def __init__(self):
"""
Initalizes DataProcessing class with utilities and parallel processing
"""
self.res = Res()
self.pool = Pool()
def __init__(self):
"""
Initalize resources, preprcess and feature engineering classes
"""
self.res = Res()
self.preprocess = Pipe()
self.feature = Vec()
self.data = Data()
class Pipe():
def __init__(self):
"""
Initalizes DataProcessing class with utilities and parallel processing
Paras:
None
Returns:
None
"""
self.res = Res()
self.pool = Pool()
def getDescription(self, description):
"""
Retuns list of cleaned description from dataframe list column
Paras:
summaries: list of work order desciptions
Returns:
summaries: list of cleaned descriptions
"""
description = [
re.sub(r"[^a-zA-Z]", " ", description[i].lower())
for i in range(len(description))
]
#print("Desc: ", description)
#return list(self.pool.map(self.res.clean_text, description))
return list(self.pool.map(self.res.clean_text, description))
def createDataframe(self, description):
"""
Creates dataframe class of cleaned descriptions.
Paras:
reviews: cleaned concated reviews
Returns:
ratings: ratings of the reviews
"""
return pd.DataFrame({"descriptions": description})
def ProcessData(self, column_names=["Description_Document"]):
"""
Runs DataProcessing class
Paras:
None
Returns:_
None
"""
dataframe = self.res.loadData(r"./Data", column_names)
#print("D: ", dataframe["Description_Document"])
description = self.getDescription(
list(dataframe["Description_Document"]))
#Sprint("des: ", description)
# review = self.getReview(list(dataframe["reviewText"]))
# reviews = self.utls.concate_columns(summaries, review)
# rating = list(dataframe["overall"])
return self.createDataframe(description)
class Pipe():
def __init__(self):
"""
Initalizes DataProcessing class with utilities and parallel processing
"""
self.res = Res()
self.pool = Pool()
def getDescription(self, description):
"""
Retuns list of cleaned description from dataframe list column
Paras:
summaries: list of work order desciptions
Returns:
summaries: list of cleaned descriptions
"""
description = [
re.sub(r"[^a-zA-Z]", " ", description[i].lower())
for i in range(len(description))
]
return list(self.pool.map(self.res.clean_text, description))
def createDataframe(self, description):
"""
Creates dataframe class of cleaned descriptions.
"""
return pd.DataFrame({"descriptions": description})
def ProcessData(self, column_names=["Description_Document"]):
"""
Runs DataProcessing class
"""
# Look in directory for dataset
dataframe = self.res.loadData(r'./Final/Data', column_names)
description = self.getDescription(
list(dataframe["Description_Document"]))
return self.createDataframe(description)
def __init__(self):
self.res = Res()
self.vector = Vec()
self.pipe = Pipe()
abspath = cfg.settings['ABS_PATH']
tag_input_file = cfg.settings['input_file']
resources_output_file = cfg.settings['output_file1']
tags_output_file = cfg.settings['output_file2']
fieldnames_tag_input = cfg.settings['input_file_fields']
fieldnames_resource_output = cfg.settings['resource_output_fields']
fieldnames_tag_output = cfg.settings['tag_output_fields']
if (args.service == 'ec2'):
# get session
conn = Connection(region_name, profile_name, "session")
# get service
service = conn.get_aws_service('ec2')
# get resource access
res = Res(service)
# if the script runs without any argument, it means get all the instances with notags
if (args.tag == None and args.value == None and args.file == None):
res_list = res.get_ec2_resources_on_taginfo(taginfo="notag")
print(res_list)
# if the script runs with only tag key and no value
if (args.tag and args.value == None):
#print("inside args tag",args.tag)
res_list = res.get_ec2_resources_on_taginfo(tagonly=args.tag)
print(res_list)
# if the script runs with both tag key and value
if (args.tag and args.value):
#print("inside args tag value",args.tag,args.value)
res_list = res.get_ec2_resources_on_taginfo(key=args.tag,