Upload app.py

app.py

@@ -85,7 +85,7 @@ def dataframe_preprocessing(df_to_preprocess:pd.DataFrame):
     Returns: df_to_preprocess (DataFrame)
     """
 
-    # userlocation will not be in dataframe is user not supplied field. So, for time being, fill with none if it does not exist.
+    # userlocation will not be in dataframe if user has not supplied field. So, for time being, fill with none if it does not exist.
     # !!! note: we will likely NOT use userlocation, so can remove this bit of code in later versions!!!
     if 'userlocation' not in df_to_preprocess.columns:
         df_to_preprocess['userlocation'] = 'None'
@@ -95,7 +95,7 @@ def dataframe_preprocessing(df_to_preprocess:pd.DataFrame):
     df_to_preprocess['created_at'] = df_to_preprocess['created_at'].dt.tz_localize(None)
     df_to_preprocess['usercreated_at'] = df_to_preprocess['usercreated_at'].dt.tz_localize(None)
     # Replacing URLs and emojis; normalizing bullet points, whitespace, etc.
-    for feature in ['text','userdescription','userlocation','userurl','username']:
+    for feature in ['text','userdescription','userlocation','username']:
         df_to_preprocess[feature] = df_to_preprocess[feature].fillna('None').apply(str)
         df_to_preprocess[feature] = df_to_preprocess[feature].apply(lambda x: textacy.preprocessing.replace.urls(text= x, repl= '_URL_'))
         df_to_preprocess[feature] = df_to_preprocess[feature].apply(lambda x: emoji.demojize(x))
@@ -343,14 +343,14 @@ def on_receipt_of_tweet_query(request:str,client:tw.Client):
         request = request.split('/')[-1]
     if '?' in request:
         request = request.split('?')[0]
-    # Collect tweet data -- interrupt if invalid input provided.
+    # Collect tweet data.
     tweet = client.get_tweets(ids=request,
                               expansions=['author_id'],
                               media_fields=None, 
                               place_fields=None,
                               poll_fields=None,
                               tweet_fields=['author_id','created_at','public_metrics','source'],
-                              user_fields=['created_at','description','location','public_metrics','verified'],
+                              user_fields=['created_at','description','location','public_metrics','url','verified'],
                               user_auth=False)
     
     # STAGE 2. PREPROCESSING OF TWEET DATA