fit data using kmeans

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 kmeans_clustered_spotify_dataset.csv filter=lfs diff=lfs merge=lfs -text
+data.csv filter=lfs diff=lfs merge=lfs -text

app.py

@@ -3,6 +3,7 @@ import spotipy
 import gradio as gr
 import pandas as pd
 
+from get_scaler import get_scaler
 from dotenv import load_dotenv
 from recommendations import recommend_songs
 from spotipy.oauth2 import SpotifyClientCredentials
@@ -17,7 +18,8 @@ client_secret = os.getenv('SPOTIFY_CLIENT_SECRET')
 # Authenticate with the Spotify API
 sp = spotipy.Spotify(auth_manager=SpotifyClientCredentials(client_id=client_id, client_secret=client_secret))
 
-data = pd.read_csv("kmeans_clustered_spotify_dataset.csv")
+# data = pd.read_csv("kmeans_clustered_spotify_dataset.csv")
+data = get_scaler()[0]
 
 def fetch_song_cover(song_name):
     # Search for the song

kmeans_clustered_spotify_dataset.csv → data.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab1f64fbf645f615ad389912e5fe63a23610a5f31c589f24aff0eafbc257a044
-size 31824490
+oid sha256:c97c42349c2e97339ff908ab01163ec5a3264f02ec65e78cb961c85077ded7f8
+size 29654587

get_scaler.py

@@ -0,0 +1,14 @@
+
+def get_scaler():
+
+  data = pd.read_csv("data.csv")
+  song_cluster_pipeline = Pipeline([("scaler", StandardScaler()),
+                                    ("kmeans", KMeans(n_clusters=20,
+                                                    verbose=False))],
+                                  verbose=False)
+
+  X = data.select_dtypes(np.number)
+  number_cols = list(X.columns)
+
+  data["cluster_label"] = song_cluster_pipeline.fit_predict(X)
+  return data, song_cluster_pipeline

recommendations.py

@@ -1,11 +1,11 @@
 
 import os
 import spotipy
-import difflib
 import pandas as pd
 import numpy as np
 from sklearn.preprocessing import StandardScaler
 
+from get_scaler import get_scaler
 from dotenv import load_dotenv
 from spotipy.oauth2 import SpotifyClientCredentials
 from collections import defaultdict
@@ -98,7 +98,7 @@ def recommend_songs( song_list, spotify_data, n_songs=10):
 
     song_center = get_song_data(song_list[0], spotify_data)[number_cols].values
 
-    scaler = StandardScaler()
+    scaler = get_scaler()[1]
     scaled_data = scaler.transform(spotify_data[number_cols])
     scaled_song_center = scaler.transform(song_center.reshape(1, -1))
     distances = cdist(scaled_song_center, scaled_data, 'cosine')