AttributeError: 'dict' object has no attribute 'Credentials' - flask

Question

I'm trying to use a service account directly from a python script with the need to have a json file path that contains the service account but I keep running into this error, btw I'm trying to run my code via a flask app.
Here is the flask app:
from flask import Flask, request, jsonify, render_template
# from google.cloud import bigquery
# from google.oauth2 import service_account
import json
# import os
import pandas as pd
# Create the app object
app = Flask(__name__)
# importing function for calculations
from Record_Matching import Matching
#app.route("/query", methods = ['get'])
def query():
params = request.json
# query1 = request.args.get('query1', type = str)
# query2 = request.args.get('query2', type = str)
# querycolumns = request.args.get('querycolumns')
# project_id = request.args.get('project_id', type = str)
# service_account = request.args.get('service_account')
# SS = request.args.get('SS', type = float)
# TT = request.args.get('TT', type = float)
result = Matching(params['query1'],params['query2'], params['SS'],params['TT'], params['service_account'], params['project_id'], params['querycolumns'])
return result
if __name__ == "__main__":
app.run(host="localhost", port=8080, debug=True)
this is my function source:
import pandas as pd
from google.cloud import bigquery
from google.oauth2 import service_account
# from google.cloud.bigquery.client import Client
import recordlinkage
from recordlinkage.preprocessing import phonetic
import uuid
from uuid import uuid4
import random
import string
import json
import os
# Results to data frame function
def gcp2df(sql, client):
query = client.query(sql)
results = query.result()
return results.to_dataframe()
# Exporting df to bigquery - table parameter example: "dataset.tablename"
# def insert(df, table):
# client = bigquery.Client()
# job_config = bigquery.LoadJobConfig(write_disposition=bigquery.job.WriteDisposition.WRITE_TRUNCATE)
# return client.load_table_from_dataframe(df, table, job_config = job_config)
def pair(df1, df2, TT, querycolumns):
# function to take pair from list and compare:
L = querycolumns
l=len(querycolumns)
p1=0
p2=1
# To generate phonetics we need to make sure all names are in english.
# thus we'll replace non-english words by random english strings
df1[L[p1]] = df1[L[p1]].astype(str)
df2[L[p2]] = df2[L[p2]].astype(str)
for i in range(0,len(df1)):
if df1[L[p1]][i].isascii() == False:
df1[L[p1]][i] = ''.join(random.choices(string.ascii_lowercase, k=5))
for i in range(0,len(df2)):
if df2[L[p2]][i].isascii() == False:
df2[L[p2]][i] = ''.join(random.choices(string.ascii_lowercase, k=5))
compare = recordlinkage.Compare()
df1["phonetic_given_name"] = phonetic(df1[L[p1]], "soundex")
df2["phonetic_given_name"] = phonetic(df2[L[p2]], "soundex")
df1["initials"] = (df1[L[p1]].str[0] + df1[L[p1]].str[-1])
df2["initials"] = (df2[L[p2]].str[0] + df2[L[p2]].str[-1])
indexer = recordlinkage.Index()
indexer.block('initials')
candidate_links = indexer.index(df1, df2)
compare.exact('phonetic_given_name', 'phonetic_given_name', label="phonetic_given_name")
# O(n) a function that uses two pointers to track consecutive pairs for the input list
while p2 <=l:
compare.string(L[p1], L[p2], method='jarowinkler',threshold = TT, label=L[p1])
p1+=2
p2+=2
features = compare.compute(candidate_links,df1, df2)
return features
def Matching(query1,query2, SS,TT, service_account, project_id, querycolumns):
# Connections
# with open('service_account.json', "w") as outfile:
# json.dump(service_account, outfile)
job_config = bigquery.LoadJobConfig()
credentials = service_account.Credentials.from_service_account_info(service_account)
client = bigquery.Client(credentials = credentials, project = service_account['project_id'])
# client = bigquery.Client(project= project_id)
# os.environ["GOOGLE_APPLICATION_CREDENTIALS"]= 'service_account.json'
# if os.path.exists("service_account.json"):
# os.remove("service_account.json")
# client = Client.from_service_account_json('service_account.json', project=project_id)
# credentials = service_account.Credentials.from_service_account_file('service_account.json')
# client = bigquery.Client(credentials=credentials, project=credentials.project_id,)
SS=int(SS)
TT=float(TT)
df1 = gcp2df("""{}""".format(query1), client)
df2 = gcp2df("""{}""".format(query2), client)
# dumb_dict = {
# "dumb":"dumb"
# }
# with open('dumb.json', "w") as outfile:
# json.dump(dumb_dict, outfile)
# os.environ["GOOGLE_APPLICATION_CREDENTIALS"]= 'dumb.json'
querycolumns = json.loads(querycolumns)
querycolumns = list(querycolumns.values())
features = pair(df1, df2, TT, querycolumns)
features['Similarity_score'] = features.sum(axis=1)
features = features[features['Similarity_score']>=SS].reset_index()
final = features[['level_0', 'level_1']]
final.rename(columns= {'level_0':'df1_index', 'level_1':'df2_index'}, inplace= True)
final['Unique_ID'] = [uuid.uuid4() for _ in range(len(final.index))]
final['Unique_ID'] = final['Unique_ID'].astype(str)
final['Similarity_Score'] = SS
final_duplicates = final['df1_index'].value_counts().max()
# insert(final,"test-ahmed-project.Record_Linkage.Matching_Indices")
message = "Mission accomplished!, your highest duplica is " + str(final_duplicates)
os.remove("service_account.json")
return {'message':message, 'final':json.loads(final.to_json()), 'df1':json.loads(df1.to_json()), 'df2':json.loads(df2.to_json())}
and this is the error:
Traceback (most recent call last):
File "C:\Users\HP\Desktop\Datalaksa\Tzu Ming\Flask exploring\Coud_Run_Example\env\lib\site-packages\flask\app.py", line 2548, in __call__
return self.wsgi_app(environ, start_response)
File "C:\Users\HP\Desktop\Datalaksa\Tzu Ming\Flask exploring\Coud_Run_Example\env\lib\site-packages\flask\app.py", line 2528, in wsgi_app
response = self.handle_exception(e)
File "C:\Users\HP\Desktop\Datalaksa\Tzu Ming\Flask exploring\Coud_Run_Example\env\lib\site-packages\flask\app.py", line 2525, in wsgi_app
response = self.full_dispatch_request()
File "C:\Users\HP\Desktop\Datalaksa\Tzu Ming\Flask exploring\Coud_Run_Example\env\lib\site-packages\flask\app.py", line 1822, in full_dispatch_request
rv = self.handle_user_exception(e)
File "C:\Users\HP\Desktop\Datalaksa\Tzu Ming\Flask exploring\Coud_Run_Example\env\lib\site-packages\flask\app.py", line 1820, in full_dispatch_request
rv = self.dispatch_request()
File "C:\Users\HP\Desktop\Datalaksa\Tzu Ming\Flask exploring\Coud_Run_Example\env\lib\site-packages\flask\app.py", line 1796, in dispatch_request
return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args)
File "C:\Users\HP\Desktop\Datalaksa\Tzu Ming\Flask exploring\Final_Coud_Run_Example\main.py", line 28, in query
result = Matching(params['query1'],params['query2'], params['SS'],params['TT'], params['service_account'], params['project_id'], params['querycolumns'])
File "C:\Users\HP\Desktop\Datalaksa\Tzu Ming\Flask exploring\Final_Coud_Run_Example\Record_Matching.py", line 75, in Matching
credentials = service_account.Credentials.from_service_account_info(service_account)
AttributeError: 'dict' object has no attribute 'Credentials'
127.0.0.1 - - [29/Nov/2022 18:50:01] "GET /query HTTP/1.1" 500 -
Traceback (most recent call last):
File "C:\Users\HP\Desktop\Datalaksa\Tzu Ming\Flask exploring\Coud_Run_Example\env\lib\site-packages\flask\app.py", line 2548, in __call__
return self.wsgi_app(environ, start_response)
File "C:\Users\HP\Desktop\Datalaksa\Tzu Ming\Flask exploring\Coud_Run_Example\env\lib\site-packages\flask\app.py", line 2528, in wsgi_app
response = self.handle_exception(e)
File "C:\Users\HP\Desktop\Datalaksa\Tzu Ming\Flask exploring\Coud_Run_Example\env\lib\site-packages\flask\app.py", line 2525, in wsgi_app
response = self.full_dispatch_request()
File "C:\Users\HP\Desktop\Datalaksa\Tzu Ming\Flask exploring\Coud_Run_Example\env\lib\site-packages\flask\app.py", line 1822, in full_dispatch_request
rv = self.handle_user_exception(e)
File "C:\Users\HP\Desktop\Datalaksa\Tzu Ming\Flask exploring\Coud_Run_Example\env\lib\site-packages\flask\app.py", line 1820, in full_dispatch_request
rv = self.dispatch_request()
File "C:\Users\HP\Desktop\Datalaksa\Tzu Ming\Flask exploring\Coud_Run_Example\env\lib\site-packages\flask\app.py", line 1796, in dispatch_request
return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args)
File "C:\Users\HP\Desktop\Datalaksa\Tzu Ming\Flask exploring\Final_Coud_Run_Example\main.py", line 28, in query
result = Matching(params['query1'],params['query2'], params['SS'],params['TT'], params['service_account'], params['project_id'], params['querycolumns'])
File "C:\Users\HP\Desktop\Datalaksa\Tzu Ming\Flask exploring\Final_Coud_Run_Example\Record_Matching.py", line 75, in Matching
credentials = service_account.Credentials.from_service_account_info(service_account)
AttributeError: 'dict' object has no attribute 'Credentials'
I tried using using a service account without a json file path, I'm expecting my code to accept the service account as a dictionary.

Answer 1

You get the error because you use the same variable name on your import and parameter name on Matching() function. Your import currently looks like this:
from google.oauth2 import service_account
Then on your function Matching(), you accept a parameter named service_account. Your code references the parameter and not the import. Your function currently looks like this:
def Matching(query1,query2, SS,TT, service_account, project_id, querycolumns):
...
...
credentials = service_account.Credentials.from_service_account_info(service_account)
To fix this, change the name of your parameter in Matching() so your code won't be confused which object to use. You can rewrite your function this way:
def Matching(query1,query2, SS,TT, sa, project_id, querycolumns):
...
...
credentials = service_account.Credentials.from_service_account_info(sa)