Update model + app from GitHub Actions

model/vectorizer.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbcc0212d7ffb1b250a2b12940ffd1a8be6bdcdd9ff96bb061065471e2ce75f0
+oid sha256:2c3bc32b8b1748519f68b771a6236026f16e6f0f2b4810129e36f777c99ff5fe
 size 6956

src/evaluate.py

@@ -35,7 +35,6 @@ def evaluate():
     with open("model/eval_report.json", "w") as f:
         json.dump({"report": report, "confusion_matrix": cm}, f, indent=2)
 
-    # pilih label target dinamis
     target_label = "judi" if "judi" in report else list(report.keys())[0]
     summary = {
         "accuracy": report["accuracy"],

src/preprocessing.py

@@ -7,8 +7,8 @@ import joblib
 
 def clean_text(text: str) -> str:
     text = text.lower()
-    text = re.sub(r"http\S+|www\S+|https\S+", "", text)  # remove urls
-    text = re.sub(r"\d+", " ", text)  # remove digits
+    text = re.sub(r"http\S+|www\S+|https\S+", "", text)  
+    text = re.sub(r"\d+", " ", text)  
     text = text.translate(str.maketrans("", "", string.punctuation))
     text = re.sub(r"\s+", " ", text).strip()
     return text

src/train.py

@@ -41,10 +41,8 @@ def train():
     with mlflow.start_run():
         model.fit(X_train, y_train)
 
-        # predictions
         y_pred = model.predict(X_test)
 
-        # metrics
         precision, recall, f1, _ = precision_recall_fscore_support(y_test, y_pred, average="binary", pos_label="judi")
         acc = accuracy_score(y_test, y_pred)
 
@@ -53,7 +51,6 @@ def train():
         mlflow.log_metric("f1_score", float(f1))
         mlflow.log_metric("accuracy", float(acc))
 
-        # save model
         model_path = os.path.join(MODEL_DIR, "saved_model.joblib")
         joblib.dump(model, model_path)
         mlflow.log_artifact(model_path, artifact_path="models")