Update app.py

app.py

@@ -1,47 +1,52 @@
 # -*- coding: utf-8 -*-
-"""FA20-BCS-OO1 final app.ipynb
-
-Automatically generated by Colab
 """
 
-# !pip install emoji gradio
+Developed by Abdul S.
+FA20-BCS-OO1 final app.ipynb
 
 
+Automatically generated by Colab
+"""
 
-import joblib, pickle, pandas as pd, numpy as np
+import pandas as pd
+import numpy as np
 import gradio as gr
 from TweetNormalizer import normalizeTweet
 import seaborn as sns
 import matplotlib.pyplot as plt
-
 from transformers import pipeline
-#  seek007/taskA-DeBERTa-bweet-1.2.5
-# seek007/taskA-DeBERTa-large-1.0.0
-# seek007/taskA-DeBERTa-bweet-1.1.0
+
+# Set pandas display option to show only 2 decimal places
+pd.set_option('display.float_format', '{:.2f}'.format)
+
 pipe= pipeline(model="seek007/taskA-DeBERTa-large-1.0.0",tokenizer='seek007/taskA-DeBERTa-large-1.0.0')
 
 # pipe = joblib.load('/content/drive/MyDrive/FYPpkl models/pipeA-wTok-0.0.1.pkl')
 
 
 
-import numpy as np
-
+# 
 def predict(text=None , fil=None):
-    # Preprocess the text
-    preprocessed_text = normalizeTweet(text)
     sentiment =None
     df=None
     fig=None
+    
+    if text == None and fil == None:
+      return "Either enter text or upload .csv or .xlsx file.!"  , df, fig
+
+    # Preprocess the text
+    preprocessed_text = normalizeTweet(text)
+   
     if fil:
       if fil.name.endswith('.csv'):
-          df = pd.read_csv(fil.name, header=None)
+          df = pd.read_csv(fil.name, header=None , names=['tweet'], usecols=[0])
       elif fil.name.endswith('.xlsx') or fil.name.endswith('.xls'):
-          df = pd.read_excel(fil.name, header=None)
+          df = pd.read_excel(fil.name, header=None, names=['tweet'], usecols=[0])
       else:
           raise ValueError("Unsupported file type. Please upload a CSV or Excel file.")
 
    
-      lst = list(df[0])
+      lst = list(df.tweet)
       m =[normalizeTweet(i) for i in lst]
 
       d = pd.DataFrame(pipe.predict(m))
@@ -49,7 +54,7 @@ def predict(text=None , fil=None):
 
 
 
-      sarcastic_count = np.sum(df.label =='sarcastic')
+      sarcastic_count = np.sum(df.label == 'sarcastic')
       non_sarcastic_count = np.sum(df.label =='non_sarcastic')
 
       labels = ['Sarcastic', 'Non-Sarcastic']
@@ -62,17 +67,17 @@ def predict(text=None , fil=None):
       ax.axis('equal')  # Equal aspect ratio ensures that pie is drawn as a circle.
 
       plt.title('Sarcastic vs Non-Sarcastic Tweets')
-
+      if text == None:
+        sentiment = df['label'][0]
   
-    if text !="" or fil !=None:
+    if text != "":
       prediction = pipe.predict([preprocessed_text])[0]
       print(prediction)
      
-      sentiment = "Sarcastic" if (prediction['label'] == 'LABEL_1' or prediction['label'] =='sarcastic') else "Non Sarcastic"
+      sentiment = "Sarcastic" if prediction['label'] == 'sarcastic' else "Non Sarcastic"
       if fil == None:
         df= pd.DataFrame([{'tweet':text, 'label':sentiment}])
-    else:
-      return "Either enter text or upload .csv or .xlsx file.!"  , df, fig
+  
 
     return sentiment, df, fig
 
@@ -82,32 +87,40 @@ def predict(text=None , fil=None):
 
 file_path =gr.File(label="Upload a File")
 output = gr.Label(num_top_classes=2, label="Predicted Labels")
-demo = gr.Interface(fn=predict, inputs=[gr.Text(label="Input"),file_path], outputs=[output, gr.DataFrame(headers =['Tweets', 'Labels'], wrap=True), gr.Plot(label="Sarcasm Predictor")], title="Sarcasm Predictor")
+detector = gr.Interface(fn=predict, inputs=[gr.Text(label="Input"),file_path], outputs=[output, gr.DataFrame(headers =['Tweets', 'Labels'], wrap=True), gr.Plot(label="Sarcasm Predictor")], title="Sarcasm Predictor")
 
 # demo.launch(debug=True)
 
 
-from transformers import pipeline
+# load classifier pipeline
 pipe2 = pipeline(model="seek007/taskB-bertweet-base-trainer-1.0.0", tokenizer="seek007/taskB-bertweet-base-trainer-1.0.0")
 
+
+# classifier
 def classifyB(text=None , fil=None):
+    sentiment = None
+    df = None
+    fig = None
+    
+    if text is None and fil is None:
+      return "Either enter text or upload .csv or .xlsx file.!"  , df, fig
+
+
     # Preprocess the text
     preprocessed_text = normalizeTweet(text)
-    sentiment =None
-    df=None
-    fig=None
+    
     
     labels = ['sarcasm', 'irony','Staire', 'understatement','overstatement', 'rhetorical question']
     
     if fil:
       if fil.name.endswith('.csv'):
-          df = pd.read_csv(fil.name, header=None)
+          df = pd.read_csv(fil.name, header=None, names=['tweet'], usecols=[0])
       elif fil.name.endswith('.xlsx') or fil.name.endswith('.xls'):
-          df = pd.read_excel(fil.name, header=None)
+          df = pd.read_excel(fil.name, header=None, names=['tweet'], usecols=[0])
       else:
           raise ValueError("Unsupported file type. Please upload a CSV or Excel file.")
 
-      lst = list(df[0])
+      lst = list(df['tweet'])
       m =[normalizeTweet(i) for i in lst]
       d = pipe2(m)
 
@@ -129,25 +142,27 @@ def classifyB(text=None , fil=None):
       plt.title('Result: Count Plot')  # Add a title to the plot
       plt.xlabel('label')  # Add label for the x-axis
       plt.ylabel('Count')
-      if text == None:
+      if text is None:
         sentiment = df['label'][0]
         
      # Perform sentiment prediction
-    if text != None:
+    if text:
       prediction = pipe2([preprocessed_text])[0]
       # print(prediction["label"])
       labels = prediction['label']
-      # scores = prediction['score']
+      scores = prediction['score']
       sentiment = labels
-    
+      if fil is None:
+        df= pd.DataFrame([{'tweet':text, 'label':sentiment, "score": scores}])
+
     return sentiment, df, fig
 
 
 
 file_path =gr.File(label="Upload a File")
 label = gr.Label( label="Labels")
-classificationB = gr.Interface(classifyB, inputs=[gr.Text(label="Input"),file_path], outputs= [label, gr.DataFrame(headers =['Tweets', 'Label', "Score"], wrap=True), gr.Plot(label="Sarcasm classifier")], title="Sarcasm Classifier")  #,theme= 'darkhuggingface'
+classifier = gr.Interface(classifyB, inputs=[gr.Text(label="Input"),file_path], outputs= [label, gr.DataFrame(headers =['Tweets', 'Label', "Score"], wrap=True), gr.Plot(label="Sarcasm classifier")], title="Sarcasm Classifier")  #,theme= 'darkhuggingface'
 
-main = gr.TabbedInterface([demo, classificationB],['Analysizer', 'Classifier'], title="Sarcasm Predictor: An Optimized Sentiment Analysis system" )
+main = gr.TabbedInterface([detector, classifier],['Analysizer', 'Classifier'], title="Sarcasm Predictor: An Optimized Sentiment Analysis system" )
 
 main.launch(share=True)