merging bugs fixed

viscy/data/hcs.py

@@ -3,6 +3,7 @@
 import os
 import re
 import tempfile
+import warnings
 from pathlib import Path
 from typing import Callable, Literal, Sequence
 
@@ -25,8 +26,12 @@
 from torch.utils.data import DataLoader, Dataset
 
 from viscy.data.typing import ChannelMap, DictTransform, HCSStackIndex, NormMeta, Sample
-import warnings
-warnings.filterwarnings("ignore", category=UserWarning, message="To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).")
+
+warnings.filterwarnings(
+    "ignore",
+    category=UserWarning,
+    message="To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).",
+)
 _logger = logging.getLogger("lightning.pytorch")
 
 
@@ -551,7 +556,7 @@ def predict_dataloader(self):
             self.predict_dataset,
             batch_size=self.batch_size,
             num_workers=self.num_workers,
-            shuffle=False, 
+            shuffle=False,
         )
 
     def _fit_transform(self) -> tuple[Compose, Compose]:

viscy/representation/contrastive.py

@@ -1,11 +1,11 @@
+import warnings
 from typing import Literal
 
 import timm
 import torch.nn as nn
 from torch import Tensor
 
 from viscy.unet.networks.unext2 import StemDepthtoChannels
-import warnings
 
 warnings.filterwarnings("ignore", category=UserWarning, module="torch")
 
@@ -84,7 +84,6 @@ def __init__(
         )
         # Append modified encoder.
         self.encoder = encoder
-        self.intermediate_projection = intermediate_projection
         # Append modified projection head.
         self.projection = projection
 

viscy/representation/evalutation/clustering.py

@@ -1,14 +1,15 @@
 """Methods for evaluating clustering performance."""
 
+import numpy as np
 from sklearn.cluster import DBSCAN
 from sklearn.metrics import (
     accuracy_score,
     adjusted_rand_score,
     normalized_mutual_info_score,
 )
-from sklearn.neighbors import KNeighborsClassifier
 from sklearn.mixture import GaussianMixture
-import numpy as np
+from sklearn.neighbors import KNeighborsClassifier
+
 
 class GMMClustering:
     def __init__(self, features_data, n_clusters_range=np.arange(2, 10)):
@@ -78,7 +79,6 @@ def predict_clusters(self):
         return cluster_labels
 
 
-
 def knn_accuracy(embeddings, annotations, k=5):
     """
     Evaluate the k-NN classification accuracy.

viscy/representation/evalutation/dimensionality_reduction.py

@@ -37,6 +37,7 @@ def compute_pca(embedding_dataset, n_components=None, normalize_features=False):
 
     return PCA_features, PCA_projection, pca_df
 
+
 def _fit_transform_umap(
     embeddings: NDArray, n_components: int = 2, normalize: bool = True
 ) -> tuple[umap.UMAP, NDArray]: