Update src/streamlit_app.py
Browse files- src/streamlit_app.py +81 -40
src/streamlit_app.py
CHANGED
|
@@ -2,68 +2,108 @@ import streamlit as st
|
|
| 2 |
import pandas as pd
|
| 3 |
import joblib
|
| 4 |
import matplotlib.pyplot as plt
|
|
|
|
| 5 |
|
| 6 |
# --------------------------------------
|
| 7 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
# --------------------------------------
|
| 9 |
@st.cache_data
|
| 10 |
def load_data():
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
# Gereksiz/Teknik sütunları temizle (Görünümü güzelleştirir)
|
| 15 |
unnecessary_cols = ['Unnamed: 0', 'track_id', 'album_name', 'explicit']
|
| 16 |
df_display = df.drop(columns=[c for c in unnecessary_cols if c in df.columns])
|
| 17 |
-
|
| 18 |
return df, df_display
|
| 19 |
|
| 20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
df, df_display = load_data()
|
| 22 |
-
model =
|
| 23 |
-
scaler = joblib.load("scaler_music.pkl")
|
| 24 |
|
| 25 |
# --------------------------------------
|
| 26 |
-
#
|
| 27 |
# --------------------------------------
|
| 28 |
-
|
| 29 |
-
st.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
st.markdown("---")
|
| 31 |
|
| 32 |
# --------------------------------------
|
| 33 |
-
#
|
| 34 |
# --------------------------------------
|
| 35 |
st.subheader("📄 Dataset Preview / Veri Önizleme")
|
| 36 |
-
st.write("Cleaned data for analysis / Analiz için temizlenmiş veri:")
|
| 37 |
st.dataframe(df_display.head(10), use_container_width=True)
|
| 38 |
|
| 39 |
# --------------------------------------
|
| 40 |
-
#
|
| 41 |
# --------------------------------------
|
| 42 |
col1, col2 = st.columns(2)
|
| 43 |
|
| 44 |
with col1:
|
| 45 |
st.subheader("📊 Cluster Distribution / Küme Dağılımı")
|
| 46 |
-
st.bar_chart(df['cluster'].value_counts())
|
| 47 |
|
| 48 |
with col2:
|
| 49 |
st.subheader("🎯 Feature Analysis / Özellik Analizi")
|
| 50 |
-
|
| 51 |
-
fig, ax = plt.subplots(figsize=(
|
| 52 |
-
scatter = ax.scatter(
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
ax.set_xlabel("Danceability / Dans Edilebilirlik")
|
| 54 |
ax.set_ylabel("Energy / Enerji")
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
|
| 58 |
st.pyplot(fig, clear_figure=True)
|
| 59 |
-
plt.close(fig)
|
| 60 |
|
| 61 |
# --------------------------------------
|
| 62 |
-
#
|
| 63 |
# --------------------------------------
|
| 64 |
st.divider()
|
| 65 |
st.subheader("🤖 Predict New Song Cluster / Yeni Şarkı Tahmini")
|
| 66 |
-
st.info("Adjust the sliders to see which cluster a song belongs to / Şarkının hangi kümeye ait olduğunu görmek için sürgüleri ayarlayın.")
|
| 67 |
|
| 68 |
c1, c2, c3 = st.columns(3)
|
| 69 |
|
|
@@ -78,34 +118,35 @@ with c2:
|
|
| 78 |
tempo = st.slider("Tempo / Tempo", 0.0, 250.0, 120.0)
|
| 79 |
|
| 80 |
with c3:
|
| 81 |
-
# Kaggle'da eğittiğin 7. özelliği buraya ekledik (Hata almamak için)
|
| 82 |
speech = st.slider("Speechiness / Konuşma Oranı", 0.0, 1.0, 0.1)
|
| 83 |
|
| 84 |
if st.button("Predict Cluster / Kümeyi Tahmin Et ✨"):
|
| 85 |
-
# SIRALAMA: Kaggle'daki modelin beklediği sırayla veriyoruz
|
| 86 |
new_data = [[pop, dur, dance, energy, loud, tempo, speech]]
|
| 87 |
-
|
| 88 |
try:
|
| 89 |
new_data_scaled = scaler.transform(new_data)
|
| 90 |
res = model.predict(new_data_scaled)[0]
|
| 91 |
-
|
| 92 |
-
st.
|
| 93 |
-
|
| 94 |
-
|
| 95 |
-
st.write(f"**Similar songs from this group / Bu gruptaki benzer şarkılar:**")
|
| 96 |
-
samples = df[df['cluster'] == res][['track_name', 'artists']].head(5)
|
| 97 |
-
st.table(samples)
|
| 98 |
-
|
| 99 |
except Exception as e:
|
| 100 |
-
st.error(f"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 101 |
|
| 102 |
# --------------------------------------
|
| 103 |
-
#
|
| 104 |
# --------------------------------------
|
| 105 |
st.divider()
|
| 106 |
-
st.subheader("🔍 Cluster Characteristics / Küme Özellikleri
|
| 107 |
-
|
| 108 |
numeric_only = df.select_dtypes(include=['float64', 'int64'])
|
|
|
|
| 109 |
if 'cluster' in df.columns:
|
| 110 |
means = numeric_only.groupby(df['cluster']).mean()
|
| 111 |
st.dataframe(means, use_container_width=True)
|
|
|
|
| 2 |
import pandas as pd
|
| 3 |
import joblib
|
| 4 |
import matplotlib.pyplot as plt
|
| 5 |
+
import os
|
| 6 |
|
| 7 |
# --------------------------------------
|
| 8 |
+
# 🎨 PAGE CONFIG
|
| 9 |
+
# --------------------------------------
|
| 10 |
+
st.set_page_config(page_title="Spotify Clustering", layout="wide")
|
| 11 |
+
|
| 12 |
+
# --------------------------------------
|
| 13 |
+
# 🔧 AUTO PATH (LOCAL + CLOUD FIX)
|
| 14 |
+
# --------------------------------------
|
| 15 |
+
def get_path(filename):
|
| 16 |
+
base_dir = os.path.dirname(os.path.abspath(__file__))
|
| 17 |
+
|
| 18 |
+
local_path = os.path.join(base_dir, filename)
|
| 19 |
+
parent_path = os.path.join(base_dir, "..", filename)
|
| 20 |
+
|
| 21 |
+
if os.path.exists(local_path):
|
| 22 |
+
return local_path
|
| 23 |
+
elif os.path.exists(parent_path):
|
| 24 |
+
return parent_path
|
| 25 |
+
else:
|
| 26 |
+
st.error(f"{filename} bulunamadı!")
|
| 27 |
+
st.stop()
|
| 28 |
+
|
| 29 |
+
DATA_PATH = get_path("spotify_clustered.csv")
|
| 30 |
+
MODEL_PATH = get_path("kmeans_music_model.pkl")
|
| 31 |
+
SCALER_PATH = get_path("scaler_music.pkl")
|
| 32 |
+
|
| 33 |
+
# --------------------------------------
|
| 34 |
+
# 📂 LOAD DATA (CACHE)
|
| 35 |
# --------------------------------------
|
| 36 |
@st.cache_data
|
| 37 |
def load_data():
|
| 38 |
+
df = pd.read_csv(DATA_PATH)
|
| 39 |
+
|
|
|
|
|
|
|
| 40 |
unnecessary_cols = ['Unnamed: 0', 'track_id', 'album_name', 'explicit']
|
| 41 |
df_display = df.drop(columns=[c for c in unnecessary_cols if c in df.columns])
|
| 42 |
+
|
| 43 |
return df, df_display
|
| 44 |
|
| 45 |
+
@st.cache_resource
|
| 46 |
+
def load_model():
|
| 47 |
+
model = joblib.load(MODEL_PATH)
|
| 48 |
+
scaler = joblib.load(SCALER_PATH)
|
| 49 |
+
return model, scaler
|
| 50 |
+
|
| 51 |
df, df_display = load_data()
|
| 52 |
+
model, scaler = load_model()
|
|
|
|
| 53 |
|
| 54 |
# --------------------------------------
|
| 55 |
+
# 🧠 SESSION STATE (NO FLICKER)
|
| 56 |
# --------------------------------------
|
| 57 |
+
if "prediction" not in st.session_state:
|
| 58 |
+
st.session_state.prediction = None
|
| 59 |
+
st.session_state.samples = None
|
| 60 |
+
|
| 61 |
+
# --------------------------------------
|
| 62 |
+
# 🏷️ TITLE
|
| 63 |
+
# --------------------------------------
|
| 64 |
+
st.title("🎵 Spotify Music Clustering / Spotify Müzik Kümeleme")
|
| 65 |
st.markdown("---")
|
| 66 |
|
| 67 |
# --------------------------------------
|
| 68 |
+
# 📄 DATA PREVIEW
|
| 69 |
# --------------------------------------
|
| 70 |
st.subheader("📄 Dataset Preview / Veri Önizleme")
|
|
|
|
| 71 |
st.dataframe(df_display.head(10), use_container_width=True)
|
| 72 |
|
| 73 |
# --------------------------------------
|
| 74 |
+
# 📊 VISUALS
|
| 75 |
# --------------------------------------
|
| 76 |
col1, col2 = st.columns(2)
|
| 77 |
|
| 78 |
with col1:
|
| 79 |
st.subheader("📊 Cluster Distribution / Küme Dağılımı")
|
| 80 |
+
st.bar_chart(df['cluster'].value_counts(), use_container_width=True)
|
| 81 |
|
| 82 |
with col2:
|
| 83 |
st.subheader("🎯 Feature Analysis / Özellik Analizi")
|
| 84 |
+
|
| 85 |
+
fig, ax = plt.subplots(figsize=(6, 4))
|
| 86 |
+
scatter = ax.scatter(
|
| 87 |
+
df['danceability'],
|
| 88 |
+
df['energy'],
|
| 89 |
+
c=df['cluster'],
|
| 90 |
+
cmap='viridis',
|
| 91 |
+
alpha=0.6
|
| 92 |
+
)
|
| 93 |
+
|
| 94 |
ax.set_xlabel("Danceability / Dans Edilebilirlik")
|
| 95 |
ax.set_ylabel("Energy / Enerji")
|
| 96 |
+
|
| 97 |
+
plt.colorbar(scatter, ax=ax)
|
| 98 |
+
|
| 99 |
st.pyplot(fig, clear_figure=True)
|
| 100 |
+
plt.close(fig)
|
| 101 |
|
| 102 |
# --------------------------------------
|
| 103 |
+
# 🤖 PREDICTION
|
| 104 |
# --------------------------------------
|
| 105 |
st.divider()
|
| 106 |
st.subheader("🤖 Predict New Song Cluster / Yeni Şarkı Tahmini")
|
|
|
|
| 107 |
|
| 108 |
c1, c2, c3 = st.columns(3)
|
| 109 |
|
|
|
|
| 118 |
tempo = st.slider("Tempo / Tempo", 0.0, 250.0, 120.0)
|
| 119 |
|
| 120 |
with c3:
|
|
|
|
| 121 |
speech = st.slider("Speechiness / Konuşma Oranı", 0.0, 1.0, 0.1)
|
| 122 |
|
| 123 |
if st.button("Predict Cluster / Kümeyi Tahmin Et ✨"):
|
|
|
|
| 124 |
new_data = [[pop, dur, dance, energy, loud, tempo, speech]]
|
| 125 |
+
|
| 126 |
try:
|
| 127 |
new_data_scaled = scaler.transform(new_data)
|
| 128 |
res = model.predict(new_data_scaled)[0]
|
| 129 |
+
|
| 130 |
+
st.session_state.prediction = res
|
| 131 |
+
st.session_state.samples = df[df['cluster'] == res][['track_name', 'artists']].head(5)
|
| 132 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
| 133 |
except Exception as e:
|
| 134 |
+
st.error(f"Error / Hata: {e}")
|
| 135 |
+
|
| 136 |
+
# SONUÇ (STABLE)
|
| 137 |
+
if st.session_state.prediction is not None:
|
| 138 |
+
st.success(f"### Predicted Cluster / Tahmin Edilen Küme: {st.session_state.prediction}")
|
| 139 |
+
st.write("Similar Songs / Benzer Şarkılar:")
|
| 140 |
+
st.table(st.session_state.samples)
|
| 141 |
|
| 142 |
# --------------------------------------
|
| 143 |
+
# 🔍 CLUSTER ANALYSIS
|
| 144 |
# --------------------------------------
|
| 145 |
st.divider()
|
| 146 |
+
st.subheader("🔍 Cluster Characteristics / Küme Özellikleri")
|
| 147 |
+
|
| 148 |
numeric_only = df.select_dtypes(include=['float64', 'int64'])
|
| 149 |
+
|
| 150 |
if 'cluster' in df.columns:
|
| 151 |
means = numeric_only.groupby(df['cluster']).mean()
|
| 152 |
st.dataframe(means, use_container_width=True)
|