First upload

config.json

@@ -0,0 +1,30 @@
+{
+  "emb_model_name": "paraphrase-multilingual-MiniLM-L12-v2",
+  "text_col": "Metin",
+  "label_cols": [
+    "cumle_uzunlugu",
+    "kelime_sikligi",
+    "zamir_hatalari",
+    "baglac_hatalari",
+    "anlam_belirsizligi",
+    "sozcuk_seciminde_tutarsizlik"
+  ],
+  "label_thresholds": {
+    "cumle_uzunlugu": 0.5,
+    "kelime_sikligi": 0.30000000000000004,
+    "zamir_hatalari": 0.65,
+    "baglac_hatalari": 0.30000000000000004,
+    "anlam_belirsizligi": 0.45000000000000007,
+    "sozcuk_seciminde_tutarsizlik": 0.55
+  },
+  "weights": {
+    "cumle_uzunlugu": 1.0,
+    "kelime_sikligi": 1.0,
+    "zamir_hatalari": 1.5,
+    "baglac_hatalari": 1.0,
+    "anlam_belirsizligi": 1.0,
+    "sozcuk_seciminde_tutarsizlik": 1.0
+  },
+  "risk_threshold": 1.5,
+  "min_pos_needed": 2
+}

predict_runtime.py

@@ -0,0 +1,56 @@
+import os, json, joblib
+import numpy as np
+import pandas as pd
+from sentence_transformers import SentenceTransformer
+
+def load_bundle(bundle_dir):
+    with open(os.path.join(bundle_dir, "config.json"), "r", encoding="utf-8") as f:
+        cfg = json.load(f)
+    emb_model = SentenceTransformer(cfg["emb_model_name"])
+    models = {}
+    for c in cfg["label_cols"]:
+        p = os.path.join(bundle_dir, f"xgb_{c}.joblib")
+        if os.path.exists(p):
+            models[c] = joblib.load(p)
+    return emb_model, models, cfg
+
+def predict_weighted_risk(texts, emb_model, models, cfg):
+    if isinstance(texts, str):
+        texts = [texts]
+    X = emb_model.encode(list(texts), convert_to_numpy=True)
+    label_cols = cfg["label_cols"]
+    label_thresholds = cfg["label_thresholds"]
+    weights = pd.Series(cfg["weights"])
+    risk_thr = cfg["risk_threshold"]
+
+    # Proba
+    proba = {}
+    for c in label_cols:
+        if c in models:
+            proba[c] = models[c].predict_proba(X)[:,1]
+        else:
+            proba[c] = np.zeros(len(texts))
+    proba = pd.DataFrame(proba)[label_cols]
+
+    # 0/1 tahmin
+    yhat_bin = pd.DataFrame({c: (proba[c] >= label_thresholds.get(c, 0.5)).astype(int) for c in label_cols})
+
+    # Ağırlıklı skor + risk
+    weighted = (yhat_bin * weights).sum(axis=1)
+    risk_pred = (weighted >= risk_thr).astype(int)
+
+    return {
+        "proba": proba,
+        "yhat_bin": yhat_bin,
+        "weighted_score": weighted,
+        "risk_pred": risk_pred
+    }
+
+if __name__ == "__main__":
+    bundle_dir = "alz_sbert_weighted_export"
+    emb, mdl, cfg = load_bundle(bundle_dir)
+    sample = "Dün sabah erken kalktım, kahvaltıdan sonra markete gittim. Akşam ailemle buluştum."
+    out = predict_weighted_risk(sample, emb, mdl, cfg)
+    print("Risk tahmini:", int(out["risk_pred"].values[0]))
+    print("Ağırlıklı skor:", float(out["weighted_score"].values[0]))
+    print("Etiket 0/1:", out["yhat_bin"].to_dict(orient="list"))

requirements.txt

@@ -0,0 +1,5 @@
+sentence-transformers
+xgboost
+joblib
+pandas
+scikit-learn

xgb_anlam_belirsizligi.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31ee6ad9a1685cec6a90039f7db6aafb52112362ffabcc5055fe97a470ab5904
+size 630429

xgb_baglac_hatalari.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d4ab3adfd0535d87aba530c56e3338b9fa16c24b65a173213259447616446ab
+size 596767

xgb_cumle_uzunlugu.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4607a0a63200d4aaf8c45788e3f45e3c3f5fd1d92af4d2e424af31336bcc06bf
+size 647293

xgb_kelime_sikligi.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52efc12518c2255d25ef1cc66c117b47560d4e520d665c217354649933e48d37
+size 639201

xgb_sozcuk_seciminde_tutarsizlik.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3441479049f1d8d991f9742b2694cd399baf5a4328aae1feab153dc0b3f901f0
+size 652597

xgb_zamir_hatalari.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19ef8d724c9b1a5f8f05722795f1dab37bf5204046f1ef17cc9b49b76e703792
+size 621793