commit d53f7ec5a6088305f082864149d34c40c1034238
Author: 202210715288 FATAH SABILA ROSYAD <202210715288@mhs.ubharajaya.ac.id>
Date:   Mon Jan 19 18:18:20 2026 +0700

    Initial commit - NLP text classification project

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..4dfd091
--- /dev/null
+++ b/README.md
@@ -0,0 +1,20 @@
+# Klasifikasi Topik Berita Menggunakan NLP
+Project ini mengimplementasikan Natural Language Processing (NLP)
+untuk mengklasifikasikan teks berita Bahasa Indonesia ke dalam
+tiga kategori: Politik, Olahraga, dan Teknologi.
+
+## Metode
+- Preprocessing teks
+- TF-IDF
+- Multinomial Naive Bayes
+
+## Tools
+- Python
+- Scikit-learn
+- Streamlit
+
+## Cara Menjalankan
+1. Install dependency
+   pip install -r requirements.txt
+2. Jalankan aplikasi
+   streamlit run app.py
diff --git a/app.py b/app.py
new file mode 100644
index 0000000..9a5cb12
--- /dev/null
+++ b/app.py
@@ -0,0 +1,28 @@
+import streamlit as st
+import joblib
+import re
+
+# Load model & vectorizer
+model = joblib.load("model_nb.pkl")
+vectorizer = joblib.load("tfidf_vectorizer.pkl")
+
+st.title("📰 Klasifikasi Topik Berita (NLP)")
+st.write("Masukkan teks berita berbahasa Indonesia")
+
+text = st.text_area("Teks Berita", height=200)
+
+def preprocess_text(text):
+    text = text.lower()
+    text = re.sub(r"http\S+", "", text)
+    text = re.sub(r"[^a-zA-Z\s]", " ", text)
+    text = re.sub(r"\s+", " ", text).strip()
+    return text
+
+if st.button("Klasifikasikan"):
+    if text.strip() == "":
+        st.warning("Teks tidak boleh kosong!")
+    else:
+        clean_text = preprocess_text(text)
+        text_tfidf = vectorizer.transform([clean_text])
+        prediction = model.predict(text_tfidf)[0]
+        st.success(f"Prediksi Topik: **{prediction}**")
diff --git a/model_nb.pkl b/model_nb.pkl
new file mode 100644
index 0000000..a12251e
Binary files /dev/null and b/model_nb.pkl differ
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..a0fc4c1
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,6 @@
+streamlit
+scikit-learn
+pandas
+numpy
+joblib
+Sastrawi
\ No newline at end of file
diff --git a/tfidf_vectorizer.pkl b/tfidf_vectorizer.pkl
new file mode 100644
index 0000000..74d269b
Binary files /dev/null and b/tfidf_vectorizer.pkl differ