app.py

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Freesound Popularity
+emoji: 🌍
+colorFrom: red
+colorTo: blue
+sdk: gradio
+sdk_version: 6.5.0
+app_file: app.py
+pinned: false
+short_description: freesound popularity music & effectSound
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,358 @@
+import gradio as gr
+import os
+import pandas as pd
+import numpy as np
+from sklearn.preprocessing import KBinsDiscretizer, StandardScaler, OneHotEncoder
+from sklearn.feature_extraction.text import HashingVectorizer
+from collections import Counter
+import joblib
+import freesound
+import gensim.downloader as api
+
+# -------- FreeSound API --------
+client = freesound.FreesoundClient()
+client.set_token("zE9NjEOgUMzH9K7mjiGBaPJiNwJLjSM53LevarRK", "token")
+
+dataset_dir = "dataset_audio"
+os.makedirs(dataset_dir, exist_ok=True)
+
+class AvgRatingTransformer:
+    def __init__(self, est, class_mapping=None):
+        self.est = est
+        if class_mapping is None:
+            self.class_mapping = {0:"MissedInfo", 1:"Low", 2:"Medium", 3:"High"}
+        else:
+            self.class_mapping = class_mapping
+
+    def transform(self, X):
+        X = X.copy()
+        mask_non_zero = X != 0
+        Xt = np.zeros_like(X, dtype=int)
+        if mask_non_zero.any():
+            Xt[mask_non_zero] = self.est.transform(X[mask_non_zero].reshape(-1,1)).flatten() + 1
+        X_transformed = np.array([self.class_mapping.get(v, "MissedInfo") for v in Xt])
+        return X_transformed
+
+
+# -------- Charger les objets sauvegardés --------
+# Music
+scaler_samplerate_music = joblib.load("music/scaler_music_samplerate.joblib")
+scaler_age_days_music = joblib.load("music/scaler_music_age_days_log.joblib")
+username_freq_music = joblib.load("music/username_freq_dict_music.joblib")
+est_num_downloads_music = joblib.load("music/est_num_downloads_music.joblib")
+avg_rating_transformer_music = joblib.load("music/avg_rating_transformer_music.joblib")
+music_subcategory_cols = joblib.load("music/music_subcategory_cols.joblib")
+music_onehot_cols = joblib.load("music/music_onehot_cols.joblib")
+music_onehot_tags = joblib.load("music/music_onehot_tags.joblib")
+
+
+# -------- MODELS --------
+
+# Music
+music_model_num_downloads = joblib.load(
+    "models/music/music_model_num_downloads.joblib"
+)
+music_model_avg_rating = joblib.load(
+    "models/music/music_xgb_avg_rating.joblib"
+)
+music_avg_rating_le = joblib.load(
+    "models/music/music_xgb_avg_rating_label_encoder.joblib"
+)
+
+# EffectSound
+effect_model_num_downloads = joblib.load(
+    "models/effectSound/effectSound_model_num_downloads.joblib"
+)
+effect_model_avg_rating = joblib.load(
+    "models/effectSound/effectSound_xgb_avg_rating.joblib"
+)
+effect_avg_rating_le = joblib.load(
+    "models/effectSound/effectSound_xgb_avg_rating_label_encoder.joblib"
+)
+
+
+# EffectSound
+scaler_samplerate_effect = joblib.load("effectSound/scaler_effectSamplerate.joblib")
+scaler_age_days_effect = joblib.load("effectSound/scaler_effectSound_age_days_log.joblib")
+username_freq_effect = joblib.load("effectSound/username_freq_dict_effectSound.joblib")
+est_num_downloads_effect = joblib.load("effectSound/est_num_downloads_effectSound.joblib")
+avg_rating_transformer_effect = joblib.load("effectSound/avg_rating_transformer_effectSound.joblib")
+effect_subcategory_cols = joblib.load("effectSound/effectSound_subcategory_cols.joblib")
+effect_onehot_cols = joblib.load("effectSound/effectSound_onehot_cols.joblib")
+effect_onehot_tags = joblib.load("effectSound/effect_onehot_tags.joblib")
+
+# GloVe pour description
+glove_model = api.load("glove-wiki-gigaword-100")
+
+# -------- Fonctions --------
+
+def fetch_sound_metadata(sound_url):
+    """Télécharge les métadonnées du son FreeSound"""
+    sound_id = int(sound_url.rstrip("/").split("/")[-1])
+    sound = client.get_sound(sound_id)
+    file_name = f"{sound.name.replace(' ', '_')}.mp3"
+    file_path = os.path.join(dataset_dir, file_name)
+    try:
+        sound.retrieve_preview(dataset_dir, file_name)
+    except Exception as e:
+        print(f"Erreur téléchargement {file_name}: {e}")
+        file_path = None
+    data = {
+        "file_path": file_path,
+        "name": sound.name,
+        "num_ratings": sound.num_ratings,
+        "tags": ",".join(sound.tags) if getattr(sound, "tags", None) else "",
+        "username": sound.username,
+        "description": sound.description if sound.description else "",
+        "created": getattr(sound, "created", ""),
+        "license": getattr(sound, "license", ""),
+        "num_downloads": getattr(sound, "num_downloads", 0),
+        "channels": getattr(sound, "channels", 0),
+        "filesize": getattr(sound, "filesize", 0),
+        "num_comments": getattr(sound, "num_comments", 0),
+        "category_is_user_provided": getattr(sound, "category_is_user_provided", 0),
+        "duration": getattr(sound, "duration", 0),
+        "avg_rating": getattr(sound, "avg_rating", 0),
+        "category": getattr(sound, "category", "Unknown"),
+        "subcategory": getattr(sound, "subcategory", "Other"),
+        "type": getattr(sound, "type", ""),
+        "samplerate": getattr(sound, "samplerate", 0)
+    }
+    return pd.DataFrame([data])
+
+def description_to_vec(text, model, dim=100):
+    if not text:
+        return np.zeros(dim)
+    words = text.lower().split()
+    vecs = [model[w] for w in words if w in model]
+    if len(vecs) == 0:
+        return np.zeros(dim)
+    return np.mean(vecs, axis=0)
+
+def preprocess_sound(df):
+    """Applique le preprocessing complet selon duration pour choisir music ou effectSound"""
+    df = df.copy()
+    dur = df["duration"].iloc[0]
+    
+    if 0.5 <= dur <= 3:
+        dataset_type = "effectSound"
+        scaler_samplerate = scaler_samplerate_effect
+        scaler_age = scaler_age_days_effect
+        username_freq = username_freq_effect
+        est_num_downloads = est_num_downloads_effect
+        avg_rating_transformer = avg_rating_transformer_effect
+        subcat_cols = effect_subcategory_cols
+        onehot_cols = effect_onehot_cols
+        onehot_tags = effect_onehot_tags
+    elif 10 <= dur <= 60:
+        dataset_type = "music"
+        scaler_samplerate = scaler_samplerate_music
+        scaler_age = scaler_age_days_music
+        username_freq = username_freq_music
+        est_num_downloads = est_num_downloads_music
+        avg_rating_transformer = avg_rating_transformer_music
+        subcat_cols = music_subcategory_cols
+        onehot_cols = music_onehot_cols
+        onehot_tags = music_onehot_tags
+    else:
+        return f"❌ Son trop court ou trop long ({dur} sec)"
+
+    # ----------------- Features -----------------
+    # Category bool
+    df["category_is_user_provided"] = df["category_is_user_provided"].astype(int)
+
+    
+    # Username frequency
+    df["username_freq"] = df["username"].map(username_freq).fillna(0)
+    
+    # Numeric features
+    for col in ["num_ratings", "num_comments", "filesize", "duration"]:
+        df[col] = np.log1p(df[col])
+    df["samplerate"] = scaler_samplerate.transform(df[["samplerate"]])
+    
+    # Age_days
+    df["created"] = pd.to_datetime(df["created"], errors="coerce").dt.tz_localize(None)
+    df["age_days"] = (pd.Timestamp.now() - df["created"]).dt.days
+    df["age_days_log"] = np.log1p(df["age_days"])
+    df["age_days_log_scaled"] = scaler_age.transform(df[["age_days_log"]])
+    df = df.drop(columns=["created", "age_days", "age_days_log"])
+  
+    # num_downloads
+    df["num_downloads_class"] = est_num_downloads.transform(df[["num_downloads"]])
+    
+    # avg_rating
+    df["avg_rating"] = avg_rating_transformer.transform(df["avg_rating"].to_numpy())
+    
+    # Subcategory
+    for col in subcat_cols:
+        df[col] = 0  # toutes les colonnes initialisées à 0
+    # activer 1 pour la bonne subcategory
+    subcat_val = df["subcategory"].iloc[0]
+    for col in subcat_cols:
+        cat_name = col.replace("subcategory_", "")
+        if subcat_val == cat_name:
+            df[col] = 1
+    df.drop(columns=["subcategory"], inplace=True)
+        
+    
+
+    # créer toutes les colonnes attendues à 0
+    for col in onehot_cols:
+        if col not in df.columns:
+            df[col] = 0
+
+    # activer les bonnes colonnes one-hot
+    license_val = df.loc[0, "license"]
+    category_val = df.loc[0, "category"]
+    type_val = df.loc[0, "type"]
+
+    for col_name in [
+        f"license_{license_val}",
+        f"category_{category_val}",
+        f"type_{type_val}",
+    ]:
+        if col_name in df.columns:
+            df[col_name] = 1
+
+
+
+
+        
+    # Tags
+    # Si la colonne "tags" n'existe pas, on la crée avec une valeur vide
+    for col in ["name", "tags", "description"]:
+        if col not in df.columns:
+            df[col] = ""
+
+    df["tags_list"] = df["tags"].fillna("").astype(str).str.lower().str.split(",")
+
+    # Si aucun tag n'existe ou que la liste est vide, mettre "Other"
+    if not df["tags_list"].iloc[0] or df["tags_list"].iloc[0] == [""]:
+        df["tags_list"] = [["Other"]]
+
+    # One-hot sur toutes les colonnes enregistrées
+    for col in onehot_tags:
+        tag_name = col.replace("tag_", "").replace("_", " ")
+        df[col] = int(tag_name in df["tags_list"].iloc[0])
+
+    # Supprimer les colonnes temporaires
+    df.drop(columns=["tags_list", "tags"], inplace=True)
+
+
+    # Name
+    df["name_clean"] = df["name"].astype(str).str.lower().str.rsplit(".", n=1).str[0]
+    vectorizer = HashingVectorizer(n_features=8, alternate_sign=False, norm=None)
+    name_vec = vectorizer.transform(df["name_clean"])
+    for i in range(8):
+        df[f"name_vec_{i}"] = name_vec.toarray()[0][i]
+    df.drop(columns=["name","name_clean"], inplace=True)
+
+    
+    # Description
+    desc_vec = description_to_vec(df["description"].iloc[0], glove_model)
+    for i in range(100):
+        df[f"description_glove_{i}"] = desc_vec[i]
+    df.drop(columns=["description"], inplace=True)
+
+    
+    df.drop(columns=[ "license","category","type","created","subcategory","id","num_downloads","file_path","username"],inplace=True, errors="ignore")
+
+    # --- SAFE REORDER (CRUCIAL) ---
+
+    final_cols = []
+
+    for col in onehot_cols:
+        if col in df.columns:
+            final_cols.append(col)
+
+    # subcategories
+    for col in subcat_cols:
+        if col in df.columns:
+            final_cols.append(col)
+
+    # le reste
+    final_cols += [c for c in df.columns if c not in final_cols]
+
+    df = df[final_cols]
+
+
+
+
+    return df
+
+# -------- Gradio --------
+def predict_with_metadata(url):
+    if url.strip() == "":
+        return "❌ Veuillez entrer une URL FreeSound."
+
+    # 1️ Récupérer les métadonnées brutes
+    df_raw = fetch_sound_metadata(url)
+
+    # Affichage ligne par ligne pour les métadonnées brutes
+    raw_lines = ["=== Métadonnées brutes ==="]
+    for col in df_raw.columns:
+        raw_lines.append(f"{col}: {df_raw[col].iloc[0]}")
+    raw_str = "\n".join(raw_lines)
+
+    # 2️ Vérifier la durée
+    dur = df_raw["duration"].iloc[0]
+    if dur < 0.5:
+        return raw_str + f"\n\n Son trop court ({dur} sec), veuillez entrer un son qui est court (0.5 à 3 s) ou  un son long (10 à 60 s)"
+    elif 3 < dur < 10 or dur > 60:
+        return raw_str + f"\n\n Son trop long ou hors plage acceptable ({dur} sec) , veuillez entrer un son qui est court (0.5 à 3 s) ou  un son long (10 à 60 s)"
+
+    # 3️ Prétraitement seulement si durée ok
+    df_processed = preprocess_sound(df_raw)
+
+    # PRÉDICTIONS
+    # =======================
+
+    if 0.5 <= dur <= 3:
+        model_nd = effect_model_num_downloads
+        model_ar = effect_model_avg_rating
+        le_ar = effect_avg_rating_le
+        sound_type = "EffectSound"
+    else:
+        model_nd = music_model_num_downloads
+        model_ar = music_model_avg_rating
+        le_ar = music_avg_rating_le
+        sound_type = "Music"
+
+    # Num downloads
+    pred_num_downloads = model_nd.predict(df_processed)[0]
+
+    # Avg rating
+    pred_avg_rating_enc = model_ar.predict(df_processed)[0]
+    pred_avg_rating = le_ar.inverse_transform([pred_avg_rating_enc])[0]
+
+    # Affichage ligne par ligne pour les features après preprocessing
+    processed_lines = ["\n=== Features après preprocessing ==="]
+    for col in df_processed.columns:
+        processed_lines.append(f"{col}: {df_processed[col].iloc[0]}")
+    processed_str = "\n".join(processed_lines)
+    
+    prediction_lines = [
+        "\n===  Prédictions ===",
+        f"Type détecté : {sound_type}",
+        f"📥 Num downloads prédit : {pred_num_downloads}",
+        f"⭐ Avg rating prédit : {pred_avg_rating}"
+    ]
+
+    prediction_str = "\n".join(prediction_lines)
+
+    return raw_str + processed_str + prediction_str
+
+
+
+
+with gr.Blocks(title="FreeSound Popularity Detector") as demo:
+    gr.Markdown("# 🎧 FreeSound Popularity Detector")
+    gr.Markdown("Collez l'URL d'un son FreeSound et le preprocessing complet sera appliqué automatiquement.")
+
+    url_input = gr.Textbox(label="URL du son FreeSound")
+    btn_meta = gr.Button("📊 Prétraiter et afficher features")
+    output = gr.Textbox(label="Résultat")
+
+    btn_meta.click(fn=predict_with_metadata, inputs=url_input, outputs=output)
+
+demo.launch()

effectSound/avg_rating_transformer_effectSound.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b2862f96050ad72ab3964d30f4f2d3908dd6b5e746f150c1baea5d2cdb2bbf
+size 944

effectSound/effectSound_onehot_cols.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3de47c718ff02e366470f28167a8e5736829fa84b0d34531ac046ceaec5371fa
+size 761

effectSound/effectSound_subcategory_cols.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6796b185bc36b2a0961c0a0b22f813f473eec2962cfa5c20a013f0f328ae8021
+size 418

effectSound/effect_onehot_tags.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9504d82fd7b4691fdc61b00f2e8ae15e28665fce17c60cf44655ccd60cf09f36
+size 69808

effectSound/est_num_downloads_effectSound.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd69b4b945f61331c7778a7ff3366a856191beff40ed439ed78705c1f94440ef
+size 831

effectSound/scaler_effectSamplerate.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac8d3018ca0d1477592952a1aa6b9d582ad589c46314854efd56b607d175b3a
+size 879

effectSound/scaler_effectSound_age_days_log.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:332ee96e7bca4c412bc0d5ac20c0876d5bf8304142d4fd57d4d5524e03228e61
+size 895

effectSound/username_freq_dict_effectSound.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:457517d900b3c05061f398d37b00f8087ae9edb1a4776c7cbc2fc77fa60a4036
+size 209269

music/avg_rating_transformer_music.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29e054a504fd9193b232384f5a2799cad18e54903f03cbfc999a77547feff2d2
+size 944

music/est_num_downloads_music.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:435f88fd8e8f46a970b39b2f255920c298c20e41cf558276dae8b09a40bd56be
+size 831

music/music_onehot_cols.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:554cb8135c47967de9f480942f6d09c79b2ac8440adecebd1dd8c013444d195a
+size 771

music/music_onehot_tags.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8d510dc14604d2d69333e144cc3212ecb3b446d5192f15940347d65610e6eb1
+size 36877

music/music_subcategory_cols.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a51f89fa69f26d5785cd8518fc594ceffbc959493572ac9b06162bfd4f509247
+size 377

music/music_xgb_avg_rating.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:528b63dab12f2d20b07086f7d7b1a8747fbc09798d5c6a199185cec57bda823d
+size 7961465

music/music_xgb_model_smote_balanced_avg_rating.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9266eb3b73bbe34dcbbf84a5cefd758b8dae561f1ee7abd11ea9e79dcb9a756
+size 4144472

music/music_xgb_model_smote_balanced_num_downloads.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca062c7c044eeb44c0acaaad0f1ee91ff79b733d877d7893795580c74b68f87
+size 5322685

music/scaler_music_age_days_log.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1941f5f48e21243a939080d9d7a1cedc677e2b0b813a451a50f64d00ce149588
+size 895

music/scaler_music_samplerate.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0339152b44141d57f6be072c67c50c074d7b6e12280a57f0434520188af83483
+size 879

music/username_freq_dict_music.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ca2078e0e0c5c0d5f871362bba1e787c6860fb547dd1f9f3c4f0f3c366b447
+size 214933

requirements.txt

@@ -0,0 +1,8 @@
+gradio==6.5.0
+scikit-learn
+numpy
+pandas
+gensim
+pytz
+git+https://github.com/MTG/freesound-python
+