1

app.py

@@ -0,0 +1,120 @@
+import streamlit as st
+import pandas as pd
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+import torch
+import matplotlib.pyplot as plt
+from datasets import Dataset
+import asyncio
+
+# Handle asyncio loop issues
+try:
+    asyncio.get_running_loop()
+except RuntimeError:  # No running event loop
+    asyncio.run(asyncio.sleep(0))
+
+# Load pre-trained model and tokenizer
+MODEL_PATH = "distilbert-base-uncased-finetuned-sst-2-english"  # Default Hugging Face sentiment model
+model = AutoModelForSequenceClassification.from_pretrained(MODEL_PATH)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
+
+# Define a sentiment analysis function
+def sentiment_analysis(text):
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
+    outputs = model(**inputs)
+    probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1)
+    sentiment = torch.argmax(probabilities, dim=1).item()
+    confidence = torch.max(probabilities, dim=1).values.item()
+    return ("POSITIVE" if sentiment == 1 else "NEGATIVE", confidence)
+
+# Streamlit app
+st.title("Twitter Sentiment Analysis App")
+st.write("Analyze sentiments in Twitter-like text data using a pre-trained model.")
+
+# Tabs for navigation
+tab1, tab2 = st.tabs(["Analyze Sentiments", "Sample Dataset"])
+
+with tab1:
+    st.header("Analyze Sentiments")
+    st.write("Upload a dataset to analyze sentiments of text data.")
+
+    # File uploader
+    data_file = st.file_uploader("Upload your CSV file", type=["csv"])
+
+    if data_file is not None:
+        # Read the dataset
+        data = pd.read_csv(data_file)
+
+        # Display the dataset
+        st.subheader("Dataset Preview")
+        st.write(data.head())
+
+        # Check for text column selection
+        text_column = st.selectbox("Select the column containing text for analysis:", data.columns)
+
+        if st.button("Analyze Sentiment"):
+            # Clean the text column: Remove NaN values and ensure text input is string type
+            data[text_column] = data[text_column].fillna("").astype(str)
+
+            # Perform sentiment analysis
+            st.write("Analyzing sentiments...")
+            results = data[text_column].apply(lambda x: sentiment_analysis(x))
+            data['Sentiment'] = results.apply(lambda x: x[0])
+            data['Confidence'] = results.apply(lambda x: x[1])
+
+            # Display results
+            st.subheader("Analysis Results")
+            st.write(data[[text_column, 'Sentiment', 'Confidence']])
+
+            # Plot sentiment distribution
+            st.subheader("Sentiment Distribution")
+            sentiment_counts = data['Sentiment'].value_counts()
+            fig, ax = plt.subplots()
+            sentiment_counts.plot(kind='bar', ax=ax, color=['green', 'blue', 'red'])
+            ax.set_title("Sentiment Distribution")
+            ax.set_xlabel("Sentiment")
+            ax.set_ylabel("Count")
+            st.pyplot(fig)
+
+        # Option to download results
+        st.subheader("Download Results")
+        csv = data.to_csv(index=False)
+        st.download_button(
+            label="Download Sentiment Analysis Results",
+            data=csv,
+            file_name="sentiment_analysis_results.csv",
+            mime="text/csv",
+        )
+    else:
+        st.write("Please upload a dataset to proceed.")
+
+with tab2:
+    st.header("Sample Dataset")
+    st.write("Download a sample dataset to try out the app.")
+
+    # Provide a sample dataset for download
+    sample_data = pd.DataFrame({
+        "Tweet": [
+            "I love this product! It's amazing.",
+            "This is the worst service I have ever received.",
+            "I'm not sure how I feel about this.",
+            "Absolutely fantastic experience!",
+            "Terrible. Would not recommend."
+        ]
+    })
+    st.write(sample_data)
+
+    sample_csv = sample_data.to_csv(index=False)
+    st.download_button(
+        label="Download Sample Dataset",
+        data=sample_csv,
+        file_name="sample_twitter_dataset.csv",
+        mime="text/csv",
+    )
+
+    st.write("Follow these steps:")
+    st.markdown("""
+    1. Go to the **Analyze Sentiments** tab.
+    2. Upload the sample dataset or your own dataset in CSV format.
+    3. Select the column containing the text to analyze.
+    4. Click **Analyze Sentiment** to view results and download them.
+    """)

requirements.txt

@@ -0,0 +1,5 @@
+streamlit
+pandas
+transformers
+torch
+matplotlib