Cytonorm 2o

README.md

@@ -8,7 +8,7 @@
 [link-tests]: https://github.com/TarikExner/CytoNormPy/actions/workflows/pytest.yml
 [badge-docs]: https://img.shields.io/readthedocs/cytonormpy
 
-A python port for the CytoNorm R library.
+A python port for the CytoNorm (2.0) R library.
 
 # Installation
 

cytonormpy/__init__.py

@@ -1,57 +1,61 @@
+import sys
 from ._cytonorm import CytoNorm, example_cytonorm, example_anndata
 from ._dataset import FCSFile
-from ._clustering import (FlowSOM,
-                          KMeans,
-                          MeanShift,
-                          AffinityPropagation)
-from ._transformation import (AsinhTransformer,
-                              HyperLogTransformer,
-                              LogTransformer,
-                              LogicleTransformer,
-                              Transformer)
-from ._plotting import Plotter
+from ._clustering import FlowSOM, KMeans, MeanShift, AffinityPropagation
+from ._transformation import (
+    AsinhTransformer,
+    HyperLogTransformer,
+    LogTransformer,
+    LogicleTransformer,
+    Transformer,
+)
 from ._cytonorm import read_model
-from ._evaluation import (mad_from_fcs,
-                          mad_comparison_from_fcs,
-                          mad_from_anndata,
-                          mad_comparison_from_anndata,
-                          emd_from_fcs,
-                          emd_comparison_from_fcs,
-                          emd_from_anndata,
-                          emd_comparison_from_anndata)
-
+from ._evaluation import (
+    mad_from_fcs,
+    mad_comparison_from_fcs,
+    mad_from_anndata,
+    mad_comparison_from_anndata,
+    emd_from_fcs,
+    emd_comparison_from_fcs,
+    emd_from_anndata,
+    emd_comparison_from_anndata,
+)
+from . import _plotting as pl
+from ._plotting import scatter, histogram, emd, mad, cv_heatmap, splineplot, Plotter
+
+sys.modules.update({f"{__name__}.{m}": globals()[m] for m in ["pl"]})
 
 __all__ = [
     "CytoNorm",
-
     "FlowSOM",
     "KMeans",
     "MeanShift",
     "AffinityPropagation",
-
     "example_anndata",
     "example_cytonorm",
-
     "Transformer",
     "AsinhTransformer",
     "HyperLogTransformer",
     "LogTransformer",
     "LogicleTransformer",
-
-    "Plotter",
     "FCSFile",
-
     "read_model",
-
     "mad_from_fcs",
     "mad_comparison_from_fcs",
     "mad_from_anndata",
     "mad_comparison_from_anndata",
-
     "emd_from_fcs",
     "emd_comparison_from_fcs",
     "emd_from_anndata",
-    "emd_comparison_from_anndata"
+    "emd_comparison_from_anndata",
+    "pl",
+    "scatter",
+    "histogram",
+    "emd",
+    "mad",
+    "cv_heatmap",
+    "splineplot",
+    "Plotter",
 ]
 
-__version__ = '0.0.3'
+__version__ = "1.0.2"

cytonormpy/_clustering/__init__.py

@@ -1,11 +1,3 @@
-from ._cluster_algorithms import (FlowSOM,
-                                  KMeans,
-                                  MeanShift,
-                                  AffinityPropagation)
+from ._cluster_algorithms import FlowSOM, KMeans, MeanShift, AffinityPropagation
 
-__all__ = [
-    "FlowSOM",
-    "KMeans",
-    "MeanShift",
-    "AffinityPropagation"
-]
+__all__ = ["FlowSOM", "KMeans", "MeanShift", "AffinityPropagation"]

cytonormpy/_clustering/_cluster_algorithms.py

@@ -1,14 +1,13 @@
 import numpy as np
+import warnings
 
-from typing import Optional
-
+from abc import abstractmethod
 from flowsom.models import FlowSOMEstimator
+from sklearn.base import clone
 from sklearn.cluster import KMeans as knnclassifier
 from sklearn.cluster import AffinityPropagation as affinitypropagationclassifier
 from sklearn.cluster import MeanShift as meanshiftclassifier
 
-from abc import abstractmethod
-
 
 class ClusterBase:
     """\
@@ -20,15 +19,15 @@ def __init__(self):
         pass
 
     @abstractmethod
-    def train(self,
-              X: np.ndarray,
-              **kwargs) -> None:
+    def train(self, X: np.ndarray, **kwargs) -> None:
         pass
 
     @abstractmethod
-    def calculate_clusters(self,
-                           X: np.ndarray,
-                           **kwargs) -> np.ndarray:
+    def calculate_clusters(self, X: np.ndarray, **kwargs) -> np.ndarray:
+        pass
+
+    @abstractmethod
+    def calculate_clusters_multiple(self, X: np.ndarray, n_clusters: list[int]) -> np.ndarray:
         pass
 
 
@@ -48,8 +47,7 @@ class FlowSOM(ClusterBase):
 
     """
 
-    def __init__(self,
-                 **kwargs):
+    def __init__(self, **kwargs):
         super().__init__()
         if not kwargs:
             kwargs = {}
@@ -59,9 +57,7 @@ def __init__(self,
             kwargs["seed"] = 187
         self.est = FlowSOMEstimator(**kwargs)
 
-    def train(self,
-              X: np.ndarray,
-              **kwargs):
+    def train(self, X: np.ndarray, **kwargs):
         """\
         Trains the SOM. Calls :class:`flowsom.FlowSOMEstimator.fit()` internally.
 
@@ -80,9 +76,7 @@ def train(self,
         self.est.fit(X, **kwargs)
         return
 
-    def calculate_clusters(self,
-                           X: np.ndarray,
-                           **kwargs) -> np.ndarray:
+    def calculate_clusters(self, X: np.ndarray, **kwargs) -> np.ndarray:
         """\
         Calculates the clusters. Calls :class:`flowsom.FlowSOMEstimator.predict()` internally.
 
@@ -100,6 +94,35 @@ def calculate_clusters(self,
         """
         return self.est.predict(X, **kwargs)
 
+    def calculate_clusters_multiple(self, X: np.ndarray, n_clusters: list[int]):
+        """\
+        Calculates the clusters for a given metacluster number. The estimator
+        will calculate a SOM once, then fit the ConsensusCluster class given
+        the n_metaclusters that are provided.
+
+        Parameters
+        ----------
+        X
+            The data that are supposed to be predicted.
+        n_metaclusters
+            A list of integers specifying the number of metaclusters per test.
+
+        Returns
+        -------
+        Cluster annotations stored in a :class:`np.ndarray`, where the n_metacluster
+        denotes the column and the rows are the individual cells.
+
+        """
+        self.est.cluster_model.fit(X)
+        y_clusters = self.est.cluster_model.predict(X)
+        X_codes = self.est.cluster_model.codes
+        assignments = np.empty((X.shape[0], len(n_clusters)), dtype=np.int16)
+        for j, n_mc in enumerate(n_clusters):
+            self.est.set_n_clusters(n_mc)
+            y_codes = self.est.metacluster_model.fit_predict(X_codes)
+            assignments[:, j] = y_codes[y_clusters]
+        return assignments
+
 
 class MeanShift(ClusterBase):
     """\
@@ -117,16 +140,11 @@ class MeanShift(ClusterBase):
 
     """
 
-    def __init__(self,
-                 **kwargs):
+    def __init__(self, **kwargs):
         super().__init__()
-        if "random_state" not in kwargs:
-            kwargs["random_state"] = 187
         self.est = meanshiftclassifier(**kwargs)
 
-    def train(self,
-              X: np.ndarray,
-              **kwargs):
+    def train(self, X: np.ndarray, **kwargs):
         """\
         Trains the classifier. Calls :class:`sklearn.cluster.MeanShift.fit()` internally.
 
@@ -145,9 +163,7 @@ def train(self,
         self.est.fit(X, **kwargs)
         return
 
-    def calculate_clusters(self,
-                           X: np.ndarray,
-                           **kwargs) -> np.ndarray:
+    def calculate_clusters(self, X: np.ndarray, **kwargs) -> np.ndarray:
         """\
         Calculates the clusters. Calls :class:`sklearn.cluster.MeanShift.predict()` internally.
 
@@ -165,6 +181,29 @@ def calculate_clusters(self,
         """
         return self.est.predict(X, **kwargs)
 
+    def calculate_clusters_multiple(self, X: np.ndarray, n_clusters: list[int]):
+        """
+        MeanShift ignores n_clusters: warns if len(n_clusters)>1,
+        then returns the same assignment in each column.
+        """
+        if len(n_clusters) > 1:
+            warnings.warn(
+                "MeanShift: ignoring requested n_clusters list, "
+                "producing identical assignments for each entry.",
+                UserWarning,
+                stacklevel=2,
+            )
+
+        n_samples = X.shape[0]
+        out = np.empty((n_samples, len(n_clusters)), dtype=int)
+
+        for j in range(len(n_clusters)):
+            est = clone(self.est)
+            est.fit(X)
+            out[:, j] = est.predict(X)
+
+        return out
+
 
 class KMeans(ClusterBase):
     """\
@@ -182,16 +221,13 @@ class KMeans(ClusterBase):
 
     """
 
-    def __init__(self,
-                 **kwargs):
+    def __init__(self, **kwargs):
         super().__init__()
         if "random_state" not in kwargs:
             kwargs["random_state"] = 187
         self.est = knnclassifier(**kwargs)
 
-    def train(self,
-              X: np.ndarray,
-              **kwargs):
+    def train(self, X: np.ndarray, **kwargs):
         """\
         Trains the classifier. Calls :class:`sklearn.cluster.KMeans.fit()` internally.
 
@@ -210,9 +246,7 @@ def train(self,
         self.est.fit(X, **kwargs)
         return
 
-    def calculate_clusters(self,
-                           X: np.ndarray,
-                           **kwargs) -> np.ndarray:
+    def calculate_clusters(self, X: np.ndarray, **kwargs) -> np.ndarray:
         """\
         Calculates the clusters. Calls :class:`sklearn.cluster.KMeans.predict()` internally.
 
@@ -230,6 +264,23 @@ def calculate_clusters(self,
         """
         return self.est.predict(X, **kwargs)
 
+    def calculate_clusters_multiple(self, X: np.ndarray, n_clusters: list[int]):
+        """
+        Returns an array of shape (n_samples, len(n_clusters)),
+        where each column i is the cluster‐assignment vector
+        for KMeans(n_clusters=n_clusters[i]).
+        """
+        n_samples = X.shape[0]
+        out = np.empty((n_samples, len(n_clusters)), dtype=int)
+
+        for j, k in enumerate(n_clusters):
+            est = clone(self.est)
+            est.set_params(n_clusters=k)
+            est.fit(X)
+            out[:, j] = est.predict(X)
+
+        return out
+
 
 class AffinityPropagation(ClusterBase):
     """\
@@ -247,16 +298,13 @@ class AffinityPropagation(ClusterBase):
 
     """
 
-    def __init__(self,
-                 **kwargs):
+    def __init__(self, **kwargs):
         super().__init__()
         if "random_state" not in kwargs:
             kwargs["random_state"] = 187
         self.est = affinitypropagationclassifier(**kwargs)
 
-    def train(self,
-              X: np.ndarray,
-              **kwargs):
+    def train(self, X: np.ndarray, **kwargs):
         """\
         Trains the classifier. Calls :class:`sklearn.cluster.AffinityPropagation.fit()` internally.
 
@@ -275,9 +323,7 @@ def train(self,
         self.est.fit(X, **kwargs)
         return
 
-    def calculate_clusters(self,
-                           X: np.ndarray,
-                           **kwargs) -> np.ndarray:
+    def calculate_clusters(self, X: np.ndarray, **kwargs) -> np.ndarray:
         """\
         Calculates the clusters. Calls :class:`sklearn.cluster.AffinityPropagation.predict()` internally.
 
@@ -294,3 +340,26 @@ def calculate_clusters(self,
 
         """
         return self.est.predict(X, **kwargs)
+
+    def calculate_clusters_multiple(self, X: np.ndarray, n_clusters: list[int]):
+        """
+        AffinityPropagation ignores n_clusters: warns if len(n_clusters)>1,
+        then returns the same assignment for each entry.
+        """
+        if len(n_clusters) > 1:
+            warnings.warn(
+                "AffinityPropagation: ignoring requested n_clusters list, "
+                "producing identical assignments for each entry.",
+                UserWarning,
+                stacklevel=2,
+            )
+
+        n_samples = X.shape[0]
+        out = np.empty((n_samples, len(n_clusters)), dtype=int)
+
+        for j in range(len(n_clusters)):
+            est = clone(self.est)
+            est.fit(X)
+            out[:, j] = est.predict(X)
+
+        return out