| import pandas as pd | |
| import numpy as np | |
| from sklearn.cluster import KMeans | |
| from sklearn.preprocessing import StandardScaler | |
| from sklearn.pipeline import Pipeline | |
| 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 | |