Update app.py

app.py

@@ -1,141 +1,111 @@
-import streamlit as st
-import pandas as pd
-import joblib
-import matplotlib.pyplot as plt
-import os
-
-# --------------------------------------
-# PAGE CONFIG
-# --------------------------------------
-st.set_page_config(page_title="Spotify Clustering", layout="wide")
-
-# --------------------------------------
-# AUTO PATH (LOCAL + HUGGING FACE)
-# --------------------------------------
-def get_path(filename):
-    # Olası tüm konumları kontrol et
-    base_dirs = [
-        ".",                 # çalıştırıldığı klasör
-        "..",                # bir üst klasör
-        os.path.dirname(os.path.abspath(__file__)),  # script klasörü
-        os.path.join(os.path.dirname(os.path.abspath(__file__)), ".."),
-        os.getcwd(),         # working dir
-        os.path.join(os.getcwd(), "..")
-    ]
-    for d in base_dirs:
-        path = os.path.join(d, filename)
-        if os.path.exists(path):
-            return path
-    # Eğer bulunamazsa
-    st.error(f"{filename} bulunamadı! Mevcut dosyalar: {os.listdir()}")
-    st.stop()
-
-DATA_PATH = get_path("spotify_clustered.csv")
-MODEL_PATH = get_path("kmeans_music_model.pkl")
-SCALER_PATH = get_path("scaler_music.pkl")
-
-# --------------------------------------
-# LOAD DATA (CACHE)
-# --------------------------------------
-@st.cache_data
-def load_data():
-    df = pd.read_csv(DATA_PATH)
-    unnecessary_cols = ['Unnamed: 0', 'track_id', 'album_name', 'explicit']
-    df_display = df.drop(columns=[c for c in unnecessary_cols if c in df.columns])
-    return df, df_display
-
-@st.cache_resource
-def load_model():
-    model = joblib.load(MODEL_PATH)
-    scaler = joblib.load(SCALER_PATH)
-    return model, scaler
-
-df, df_display = load_data()
-model, scaler = load_model()
-
-# --------------------------------------
-# SESSION STATE (NO FLICKER)
-# --------------------------------------
-if "prediction" not in st.session_state:
-    st.session_state.prediction = None
-    st.session_state.samples = None
-
-# --------------------------------------
-# TITLE
-# --------------------------------------
-st.title("🎵 Spotify Music Clustering / Spotify Müzik Kümeleme")
-st.markdown("---")
-
-# --------------------------------------
-# DATA PREVIEW
-# --------------------------------------
-st.subheader("📄 Dataset Preview / Veri Önizleme")
-st.dataframe(df_display.head(10), use_container_width=True)
-
-# --------------------------------------
-# VISUALS
-# --------------------------------------
-col1, col2 = st.columns(2)
-
-with col1:
-    st.subheader("📊 Cluster Distribution / Küme Dağılımı")
-    st.bar_chart(df['cluster'].value_counts(), use_container_width=True)
-
-with col2:
-    st.subheader("🎯 Feature Analysis / Özellik Analizi")
-    fig, ax = plt.subplots(figsize=(6, 4))
-    scatter = ax.scatter(df['danceability'], df['energy'], c=df['cluster'], cmap='viridis', alpha=0.6)
-    ax.set_xlabel("Danceability / Dans Edilebilirlik")
-    ax.set_ylabel("Energy / Enerji")
-    plt.colorbar(scatter, ax=ax)
-    st.pyplot(fig, clear_figure=True)
-    plt.close(fig)
-
-# --------------------------------------
-# PREDICTION
-# --------------------------------------
-st.divider()
-st.subheader("🤖 Predict New Song Cluster / Yeni Şarkı Tahmini")
-
-c1, c2, c3 = st.columns(3)
-with c1:
-    pop = st.slider("Popularity / Popülerlik", 0, 100, 50)
-    dur = st.slider("Duration (ms) / Süre", 0, 600000, 200000)
-    dance = st.slider("Danceability / Dans Edilebilirlik", 0.0, 1.0, 0.5)
-with c2:
-    energy = st.slider("Energy / Enerji", 0.0, 1.0, 0.5)
-    loud = st.slider("Loudness / Ses Yüksekliği", -60.0, 0.0, -10.0)
-    tempo = st.slider("Tempo / Tempo", 0.0, 250.0, 120.0)
-with c3:
-    speech = st.slider("Speechiness / Konuşma Oranı", 0.0, 1.0, 0.1)
-
-if st.button("Predict Cluster / Kümeyi Tahmin Et ✨"):
-    new_data = [[pop, dur, dance, energy, loud, tempo, speech]]
-    try:
-        new_data_scaled = scaler.transform(new_data)
-        res = model.predict(new_data_scaled)[0]
-        st.session_state.prediction = res
-        st.session_state.samples = df[df['cluster'] == res][['track_name', 'artists']].head(5)
-    except Exception as e:
-        st.error(f"Error / Hata: {e}")
-
-if st.session_state.prediction is not None:
-    st.success(f"### Predicted Cluster / Tahmin Edilen Küme: {st.session_state.prediction}")
-    st.write("Similar Songs / Benzer Şarkılar:")
-    st.table(st.session_state.samples)
-
-# --------------------------------------
-# CLUSTER ANALYSIS
-# --------------------------------------
-st.divider()
-st.subheader("🔍 Cluster Characteristics / Küme Özellikleri")
-numeric_only = df.select_dtypes(include=['float64', 'int64'])
-if 'cluster' in df.columns:
-    means = numeric_only.groupby(df['cluster']).mean()
-    st.dataframe(means, use_container_width=True)
-
-# --------------------------------------
-# DEBUG (Opsiyonel)
-# --------------------------------------
-# st.write("Current working dir:", os.getcwd())
-# st.write("Files here:", os.listdir())
+# streamlit_app.py
+import streamlit as st
+import pandas as pd
+import joblib
+import matplotlib.pyplot as plt
+
+# --------------------------------------
+# 1️⃣ Load Files & Data Cleaning / Dosyaları Yükle ve Temizle
+# --------------------------------------
+DATA_PATH = "spotify_clustered.csv"
+MODEL_PATH = "kmeans_music_model.pkl"
+SCALER_PATH = "scaler_music.pkl"
+
+@st.cache_data
+def load_data():
+    try:
+        df = pd.read_csv(DATA_PATH)
+    except FileNotFoundError:
+        st.error(f"spotify_clustered.csv bulunamadı! Lütfen aynı klasöre yükleyin.")
+        return None, None
+
+    # Gereksiz sütunları kaldır
+    unnecessary_cols = ['Unnamed: 0', 'track_id', 'album_name', 'explicit']
+    df_display = df.drop(columns=[c for c in unnecessary_cols if c in df.columns])
+    return df, df_display
+
+# Dosyaları yükle
+df, df_display = load_data()
+if df is None:
+    st.stop()
+
+# Model ve scaler yükle
+model = joblib.load(MODEL_PATH)
+scaler = joblib.load(SCALER_PATH)
+
+# --------------------------------------
+# 2️⃣ Page Config / Sayfa Ayarları
+# --------------------------------------
+st.set_page_config(page_title="Spotify Clusters", layout="wide")
+st.title("🎵 Spotify Music Clustering / Spotify Müzik Kümeleme")
+st.markdown("---")
+
+# --------------------------------------
+# 3️⃣ Dataset Preview / Veri Önizleme
+# --------------------------------------
+st.subheader("📄 Dataset Preview / Veri Önizleme")
+st.write("Cleaned data for analysis / Analiz için temizlenmiş veri:")
+st.dataframe(df_display.head(10), use_container_width=True)
+
+# --------------------------------------
+# 4️⃣ Visualizations / Görselleştirmeler
+# --------------------------------------
+col1, col2 = st.columns(2)
+
+with col1:
+    st.subheader("📊 Cluster Distribution / Küme Dağılımı")
+    st.bar_chart(df['cluster'].value_counts())
+
+with col2:
+    st.subheader("🎯 Feature Analysis / Özellik Analizi")
+    fig, ax = plt.subplots(figsize=(8, 5))
+    scatter = ax.scatter(df['danceability'], df['energy'], c=df['cluster'], cmap='viridis', alpha=0.6)
+    ax.set_xlabel("Danceability / Dans Edilebilirlik")
+    ax.set_ylabel("Energy / Enerji")
+    plt.colorbar(scatter, label="Cluster / Küme")
+    st.pyplot(fig, clear_figure=True)
+    plt.close(fig)
+
+# --------------------------------------
+# 5️⃣ Prediction Section / Tahmin Bölümü
+# --------------------------------------
+st.divider()
+st.subheader("🤖 Predict New Song Cluster / Yeni Şarkı Tahmini")
+st.info("Adjust the sliders to see which cluster a song belongs to / Şarkının hangi kümeye ait olduğunu görmek için sürgüleri ayarlayın.")
+
+c1, c2, c3 = st.columns(3)
+
+with c1:
+    pop = st.slider("Popularity / Popülerlik", 0, 100, 50)
+    dur = st.slider("Duration (ms) / Süre", 0, 600000, 200000)
+    dance = st.slider("Danceability / Dans Edilebilirlik", 0.0, 1.0, 0.5)
+
+with c2:
+    energy = st.slider("Energy / Enerji", 0.0, 1.0, 0.5)
+    loud = st.slider("Loudness / Ses Yüksekliği", -60.0, 0.0, -10.0)
+    tempo = st.slider("Tempo / Tempo", 0.0, 250.0, 120.0)
+
+with c3:
+    speech = st.slider("Speechiness / Konuşma Oranı", 0.0, 1.0, 0.1)
+
+if st.button("Predict Cluster / Kümeyi Tahmin Et ✨"):
+    new_data = [[pop, dur, dance, energy, loud, tempo, speech]]
+    try:
+        new_data_scaled = scaler.transform(new_data)
+        res = model.predict(new_data_scaled)[0]
+        st.success(f"### Predicted Cluster / Tahmin Edilen Küme: {res}")
+        st.write(f"**Similar songs from this group / Bu gruptaki benzer şarkılar:**")
+        samples = df[df['cluster'] == res][['track_name', 'artists']].head(5)
+        st.table(samples)
+    except Exception as e:
+        st.error(f"Prediction Error / Tahmin Hatası: {e}")
+
+# --------------------------------------
+# 6️⃣ Cluster Characteristics / Küme Karakteristikleri
+# --------------------------------------
+st.divider()
+st.subheader("🔍 Cluster Characteristics / Küme Özellikleri (Ortalamalar)")
+numeric_only = df.select_dtypes(include=['float64', 'int64'])
+if 'cluster' in df.columns:
+    means = numeric_only.groupby(df['cluster']).mean()
+    st.dataframe(means, use_container_width=True)