risk-network 0.0.9b37__py3-none-any.whl → 0.0.9b38__py3-none-any.whl

risk/__init__.py

@@ -7,4 +7,4 @@ RISK: Regional Inference of Significant Kinships
 
 from risk.risk import RISK
 
-__version__ = "0.0.9-beta.37"
+__version__ = "0.0.9-beta.38"

risk/neighborhoods/domains.py

@@ -10,6 +10,7 @@ from typing import Tuple, Union
 import numpy as np
 import pandas as pd
 from scipy.cluster.hierarchy import linkage, fcluster
+from scipy.optimize import minimize_scalar
 from sklearn.metrics import calinski_harabasz_score, davies_bouldin_score, silhouette_score
 from tqdm import tqdm
 
@@ -42,8 +43,8 @@ def define_domains(
             clustering or "maxclust" for a fixed number of clusters. Use "off" to skip clustering.
         linkage_method (str): The linkage method for clustering. Use "auto" to try multiple methods.
         linkage_metric (str): The linkage metric for clustering. Use "auto" to try multiple metrics.
-        linkage_threshold (float): The linkage threshold for clustering, or one of "silhouette", "calinski_harabasz",
-            or "davies_bouldin" to optimize the threshold.
+        linkage_threshold (str, float): The linkage threshold for clustering, or one of "silhouette",
+            "calinski_harabasz", or "davies_bouldin" to optimize the threshold.
 
     Returns:
         pd.DataFrame: DataFrame with the primary domain for each node.
@@ -229,7 +230,7 @@ def _optimize_linkage_threshold_across_methods_and_metrics(
         linkage_criterion (str): Criterion for fcluster (typically "distance").
         linkage_method (str): Linkage method for clustering, or "auto" to try multiple methods.
         linkage_metric (str): Distance metric for clustering, or "auto" to try multiple metrics.
-        linkage_threshold (Union[str, float]): Either a numeric threshold or one of
+        linkage_threshold (str, float): Either a numeric threshold or one of the following keywords:
             "silhouette", "calinski_harabasz", or "davies_bouldin" to trigger optimization.
 
     Returns:
@@ -306,86 +307,62 @@ def _find_optimal_linkage_threshold(
     linkage_criterion: str,
     opt_metric: str = "silhouette",
 ) -> Tuple[float, float]:
-    """Find the optimal linkage threshold coefficient (multiplier for np.max(Z[:, 2])) via binary search.
-    The threshold is chosen to optimize clustering quality, as measured by the chosen metric.
+    """Find the optimal linkage threshold coefficient for hierarchical clustering. The function optimizes
+    the threshold value using the specified metric (opt_metric).
 
     Args:
-        Z (np.ndarray): Linkage matrix.
-        m (np.ndarray): Data matrix.
-        linkage_metric (str): The metric used for clustering quality calculation.
-        linkage_criterion (str): The criterion to pass to fcluster (typically "distance").
-        opt_metric (str): The metric to optimize; one of "silhouette", "calinski_harabasz", or "davies_bouldin".
-            For "silhouette" and "calinski_harabasz", higher is better; for "davies_bouldin", lower is better.
+        Z (np.ndarray): Linkage matrix generated by a hierarchical clustering algorithm.
+        m (np.ndarray): Data matrix used for clustering.
+        linkage_metric (str): Metric used to calculate distances between data points
+            (e.g., "euclidean" or "cosine").
+        linkage_criterion (str): Criterion to pass to `fcluster`, typically "distance".
+        opt_metric (str, optional): Metric to optimize clustering quality. Options are:
+            "silhouette", "calinski_harabasz", or "davies_bouldin". Defaults to "silhouette".
 
     Returns:
         Tuple[float, float]:
-            - best_threshold: The optimal linkage coefficient for np.max(Z[:, 2]).
-            - best_metric_value: The clustering quality metric achieved (with higher being better for
-              "silhouette" and "calinski_harabasz", and lower for "davies_bouldin").
+            - best_threshold (float): The optimal linkage threshold coefficient.
+            - best_metric_value (float): The value of the clustering quality metric achieved
+              at the optimal threshold (higher for "silhouette" and "calinski_harabasz",
+              lower for "davies_bouldin").
+
+    Raises:
+        ValueError: If the `opt_metric` argument is not one of the supported metrics.
     """
+    # Get the maximum distance in the linkage matrix
     max_d = np.max(Z[:, 2])
-    lower_bound = 0.0
-    upper_bound = 1.0
     resolution = 1e-6
 
     def compute_objective(coefficient: float) -> float:
-        """Compute the objective function for a given linkage threshold coefficient."""
+        """Compute the objective function for optimization."""
         threshold_val = coefficient * max_d
         clusters = fcluster(Z, threshold_val, criterion=linkage_criterion)
         unique_clusters = np.unique(clusters)
-        # Return a heavy penalty if the clustering is trivial.
         if len(unique_clusters) <= 1 or len(unique_clusters) == m.shape[0]:
             return 1e6
         try:
             if opt_metric == "silhouette":
                 score = silhouette_score(m, clusters, metric=linkage_metric)
-                return -score  # We want to maximize the silhouette score.
+                return -score  # We want to maximize the score.
             elif opt_metric == "calinski_harabasz":
                 score = calinski_harabasz_score(m, clusters)
-                return -score  # Higher is better.
+                return -score
             elif opt_metric == "davies_bouldin":
                 score = davies_bouldin_score(m, clusters)
-                return score  # Lower is better.
+                return score
             else:
-                raise LinkageThresholdError(f"Unknown optimization metric: {opt_metric}.")
+                raise ValueError(f"Unknown optimization metric: {opt_metric}.")
         except Exception:
             return 1e6
 
-    # Initialize the bounds and the best objective value
-    obj_lower = compute_objective(lower_bound)
-    obj_upper = compute_objective(upper_bound)
-    # Determine the initial direction of the search
-    if obj_lower < obj_upper:
-        best_obj = obj_lower
-        best_threshold = lower_bound
-        lower = lower_bound
-        upper = (lower_bound + upper_bound) / 2
-    else:
-        best_obj = obj_upper
-        best_threshold = upper_bound
-        lower = (lower_bound + upper_bound) / 2
-        upper = upper_bound
-
-    # Perform binary search to find the optimal linkage threshold coefficient
-    while (upper - lower) > resolution:
-        mid = (upper + lower) / 2
-        obj_mid = compute_objective(mid)
-        if obj_mid < best_obj:
-            best_obj = obj_mid
-            best_threshold = mid
-
-        # Update the bounds based on the objective value
-        obj_left = compute_objective((lower + mid) / 2)
-        obj_right = compute_objective((mid + upper) / 2)
-        if obj_left < obj_right:
-            upper = mid
-        else:
-            lower = mid
+    # Optimize the threshold using the specified metric
+    res = minimize_scalar(
+        compute_objective, bounds=(0.0, 1.0), method="bounded", options={"xatol": resolution}
+    )
 
-    # If the optimization metric is silhouette or calinski_harabasz, return the negative value
-    if opt_metric in ["silhouette", "calinski_harabasz"]:
-        best_metric_value = -best_obj
-    else:
-        best_metric_value = best_obj
+    best_threshold = res.x
+    best_obj = res.fun
+    # For silhouette and calinski_harabasz, the objective was negative.
+    best_metric_value = -best_obj if opt_metric in ["silhouette", "calinski_harabasz"] else best_obj
 
     return best_threshold, float(best_metric_value)

risk/network/graph/api.py

@@ -58,9 +58,12 @@ class GraphAPI:
             impute_depth (int, optional): Depth for imputing neighbors. Defaults to 0.
             prune_threshold (float, optional): Distance threshold for pruning neighbors. Defaults to 0.0.
             linkage_criterion (str, optional): Clustering criterion for defining domains. Defaults to "distance".
-            linkage_method (str, optional): Clustering method to use. Defaults to "average".
-            linkage_metric (str, optional): Metric to use for calculating distances. Defaults to "yule".
-            linkage_threshold (float, optional): Threshold for clustering. Defaults to 0.2.
+            linkage_method (str, optional): Clustering method to use. Defaults to "average". Choose "auto"
+                to automatically select the best linkage method.
+            linkage_metric (str, optional): Metric to use for calculating distances. Defaults to "yule". Choose "auto"
+                to automatically select the best linkage metric.
+            linkage_threshold (str, float, optional): Threshold for clustering. Choose "silhouette", "calinski_harabasz",
+                or "davies_bouldin" to automatically select the best threshold. Defaults to 0.2.
             min_cluster_size (int, optional): Minimum size for clusters. Defaults to 5.
             max_cluster_size (int, optional): Maximum size for clusters. Defaults to 1000.
 

{risk_network-0.0.9b37.dist-info → risk_network-0.0.9b38.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: risk-network
-Version: 0.0.9b37
+Version: 0.0.9b38
 Summary: A Python package for biological network analysis
 Author: Ira Horecka
 Author-email: Ira Horecka <ira89@icloud.com>

{risk_network-0.0.9b37.dist-info → risk_network-0.0.9b38.dist-info}/RECORD

@@ -1,4 +1,4 @@
-risk/__init__.py,sha256=T82k1TIYSqPy3KdA5kWb-5ZtqtksCWdHZ4e5vTYhTSY,127
+risk/__init__.py,sha256=S22dtKjPn7IvWeLakeN4IajRLsqHuSbBhjvf6z5kHoo,127
 risk/constants.py,sha256=XInRaH78Slnw_sWgAsBFbUHkyA0h0jL0DKGuQNbOvjM,550
 risk/risk.py,sha256=s827_lRknFseOP9O4zW8sP-IcCd2EzrpV_tnVY_tz5s,1104
 risk/annotations/__init__.py,sha256=parsbcux1U4urpUqh9AdzbDWuLj9HlMidycMPkpSQFo,179
@@ -10,13 +10,13 @@ risk/log/parameters.py,sha256=VtwfMzLU1xI4yji3-Ch5vHjH-KdwTfwaEMmi7hFQTs0,5716
 risk/neighborhoods/__init__.py,sha256=Q74HwTH7okI-vaskJPy2bYwb5sNjGASTzJ6m8V8arCU,234
 risk/neighborhoods/api.py,sha256=ywngw2TQVV27gYlWDXcs8-qnmeepnvb-W9ov6J6VEPM,23341
 risk/neighborhoods/community.py,sha256=5Q_-VAJC-5SY5EUsB8gIlemeDoAL85uLjyl16pItHiQ,16699
-risk/neighborhoods/domains.py,sha256=lMEKwZaOcFIVFqCPPgER1GQQR_ANIWaNk5m2zRdUH08,16774
+risk/neighborhoods/domains.py,sha256=yaSHymGfRJVuXHIa7BwoKzvIRSg5oLhNoOMg0tsVqV8,15961
 risk/neighborhoods/neighborhoods.py,sha256=l9FhADB1C-OxM8E9QXOcA4osUDgA1vs4ud-OCGKKybc,21457
 risk/network/__init__.py,sha256=oVi3FA1XXKD84014Cykq-9bpX4_s0F3aAUfNOU-07Qw,73
 risk/network/geometry.py,sha256=eVtGHMgBf9fEqQZUFdHWjw-zFYYpfUONoHFSAxoRkug,6219
 risk/network/io.py,sha256=RCH4nQdgYDXcNwMfpSz7qEmPO0pJ1p9fL0rNQptsQrc,21673
 risk/network/graph/__init__.py,sha256=ziGJew3yhtqvrb9LUuneDu_LwW2Wa9vd4UuhoL5l1CA,91
-risk/network/graph/api.py,sha256=9yoviP7EqFU1okLJZlaLBZzFNmjOHv30B1JgDFNP1bg,8399
+risk/network/graph/api.py,sha256=fOyd-5rRnqmtquproP90scehewd0UtOVZS65hCuwasI,8684
 risk/network/graph/graph.py,sha256=qEWyZvuaGT_vvjhreBdmRPX3gst2wQFaXhFAvikPSqw,12158
 risk/network/graph/summary.py,sha256=Y_0rL2C1UoQeZQIPVe5LbaCO356Mcc8HisnrXwQsRm8,10289
 risk/network/plotter/__init__.py,sha256=4gWtQHGzQVNHmEBXi31Zf0tX0y2sTcE66J_yGnn7268,99
@@ -34,8 +34,8 @@ risk/stats/stat_tests.py,sha256=tj0ri9w89_1fsjGLuafTWpfBEwZXpSLn7Ej2aAQ5lxk,1177
 risk/stats/permutation/__init__.py,sha256=OLmYLm2uj96hPsSaUs0vUqFYw6Thwch_aHtpL7L0ZFw,127
 risk/stats/permutation/permutation.py,sha256=BWjgdBpLVcHvmwHy0bmD4aJFccxifNBSrrCBPppyKf4,10569
 risk/stats/permutation/test_functions.py,sha256=KlECWTz1EZ6EPF_OAgHb0uznaIhopiVYb_AKUKuC4no,3120
-risk_network-0.0.9b37.dist-info/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
-risk_network-0.0.9b37.dist-info/METADATA,sha256=5tQlDkFQSqNgXhv-_TZSfraFKAseXh7LCHciBQIR4CQ,47627
-risk_network-0.0.9b37.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-risk_network-0.0.9b37.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
-risk_network-0.0.9b37.dist-info/RECORD,,
+risk_network-0.0.9b38.dist-info/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
+risk_network-0.0.9b38.dist-info/METADATA,sha256=mAB2KQoRWeOH13radrcMeW5dalpkPkl4YtjfUpQhJXI,47627
+risk_network-0.0.9b38.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+risk_network-0.0.9b38.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
+risk_network-0.0.9b38.dist-info/RECORD,,