Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,87 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch.nn.functional as F
 
-"""
-# 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])),
-    ))
+# ================= CONFIG STREAMLIT =================
+st.set_page_config(
+    page_title="Emotion Mining - Tom Lembong Case",
+    page_icon="💬",
+    layout="wide"
+)
+
+# ================= MODEL CONFIG =================
+MODEL_PATH = "./model"  # ganti path ke folder model kamu
+LABELS = ["SADNESS", "ANGER", "HOPE", "DISAPPOINTMENT", "SUPPORT"]
+
+# ================= LOAD MODEL =================
+@st.cache_resource(show_spinner=True)
+def load_model(path):
+    tokenizer = AutoTokenizer.from_pretrained(path)
+    model = AutoModelForSequenceClassification.from_pretrained(path)
+    model.eval()
+    return tokenizer, model
+
+tokenizer, model = load_model(MODEL_PATH)
+
+# ================= SIDEBAR =================
+st.sidebar.title("💬 Emotion Mining")
+st.sidebar.markdown("Masukkan komentar Instagram terkait kasus **Tom Lembong** dan dapatkan klasifikasi emosi.")
+
+input_text = st.sidebar.text_area("📝 Komentar Instagram", height=150)
+predict_btn = st.sidebar.button("🚀 Klasifikasikan")
+
+# ================= MAIN PAGE =================
+st.title("📊 Emotion Mining - Kasus Tom Lembong")
+
+with st.expander("ℹ️ Tentang Dataset", expanded=True):
+    st.markdown("""
+    **Latar Belakang Kasus:**  
+    Tom Lembong, mantan Menteri Perdagangan, pada tahun 2024 ditetapkan sebagai tersangka kasus korupsi impor gula. 
+    Ia sempat dijatuhi hukuman, namun kemudian mendapat abolisi dari Presiden. 
+    Kasus ini menimbulkan berbagai emosi publik di media sosial, khususnya Instagram.
+
+    **Tujuan Dataset:**  
+    Mengklasifikasikan komentar publik ke dalam **5 kategori emosi**:
+    - 😢 **SADNESS** – komentar sedih atau prihatin  
+    - 😡 **ANGER** – komentar marah atau mengecam  
+    - 🙏 **HOPE** – komentar penuh harapan atau doa  
+    - 😞 **DISAPPOINTMENT** – rasa kecewa atau frustrasi  
+    - 🤝 **SUPPORT** – dukungan atau semangat  
+
+    **Evaluasi:**  
+    Model dievaluasi menggunakan **Macro F1-Score**, agar performa tetap seimbang meskipun distribusi label tidak merata.
+    """)
+
+st.markdown("---")
+
+# ================= PREDIKSI =================
+if predict_btn:
+    if not input_text.strip():
+        st.warning("⚠️ Masukkan komentar terlebih dahulu!")
+    else:
+        # Tokenisasi
+        inputs = tokenizer(input_text, return_tensors="pt", truncation=True, padding=True, max_length=128)
+
+        # Inference
+        with torch.no_grad():
+            outputs = model(**inputs)
+            probs = F.softmax(outputs.logits, dim=-1).squeeze().tolist()
+
+        # Ambil hasil
+        pred_idx = int(torch.argmax(outputs.logits))
+        pred_label = LABELS[pred_idx]
+
+        # Layout 2 kolom: Hasil + Chart
+        col1, col2 = st.columns([1, 2])
+
+        with col1:
+            st.markdown("### 📌 Hasil Prediksi")
+            st.success(f"**Emosi:** {pred_label}")
+
+        with col2:
+            st.markdown("### 📊 Distribusi Probabilitas")
+            st.bar_chart({label: prob for label, prob in zip(LABELS, probs)})
+
+st.markdown("---")
+st.caption("Made with ❤️ by Akmal | Powered by HuggingFace & Streamlit")