diff --git a/app.py b/app.py
index 935a508946168fb8311b56ae5056eeb58c4bc727..587200ea0a37aa92a117cdeb228b6776352c5721 100644
--- a/app.py
+++ b/app.py
@@ -7,9 +7,13 @@ import numpy as np
app = Flask(__name__)
# Charger le modèle
-with open('random_forest_model.pkl', 'rb') as model_file:
+with open('random_forest_model_binaire.pkl', 'rb') as model_file:
rf = pickle.load(model_file)
+# Charger le scaler entraîné
+with open('scaler_binaire.pkl', 'rb') as scaler_file:
+ scaler = pickle.load(scaler_file)
+
@app.route('/')
def home():
return render_template('index.html')
@@ -18,16 +22,42 @@ def home():
def predict():
# Récupérer les données du formulaire
data = request.form.to_dict()
- input_data = pd.DataFrame([data])
-
+
+ # Calculer automatiquement le nombre de caractères sans espaces
+ if 'name' in data:
+ data['nb_caracteres_sans_espaces'] = len(data['name'].replace(" ", ""))
+
+ # Supprimer la clé 'name' qui n'est pas une feature
+ data.pop('name', None)
+
+ # Convertir les valeurs en float si possible
+ for key in data:
+ try:
+ data[key] = float(data[key])
+ except ValueError:
+ pass # Garder les valeurs non convertibles (ex: texte)
+
+ # Liste des features dans le bon ordre (comme lors de l'entraînement)
+ expected_features = ['year', 'acousticness', 'danceability', 'energy', 'explicit',
+ 'instrumentalness', 'key', 'liveness', 'loudness', 'mode',
+ 'speechiness', 'tempo', 'valence', 'nb_artistes', 'featuring',
+ 'duree_minute', 'categorie_annee', 'categorie_tempo', 'nb_caracteres_sans_espaces']
+
+ # S'assurer que les colonnes du DataFrame correspondent à celles du modèle, dans le bon ordre
+ input_data = pd.DataFrame([[data.get(key, 0) for key in expected_features]], columns=expected_features)
+
+ # Vérifier que toutes les colonnes attendues sont présentes
+ missing_cols = [col for col in expected_features if col not in input_data.columns]
+ if missing_cols:
+ return jsonify({'error': f'Missing features: {missing_cols}'}), 400
+
# Normalisation des features
- scaler = StandardScaler()
- input_data_scaled = scaler.fit_transform(input_data)
-
+ input_data_scaled = scaler.transform(input_data)
+
# Prédiction
- predictions = np.round(rf.predict(input_data_scaled),4)
-
- return jsonify({'predictions': predictions.tolist()})
+ predictions = rf.predict(input_data_scaled)
+
+ return jsonify({'predictions': int(predictions[0])})
if __name__ == '__main__':
- app.run(debug=True)
+ app.run(debug=True)
\ No newline at end of file
diff --git a/ml_binairefinal.py b/ml_binairefinal.py
index 0688e9ed318f280dd16008fe2999bfcbf278f8aa..16f67a598790f19e66aeaeff94d44d32230dfe0a 100644
--- a/ml_binairefinal.py
+++ b/ml_binairefinal.py
@@ -5,6 +5,8 @@ from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, classification_report
+import pickle
+
def load_and_describe_data(file_path):
"""Charge un fichier CSV et affiche les informations de base."""
@@ -12,16 +14,26 @@ def load_and_describe_data(file_path):
print(df.info())
return df
+
def train_random_forest(df):
start_time = time.time() # ⏳ Timer
# 1️⃣ Séparation des features et de la cible
y = df["popularity_2"]
- X = df.drop(columns=['popularity_2', 'popularity', 'id', 'artists', 'name',
+ X = df.drop(columns=['popularity_2', 'popularity', 'id', 'artists', 'name',
'release_date', 'date_sortie', 'duration_ms', 'nom_artiste'])
+ # Liste des features dans le bon ordre (doit être identique dans l'API Flask)
+ expected_features = ['year', 'acousticness', 'danceability', 'energy', 'explicit',
+ 'instrumentalness', 'key', 'liveness', 'loudness', 'mode',
+ 'speechiness', 'tempo', 'valence', 'nb_artistes', 'featuring',
+ 'duree_minute', 'categorie_annee', 'categorie_tempo', 'nb_caracteres_sans_espaces']
+
+ # Vérification des colonnes pour éviter les erreurs
+ X = X.reindex(columns=expected_features, fill_value=0)
+
# 2️⃣ Split train/test
- X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, stratify=y)
+ X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, stratify=y, random_state=42)
# 3️⃣ Normalisation des features
scaler = StandardScaler()
@@ -29,49 +41,33 @@ def train_random_forest(df):
X_test_scaled = scaler.transform(X_test)
# 4️⃣ Initialisation du modèle avec les hyperparamètres optimisés
- rf = RandomForestClassifier(n_estimators=200, max_depth=None, criterion="gini",class_weight='balanced')
-
+ rf = RandomForestClassifier(n_estimators=200, max_depth=None, criterion="gini", class_weight='balanced', random_state=42)
+
# 5️⃣ Entraînement du modèle
rf.fit(X_train_scaled, y_train)
- import pickle
- # Sauvegarder le modèle
- with open('random_forest_model.pkl', 'wb') as model_file:
+
+ # 6️⃣ Sauvegarde du modèle et du scaler
+ with open('random_forest_model_binaire.pkl', 'wb') as model_file:
pickle.dump(rf, model_file)
+ with open('scaler_binaire.pkl', 'wb') as scaler_file:
+ pickle.dump(scaler, scaler_file)
- # 6️⃣ Prédiction
+ # 7️⃣ Prédiction
y_pred = rf.predict(X_test_scaled)
- # 7️⃣ Évaluation
+ # 8️⃣ Évaluation
accuracy = accuracy_score(y_test, y_pred)
print(f"\n✅ Accuracy : {accuracy:.2%}")
print("\n🔍 Rapport de classification :\n", classification_report(y_test, y_pred))
- # 8️⃣ Ajout des prédictions au DataFrame
- df.loc[X_test.index, "pred_rf"] = y_pred
- print(df.head(10))
-
# ⏳ Temps d'exécution
elapsed_time = time.time() - start_time
print(f"\n⏱️ Temps d'exécution : {elapsed_time:.2f} secondes")
return df
+
# 📂 Chargement et entraînement
df = load_and_describe_data("data_binaire.csv")
df = train_random_forest(df)
-
-def get_independent_variables(df):
- # Séparation des features et de la cible
- y = df["popularity_2"]
- X = df.drop(columns=['popularity_2', 'popularity', 'id', 'artists', 'name',
- 'release_date', 'date_sortie', 'duration_ms', 'nom_artiste'])
-
- # Liste des variables indépendantes
- independent_variables = X.columns.tolist()
- return independent_variables
-
-# Obtenir la liste des variables indépendantes
-independent_variables = get_independent_variables(df)
-
-print(df['popularity_2'].value_counts())
\ No newline at end of file
diff --git a/random_forest_model.pkl b/random_forest_model.pkl
index 348339307c70b4af2bf48bbebfc2613bc6cc61b8..234110c4bf1057de8989392de18bc3ace42a9fda 100644
Binary files a/random_forest_model.pkl and b/random_forest_model.pkl differ
diff --git a/random_forest_model_binaire.pkl b/random_forest_model_binaire.pkl
new file mode 100644
index 0000000000000000000000000000000000000000..234110c4bf1057de8989392de18bc3ace42a9fda
Binary files /dev/null and b/random_forest_model_binaire.pkl differ
diff --git a/scaler.pkl b/scaler.pkl
new file mode 100644
index 0000000000000000000000000000000000000000..19ab04faf34282436158f3112f223e18033a08ff
Binary files /dev/null and b/scaler.pkl differ
diff --git a/scaler_binaire.pkl b/scaler_binaire.pkl
new file mode 100644
index 0000000000000000000000000000000000000000..19ab04faf34282436158f3112f223e18033a08ff
Binary files /dev/null and b/scaler_binaire.pkl differ
diff --git a/templates/index.html b/templates/index.html
index 1aad35ee4c7d0330d179ab24bf4cb1d6434a82d5..a79ed2f7a26f5ceaf7cca8285c4708fe53db9cf3 100644
--- a/templates/index.html
+++ b/templates/index.html
@@ -21,7 +21,7 @@
margin-top: 10px;
font-weight: bold;
}
- input[type="text"] {
+ input[type="text"], input[type="number"] {
width: 100%;
padding: 8px;
margin-top: 5px;
@@ -49,81 +49,80 @@
</head>
<body>
<h1>Prédire la Popularité</h1>
- <form action="/predict" method="post">
+ <form id="predictionForm">
+ <label for="name">Titre de la chanson :</label>
+ <input type="text" id="name" name="name" required>
+
<label for="year">Année :</label>
- <input type="text" id="year" name="year">
+ <input type="number" id="year" name="year" required>
<label for="acousticness">Acousticness :</label>
- <input type="text" id="acousticness" name="acousticness">
+ <input type="number" step="0.01" id="acousticness" name="acousticness" required>
<label for="danceability">Danceability :</label>
- <input type="text" id="danceability" name="danceability">
+ <input type="number" step="0.01" id="danceability" name="danceability" required>
<label for="energy">Energy :</label>
- <input type="text" id="energy" name="energy">
+ <input type="number" step="0.01" id="energy" name="energy" required>
<label for="explicit">Explicit :</label>
- <input type="text" id="explicit" name="explicit">
+ <input type="number" id="explicit" name="explicit" required>
<label for="instrumentalness">Instrumentalness :</label>
- <input type="text" id="instrumentalness" name="instrumentalness">
+ <input type="number" step="0.01" id="instrumentalness" name="instrumentalness" required>
<label for="key">Key :</label>
- <input type="text" id="key" name="key">
+ <input type="number" id="key" name="key" required>
<label for="liveness">Liveness :</label>
- <input type="text" id="liveness" name="liveness">
+ <input type="number" step="0.01" id="liveness" name="liveness" required>
<label for="loudness">Loudness :</label>
- <input type="text" id="loudness" name="loudness">
+ <input type="number" step="0.01" id="loudness" name="loudness" required>
<label for="mode">Mode :</label>
- <input type="text" id="mode" name="mode">
+ <input type="number" id="mode" name="mode" required>
<label for="speechiness">Speechiness :</label>
- <input type="text" id="speechiness" name="speechiness">
+ <input type="number" step="0.01" id="speechiness" name="speechiness" required>
<label for="tempo">Tempo :</label>
- <input type="text" id="tempo" name="tempo">
+ <input type="number" step="0.01" id="tempo" name="tempo" required>
<label for="valence">Valence :</label>
- <input type="text" id="valence" name="valence">
-
- <label for="nb_caracteres_sans_espaces">Nombre de caractères sans espaces :</label>
- <input type="text" id="nb_caracteres_sans_espaces" name="nb_caracteres_sans_espaces">
+ <input type="number" step="0.01" id="valence" name="valence" required>
<label for="nb_artistes">Nombre d'artistes :</label>
- <input type="text" id="nb_artistes" name="nb_artistes">
+ <input type="number" id="nb_artistes" name="nb_artistes" required>
<label for="featuring">Featuring :</label>
- <input type="text" id="featuring" name="featuring">
+ <input type="number" id="featuring" name="featuring" required>
<label for="duree_minute">Durée (minutes) :</label>
- <input type="text" id="duree_minute" name="duree_minute">
+ <input type="number" step="0.01" id="duree_minute" name="duree_minute" required>
<label for="categorie_annee">Catégorie année :</label>
- <input type="text" id="categorie_annee" name="categorie_annee">
+ <input type="number" id="categorie_annee" name="categorie_annee" required>
<label for="categorie_tempo">Catégorie tempo :</label>
- <input type="text" id="categorie_tempo" name="categorie_tempo">
+ <input type="number" id="categorie_tempo" name="categorie_tempo" required>
<input type="submit" value="Prédire">
</form>
<div id="result"></div>
<script>
- document.querySelector('form').addEventListener('submit', async function(event) {
+ document.getElementById("predictionForm").addEventListener("submit", async function(event) {
event.preventDefault();
- const form = event.target;
- const formData = new FormData(form);
+ const formData = new FormData(this);
- const response = await fetch('/predict', {
- method: 'POST',
- body: formData,
+ const response = await fetch("/predict", {
+ method: "POST",
+ body: formData
});
-
+
const result = await response.json();
- document.getElementById('result').innerText = `Prédiction: ${result.predictions}`;
+ document.getElementById("result").innerText = `Prédiction: ${result.predictions}`;
});
</script>
</body>