Create app.py

app.py

@@ -0,0 +1,79 @@
+import gradio as gr
+import pandas as pd
+import numpy as np
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from textblob import TextBlob
+import os
+from huggingface_hub import login
+
+# Get the Hugging Face API token from the environment variable
+hf_token = os.getenv("pasavectoi")
+login(hf_token)
+
+# Load the dataset from the local file
+data = pd.read_csv('twitter_dataset.csv').head(1000)
+
+# Calculate sentiment polarity and popularity
+data['Sentiment'] = data['Text'].apply(lambda x: TextBlob(x).sentiment.polarity)
+data['Popularity'] = data['Retweets'] + data['Likes']
+data['Popularity'] = (data['Popularity'] - data['Popularity'].mean()) / data['Popularity'].std()
+data['Popularity'] = data['Popularity'] / data['Popularity'].abs().max()
+
+# Load the fake news classification model
+model_name = "hamzab/roberta-fake-news-classification"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model = model.to(device)
+
+# Process tweets in batches to avoid memory issues
+batch_size = 100
+predictions = []
+for i in range(0, len(data), batch_size):
+    batch = data['Text'][i:i + batch_size].tolist()
+    inputs = tokenizer(batch, return_tensors="pt", padding=True, truncation=True, max_length=128)
+    inputs = {key: val.to(device) for key, val in inputs.items()}
+    with torch.no_grad():
+        outputs = model(**inputs)
+    predictions.extend(outputs.logits.argmax(dim=1).cpu().numpy())
+
+data['Fake_News_Prediction'] = predictions
+data['Credibility'] = data['Fake_News_Prediction'].apply(lambda x: 1 if x == 1 else -1)
+
+# Define the prediction and recommendation function
+def predict_and_recommend(title, text, visibility_weight, sentiment_weight, popularity_weight):
+    # Adjust weights and calculate the final score
+    total_weight = visibility_weight + sentiment_weight + popularity_weight
+    visibility_weight /= total_weight
+    sentiment_weight /= total_weight
+    popularity_weight /= total_weight
+
+    # Update final visibility score with user-defined weights
+    data['User_Final_Visibility_Score'] = (
+        data['Credibility'] * visibility_weight +
+        data['Sentiment'] * sentiment_weight +
+        data['Popularity'] * popularity_weight
+    )
+    # Sort and randomly sample 10 recommendations
+    top_100_data = data.nlargest(100, 'User_Final_Visibility_Score')
+    recommended_data = top_100_data.sample(10)
+
+    return recommended_data[['Text', 'User_Final_Visibility_Score']]
+
+# Set up Gradio interface
+iface = gr.Interface(
+    fn=predict_and_recommend,
+    inputs=[
+        gr.Textbox(label="Title"),
+        gr.Textbox(label="Text", lines=10),
+        gr.Slider(0, 1, 0.5, label="Visibility Weight"),
+        gr.Slider(0, 1, 0.3, label="Sentiment Weight"),
+        gr.Slider(0, 1, 0.2, label="Popularity Weight")
+    ],
+    outputs="dataframe",
+    title="Customizable Fake News Recommendation System",
+    description="Adjust weights to receive customized tweet recommendations based on visibility, sentiment, and popularity."
+)
+
+iface.launch()