Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,97 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import torch
+import torch.nn.functional as F
+import numpy as np
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from normalizer import normalize
+
+st.set_page_config(page_title="Political Sentiment AI", page_icon="🇧🇩", layout="wide")
+
+st.markdown("""
+    <style>
+    .main { background-color: #f8f9fa; }
+    .stTextArea textarea { border-radius: 15px; border: 2px solid #e0e0e0; }
+    .sentiment-card { padding: 25px; border-radius: 15px; background-color: white; box-shadow: 0 4px 15px rgba(0,0,0,0.05); margin-bottom: 20px; border-left: 10px solid; }
+    .model-box { background-color: #ffffff; padding: 15px; border-radius: 10px; border: 1px solid #eee; text-align: center; }
+    .bar-container { width: 100%; background-color: #f1f1f1; border-radius: 10px; margin: 5px 0 15px 0; }
+    .bar-fill { height: 20px; border-radius: 10px; text-align: center; color: white; font-size: 12px; line-height: 20px; font-weight: bold; }
+    </style>
+    """, unsafe_allow_html=True)
+
+id2label = {0: 'Very Negative', 1: 'Negative', 2: 'Neutral', 3: 'Positive', 4: 'Very Positive'}
+label_colors = {
+    'Very Negative': '#D32F2F', 'Negative': '#F44336', 
+    'Neutral': '#757575', 'Positive': '#4CAF50', 'Very Positive': '#1B5E20'
+}
+
+@st.cache_resource
+def load_all_transformers():
+    # Replace 'your-username' with your actual Hugging Face username
+    model_repos = {
+        "BanglaBERT": "rocky250/political-banglabert",
+        "mBERT": "rocky250/political-mbert",
+        "B-Base": "rocky250/political-bbase",
+        "XLM-R": "rocky250/political-xlmr"
+    }
+    loaded_models = {}
+    for name, repo_path in model_repos.items():
+        tokenizer = AutoTokenizer.from_pretrained(repo_path)
+        model = AutoModelForSequenceClassification.from_pretrained(repo_path)
+        loaded_models[name] = (tokenizer, model)
+    return loaded_models
+
+models_dict = load_all_transformers()
+
+def get_detailed_prediction(text):
+    clean_text = normalize(text)
+    all_probs = []
+    votes = []
+    for name, (tokenizer, model) in models_dict.items():
+        inputs = tokenizer(clean_text, return_tensors="pt", truncation=True, padding=True, max_length=128)
+        with torch.no_grad():
+            logits = model(**inputs).logits
+            probs = F.softmax(logits, dim=1).numpy()[0]
+            all_probs.append(probs)
+            prediction_id = np.argmax(probs)
+            votes.append(id2label[prediction_id])
+    avg_probs = np.mean(all_probs, axis=0)
+    final_vote = max(set(votes), key=votes.count)
+    return final_vote, votes, avg_probs
+
+st.title("🇧🇩 Political Sentiment Analysis")
+st.markdown("Advanced Multi-Model Ensemble Dashboard")
+
+with st.container():
+    st.markdown('<div class="sentiment-card" style="border-left-color: #007BFF;">', unsafe_allow_html=True)
+    user_input = st.text_area("Input Political Comment:", height=120)
+    analyze_btn = st.button("🚀 Analyze Sentiment")
+    st.markdown('</div>', unsafe_allow_html=True)
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+if analyze_btn:
+    if user_input.strip() == "":
+        st.warning("Please provide input text.")
+    else:
+        with st.spinner('Fetching models from Cloud & Analyzing...'):
+            final_res, all_votes, avg_probs = get_detailed_prediction(user_input)
+            col1, col2 = st.columns([1, 1])
+            with col1:
+                st.markdown(f"""
+                    <div class="sentiment-card" style="border-left-color: {label_colors[final_res]};">
+                        <h3 style="margin:0;">Ensemble Decision</h3>
+                        <h1 style="color: {label_colors[final_res]}; margin:0;">{final_res}</h1>
+                    </div>
+                """, unsafe_allow_html=True)
+                for i in range(5):
+                    label = id2label[i]
+                    prob = avg_probs[i] * 100
+                    st.markdown(f"""
+                        <div style="display: flex; justify-content: space-between;"><span>{label}</span><span>{prob:.1f}%</span></div>
+                        <div class="bar-container"><div class="bar-fill" style="width: {prob}%; background-color: {label_colors[label]};"></div></div>
+                    """, unsafe_allow_html=True)
+            with col2:
+                m_names = list(models_dict.keys())
+                m_cols = st.columns(2)
+                for i in range(4):
+                    with m_cols[i % 2]:
+                        vote = all_votes[i]
+                        st.markdown(f'<div class="model-box"><small>{m_names[i]}</small><div style="color: {label_colors[vote]}; font-weight: bold;">{vote}</div></div><br>', unsafe_allow_html=True)