Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,41 @@
+FROM python:3.12-slim
+
+ENV PYTHONUNBUFFERED=1 \
+    DEBIAN_FRONTEND=noninteractive \
+    PYTHONPATH=/app:/app/common:$PYTHONPATH
+
+WORKDIR /app
+
+# System deps
+RUN apt-get update && apt-get install -y \
+    git build-essential curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install uv
+RUN curl -LsSf https://astral.sh/uv/install.sh | sh
+ENV PATH="/root/.local/bin:$PATH"
+
+# Copy project metadata
+COPY app.py .
+COPY pyproject.toml .
+COPY uv.lock .
+
+
+# Install dependencies using uv, then export and install with pip to system
+RUN uv sync --frozen --no-dev && \
+    uv pip install -e . --system
+
+# --- Pre-download model to speed up startup ---
+RUN python - <<EOF
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+model_id = "mishrabp/bert-base-uncased-tweet-sentiment-analysis"
+AutoTokenizer.from_pretrained(model_id)
+AutoModelForSequenceClassification.from_pretrained(model_id)
+EOF
+
+# --- Expose Hugging Face Space port ---
+EXPOSE 7860
+
+# --- Run Streamlit app ---
+CMD ["streamlit", "run", "app.py", "--server.port=7860", "--server.address=0.0.0.0"]

README.md

@@ -1,10 +1,67 @@
 ---
-title: Twitter Sentiment Analysis
-emoji: 🔥
-colorFrom: indigo
-colorTo: yellow
+title: Tweet Sentiment Analyzer
+emoji: 📝
+colorFrom: blue
+colorTo: green
 sdk: docker
-pinned: false
+app_file: app.py
+pinned: true
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Tweet Sentiment Analyzer
+
+This is a **Streamlit app** that uses a fine-tuned BERT model to classify the sentiment of tweets.  
+It predicts whether a tweet expresses **joy, sadness, anger, love, fear, or surprise**.
+
+---
+
+## How to Use
+
+1. Enter one or multiple tweets in the text area (one per line).  
+2. Click **Analyze Sentiment**.  
+3. The app will display each tweet's predicted sentiment along with the confidence score.
+
+---
+
+## Example
+
+Tweet: I love spending time with my friends!
+Sentiment: joy (0.95)
+
+Tweet: I feel so sad about the news today.
+Sentiment: sadness (0.88)
+
+---
+
+## Model Used
+
+- **Hugging Face Model:** `mishrabp/bert-base-uncased-tweet-sentiment-analysis`
+- **Base Model:** `bert-base-uncased`
+- **Task:** Tweet Sentiment Analysis
+- **Language:** English
+
+---
+
+## About
+
+This app is useful for:
+
+- Social media managers to monitor audience sentiment.
+- Researchers analyzing public reactions.
+- Companies tracking customer feedback.
+- Quick, automated sentiment analysis pipelines.
+
+---
+
+## Installation (for local run)
+
+```bash
+pip install streamlit transformers torch
+streamlit run app.py
+```
+
+## Author
+
+Developed by Bibhu Mishra
+
+---

app.py

@@ -0,0 +1,52 @@
+import streamlit as st
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
+
+# --- Page config ---
+st.set_page_config(
+    page_title="Tweet Sentiment Analyzer",
+    page_icon="📝",
+    layout="centered"
+)
+
+# --- App title and description ---
+st.title("📝 Tweet Sentiment Analyzer")
+st.markdown("""
+This app uses a fine-tuned BERT model (**_mishrabp/bert-base-uncased-tweet-sentiment-analysis_**) to classify the sentiment of tweets.
+You can enter one or multiple tweets (one per line), and the model will predict 
+whether each tweet expresses **joy, sadness, anger, love, fear, or surprise**.
+""")
+
+# --- Load model and tokenizer ---
+@st.cache_resource(show_spinner=True)
+def load_model(model_name):
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForSequenceClassification.from_pretrained(model_name)
+    classifier = pipeline("text-classification", model=model, tokenizer=tokenizer)
+    return classifier
+
+model_name = "mishrabp/bert-base-uncased-tweet-sentiment-analysis"
+classifier = load_model(model_name)
+
+# --- Text input for tweets ---
+tweets_input = st.text_area(
+    "Enter your tweets (one per line):",
+    height=200
+)
+
+# --- Button to run classification ---
+if st.button("Analyze Sentiment"):
+    if not tweets_input.strip():
+        st.warning("Please enter at least one tweet to analyze.")
+    else:
+        tweets = [line.strip() for line in tweets_input.split("\n") if line.strip()]
+        with st.spinner("Classifying tweets..."):
+            results = classifier(tweets)
+
+        # --- Display results ---
+        st.subheader("Results:")
+        for tweet, result in zip(tweets, results):
+            label = result["label"]
+            score = result["score"]
+            st.write(f"**Tweet:** {tweet}")
+            st.write(f"**Sentiment:** {label} ({score:.2f})")
+            st.markdown("---")

pyproject.toml

@@ -0,0 +1,19 @@
+[build-system]
+requires = ["setuptools>=42", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "tweet-sentiment-analyzer"
+version = "0.1.0"
+description = "Streamlit app for tweet sentiment analysis using a fine-tuned BERT model."
+authors = [
+    {name="Bibhu Mishra", email="bibhu.mishra@example.com"}
+]
+readme = "README.md"
+requires-python = ">=3.8"
+
+dependencies = [
+    "streamlit>=1.24.1",
+    "transformers>=4.30.0",
+    "torch>=2.1.0",
+]