Update app.py

app.py

@@ -1,15 +1,18 @@
-import pandas as pd
-from sklearn.feature_extraction.text import CountVectorizer
-from sklearn.naive_bayes import MultinomialNB
-import gradio as gr
 import csv
 
-# Load Dataset
-try:
-    df = pd.read_csv("dataset.csv")
-except FileNotFoundError:
-    data = {"pertanyaan": [], "jawaban": []}
-    df = pd.DataFrame(data)
+# Nama file input dan output
+input_file = "dataset.csv"
+output_file = "cleaned_dataset.csv"
 
-# Preprocessing Data
-vectorizer = CountVectorize
+# Bersihkan dataset
+with open(input_file, "r") as infile, open(output_file, "w", newline="") as outfile:
+    reader = csv.reader(infile)
+    writer = csv.writer(outfile)
+
+    # Periksa setiap baris
+    for row in reader:
+        # Hanya simpan baris dengan 2 kolom
+        if len(row) == 2:
+            writer.writerow(row)
+
+print(f"Dataset telah dibersihkan. Simpan ke: {output_file}")