fix bug when checking break condition for get_request_data_csv

server/utils/README.md

@@ -2,6 +2,6 @@ The utils directory will serve as a location for mutltiple utilty tools.  get_re
 
 The 311 request data from [lacity.org](https://data.lacity.org/browse?q=MyLA311%20Service%20Request%20Data%20&sortBy=relevance) has 34 columns. The get_request_data_csv.py script can be run from the command line passing the arguments start_date and end_date that lets you retreive the 311 request data from the [311 data server](https://dev-api.311-data.org/docs). The 311 server processes the data from lacity.org. The data cleaning procedure is mentioned [here](https://github.com/hackforla/311-data/blob/dev/docs/data_loading.md). The result is written to a csv file and saved in the current working directory of the user. A preview of the data_final dataframe is printed in the command line. 
 
-Example: `python get_311_request_data_csv.py "2021-01-01" "2021-01-03"` will return 261 rows and 15 columns.
+Example: `python get_request_data_csv.py "2021-01-01" "2021-01-03"` will return 261 rows and 15 columns.
 
 ![image](https://user-images.githubusercontent.com/10836669/188473763-52bc9474-0878-432c-b4e8-6e4ff21dcda2.png)

server/utils/get_request_data_csv.py

@@ -4,47 +4,53 @@
 
 REQUESTS_BATCH_SIZE = 10000
 
+
 def get_311_request_data(start_date, end_date):
     """Fetches 311 requests from the 311 data server. 
-    
+
     Retreives 311 requests from the 311 data server for a given start_date and end_date.
-    
+
     Args:
         start_date: The date from which the 311 request data have to be collected. Datatype: Datetime. 
         end_date: The date upto which the 311 request data have to be fetched. Datatype: Datetime.  
-        
+
     Return:    
         Dataframe data_final is returned with 15 columns. The dataframe is saved as a CSV file ('data_final.csv') in the current directory.
     """
-    
+
     skip = 0
     all_requests = []
     while True:
-        url=f'https://dev-api.311-data.org/requests?start_date={start_date}&end_date={end_date}&skip={skip}&limit={REQUESTS_BATCH_SIZE}'
+        url = f'https://dev-api.311-data.org/requests?start_date={start_date}&end_date={end_date}&skip={skip}&limit={REQUESTS_BATCH_SIZE}'
         response = requests.get(url)
         data = response.json()
         all_requests.extend(data)
         skip += REQUESTS_BATCH_SIZE
-        if len(data) < skip:
-            break   
-    data_final = pd.DataFrame(all_requests) 
-    data_final.sort_values(by='createdDate', inplace = True, ignore_index = True)
+        if len(data) < REQUESTS_BATCH_SIZE:
+            break
+    data_final = pd.DataFrame(all_requests)
+    data_final.sort_values(by='createdDate', inplace=True, ignore_index=True)
     return data_final
 
+
 def main():
     """Prints out the preview of the dataframe data_final in the command line. 
     The result is written to a csv file and saved in the current working directory of the user.
     """
-
-    parser = argparse.ArgumentParser(description='Gets 311 request data from the server')
-    parser.add_argument('start_date', type=str,  help='The start date that has to be entered')
-    parser.add_argument('end_date', type=str, help='The end data that has to be entered')
+
+    parser = argparse.ArgumentParser(
+        description='Gets 311 request data from the server')
+    parser.add_argument('start_date', type=str,
+                        help='The start date that has to be entered')
+    parser.add_argument('end_date', type=str,
+                        help='The end data that has to be entered')
     args = parser.parse_args()
     start_date = args.start_date
     end_date = args.end_date
-    data_final = get_311_request_data(start_date, end_date) 
+    data_final = get_311_request_data(start_date, end_date)
     data_final.to_csv('data_final.csv')
-    print(data_final)   
-
-if __name__  == "__main__":
+    print(data_final)
+
+
+if __name__ == "__main__":
     main()