Upload 2 files

app.py

@@ -0,0 +1,179 @@
+import streamlit as st
+from transformers import pipeline
+import numpy as np
+import torch
+
+# Set page configuration
+st.set_page_config(
+    page_title="Sentiment Analysis API",
+    page_icon="😀",
+    layout="centered",
+    initial_sidebar_state="collapsed",
+)
+
+# App title and description
+st.title("Sentiment Analysis API")
+st.write("This API uses a pre-trained BERT model to classify text sentiment as positive, negative, or neutral.")
+
+# Load the sentiment analysis model
+@st.cache_resource
+def load_model():
+    return pipeline('sentiment-analysis', model="cardiffnlp/twitter-roberta-base-sentiment")
+
+# Get the model
+model = load_model()
+
+# Sample text examples
+examples = [
+    "I absolutely love this new feature! It's amazing.",
+    "This product is terrible and doesn't work as advertised.",
+    "The weather is just okay today, nothing special."
+]
+
+# Create the UI elements
+text_input = st.text_area("Enter text to analyze:", height=150, 
+                          placeholder="Type or paste your text here...")
+
+# Add example buttons
+st.write("Or try one of these examples:")
+col1, col2, col3 = st.columns(3)
+with col1:
+    if st.button("Positive Example"):
+        text_input = examples[0]
+with col2:
+    if st.button("Negative Example"):
+        text_input = examples[1]
+with col3:
+    if st.button("Neutral Example"):
+        text_input = examples[2]
+
+# Function to analyze and display sentiment
+def analyze_sentiment(text):
+    try:
+        result = model(text)[0]
+        
+        # Map labels to user-friendly sentiment names
+        sentiment_mapping = {
+            'LABEL_0': 'Negative',
+            'LABEL_1': 'Neutral',
+            'LABEL_2': 'Positive'
+        }
+        
+        sentiment = sentiment_mapping[result['label']]
+        confidence = result['score']
+        
+        # Display results with color-coded box
+        if sentiment == "Positive":
+            st.success(f"Sentiment: {sentiment} (Confidence: {confidence:.4f})")
+        elif sentiment == "Negative":
+            st.error(f"Sentiment: {sentiment} (Confidence: {confidence:.4f})")
+        else:
+            st.info(f"Sentiment: {sentiment} (Confidence: {confidence:.4f})")
+            
+        # Display confidence as a progress bar
+        st.progress(confidence)
+        
+        # Show detailed sentiment breakdown
+        st.subheader("Sentiment Breakdown")
+        sentiment_data = {
+            'Sentiment': ['Negative', 'Neutral', 'Positive'],
+            'Score': [0, 0, 0]  # Default values
+        }
+        
+        # Update the score for the detected sentiment
+        if sentiment == "Positive":
+            sentiment_data['Score'][2] = confidence
+        elif sentiment == "Negative":
+            sentiment_data['Score'][0] = confidence
+        else:
+            sentiment_data['Score'][1] = confidence
+            
+        # Display as a horizontal bar chart
+        st.bar_chart(sentiment_data, x='Sentiment', y='Score')
+        
+    except Exception as e:
+        st.error(f"An error occurred: {str(e)}")
+
+# Process the text when the analyze button is clicked
+if st.button("Analyze Sentiment") and text_input:
+    with st.spinner("Analyzing sentiment..."):
+        analyze_sentiment(text_input)
+elif text_input:
+    st.info("Click 'Analyze Sentiment' to process the text.")
+else:
+    st.info("Please enter some text to analyze.")
+
+def analyze_sentiment(text):
+    try:
+        if len(text.split()) > 512:
+            st.error("Input too long (max 512 words). Please shorten the text.")
+            return
+        result = model(text)[0]
+        sentiment_mapping = {
+            'LABEL_0': 'Negative',
+            'LABEL_1': 'Neutral',
+            'LABEL_2': 'Positive'
+        }
+        sentiment = sentiment_mapping[result['label']]
+        confidence = result['score']
+        if sentiment == "Positive":
+            st.success(f"Sentiment: {sentiment} (Confidence: {confidence:.4f})")
+        elif sentiment == "Negative":
+            st.error(f"Sentiment: {sentiment} (Confidence: {confidence:.4f})")
+        else:
+            st.info(f"Sentiment: {sentiment} (Confidence: {confidence:.4f})")
+        st.progress(confidence)
+        st.subheader("Sentiment Breakdown")
+        sentiment_data = {
+            'Sentiment': ['Negative', 'Neutral', 'Positive'],
+            'Score': [0, 0, 0]
+        }
+        if sentiment == "Positive":
+            sentiment_data['Score'][2] = confidence
+        elif sentiment == "Negative":
+            sentiment_data['Score'][0] = confidence
+        else:
+            sentiment_data['Score'][1] = confidence
+        st.bar_chart(sentiment_data, x='Sentiment', y='Score')
+    except Exception as e:
+        st.error(f"Error analyzing sentiment: {str(e)}. Please try again or use shorter text.")
+
+# Add information about the model
+with st.expander("About the Model"):
+    st.write("""
+    This application uses the `cardiffnlp/twitter-roberta-base-sentiment` model from Hugging Face.
+    
+    The model is a RoBERTa-base model trained on ~58M tweets and fine-tuned for sentiment analysis 
+    with the TweetEval benchmark. It classifies text into three sentiment categories:
+    
+    - Negative (LABEL_0)
+    - Neutral (LABEL_1)
+    - Positive (LABEL_2)
+    
+    Source: [cardiffnlp/twitter-roberta-base-sentiment](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment)
+    """)
+
+with st.expander("Model Performance"):
+    st.write("Tested on 100 samples from `tweet_eval` dataset.")
+    if st.button("Show Test Accuracy"):
+        from datasets import load_dataset
+        dataset = load_dataset("tweet_eval", "sentiment", split="test[:100]")
+        correct = sum(1 for text, label in zip(dataset['text'], dataset['label']) if (2 if model(text)[0]['label'] == 'LABEL_2' else 0 if model(text)[0]['label'] == 'LABEL_0' else 1) == label)
+        st.write(f"Accuracy: {correct/100:.2f}")
+        
+# Footer
+st.markdown("---")
+st.markdown("Created as part of Mini Project 1: Sentiment Analysis API")
+
+@inproceedings{barbieri-etal-2020-tweeteval,
+    title = "{T}weet{E}val: Unified Benchmark and Comparative Evaluation for Tweet Classification",
+    author = "Barbieri, Francesco, Camacho-Collados, Jose, Espinosa Anke, Luis, Neves, Leonardo",
+    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
+    month = nov,
+    year = "2020",
+    address = "Online",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2020.findings-emnlp.148",
+    doi = "10.18653/v1/2020.findings-emnlp.148",
+    pages = "1644--1650"
+}

requirements.txt

@@ -0,0 +1,141 @@
+aiohappyeyeballs==2.6.1
+aiohttp==3.11.16
+aiosignal==1.3.2
+altair==5.5.0
+anyio==4.9.0
+argon2-cffi==23.1.0
+argon2-cffi-bindings==21.2.0
+arrow==1.3.0
+asttokens==3.0.0
+async-lru==2.0.5
+attrs==25.3.0
+babel==2.17.0
+beautifulsoup4==4.13.4
+bleach==6.2.0
+blinker==1.9.0
+cachetools==5.5.2
+certifi==2025.1.31
+cffi==1.17.1
+charset-normalizer==3.4.1
+click==8.1.8
+colorama==0.4.6
+comm==0.2.2
+datasets==3.5.0
+debugpy==1.8.14
+decorator==5.2.1
+defusedxml==0.7.1
+dill==0.3.8
+executing==2.2.0
+fastjsonschema==2.21.1
+filelock==3.18.0
+fqdn==1.5.1
+frozenlist==1.6.0
+fsspec==2024.12.0
+gitdb==4.0.12
+GitPython==3.1.44
+h11==0.14.0
+httpcore==1.0.8
+httpx==0.28.1
+huggingface-hub==0.30.2
+idna==3.10
+ipykernel==6.29.5
+ipython==9.1.0
+ipython_pygments_lexers==1.1.1
+ipywidgets==8.1.6
+isoduration==20.11.0
+jedi==0.19.2
+Jinja2==3.1.6
+json5==0.12.0
+jsonpointer==3.0.0
+jsonschema==4.23.0
+jsonschema-specifications==2024.10.1
+jupyter==1.1.1
+jupyter-console==6.6.3
+jupyter-events==0.12.0
+jupyter-lsp==2.2.5
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+jupyter_server==2.15.0
+jupyter_server_terminals==0.5.3
+jupyterlab==4.4.0
+jupyterlab_pygments==0.3.0
+jupyterlab_server==2.27.3
+jupyterlab_widgets==3.0.14
+MarkupSafe==3.0.2
+matplotlib-inline==0.1.7
+mistune==3.1.3
+mpmath==1.3.0
+multidict==6.4.3
+multiprocess==0.70.16
+narwhals==1.35.0
+nbclient==0.10.2
+nbconvert==7.16.6
+nbformat==5.10.4
+nest-asyncio==1.6.0
+networkx==3.4.2
+notebook==7.4.0
+notebook_shim==0.2.4
+numpy==2.2.4
+overrides==7.7.0
+packaging==24.2
+pandas==2.2.3
+pandocfilters==1.5.1
+parso==0.8.4
+pillow==11.2.1
+platformdirs==4.3.7
+prometheus_client==0.21.1
+prompt_toolkit==3.0.51
+propcache==0.3.1
+protobuf==5.29.4
+psutil==7.0.0
+pure_eval==0.2.3
+pyarrow==19.0.1
+pycparser==2.22
+pydeck==0.9.1
+Pygments==2.19.1
+python-dateutil==2.9.0.post0
+python-json-logger==3.3.0
+pytz==2025.2
+pywin32==310
+pywinpty==2.0.15
+PyYAML==6.0.2
+pyzmq==26.4.0
+referencing==0.36.2
+regex==2024.11.6
+requests==2.32.3
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rpds-py==0.24.0
+safetensors==0.5.3
+Send2Trash==1.8.3
+setuptools==78.1.0
+six==1.17.0
+smmap==5.0.2
+sniffio==1.3.1
+soupsieve==2.6
+stack-data==0.6.3
+streamlit==1.44.1
+sympy==1.13.1
+tenacity==9.1.2
+terminado==0.18.1
+tinycss2==1.4.0
+tokenizers==0.21.1
+toml==0.10.2
+torch==2.6.0
+tornado==6.4.2
+tqdm==4.67.1
+traitlets==5.14.3
+transformers==4.51.3
+types-python-dateutil==2.9.0.20241206
+typing_extensions==4.13.2
+tzdata==2025.2
+uri-template==1.3.0
+urllib3==2.4.0
+watchdog==6.0.0
+wcwidth==0.2.13
+webcolors==24.11.1
+webencodings==0.5.1
+websocket-client==1.8.0
+widgetsnbextension==4.0.14
+xxhash==3.5.0
+yarl==1.20.0