testtest2

app.py

@@ -1,56 +1,40 @@
+import os
 import gradio as gr
 import pandas as pd
-import numpy as np
 import joblib
 import xgboost as xgb
 import freesound
 
 
 # =========================
-# Token FreeSound
+# CONFIG
 # =========================
-API_TOKEN = "A ECRIRE"   # <- tu remplaces ici
+API_TOKEN = "zE9NjEOgUMzH9K7mjiGBaPJiNwJLjSM53LevarRK"  # <-- remplace ici
 
-
-# =========================
-# Durées
-# =========================
 MIN_EFFECT, MAX_EFFECT = 0.5, 3.0
 MIN_MUSIC, MAX_MUSIC = 10.0, 60.0
 
+BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+
 
 # =========================
 # UI (CSS)
 # =========================
 CSS = """
-.card {
-  border: 1px solid #e5e7eb;
-  background: #ffffff;
-  padding: 16px;
-  border-radius: 16px;
-}
-.card-error{
-  border-color: #fca5a5;
-  background: #fff1f2;
-}
-.card-title{ font-weight: 950; margin-bottom: 8px; }
+.card { border:1px solid #e5e7eb; background:#fff; padding:16px; border-radius:16px; }
+.card-error{ border-color:#fca5a5; background:#fff1f2; }
+.card-title{ font-weight:950; margin-bottom:8px; }
 .badges{ display:flex; gap:10px; flex-wrap:wrap; margin-bottom:12px; }
-.badge{
-  padding:6px 10px; border-radius:999px; font-weight:900; font-size:13px;
-  border: 1px solid #e5e7eb;
-}
-.badge-type{ background:#eef2ff; color:#3730a3;}
-.badge-time{ background:#ecfeff; color:#155e75;}
-
+.badge{ padding:6px 10px; border-radius:999px; font-weight:900; font-size:13px; border:1px solid #e5e7eb; }
+.badge-type{ background:#eef2ff; color:#3730a3; }
+.badge-time{ background:#ecfeff; color:#155e75; }
 .grid{ display:grid; grid-template-columns:1fr; gap:10px; }
 .box{ border:1px solid #e5e7eb; border-radius:14px; padding:12px; background:#fafafa; }
 .box-title{ font-weight:900; margin-bottom:4px; }
 .box-value{ font-size:18px; font-weight:800; }
-
 .hint{ margin-top:10px; color:#6b7280; font-size:12px; }
-
-#header-title { font-size: 28px; font-weight: 950; margin-bottom: 6px; }
-#header-sub { color:#6b7280; margin-top:0px; line-height:1.45; }
+#header-title{ font-size:28px; font-weight:950; margin-bottom:6px; }
+#header-sub{ color:#6b7280; margin-top:0px; line-height:1.45; }
 """
 
 
@@ -92,9 +76,13 @@ def html_result(badge_text, duration, rating_text, downloads_text, extra_html=""
 
 
 # =========================
-# Interprétation
+# INTERPRETATION
 # =========================
 def interpret_results(avg_class: int, dl_class: int) -> str:
+    """
+    avg_class: 0=Missed info, 1=Low, 2=Medium, 3=High (déduit du label texte)
+    dl_class: 0=Low, 1=Medium, 2=High (sortie num_downloads)
+    """
     if avg_class == 0:
         return (
             "ℹ️ <b>Interprétation</b> :<br>"
@@ -133,9 +121,13 @@ def interpret_results(avg_class: int, dl_class: int) -> str:
 
 
 def avg_label_to_class(avg_label: str) -> int:
+    """
+    Convertit label texte du label encoder en 0..3
+    """
     if avg_label is None:
         return 0
     s = str(avg_label).strip().lower()
+
     if "miss" in s or "missing" in s or "none" in s or "no" in s:
         return 0
     if "high" in s or "élev" in s or "eleve" in s:
@@ -148,28 +140,27 @@ def avg_label_to_class(avg_label: str) -> int:
 
 
 # =========================
-# Init FreeSound Client
+# FreeSound client
 # =========================
 client = freesound.FreesoundClient()
 client.set_token(API_TOKEN, "token")
 
 
 # =========================
-# Charger modèles (metadata)
+# Charger les modèles (NOMS EXACTS DU REPO)
 # =========================
+
 # Music
-xgb_music_num = joblib.load("xgb_num_downloads_music_model.pkl")
-xgb_music_feat_num = joblib.load("xgb_num_downloads_music_features.pkl")
-xgb_music_avg = joblib.load("xgb_avg_rating_music_model.pkl")
-xgb_music_feat_avg = joblib.load("xgb_avg_rating_music_features.pkl")
-le_music_avg = joblib.load("xgb_avg_rating_music_label_encoder.pkl")
-
-# Effect Sound
-xgb_effect_num = joblib.load("xgb_num_downloads_effectsound_model.pkl")
-xgb_effect_feat_num = joblib.load("xgb_num_downloads_effectsound_features.pkl")
-xgb_effect_avg = joblib.load("xgb_avg_rating_effectsound_model.pkl")
-xgb_effect_feat_avg = joblib.load("xgb_avg_rating_effectsound_features.pkl")
-le_effect_avg = joblib.load("xgb_avg_rating_effectsound_label_encoder.pkl")
+music_num_model = joblib.load(os.path.join(BASE_DIR, "music_model_num_downloads.joblib"))
+music_feat_list = joblib.load(os.path.join(BASE_DIR, "music_model_features_list.joblib"))
+music_avg_model = joblib.load(os.path.join(BASE_DIR, "music_xgb_avg_rating.joblib"))
+music_avg_le = joblib.load(os.path.join(BASE_DIR, "music_xgb_avg_rating_label_encoder.joblib"))
+
+# Effect sound
+effect_num_model = joblib.load(os.path.join(BASE_DIR, "effectSound_model_num_downloads.joblib"))
+effect_feat_list = joblib.load(os.path.join(BASE_DIR, "effect_model_features_list.joblib"))
+effect_avg_model = joblib.load(os.path.join(BASE_DIR, "effectSound_xgb_avg_rating.joblib"))
+effect_avg_le = joblib.load(os.path.join(BASE_DIR, "effectSound_xgb_avg_rating_label_encoder.joblib"))
 
 NUM_DOWNLOADS_MAP = {0: "Faible", 1: "Moyen", 2: "Élevé"}
 
@@ -181,19 +172,22 @@ def safe_float(v):
         return 0.0
 
 
-def predict_with_model(model, features, feat_list, le=None):
+def predict_with_model(model, features_dict, feat_list, le=None):
     row = []
     for col in feat_list:
-        val = features.get(col, 0)
+        val = features_dict.get(col, 0)
         if val is None or isinstance(val, (list, dict)):
             val = 0
         row.append(safe_float(val))
 
     X = pd.DataFrame([row], columns=feat_list)
-    dmatrix = xgb.DMatrix(X.values, feature_names=feat_list)
-    pred_int = int(model.get_booster().predict(dmatrix)[0])
 
-    if le:
+    # DMatrix (avec feature names)
+    dm = xgb.DMatrix(X.values, feature_names=feat_list)
+
+    pred_int = int(model.get_booster().predict(dm)[0])
+
+    if le is not None:
         return le.inverse_transform([pred_int])[0]
     return pred_int
 
@@ -202,15 +196,14 @@ def extract_and_predict(url: str):
     if not url or not url.strip():
         return html_error("URL vide", "Collez une URL FreeSound du type <code>https://freesound.org/s/123456/</code>")
 
+    # Parse ID
     try:
         sound_id = int(url.rstrip("/").split("/")[-1])
     except Exception:
         return html_error("URL invalide", "Impossible d'extraire l'ID depuis l'URL.")
 
-    # Champs nécessaires
-    all_features = list(set(
-        xgb_music_feat_num + xgb_music_feat_avg + xgb_effect_feat_num + xgb_effect_feat_avg
-    ))
+    # champs nécessaires (union music+effect)
+    all_features = list(set(music_feat_list + effect_feat_list))
     fields = "duration," + ",".join(all_features)
 
     try:
@@ -224,7 +217,7 @@ def extract_and_predict(url: str):
     sound = results.results[0]
     duration = safe_float(sound.get("duration", 0))
 
-    # Vérif durées
+    # Durées supportées
     if duration < MIN_EFFECT:
         return html_error(
             "Audio trop court",
@@ -238,11 +231,11 @@ def extract_and_predict(url: str):
             f"Plages : Effet sonore <b>{MIN_EFFECT}-{MAX_EFFECT}s</b> | Musique <b>{MIN_MUSIC}-{MAX_MUSIC}s</b>"
         )
 
-    # Effect
+    # Décision type
     if MIN_EFFECT <= duration <= MAX_EFFECT:
         badge = "🔊 Effet sonore (metadata FreeSound)"
-        dl_class = int(predict_with_model(xgb_effect_num, sound, xgb_effect_feat_num))
-        avg_text = str(predict_with_model(xgb_effect_avg, sound, xgb_effect_feat_avg, le_effect_avg))
+        dl_class = int(predict_with_model(effect_num_model, sound, effect_feat_list))
+        avg_text = str(predict_with_model(effect_avg_model, sound, effect_feat_list, effect_avg_le))
         dl_text = NUM_DOWNLOADS_MAP.get(dl_class, str(dl_class))
 
         avg_class = avg_label_to_class(avg_text)
@@ -256,8 +249,8 @@ def extract_and_predict(url: str):
 
     # Music
     badge = "🎵 Musique (metadata FreeSound)"
-    dl_class = int(predict_with_model(xgb_music_num, sound, xgb_music_feat_num))
-    avg_text = str(predict_with_model(xgb_music_avg, sound, xgb_music_feat_avg, le_music_avg))
+    dl_class = int(predict_with_model(music_num_model, sound, music_feat_list))
+    avg_text = str(predict_with_model(music_avg_model, sound, music_feat_list, music_avg_le))
     dl_text = NUM_DOWNLOADS_MAP.get(dl_class, str(dl_class))
 
     avg_class = avg_label_to_class(avg_text)
@@ -271,7 +264,7 @@ def extract_and_predict(url: str):
 
 
 # =========================
-# UI Gradio (metadata only)
+# UI
 # =========================
 theme = gr.themes.Soft()