Initial commit for hoax detector

app.py

@@ -1,72 +0,0 @@
-import gradio as gr
-import pickle
-from transformers import pipeline
-import re
-import unicodedata
-
-# Load pipelines
-qa_pipeline = pipeline("question-answering", model="Rifky/Indobert-QA", tokenizer="Rifky/Indobert-QA")
-ner_pipeline = pipeline("ner", model="cahya/bert-base-indonesian-NER", tokenizer="cahya/bert-base-indonesian-NER", grouped_entities=True)
-
-# Load model hoax
-with open("ensemble_model.pkl", "rb") as f:
-    model = pickle.load(f)
-
-with open("vectorizer.pkl", "rb") as f:
-    vectorizer = pickle.load(f)
-
-def clean_text(text):
-    text = re.sub(r'[\n\r]+', ' ', text)
-    text = re.sub(r'\s{2,}', ' ', text)
-    text = text.strip()
-    text = unicodedata.normalize('NFKC', text)
-    text = text.lower()
-    text = re.sub(r'https?://\S+|www\.\S+', ' url ', text)
-    asian_char_pattern = re.compile(
-        r'[\u4e00-\u9FFF\u30A0-\u30FF\u3040-\u309F\uAC00-\uD7AF\u1100-\u11FF\u3130-\u318F]'
-    )
-    text = asian_char_pattern.sub(' ', text)
-    unwanted_scripts_pattern = re.compile(
-        r'[\u2D30-\u2D7F\uA980-\uA9DF\u1E00-\u1EFF\u0250-\u02AF\u1D00-\u1D7F]'
-    )
-    text = ' '.join(word for word in text.split() if not unwanted_scripts_pattern.search(word))
-    text = re.sub(r'[^a-z0-9\s.,!?;:\'\"()-]', ' ', text)
-    return re.sub(r'\s{2,}', ' ', text).strip()
-
-# === Fungsi Utama ===
-def detect_hoax(text):
-    cleaned = clean_text(text)
-    tfidf = vectorizer.transform([cleaned])
-    prediction = model.predict(tfidf)[0]
-    return "Hoaks" if prediction == 1 else "Bukan Hoaks"
-
-def run_qa(context, question):
-    if not context or not question:
-        return "Masukkan context dan pertanyaan."
-    result = qa_pipeline(question=question, context=context)
-    return result["answer"]
-
-def run_ner(text):
-    if not text:
-        return []
-    result = ner_pipeline(text)
-    return [(ent["word"], ent["entity_group"]) for ent in result]
-
-# === Gradio UI ===
-hoax_tab = gr.Interface(fn=detect_hoax, inputs="text", outputs="text", title="Deteksi Hoaks")
-
-qa_tab = gr.Interface(
-    fn=run_qa,
-    inputs=[gr.Textbox(label="Context"), gr.Textbox(label="Pertanyaan")],
-    outputs="text",
-    title="Question Answering"
-)
-
-ner_tab = gr.Interface(
-    fn=run_ner,
-    inputs="text",
-    outputs=gr.HighlightedText(label="Hasil NER", combine_adjacent=True),
-    title="Named Entity Recognition"
-)
-
-gr.TabbedInterface([hoax_tab, qa_tab, ner_tab], ["Deteksi Hoaks", "QA", "NER"]).launch()

requirements.txt

@@ -2,4 +2,5 @@ gradio
 scikit-learn
 transformers
 torch
-regex
+regex
+joblib