log"
log_collection = "general_log"
self.az_blob_mgt.createDir(self.good_directory_path,
is_replace=True)
self.az_blob_mgt.createDir(self.bad_directory_path,
is_replace=True)
msg = self.good_directory_path + " and " + self.bad_directory_path + " created successfully."
self.logger_db_writer.log(log_database, log_collection, msg)
except Exception as e:
msg = "Error Occured in class Prediction_Data_validation method:createDirectoryForGoodBadRawData error: Failed to create directory " + self.good_directory_path + " and " + self.bad_directory_path
self.logger_db_writer.log(log_database, log_collection, msg)
raise e
def deleteExistingGoodDataTrainingFolder(self):
"""
Method Name: deleteExistingGoodDataTrainingFolder
Description: This method deletes the directory made to store the Good Data
after loading the data in the table. Once the good files are
loaded in the DB,deleting the directory ensures space optimization.
Output: None
On Failure: OSError
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
log_database = "strength_prediction_log"
log_collection = "general_log"
try:
log_database = "strength_prediction_log"
log_collection = "general_log"
self.az_blob_mgt.deleteDir(self.good_directory_path)
self.logger_db_writer.log(
log_database, log_collection,
self.good_directory_path + " deleted successfully!!")
except Exception as e:
msg = "Error Occured in class Raw_Data_validation method:deleteExistingGoodDataTrainingFolder Error occured while deleting :" + self.good_directory_path
self.logger_db_writer.log(log_database, log_collection, msg)
raise e
def deleteExistingBadDataTrainingFolder(self):
"""
Method Name: deleteExistingBadDataTrainingFolder
Description: This method deletes the directory made to store the bad Data.
Output: None
On Failure: OSError
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
log_database = "strength_prediction_log"
log_collection = "general_log"
try:
log_database = "strength_prediction_log"
log_collection = "general_log"
self.az_blob_mgt.deleteDir(self.bad_directory_path)
self.logger_db_writer.log(
log_database, log_collection,
self.bad_directory_path + " deleted successfully!!")
except Exception as e:
msg = "Error Occured in class Raw_Data_validation method:deleteExistingGoodDataTrainingFolder Error occured while deleting :" + self.good_directory_path
self.logger_db_writer.log(log_database, log_collection, msg)
raise e
def moveBadFilesToArchiveBad(self):
"""
Method Name: moveBadFilesToArchiveBad
Description: This method deletes the directory made to store the Bad Data
after moving the data in an archive folder. We archive the bad
files to send them back to the client for invalid data issue.
Output: None
On Failure: OSError
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
now = datetime.now()
date = now.date()
time = now.strftime("%H%M%S")
log_database = "strength_prediction_log"
log_collection = "general_log"
try:
log_database = "strength_prediction_log"
log_collection = "general_log"
# source = 'Training_Raw_files_validated/Bad_Raw/'
source = self.bad_directory_path
destination = "lap-" + self.execution_id
self.logger_db_writer.log(log_database, log_collection,
"Started moving bad raw data..")
for file in self.az_blob_mgt.getAllFileNameFromDirectory(source):
self.az_blob_mgt.moveFileinDir(source, destination, file)
self.logger_db_writer.log(
log_database, log_collection, "File:" + file +
" moved to directory:" + destination + " successfully.")
self.logger_db_writer.log(
log_database, log_collection,
"All bad raw file moved to directory:" + destination)
self.az_blob_mgt.deleteDir(source)
self.logger_db_writer.log(log_database, log_collection,
"Deleting bad raw directory:" + source)
except Exception as e:
self.logger_db_writer.log(
log_database, log_collection,
"class Raw_Data_validation method:moveBadFilesToArchiveBad Error while moving bad files to archive:"
+ str(e))
raise e
def validationFileNameRaw(self, regex, LengthOfDateStampInFile,
LengthOfTimeStampInFile):
"""
Method Name: validationFileNameRaw
Description: This function validates the name of the prediction csv file as per given name in the schema!
Regex pattern is used to do the validation.If name format do not match the file is moved
to Bad Raw Data folder else in Good raw data.
Output: None
On Failure: Exception
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
# delete the directories for good and bad data in case last run was unsuccessful and folders were not deleted.
self.createDirectoryForGoodBadRawData()
onlyfiles = self.az_blob_mgt.getAllFileNameFromDirectory(
self.Batch_Directory)
try:
log_database = "strength_prediction_log"
log_collection = "name_validation_log"
for filename in onlyfiles:
if (re.match(regex, filename)):
splitAtDot = re.split('.csv', filename)
splitAtDot = (re.split('_', splitAtDot[0]))
if len(splitAtDot[2]) == LengthOfDateStampInFile:
if len(splitAtDot[3]) == LengthOfTimeStampInFile:
self.az_blob_mgt.CopyFileinDir(
self.Batch_Directory, self.good_directory_path,
filename)
self.logger_db_writer.log(
log_database, log_collection,
"Valid File name!! File moved to " +
self.good_directory_path + filename)
else:
self.az_blob_mgt.CopyFileinDir(
self.Batch_Directory, self.bad_directory_path,
filename)
msg = "Invalid File Name !! File moved to " + self.bad_directory_path + filename
self.logger_db_writer.log(log_database,
log_collection, msg)
else:
self.az_blob_mgt.CopyFileinDir(self.Batch_Directory,
self.bad_directory_path,
filename)
msg = "Invalid File Name !! File moved to " + self.bad_directory_path + filename
self.logger_db_writer.log(log_database, log_collection,
msg)
else:
self.az_blob_mgt.CopyFileinDir(self.Batch_Directory,
self.bad_directory_path,
filename)
msg = "Invalid File Name !! File moved to " + self.bad_directory_path + filename
self.logger_db_writer.log(log_database, log_collection,
msg)
except Exception as e:
msg = "Error occured while validating FileName " + str(e)
self.logger_db_writer.log(log_database, log_collection, msg)
raise e
def validateColumnLength(self, NumberofColumns):
"""
Method Name: validateColumnLength
Description: This function validates the number of columns in the csv files.
It is should be same as given in the schema file.
If not same file is not suitable for processing and thus is moved to Bad Raw Data folder.
If the column number matches, file is kept in Good Raw Data for processing.
The csv file is missing the first column name, this function changes the missing name to "Wafer".
Output: None
On Failure: Exception
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
try:
log_database = "strength_prediction_log"
log_collection = "column_validation_log"
self.logger_db_writer.log(log_database, log_collection,
"Column length validation Started!!")
#for file in listdir('Prediction_Raw_Files_Validated/Good_Raw/'):
for file in self.az_blob_mgt.getAllFileNameFromDirectory(
self.good_directory_path):
#csv = pd.read_csv("Prediction_Raw_Files_Validated/Good_Raw/" + file)
csv = self.az_blob_mgt.readCSVFilefromDir(
self.good_directory_path, file)
print(csv.shape)
if csv.shape[1] == NumberofColumns:
#csv.rename(columns={"Unnamed: 0": "Wafer"}, inplace=True)
print(csv)
#csv.to_csv("Prediction_Raw_Files_Validated/Good_Raw/" + file, index=None, header=True)
self.az_blob_mgt.saveDataFrametoCSV(
self.good_directory_path,
file,
csv,
index=None,
header=True)
else:
self.az_blob_mgt.moveFileinDir(self.good_directory_path,
self.bad_directory_path,
file)
self.logger_db_writer.log(
log_database, log_collection,
"Invalid Column Length for the file!! "
"File moved to Bad Raw Folder :: %s" % file)
self.logger_db_writer.log(log_database, log_collection,
"Column Length Validation Completed!!")
except Exception as e:
self.logger_db_writer.log(log_database, log_collection,
'Error Occured::' + str(e))
raise e
def deletePredictionFile(self):
try:
log_database = "strenth_prediction_log"
log_collection = "general_log"
directory = "prediction-file"
filename = "Prediction.csv"
if directory in self.az_blob_mgt.dir_list:
filenames = self.az_blob_mgt.getAllFileNameFromDirectory(
directory_name=directory)
if filename in filenames:
self.az_blob_mgt.deleteFilefromDir(
directory_name=directory, filename=filename)
self.logger_db_writer.log(
log_database, log_collection, filename +
" is deleted from dir:" + directory + " successfully")
except Exception as e:
self.logger_db_writer.log(
log_database, log_collection,
"Error occure while deleting prediction file from prediction-file directory"
+ str(e))
raise e
def validateMissingValuesInWholeColumn(self):
"""
Method Name: validateMissingValuesInWholeColumn
Description: This function validates if any column in the csv file has all values missing.
If all the values are missing, the file is not suitable for processing.
SUch files are moved to bad raw data.
Output: None
On Failure: Exception
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
try:
log_database = "strength_prediction_log"
log_collection = "missing_values_in_column"
#f = open("Prediction_Logs/missingValuesInColumn.txt", 'a+')
#self.logger.log(f, "Missing Values Validation Started!!")
self.logger_db_writer.log(log_database, log_collection,
"Missing Values Validation Started!!")
#for file in listdir('Prediction_Raw_Files_Validated/Good_Raw/'):
for file in self.az_blob_mgt.getAllFileNameFromDirectory(
self.good_directory_path):
#csv = pd.read_csv("Prediction_Raw_Files_Validated/Good_Raw/" + file)
csv = self.az_blob_mgt.readCSVFilefromDir(
self.good_directory_path, file)
print(csv)
count = 0
for columns in csv:
if (len(csv[columns]) - csv[columns].count()) == len(
csv[columns]):
count += 1
#shutil.move("Prediction_Raw_Files_Validated/Good_Raw/" + file,
# "Prediction_Raw_Files_Validated/Bad_Raw")
self.az_blob_mgt.moveFileinDir(
self.good_directory_path, self.bad_directory_path,
file)
#self.logger.log(f,"Invalid Column Length for the file!! File moved to Bad Raw Folder :: %s" % file)
self.logger_db_writer.log(
log_database, log_collection,
"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)
print("column unnamed may not be present")
self.az_blob_mgt.saveDataFrametoCSV(
self.good_directory_path,
file,
csv,
index=None,
header=True)
#csv.to_csv("Prediction_Raw_Files_Validated/Good_Raw/" + file, index=None, header=True)
except Exception as e:
self.logger_db_writer.log(log_database, log_collection,
"Error occured:" + str(e))
raise e
class Raw_Data_validation:
"""
This class shall be used for handling all the validation done on the Raw Training Data!!.
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
def __init__(self, path, execution_id):
self.Batch_Directory = path
self.execution_id = execution_id
#self.schema_path = 'schema_training.json'
self.collection_name = "schema-training" #code added by Avnish yadav
self.database_name = "Wafer-sys" #code added by Avnish yadav
self.logger_db_writer = App_LoggerDB(execution_id=execution_id)
self.mongdb = MongodbOperation()
self.az_blob_mgt = AzureBlobManagement()
self.good_directory_path = "good-raw-file-train-validated"
self.bad_directory_path = "bad-raw-file-train-validated"
def valuesFromSchema(self):
"""
Method Name: valuesFromSchema
Description: This method extracts all the relevant information from the pre-defined "Schema" file.
Output: LengthOfDateStampInFile, LengthOfTimeStampInFile, column_names, Number of Columns
On Failure: Raise ValueError,KeyError,Exception
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
log_database = "wafer_training_log"
log_collection = "values_from_schema_validation"
try:
#with open(self.schema_path, 'r') as f:
# dic = json.load(f)
# f.close()
log_database = "wafer_training_log"
log_collection = "values_from_schema_validation"
df_schema_training = self.mongdb.getDataFrameofCollection(
self.database_name, self.collection_name)
dic = {}
for i in df_schema_training.columns:
dic.update({i: df_schema_training.loc[0, i]})
#[dic.update({i: df_schema_training.loc[0, i]}) for i in df_schema_training.columns]
print(dic)
del df_schema_training
pattern = dic['SampleFileName']
LengthOfDateStampInFile = dic['LengthOfDateStampInFile']
LengthOfTimeStampInFile = dic['LengthOfTimeStampInFile']
column_names = dic['ColName']
NumberofColumns = dic['NumberofColumns']
#file = open("Training_Logs/valuesfromSchemaValidationLog.txt", 'a+')
message = "LengthOfDateStampInFile:: %s" % LengthOfDateStampInFile + "\t" + "LengthOfTimeStampInFile:: %s" % LengthOfTimeStampInFile + "\t " + "NumberofColumns:: %s" % NumberofColumns + "\n"
self.logger_db_writer.log(log_database, log_collection, message)
#file.close()
except ValueError:
file = open("Training_Logs/valuesfromSchemaValidationLog.txt",
'a+')
self.logger_db_writer.log(
log_database, log_collection,
"ValueError:Value not found inside schema_training.json")
file.close()
raise ValueError
except KeyError:
file = open("Training_Logs/valuesfromSchemaValidationLog.txt",
'a+')
self.logger_db_writer.log(
log_database, log_collection,
"KeyError:Key value error incorrect key passed")
file.close()
raise KeyError
except Exception as e:
file = open("Training_Logs/valuesfromSchemaValidationLog.txt",
'a+')
self.logger_db_writer.log(log_database, log_collection, str(e))
file.close()
raise e
return LengthOfDateStampInFile, LengthOfTimeStampInFile, column_names, NumberofColumns
def manualRegexCreation(self):
"""
Method Name: manualRegexCreation
Description: This method contains a manually defined regex based on the "FileName" given in "Schema" file.
This Regex is used to validate the filename of the training data.
Output: Regex pattern
On Failure: None
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
regex = "['wafer']+['\_'']+[\d_]+[\d]+\.csv"
return regex
def createDirectoryForGoodBadRawData(self):
"""
Method Name: createDirectoryForGoodBadRawData
Description: This method creates directories to store the Good Data and Bad Data
after validating the training data.
Output: None
On Failure: OSError
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
"""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)"""
log_database = "wafer_training_log"
log_collection = "general_log"
try:
log_database = "wafer_training_log"
log_collection = "general_log"
self.az_blob_mgt.createDir(self.good_directory_path,
is_replace=True)
self.az_blob_mgt.createDir(self.bad_directory_path,
is_replace=True)
msg = self.good_directory_path + " and " + self.bad_directory_path + " created successfully."
print(msg)
self.logger_db_writer.log(log_database, log_collection, msg)
except Exception as e:
msg = "Error Occured in class Raw_Data_validation method:createDirectoryForGoodBadRawData error: Failed to create directory " + self.good_directory_path + " and " + self.bad_directory_path
self.logger_db_writer.log(log_database, log_collection, msg)
raise e
def deleteExistingGoodDataTrainingFolder(self):
"""
Method Name: deleteExistingGoodDataTrainingFolder
Description: This method deletes the directory made to store the Good Data
after loading the data in the table. Once the good files are
loaded in the DB,deleting the directory ensures space optimization.
Output: None
On Failure: OSError
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
#try:
#path = 'Training_Raw_files_validated/'
### if os.path.isdir("ids/" + userName):
## if os.path.isdir(path + 'Bad_Raw/'):
## shutil.rmtree(path + 'Bad_Raw/')
#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()
log_database = "wafer_training_log"
log_collection = "general_log"
try:
log_database = "wafer_training_log"
log_collection = "general_log"
self.az_blob_mgt.deleteDir(self.good_directory_path)
self.logger_db_writer.log(
log_database, log_collection,
self.good_directory_path + " deleted successfully!!")
except Exception as e:
msg = "Error Occured in class Raw_Data_validation method:deleteExistingGoodDataTrainingFolder Error occured while deleting :" + self.good_directory_path
self.logger_db_writer.log(log_database, log_collection, msg)
raise e
def deleteExistingBadDataTrainingFolder(self):
"""
Method Name: deleteExistingBadDataTrainingFolder
Description: This method deletes the directory made to store the bad Data.
Output: None
On Failure: OSError
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None """
#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
log_database = "wafer_training_log"
log_collection = "general_log"
try:
log_database = "wafer_training_log"
log_collection = "general_log"
self.az_blob_mgt.deleteDir(self.bad_directory_path)
self.logger_db_writer.log(
log_database, log_collection,
self.bad_directory_path + " deleted successfully!!")
except Exception as e:
msg = "Error Occured in class Raw_Data_validation method:deleteExistingGoodDataTrainingFolder Error occured while deleting :" + self.good_directory_path
self.logger_db_writer.log(log_database, log_collection, msg)
raise e
def moveBadFilesToArchiveBad(self):
"""
Method Name: moveBadFilesToArchiveBad
Description: This method deletes the directory made to store the Bad Data
after moving the data in an archive folder. We archive the bad
files to send them back to the client for invalid data issue.
Output: None
On Failure: OSError
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
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() #
log_database = "wafer_training_log"
log_collection = "general_log"
try:
log_database = "wafer_training_log"
log_collection = "general_log"
# source = 'Training_Raw_files_validated/Bad_Raw/'
source = self.bad_directory_path
destination = "lat-" + self.execution_id
self.logger_db_writer.log(log_database, log_collection,
"Started moving bad raw data..")
for file in self.az_blob_mgt.getAllFileNameFromDirectory(source):
self.az_blob_mgt.moveFileinDir(source, destination, file)
self.logger_db_writer.log(
log_database, log_collection, "File:" + file +
" moved to directory:" + destination + " successfully.")
self.logger_db_writer.log(
log_database, log_collection,
"All bad raw file moved to directory:" + destination)
self.az_blob_mgt.deleteDir(source)
self.logger_db_writer.log(log_database, log_collection,
"Deleting bad raw directory:" + source)
except Exception as e:
self.logger_db_writer.log(
log_database, log_collection,
"class Raw_Data_validation method:moveBadFilesToArchiveBad "
"Error while moving bad files to archive:" + str(e))
raise e
def validationFileNameRaw(self, regex, LengthOfDateStampInFile,
LengthOfTimeStampInFile):
"""
Method Name: validationFileNameRaw
Description: This function validates the name of the training csv files as per given name in the schema!
Regex pattern is used to do the validation.If name format do not match the file is moved
to Bad Raw Data folder else in Good raw data.
Output: None
On Failure: Exception
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
#pattern = "['Wafer']+['\_'']+[\d_]+[\d]+\.csv"
# delete the directories for good and bad data in case last run was unsuccessful and folders were not deleted.
#self.deleteExistingBadDataTrainingFolder()
#self.deleteExistingGoodDataTrainingFolder()
#create new directories
self.createDirectoryForGoodBadRawData()
onlyfiles = self.az_blob_mgt.getAllFileNameFromDirectory(
self.Batch_Directory)
#onlyfiles = [f for f in listdir(self.Batch_Directory)]
log_database = "wafer_training_log"
log_collection = "name_validation_log"
try:
log_database = "wafer_training_log"
log_collection = "name_validation_log"
#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:
if len(splitAtDot[2]) == LengthOfTimeStampInFile:
#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)
self.az_blob_mgt.CopyFileinDir(
self.Batch_Directory, self.good_directory_path,
filename)
self.logger_db_writer.log(
log_database, log_collection,
"Valid File name!! File moved to " +
self.good_directory_path + 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)
self.az_blob_mgt.CopyFileinDir(
self.Batch_Directory, self.bad_directory_path,
filename)
msg = "Invalid File Name !! File moved to " + self.bad_directory_path + filename
self.logger_db_writer.log(log_database,
log_collection, msg)
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)
self.az_blob_mgt.CopyFileinDir(self.Batch_Directory,
self.bad_directory_path,
filename)
msg = "Invalid File Name !! File moved to " + self.bad_directory_path + filename
self.logger_db_writer.log(log_database, log_collection,
msg)
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)
self.az_blob_mgt.CopyFileinDir(self.Batch_Directory,
self.bad_directory_path,
filename)
msg = "Invalid File Name !! File moved to " + self.bad_directory_path + filename
self.logger_db_writer.log(log_database, log_collection,
msg)
# f.close()
except Exception as e:
msg = "Error occured while validating FileName " + str(e)
self.logger_db_writer.log(log_database, log_collection, msg)
raise 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):
"""
Method Name: validateColumnLength
Description: This function validates the number of columns in the csv files.
It is should be same as given in the schema file.
If not same file is not suitable for processing and thus is moved to Bad Raw Data folder.
If the column number matches, file is kept in Good Raw Data for processing.
The csv file is missing the first column name, this function changes the missing name to "Wafer".
Output: None
On Failure: Exception
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
log_collection = "column_validation_log"
log_database = "wafer_training_log"
try:
log_collection = "column_validation_log"
log_database = "wafer_training_log"
#f = open("Training_Logs/columnValidationLog.txt", 'a+')
#self.logger.log(f,"Column Length Validation Started!!")
self.logger_db_writer.log(log_database, log_collection,
"Column Length Validation Started!!")
print("column lenght validation started")
for file in self.az_blob_mgt.getAllFileNameFromDirectory(
self.good_directory_path):
#csv = pd.read_csv("Training_Raw_files_validated/Good_Raw/" + file)
print(file)
csv = self.az_blob_mgt.readCSVFilefromDir(
self.good_directory_path, file)
print(csv.shape)
if csv.shape[1] == NumberofColumns:
csv.rename(columns={"Unnamed: 0": "Wafer"}, inplace=True)
print("pass statement ")
pass
#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:
self.az_blob_mgt.moveFileinDir(self.good_directory_path,
self.bad_directory_path,
file)
msg = "Invalid Column Length for the file!! File moved to " + self.bad_directory_path + "file:" + file
self.logger_db_writer.log(log_database, log_collection,
msg)
self.logger_db_writer.log(
log_database, log_collection,
"Column Length Validation Completed!!")
except Exception as e:
self.logger_db_writer.log(
log_database, log_collection,
"Error Occured in class Raw_Data_validation method: validateColumnLength error:"
+ str(e))
raise e
# 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):
"""
Method Name: validateMissingValuesInWholeColumn
Description: This function validates if any column in the csv file has all values missing.
If all the values are missing, the file is not suitable for processing.
SUch files are moved to bad raw data.
Output: None
On Failure: Exception
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
log_database = "wafer_training_log"
log_collection = "missing_values_in_column"
try:
log_database = "wafer_training_log"
log_collection = "missing_values_in_column"
self.logger_db_writer.log(log_database, log_collection,
"Missing Values Validation Started!!")
#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)
for file in self.az_blob_mgt.getAllFileNameFromDirectory(
self.good_directory_path):
csv = self.az_blob_mgt.readCSVFilefromDir(
self.good_directory_path, file)
print(csv)
count = 0
for columns in csv:
print(columns)
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)
self.az_blob_mgt.moveFileinDir(
self.good_directory_path, self.bad_directory_path,
file)
msg = "Invalid Column Length for the file!! File moved to " + self.bad_directory_path + ":: %s" % file
self.logger_db_writer.log(log_database, log_collection,
msg)
break
if count == 0:
print("entering rename")
csv.rename(columns={"Unnamed: 0": "Wafer"}, inplace=True)
self.az_blob_mgt.saveDataFrametoCSV(
self.good_directory_path,
file,
csv,
index=None,
header=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()
self.logger_db_writer.log(
log_database, log_collection,
"Error Occured class:Raw_Data_validation method:validateMissingValuesInWholeColumn error:"
+ str(e))
raise e
#path = 'training-batch-files'
#noofcolumns=592
#a=Raw_Data_validation
#res=a.validateMissingValuesInWholeColumn(a(path,333))
#print(res)
def __init__(self, execution_id):
self.mongodb=MongodbOperation()
self.az_blob_mgt=AzureBlobManagement()
self.logger_db_writer=App_LoggerDB(execution_id=execution_id)
self.good_file_path="good-raw-file-prediction-validated"
self.bad_file_path="bad-raw-file-prediction-validated"
class DbOperationMongoDB:
"""
This class shall be used for handling all the mongodb operations.
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
def __init__(self, execution_id):
self.mongodb=MongodbOperation()
self.az_blob_mgt=AzureBlobManagement()
self.logger_db_writer=App_LoggerDB(execution_id=execution_id)
self.good_file_path="good-raw-file-prediction-validated"
self.bad_file_path="bad-raw-file-prediction-validated"
def insertIntoTableGoodData(self,column_names):
"""
Description: Load all csv file into mongo db database "prediction_database" ,collection:"Good_Raw_Data"
from azure storage -good data and clear the storage space.
:return:
"""
try:
prediction_database="prediction_database" # mongodb name
prediction_collection="Good_Raw_Data" # mongodb name
database_name = "wafer_prediction_log" ## logger name
collection_name = "db_insert_log" ## logger name
self.mongodb.dropCollection(prediction_database,prediction_collection)
self.logger_db_writer.log(database_name,collection_name,"Droping collection:"+prediction_collection+" from database:"+prediction_database)
self.logger_db_writer.log(database_name, collection_name,"Starting loading of good files in database:training_database and collection: Good_Raw_Data")
files = self.az_blob_mgt.getAllFileNameFromDirectory(self.good_file_path)
self.logger_db_writer.log(database_name, collection_name,"No of file found in good-raw-file-train-validated " + str(len(files)))
for file in files:
try:
self.logger_db_writer.log(database_name, collection_name,
"Insertion of file +" + file + " started...")
df = self.az_blob_mgt.readCSVFilefromDir(self.good_file_path, file)
df.columns=column_names
print("dataframe before insertion")
print(df)
self.mongodb.insertDataFrame(prediction_database, prediction_collection, df)
self.logger_db_writer.log(database_name, collection_name,
"File: {0} loaded successfully".format(file))
except Exception as e:
self.logger_db_writer.log(database_name, collection_name, str(e))
self.az_blob_mgt.moveFileinDir(self.good_file_path, self.bad_file_path, file)
self.logger_db_writer.log(database_name, collection_name,
"File: " + file + " was not loaded successfully hence moved to dir:" + self.bad_file_path)
except Exception as e:
error_message = "Error occured in class:DbOperationMongoDB method:insertIntoTableGoodData error:" + str(e)
self.logger_db_writer.log(database_name, collection_name, error_message)
def selectingDatafromtableintocsv(self,):
"""
:return:
"""
try:
directory_name="prediction-file-from-db" # azure storage name
file_name="InputFile.csv" # azure storage name
database_name = "wafer_prediction_log" # logger name
collection_name = "export_to_csv" # logger name
prediction_database="prediction_database" # mongodb name
prediction_collection="Good_Raw_Data" # mongodb name
msg="starting of loading of database:"+prediction_database+",collection:"+prediction_collection+" records into file:"+file_name
self.logger_db_writer.log(database_name,collection_name,msg)
df=self.mongodb.getDataFrameofCollection(prediction_database,prediction_collection)
print("after dataframe from db extraction")
print(df)
msg="Good_Raw_data has been loaded into pandas dataframe"
print(msg)
self.logger_db_writer.log(database_name,collection_name,msg)
self.az_blob_mgt.saveDataFrametoCSV(directory_name,file_name,df,index=None,header=True)
# since the inputFile.csv has unammed column, added index =0 later removed as unnamed 0.1 is present in predictionDatavalidation.py ln 410.
msg = "InputFile.csv created successfully in directory"+directory_name
print(msg)
self.logger_db_writer.log(database_name, collection_name, msg)
except Exception as e:
msg="Error occured in class:DbOperationMongoDB method:insertIntoTableGoodData error:"+str(e)
self.logger_db_writer.log(database_name,collection_name,msg)
class DbOperationMongoDB:
"""
This class shall be used for handling all the SQL operations.
Written By: iNeuron Intelligence
Version: 1.0
Revisions: None
"""
def __init__(self, execution_id):
self.mongodb = MongodbOperation()
self.az_blob_mgt = AzureBlobManagement()
self.logger_db_writer = App_LoggerDB(execution_id=execution_id)
self.good_file_path = "good-raw-file-train-validated"
self.bad_file_path = "bad-raw-file-train-validated"
def insertIntoTableGoodData(self, column_name):
"""
Description: Load all csv file into mongo db database "training_database" ,collection:"Good_Raw_Data"
:return:
"""
database_name = "wafer_training_log"
collection_name = "db_insert_log"
try:
database_name = "wafer_training_log" # logger name
collection_name = "db_insert_log" # logger name
self.logger_db_writer.log(
database_name, collection_name,
"Droping existing collection if present in database training_database"
)
self.mongodb.dropCollection("training_database", "Good_Raw_Data")
self.logger_db_writer.log(
database_name, collection_name,
"Starting loading of good files in database:training_database and collection: Good_Raw_Data"
)
files = self.az_blob_mgt.getAllFileNameFromDirectory(
self.good_file_path)
self.logger_db_writer.log(
database_name, collection_name,
"No of file found in good-raw-file-train-validated " +
str(len(files)))
for file in files:
try:
self.logger_db_writer.log(
database_name, collection_name,
"Insertion of file " + file + " started...")
df = self.az_blob_mgt.readCSVFilefromDir(
self.good_file_path, file)
df.columns = column_name
self.mongodb.insertDataFrame("training_database",
"Good_Raw_Data", df)
self.logger_db_writer.log(
database_name, collection_name,
"File: {0} loaded successfully".format(file))
except Exception as e:
self.logger_db_writer.log(database_name, collection_name,
str(e))
self.az_blob_mgt.moveFileinDir(self.good_file_path,
self.bad_file_path, file)
self.logger_db_writer.log(
database_name, collection_name, "File " + file +
" was not loaded successfully hence moved tp dir:" +
self.bad_file_path)
except Exception as e:
error_message = "Error occured in class:DbOperationMongoDB method:insertIntoTableGoodData error:" + str(
e)
self.logger_db_writer.log(database_name, collection_name,
error_message)
def selectingDatafromtableintocsv(self, ):
"""
:return:
"""
database_name = "wafer_training_log"
collection_name = "export_to_csv"
try:
directory_name = "training-file-from-db"
file_name = "InputFile"
training_database = "training_database"
training_collection = "Good_Raw_Data"
msg = "starting of loading of database:training_database,collection:Good_Raw_Data records into InputFile.csv"
print(msg)
self.logger_db_writer.log(database_name, collection_name, msg)
df = self.mongodb.getDataFrameofCollection(training_database,
training_collection)
print(df)
msg = "Good_Raw_data has been loaded into pandas dataframe"
self.logger_db_writer.log(database_name, collection_name, msg)
self.az_blob_mgt.saveDataFrametoCSV(directory_name, file_name, df)
msg = "InputFile.csv created successfully in directory " + directory_name
self.logger_db_writer.log(database_name, collection_name, msg)
except Exception as e:
msg = "Error occured in class:DbOperationMongoDB method:insertIntoTableGoodData error:" + str(
e)
self.logger_db_writer.log(database_name, collection_name, msg)
def __init__(self, execution_id):
self.mongoDBObject = MongodbOperation()
self.azureBlobObject = AzureBlobManagement()
self.execution_id = execution_id
pass