Upload app.py

app.py

@@ -11,7 +11,6 @@ Note: This is a continuation of [this](https://colab.research.google.com/drive/1
 # Imports
 """
 
-'''
 !pip install transformers
 
 !pip install https://huggingface.co/Madhana/en_pipeline/resolve/main/en_pipeline-any-py3-none-any.whl
@@ -20,7 +19,6 @@ Note: This is a continuation of [this](https://colab.research.google.com/drive/1
 !pip install spacy-transformers
 
 !pip install gradio
-'''
 
 import json
 import requests
@@ -65,31 +63,32 @@ def get_data(bot_token):
         text_list = [r['channel_post']['text'] for r in response_json['result']]
         return text_list
     except KeyError:
-        print('An error occurred. Possibly empty request result or your Telegram Bot Token is incorrect.')
+        # print('An error occurred. Possibly empty request result or your Telegram Bot Token is incorrect.')
         error_list = ['An error occurred. Possibly empty request result or your Telegram Bot Token is incorrect.']
         return error_list
     except Exception as e:
-        print('An error occurred. Possibly empty request result or your Telegram Bot Token is incorrect.') #, e
+        # print('An error occurred. Possibly empty request result or your Telegram Bot Token is incorrect.') #, e
         error_list = ['An error occurred. Possibly empty request result or your Telegram Bot Token is incorrect.']
         return error_list
 
+get_data('6261742702:AAGkil1tWLckpBbC088rTO3Lb-lH2hJVmBg')
+
 """# Classifier"""
 
 def classify_message(bot_token):
-  if get_data(bot_token) != ['An error occurred. Possibly empty request result or your Telegram Bot Token is incorrect.']:
-    disaster_docs = []
-    classifier = pipeline("sentiment-analysis", model="Madhana/disaster_msges_classifier_v1")
-    results = []
-    for data in get_data(bot_token):
-      classification = classifier(data)
-      label = classification[0]['label']
-      results.append((data, label))
-      if label == 'DISASTER':
-        disaster_docs.append(data)
-    return disaster_docs
-  else:
-    error_list = ['An error occurred. Possibly empty request result or your Telegram Bot Token is incorrect.']
-    return error_list
+  error_msg = ['An error occurred. Possibly empty request result or your Telegram Bot Token is incorrect.']
+  disaster_docs = []
+  classifier = pipeline("sentiment-analysis", model="Madhana/disaster_msges_classifier_v1")
+  results = []
+  for data in get_data(bot_token):
+    if data == error_msg[0]:
+      return error_msg
+    classification = classifier(data)
+    label = classification[0]['label']
+    results.append((data, label))
+    if label == 'DISASTER':
+      disaster_docs.append(data)
+  return disaster_docs
 
 """# NER Pipeline"""
 
@@ -108,9 +107,6 @@ Tamil_words = ['மதனா பாலா'] # umm, that's my name in Tamil, cons
 nlp = spacy.load("en_pipeline")
 nlp.add_pipe("disaster_ner", name="disaster_ner", before='ner')
 
-entity_types = ["NAME", "STREET", "NEIGHBORHOOD", "CITY", "PHONE NUMBER","YO!"]
-df = pd.DataFrame(columns=["Text"] + entity_types)
-
 def create_address(row):
     return f"{row['STREET']}, {row['NEIGHBORHOOD']}, {row['CITY']}"
 
@@ -127,6 +123,8 @@ def geocode_address(address):
 
 def get_classifier_ner(bot_token):
   data = classify_message(bot_token)
+  entity_types = ["NAME", "STREET", "NEIGHBORHOOD", "CITY", "PHONE NUMBER","YO!"]
+  df = pd.DataFrame(columns=["Text"] + entity_types)
 
   for text in data:
     doc = nlp(text)
@@ -152,6 +150,8 @@ def get_classifier_ner(bot_token):
 
 def get_ner(bot_token):
   data = get_data(bot_token)
+  entity_types = ["NAME", "STREET", "NEIGHBORHOOD", "CITY", "PHONE NUMBER","YO!"]
+  df = pd.DataFrame(columns=["Text"] + entity_types)
 
   for text in data:
     doc = nlp(text)
@@ -162,6 +162,7 @@ def get_ner(bot_token):
     # html = displacy.render(doc, style="ent")
     # row.append(html)
 
+    
     num_cols = len(df.columns)
     while len(row) < num_cols:
       row.append("")
@@ -201,18 +202,20 @@ with demo:
             with gr.Row(): 
               gr.Markdown("""This is an Telegram based Disaster Recovery Assist app that uses Named Entity Recognition to extract important entities from the unstructured text and stores it in an dataframe. 
               You need to provide your personal Telegram Bot API token (API token of the bot that is added to the channel as an administrator) to use this app.
-              Steps to create a Telegram Bot: 
+              **Steps to create a Telegram Bot**: 
               1. Download the Telegram app on your device or use the web version. 
               2. Open the app and search for the "BotFather" bot. 
               3. Start a chat with the BotFather bot by clicking on the "START" button. 
               4. Type "/newbot" and follow the on-screen instructions to create a new bot. 
               5. Choose a name and username for your bot. \6. Once your bot is created, the BotFather will give you a unique API token.
               
-              Steps to add your telegram bot to your channel as an administrator: 
+              **Steps to add your telegram bot to your channel as an administrator**: 
               1. Create a new channel or choose an existing one that you want to use the bot in. 
               2. Add your bot to the channel as an administrator. To do this, go to the channel settings, click on "Administrators", and then click on "Add Administrator". Search for your bot and add it to the channel. 
               3. Now you can send commands to the bot in the channel by mentioning the bot using the "@" symbol followed by the bot's username. For example, "@my_bot help" will send the "help" command to the bot.
               
+              **Get Classifier-NER Output VS Get NER Output**:
+              The 'Get Classifier Ner Output' function first classifies the message as either a disaster message or a random message, and then applies the NER pipeline to the classified output. In contrast, the 'Get NER Output' function applies the NER pipeline directly to the message.
               *If you get any errors or dependency issues, feel free to reach out to me!*""")
                         
 
@@ -222,4 +225,5 @@ with demo:
     clear.click(lambda: None, None, ner_df, queue=True)  
     
 demo.queue(concurrency_count=3)
-demo.launch()
+demo.launch(share=True, debug=True) # share=True, debug=True
+