risk-network 0.0.8b27__py3-none-any.whl → 0.0.9b2__py3-none-any.whl

risk/__init__.py

@@ -7,4 +7,4 @@ RISK: RISK Infers Spatial Kinships
 
 from risk.risk import RISK
 
-__version__ = "0.0.8-beta.27"
+__version__ = "0.0.9-beta.2"

risk/annotations/annotations.py

@@ -83,69 +83,69 @@ def load_annotations(network: nx.Graph, annotations_input: Dict[str, Any]) -> Di
 def define_top_annotations(
     network: nx.Graph,
     ordered_annotation_labels: List[str],
-    neighborhood_enrichment_sums: List[int],
-    significant_enrichment_matrix: np.ndarray,
-    significant_binary_enrichment_matrix: np.ndarray,
+    neighborhood_significance_sums: List[int],
+    significant_significance_matrix: np.ndarray,
+    significant_binary_significance_matrix: np.ndarray,
     min_cluster_size: int = 5,
     max_cluster_size: int = 1000,
 ) -> pd.DataFrame:
-    """Define top annotations based on neighborhood enrichment sums and binary enrichment matrix.
+    """Define top annotations based on neighborhood significance sums and binary significance matrix.
 
     Args:
         network (NetworkX graph): The network graph.
         ordered_annotation_labels (list of str): List of ordered annotation labels.
-        neighborhood_enrichment_sums (list of int): List of neighborhood enrichment sums.
-        significant_enrichment_matrix (np.ndarray): Enrichment matrix below alpha threshold.
-        significant_binary_enrichment_matrix (np.ndarray): Binary enrichment matrix below alpha threshold.
+        neighborhood_significance_sums (list of int): List of neighborhood significance sums.
+        significant_significance_matrix (np.ndarray): Enrichment matrix below alpha threshold.
+        significant_binary_significance_matrix (np.ndarray): Binary significance matrix below alpha threshold.
         min_cluster_size (int, optional): Minimum cluster size. Defaults to 5.
         max_cluster_size (int, optional): Maximum cluster size. Defaults to 1000.
 
     Returns:
         pd.DataFrame: DataFrame with top annotations and their properties.
     """
-    # Sum the columns of the significant enrichment matrix (positive floating point values)
-    significant_enrichment_scores = significant_enrichment_matrix.sum(axis=0)
-    # Create DataFrame to store annotations, their neighborhood enrichment sums, and enrichment scores
-    annotations_enrichment_matrix = pd.DataFrame(
+    # Sum the columns of the significant significance matrix (positive floating point values)
+    significant_significance_scores = significant_significance_matrix.sum(axis=0)
+    # Create DataFrame to store annotations, their neighborhood significance sums, and significance scores
+    annotations_significance_matrix = pd.DataFrame(
         {
             "id": range(len(ordered_annotation_labels)),
             "full_terms": ordered_annotation_labels,
-            "significant_neighborhood_enrichment_sums": neighborhood_enrichment_sums,
-            "significant_enrichment_score": significant_enrichment_scores,
+            "significant_neighborhood_significance_sums": neighborhood_significance_sums,
+            "significant_significance_score": significant_significance_scores,
         }
     )
-    annotations_enrichment_matrix["significant_annotations"] = False
+    annotations_significance_matrix["significant_annotations"] = False
     # Apply size constraints to identify potential significant annotations
-    annotations_enrichment_matrix.loc[
+    annotations_significance_matrix.loc[
         (
-            annotations_enrichment_matrix["significant_neighborhood_enrichment_sums"]
+            annotations_significance_matrix["significant_neighborhood_significance_sums"]
             >= min_cluster_size
         )
         & (
-            annotations_enrichment_matrix["significant_neighborhood_enrichment_sums"]
+            annotations_significance_matrix["significant_neighborhood_significance_sums"]
             <= max_cluster_size
         ),
         "significant_annotations",
     ] = True
     # Initialize columns for connected components analysis
-    annotations_enrichment_matrix["num_connected_components"] = 0
-    annotations_enrichment_matrix["size_connected_components"] = None
-    annotations_enrichment_matrix["size_connected_components"] = annotations_enrichment_matrix[
+    annotations_significance_matrix["num_connected_components"] = 0
+    annotations_significance_matrix["size_connected_components"] = None
+    annotations_significance_matrix["size_connected_components"] = annotations_significance_matrix[
         "size_connected_components"
     ].astype(object)
-    annotations_enrichment_matrix["num_large_connected_components"] = 0
+    annotations_significance_matrix["num_large_connected_components"] = 0
 
-    for attribute in annotations_enrichment_matrix.index.values[
-        annotations_enrichment_matrix["significant_annotations"]
+    for attribute in annotations_significance_matrix.index.values[
+        annotations_significance_matrix["significant_annotations"]
     ]:
-        # Identify enriched neighborhoods based on the binary enrichment matrix
-        enriched_neighborhoods = list(
-            compress(list(network), significant_binary_enrichment_matrix[:, attribute])
+        # Identify significant neighborhoods based on the binary significance matrix
+        significant_neighborhoods = list(
+            compress(list(network), significant_binary_significance_matrix[:, attribute])
         )
-        enriched_network = nx.subgraph(network, enriched_neighborhoods)
-        # Analyze connected components within the enriched subnetwork
+        significant_network = nx.subgraph(network, significant_neighborhoods)
+        # Analyze connected components within the significant subnetwork
         connected_components = sorted(
-            nx.connected_components(enriched_network), key=len, reverse=True
+            nx.connected_components(significant_network), key=len, reverse=True
         )
         size_connected_components = np.array([len(c) for c in connected_components])
 
@@ -159,23 +159,24 @@ def define_top_annotations(
         num_large_connected_components = len(filtered_size_connected_components)
 
         # Assign the number of connected components
-        annotations_enrichment_matrix.loc[attribute, "num_connected_components"] = (
+        annotations_significance_matrix.loc[attribute, "num_connected_components"] = (
             num_connected_components
         )
         # Filter out attributes with more than one connected component
-        annotations_enrichment_matrix.loc[
-            annotations_enrichment_matrix["num_connected_components"] > 1, "significant_annotations"
+        annotations_significance_matrix.loc[
+            annotations_significance_matrix["num_connected_components"] > 1,
+            "significant_annotations",
         ] = False
         # Assign the number of large connected components
-        annotations_enrichment_matrix.loc[attribute, "num_large_connected_components"] = (
+        annotations_significance_matrix.loc[attribute, "num_large_connected_components"] = (
             num_large_connected_components
         )
         # Assign the size of connected components, ensuring it is always a list
-        annotations_enrichment_matrix.at[attribute, "size_connected_components"] = (
+        annotations_significance_matrix.at[attribute, "size_connected_components"] = (
             filtered_size_connected_components.tolist()
         )
 
-    return annotations_enrichment_matrix
+    return annotations_significance_matrix
 
 
 def get_weighted_description(words_column: pd.Series, scores_column: pd.Series) -> str:
@@ -184,16 +185,16 @@ def get_weighted_description(words_column: pd.Series, scores_column: pd.Series)
 
     Args:
         words_column (pd.Series): A pandas Series containing strings to process.
-        scores_column (pd.Series): A pandas Series containing enrichment scores to weigh the terms.
+        scores_column (pd.Series): A pandas Series containing significance scores to weigh the terms.
 
     Returns:
-        str: A coherent description formed from the most frequent and significant words, weighed by enrichment scores.
+        str: A coherent description formed from the most frequent and significant words, weighed by significance scores.
     """
     # Handle case where all scores are the same
     if scores_column.max() == scores_column.min():
         normalized_scores = pd.Series([1] * len(scores_column))
     else:
-        # Normalize the enrichment scores to be between 0 and 1
+        # Normalize the significance scores to be between 0 and 1
         normalized_scores = (scores_column - scores_column.min()) / (
             scores_column.max() - scores_column.min()
         )

risk/annotations/io.py

@@ -76,11 +76,13 @@ class AnnotationsIO:
         _log_loading(filetype, filepath=filepath)
 
         # Load the specified sheet from the Excel file
-        df = pd.read_excel(filepath, sheet_name=sheet_name)
+        annotation = pd.read_excel(filepath, sheet_name=sheet_name)
         # Split the nodes column by the specified nodes_delimiter
-        df[nodes_colname] = df[nodes_colname].apply(lambda x: x.split(nodes_delimiter))
+        annotation[nodes_colname] = annotation[nodes_colname].apply(
+            lambda x: x.split(nodes_delimiter)
+        )
         # Convert the DataFrame to a dictionary pairing labels with their corresponding nodes
-        label_node_dict = df.set_index(label_colname)[nodes_colname].to_dict()
+        label_node_dict = annotation.set_index(label_colname)[nodes_colname].to_dict()
 
         # Load the annotations into the provided network
         return load_annotations(network, label_node_dict)
@@ -203,11 +205,11 @@ def _load_matrix_file(
         Dict[str, Any]: A dictionary where each label is paired with its respective list of nodes.
     """
     # Load the CSV or TSV file into a DataFrame
-    df = pd.read_csv(filepath, delimiter=delimiter)
+    annotation = pd.read_csv(filepath, delimiter=delimiter)
     # Split the nodes column by the nodes_delimiter to handle multiple nodes per label
-    df[nodes_colname] = df[nodes_colname].apply(lambda x: x.split(nodes_delimiter))
+    annotation[nodes_colname] = annotation[nodes_colname].apply(lambda x: x.split(nodes_delimiter))
     # Create a dictionary pairing labels with their corresponding list of nodes
-    label_node_dict = df.set_index(label_colname)[nodes_colname].to_dict()
+    label_node_dict = annotation.set_index(label_colname)[nodes_colname].to_dict()
     return label_node_dict
 
 

risk/log/__init__.py

@@ -4,6 +4,8 @@ risk/log
 """
 
 from .console import logger, log_header, set_global_verbosity
-from .params import Params
+from .parameters import Params
 
+# Initialize the global parameters logger
 params = Params()
+params.initialize()

risk/log/{params.py → parameters.py}

@@ -1,50 +1,22 @@
 """
-risk/log/params
-~~~~~~~~~~~~~~~
+risk/log/parameters
+~~~~~~~~~~~~~~~~~~~
 """
 
 import csv
 import json
 import warnings
 from datetime import datetime
-from functools import wraps
 from typing import Any, Dict
 
 import numpy as np
 
-from .console import logger, log_header
+from risk.log.console import logger, log_header
 
 # Suppress all warnings - this is to resolve warnings from multiprocessing
 warnings.filterwarnings("ignore")
 
 
-def _safe_param_export(func):
-    """A decorator to wrap parameter export functions in a try-except block for safe execution.
-
-    Args:
-        func (function): The function to be wrapped.
-
-    Returns:
-        function: The wrapped function with error handling.
-    """
-
-    @wraps(func)
-    def wrapper(*args, **kwargs):
-        try:
-            result = func(*args, **kwargs)
-            filepath = (
-                kwargs.get("filepath") or args[1]
-            )  # Assuming filepath is always the second argument
-            logger.info(f"Parameters successfully exported to filepath: {filepath}")
-            return result
-        except Exception as e:
-            filepath = kwargs.get("filepath") or args[1]
-            logger.error(f"An error occurred while exporting parameters to {filepath}: {e}")
-            return None
-
-    return wrapper
-
-
 class Params:
     """Handles the storage and logging of various parameters for network analysis.
 
@@ -106,7 +78,6 @@ class Params:
         """
         self.plotter = {**self.plotter, **kwargs}
 
-    @_safe_param_export
     def to_csv(self, filepath: str) -> None:
         """Export the parameters to a CSV file.
 
@@ -128,7 +99,8 @@ class Params:
                 else:
                     writer.writerow([parent_key, "", parent_value])
 
-    @_safe_param_export
+        logger.info(f"Parameters exported to CSV file: {filepath}")
+
     def to_json(self, filepath: str) -> None:
         """Export the parameters to a JSON file.
 
@@ -138,7 +110,8 @@ class Params:
         with open(filepath, "w") as json_file:
             json.dump(self.load(), json_file, indent=4)
 
-    @_safe_param_export
+        logger.info(f"Parameters exported to JSON file: {filepath}")
+
     def to_txt(self, filepath: str) -> None:
         """Export the parameters to a text file.
 
@@ -155,6 +128,8 @@ class Params:
             # Add a blank line after each entry
             txt_file.write("\n")
 
+        logger.info(f"Parameters exported to text file: {filepath}")
+
     def load(self) -> Dict[str, Any]:
         """Load and process various parameters, converting any np.ndarray values to lists.
 

risk/neighborhoods/domains.py

@@ -20,17 +20,17 @@ from risk.log import logger
 
 def define_domains(
     top_annotations: pd.DataFrame,
-    significant_neighborhoods_enrichment: np.ndarray,
+    significant_neighborhoods_significance: np.ndarray,
     linkage_criterion: str,
     linkage_method: str,
     linkage_metric: str,
 ) -> pd.DataFrame:
-    """Define domains and assign nodes to these domains based on their enrichment scores and clustering,
+    """Define domains and assign nodes to these domains based on their significance scores and clustering,
     handling errors by assigning unique domains when clustering fails.
 
     Args:
         top_annotations (pd.DataFrame): DataFrame of top annotations data for the network nodes.
-        significant_neighborhoods_enrichment (np.ndarray): The binary enrichment matrix below alpha.
+        significant_neighborhoods_significance (np.ndarray): The binary significance matrix below alpha.
         linkage_criterion (str): The clustering criterion for defining groups.
         linkage_method (str): The linkage method for clustering.
         linkage_metric (str): The linkage metric for clustering.
@@ -40,7 +40,7 @@ def define_domains(
     """
     try:
         # Transpose the matrix to cluster annotations
-        m = significant_neighborhoods_enrichment[:, top_annotations["significant_annotations"]].T
+        m = significant_neighborhoods_significance[:, top_annotations["significant_annotations"]].T
         best_linkage, best_metric, best_threshold = _optimize_silhouette_across_linkage_and_metrics(
             m, linkage_criterion, linkage_method, linkage_metric
         )
@@ -65,13 +65,13 @@ def define_domains(
         top_annotations["domain"] = range(1, n_rows + 1)  # Assign unique domains
 
     # Create DataFrames to store domain information
-    node_to_enrichment = pd.DataFrame(
-        data=significant_neighborhoods_enrichment,
+    node_to_significance = pd.DataFrame(
+        data=significant_neighborhoods_significance,
         columns=[top_annotations.index.values, top_annotations["domain"]],
     )
-    node_to_domain = node_to_enrichment.groupby(level="domain", axis=1).sum()
+    node_to_domain = node_to_significance.groupby(level="domain", axis=1).sum()
 
-    # Find the maximum enrichment score for each node
+    # Find the maximum significance score for each node
     t_max = node_to_domain.loc[:, 1:].max(axis=1)
     t_idxmax = node_to_domain.loc[:, 1:].idxmax(axis=1)
     t_idxmax[t_max == 0] = 0
@@ -101,7 +101,7 @@ def trim_domains_and_top_annotations(
         max_cluster_size (int, optional): Maximum size of a cluster to be retained. Defaults to 1000.
 
     Returns:
-        Tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame]: A tuple containing:
+        Tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame]:
             - Trimmed annotations (pd.DataFrame)
             - Trimmed domains (pd.DataFrame)
             - A DataFrame with domain labels (pd.DataFrame)
@@ -119,27 +119,27 @@ def trim_domains_and_top_annotations(
     top_annotations["domain"].replace(to_remove, invalid_domain_id, inplace=True)
     domains.loc[domains["primary_domain"].isin(to_remove), ["primary_domain"]] = invalid_domain_id
 
-    # Normalize "num enriched neighborhoods" by percentile for each domain and scale to 0-10
+    # Normalize "num significant neighborhoods" by percentile for each domain and scale to 0-10
     top_annotations["normalized_value"] = top_annotations.groupby("domain")[
-        "significant_neighborhood_enrichment_sums"
+        "significant_neighborhood_significance_sums"
     ].transform(lambda x: (x.rank(pct=True) * 10).apply(np.ceil).astype(int))
-    # Modify the lambda function to pass both full_terms and significant_enrichment_score
+    # Modify the lambda function to pass both full_terms and significant_significance_score
     top_annotations["combined_terms"] = top_annotations.apply(
         lambda row: " ".join([str(row["full_terms"])] * row["normalized_value"]), axis=1
     )
 
-    # Perform the groupby operation while retaining the other columns and adding the weighting with enrichment scores
+    # Perform the groupby operation while retaining the other columns and adding the weighting with significance scores
     domain_labels = (
         top_annotations.groupby("domain")
         .agg(
             full_terms=("full_terms", lambda x: list(x)),
-            enrichment_scores=("significant_enrichment_score", lambda x: list(x)),
+            significance_scores=("significant_significance_score", lambda x: list(x)),
         )
         .reset_index()
     )
     domain_labels["combined_terms"] = domain_labels.apply(
         lambda row: get_weighted_description(
-            pd.Series(row["full_terms"]), pd.Series(row["enrichment_scores"])
+            pd.Series(row["full_terms"]), pd.Series(row["significance_scores"])
         ),
         axis=1,
     )
@@ -150,7 +150,7 @@ def trim_domains_and_top_annotations(
             "domain": "id",
             "combined_terms": "normalized_description",
             "full_terms": "full_descriptions",
-            "enrichment_scores": "enrichment_scores",
+            "significance_scores": "significance_scores",
         }
     ).set_index("id")
 
@@ -177,7 +177,7 @@ def _optimize_silhouette_across_linkage_and_metrics(
         linkage_metric (str): Linkage metric for clustering.
 
     Returns:
-        Tuple[str, str, float]: A tuple containing:
+        Tuple[str, str, float]:
             - Best linkage method (str)
             - Best linkage metric (str)
             - Best threshold (float)
@@ -231,7 +231,7 @@ def _find_best_silhouette_score(
         resolution (float, optional): Desired resolution for the best threshold. Defaults to 0.001.
 
     Returns:
-        Tuple[float, float]: A tuple containing:
+        Tuple[float, float]:
             - Best threshold (float): The threshold that yields the best silhouette score.
             - Best silhouette score (float): The highest silhouette score achieved.
     """