Evaluation and edition of modules

BML_project/active_learning/ss_active_learning.py

@@ -57,6 +57,30 @@ def run_minibatch_kmeans(data_loader, n_clusters, device, batch_size=100):
 
     return minibatch_kmeans
 
+""" from sklearn.cluster import MiniBatchKMeans
+import numpy as np
+
+def run_minibatch_kmeans(data_loader, n_clusters, device, batch_size=100, n_init='auto'):
+    # Initialize MiniBatchKMeans with explicit n_init to suppress the FutureWarning
+    minibatch_kmeans = MiniBatchKMeans(n_clusters=n_clusters, n_init=n_init, random_state=0, batch_size=batch_size)
+
+    # Prepare an empty list to collect all data for fitting
+    all_data = []
+
+    # Iterate through data_loader and collect data
+    for batch in data_loader:
+        # Assuming 'data' is a key in your batch dict that contains the features
+        data = batch['data'].view(batch['data'].size(0), -1).cpu().numpy()  # Adjust as necessary
+        all_data.append(data)
+
+    # Concatenate all data collected from the batches
+    all_data_np = np.concatenate(all_data, axis=0)
+
+    # Fit MiniBatchKMeans with all collected data at once
+    minibatch_kmeans.fit(all_data_np)
+
+    return minibatch_kmeans """
+
 # def compare_kmeans_gp_predictions(kmeans_model, gp_model, data_loader, device):
 #     # Compare K-Means with GP model predictions
 #     all_data, all_labels = [], []