Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,59 @@
+import gradio as gr
+import joblib
+import numpy as np
+from tensorflow.keras.models import load_model
+from huggingface_hub import snapshot_download
+import unicodedata
+
+# ====== Mapping nhãn ======
+label_map = {
+    0: "Tiêu cực",
+    1: "Trung lập",
+    2: "Tích cực"
+}
+
+MAX_LEN = 200
+
+# ====== Load model ======
+local_dir = snapshot_download(
+    repo_id="phucn001/SentimentAnalysisModels",
+    local_dir="./Models"
+)
+cnn_lstm_model = load_model(f"{local_dir}/CNNLSTM/best_model.h5", compile=False)
+cnn_lstm_tokenizer = joblib.load(f"{local_dir}/CNNLSTM/tokenizer.pkl")
+cnn_label_encoder = joblib.load(f"{local_dir}/CNNLSTM/label_encoder.pkl")
+
+def normalize_text(text):
+    return unicodedata.normalize("NFC", text).strip().lower()
+
+reverse_label_map = {normalize_text(v): k for k, v in label_map.items()}
+
+def predict_cnn_lstm(text):
+    seq = cnn_lstm_tokenizer.texts_to_sequences([text])
+    padded = np.zeros((1, MAX_LEN))
+    padded[0, -len(seq[0]):] = seq[0][:MAX_LEN]
+
+    probs = cnn_lstm_model.predict(padded, verbose=0)[0]
+
+    # reorder theo label_map
+    probs_reordered = np.zeros_like(probs)
+    for i, label in enumerate(cnn_label_encoder.classes_):
+        norm_label = normalize_text(label)
+        new_index = reverse_label_map[norm_label]
+        probs_reordered[new_index] = probs[i]
+
+    pred = int(np.argmax(probs_reordered))
+    return {
+        "label": label_map[pred],
+        "probabilities": {label_map[i]: float(probs_reordered[i]) for i in range(len(probs_reordered))}
+    }
+
+demo = gr.Interface(
+    fn=predict_cnn_lstm,
+    inputs=gr.Textbox(lines=2, placeholder="Nhập câu bình luận..."),
+    outputs="json",
+    title="Sentiment Analysis - CNN-LSTM"
+)
+
+if __name__ == "__main__":
+    demo.launch()