Update app.py

app.py

@@ -1,10 +1,10 @@
 import streamlit as st
 import pandas as pd
 import joblib
-import matplotlib.pyplot as plt
+import plotly.express as px
 
 # -------------------------------
-# 1️⃣ Dosya yolları
+# 1️⃣ Dosyaları yükle
 # -------------------------------
 DATA_PATH = "spotify_clustered.csv"
 MODEL_PATH = "kmeans_music_model.pkl"
@@ -12,11 +12,7 @@ SCALER_PATH = "scaler_music.pkl"
 
 @st.cache_data
 def load_data():
-    try:
-        df = pd.read_csv(DATA_PATH)
-    except FileNotFoundError:
-        st.error("spotify_clustered.csv bulunamadı! Lütfen root klasöre yükleyin.")
-        st.stop()
+    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
@@ -44,72 +40,50 @@ st.subheader("📄 Dataset Preview / Veri Önizleme")
 st.dataframe(df_display.head(10), use_container_width=True)
 
 # -------------------------------
-# 4️⃣ Görselleştirme (Titreme önlendi)
+# 4️⃣ Titremesiz grafik – Plotly
 # -------------------------------
-col1, col2 = st.columns(2)
-
-with col1:
-    st.subheader("📊 Cluster Distribution / Küme Dağılımı")
-    # Bar chart için st.bar_chart doğrudan kullanıyoruz
-    cluster_counts = df['cluster'].value_counts()
-    st.bar_chart(cluster_counts)
-
-with col2:
-    st.subheader("🎯 Feature Analysis / Özellik Analizi")
-    # Matplotlib figürünü cache ile tutuyoruz, titremeyi önlüyoruz
-    @st.cache_data
-    def create_scatter(df):
-        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")
-        return fig
-
-    fig = create_scatter(df)
-    st.pyplot(fig, clear_figure=False)
-    plt.close(fig)
+st.subheader("🎯 Feature Analysis / Özellik Analizi")
+fig = px.scatter(
+    df,
+    x='danceability',
+    y='energy',
+    color='cluster',
+    labels={'danceability': 'Danceability / Dans Edilebilirlik', 
+            'energy': 'Energy / Enerji', 
+            'cluster': 'Cluster / Küme'},
+    opacity=0.6
+)
+st.plotly_chart(fig, use_container_width=True)
 
 # -------------------------------
-# 5️⃣ Tahmin bölümü
+# 5️⃣ Prediction Section / Tahmin
 # -------------------------------
 st.divider()
 st.subheader("🤖 Predict New Song Cluster / Yeni Şarkı Tahmini")
-st.info("Adjust sliders to see which cluster a song belongs to / 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)
-
+    pop = st.slider("Popularity", 0, 100, 50)
+    dur = st.slider("Duration (ms)", 0, 600000, 200000)
+    dance = st.slider("Danceability", 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)
-
+    energy = st.slider("Energy", 0.0, 1.0, 0.5)
+    loud = st.slider("Loudness", -60.0, 0.0, -10.0)
+    tempo = st.slider("Tempo", 0.0, 250.0, 120.0)
 with c3:
-    speech = st.slider("Speechiness / Konuşma Oranı", 0.0, 1.0, 0.1)
+    speech = st.slider("Speechiness", 0.0, 1.0, 0.1)
 
-if st.button("Predict Cluster / Kümeyi Tahmin Et ✨"):
+if st.button("Predict Cluster"):
     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("**Similar songs / 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}")
+    new_data_scaled = scaler.transform(new_data)
+    res = model.predict(new_data_scaled)[0]
+    st.success(f"Predicted Cluster: {res}")
+    st.write(df[df['cluster']==res][['track_name','artists']].head(5))
 
 # -------------------------------
-# 6️⃣ Küme ortalamaları
+# 6️⃣ Cluster means
 # -------------------------------
 st.divider()
-st.subheader("🔍 Cluster Characteristics / Küme Özellikleri (Ortalamalar)")
+st.subheader("Cluster Characteristics / Küme Ortalamaları")
 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)
+means = numeric_only.groupby(df['cluster']).mean()
+st.dataframe(means, use_container_width=True)