Remove unused imports and print statements

src/squidpy/gr/_niche.py

@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-import itertools
 from collections.abc import Iterator
 from typing import Any
 
@@ -10,12 +9,10 @@
 import scanpy as sc
 import scipy.sparse as sps
 from anndata import AnnData
-from scipy.sparse import csr_matrix, hstack, issparse, spdiags
-from scipy.stats import ranksums
+from scipy.sparse import hstack, issparse, spdiags
 from sklearn import metrics
-from sklearn.metrics import adjusted_rand_score, fowlkes_mallows_score, normalized_mutual_info_score
 from sklearn.mixture import GaussianMixture
-from sklearn.preprocessing import StandardScaler, normalize
+from sklearn.preprocessing import normalize
 from spatialdata import SpatialData
 
 from squidpy._utils import NDArrayA
@@ -26,7 +23,7 @@
 def calculate_niche(
     adata: AnnData | SpatialData,
     flavor: str = "neighborhood",
-    library_key: str | None = None,
+    library_key: str | None = None,  # TODO: calculate niches on a per-slide basis
     table_key: str | None = None,
     mask: pd.core.series.Series = None,
     groups: str | None = None,
@@ -132,9 +129,7 @@ def calculate_niche(
             adata_neighborhood = adata_neighborhood[mask]
 
         # required for leiden clustering (note: no dim reduction performed in original implementation)
-        print("calculating neighbors...")
         sc.pp.neighbors(adata_neighborhood, n_neighbors=n_neighbors, use_rep="X")
-        print("finished calculating neighbors")
 
         if resolutions is not None:
             if not isinstance(resolutions, list):
@@ -143,13 +138,11 @@ def calculate_niche(
             raise ValueError("Please provide resolutions for leiden clustering.")
 
         # For each resolution, apply leiden on neighborhood profile. Each cluster label equals to a niche label
-        print("starting clustering...")
         for res in resolutions:
             sc.tl.leiden(adata_neighborhood, resolution=res, key_added=f"neighborhood_niche_res={res}")
             adata.obs[f"neighborhood_niche_res={res}"] = adata.obs.index.map(
                 adata_neighborhood.obs[f"neighborhood_niche_res={res}"]
             ).fillna("not_a_niche")
-            print(f"finished clustering at resolution {res}")
 
             # filter niches with n_cells < min_niche_size
             if min_niche_size is not None:
@@ -337,13 +330,9 @@ def _get_GMM_clusters(A: np.ndarray[np.float64, Any], n_components: int, random_
     """Returns niche labels generated by GMM clustering.
     Compared to cellcharter this approach is simplified by using sklearn's GaussianMixture model without stability analysis."""
 
-    print("initializing GMM...")
     gmm = GaussianMixture(n_components=n_components, random_state=random_state, init_params="random_from_data")
-    print("fitting GMM...")
     gmm.fit(A)
-    print("predicting labels...")
     labels = gmm.predict(A)
-    print("done")
 
     return labels