risk-network 0.0.13b4__tar.gz → 0.0.13b5__tar.gz

{risk_network-0.0.13b4/src/risk_network.egg-info → risk_network-0.0.13b5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: risk-network
-Version: 0.0.13b4
+Version: 0.0.13b5
 Summary: A Python package for scalable network analysis and high-quality visualization.
 Author-email: Ira Horecka <ira89@icloud.com>
 License: GPL-3.0-or-later

risk_network-0.0.13b5/src/risk/__init__.py

@@ -0,0 +1,11 @@
+"""
+risk
+~~~~
+
+RISK: Regional Inference of Significant Kinships
+"""
+
+from .risk import RISK
+
+__all__ = ["RISK"]
+__version__ = "0.0.13-beta.5"

risk_network-0.0.13b5/src/risk/_annotation/__init__.py

@@ -0,0 +1,10 @@
+"""
+risk/_annotation
+~~~~~~~~~~~~~~~~
+"""
+
+from ._annotation import (
+    define_top_annotation,
+    get_weighted_description,
+)
+from ._io import AnnotationIO

risk_network-0.0.13b4/src/risk/annotation/annotation.py → risk_network-0.0.13b5/src/risk/_annotation/_annotation.py

@@ -1,6 +1,6 @@
 """
-risk/annotation/annotation
-~~~~~~~~~~~~~~~~~~~~~~~~~~
+risk/_annotation/_annotation
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 """
 
 import re
@@ -14,12 +14,13 @@ import pandas as pd
 from nltk.tokenize import word_tokenize
 from scipy.sparse import coo_matrix
 
-from risk.annotation.nltk_setup import setup_nltk_resources
-from risk.log import logger
+from .._log import logger
+from ._nltk_setup import setup_nltk_resources
 
 
 def initialize_nltk():
-    """Initialize all required NLTK components."""
+    """
+    Initialize all required NLTK components."""
     setup_nltk_resources()
 
     # After resources are available, initialize the components
@@ -41,7 +42,8 @@ def load_annotation(
     min_nodes_per_term: int = 1,
     max_nodes_per_term: int = 10_000,
 ) -> Dict[str, Any]:
-    """Convert annotation input to a sparse matrix and reindex based on the network's node labels.
+    """
+    Convert annotation input to a sparse matrix and reindex based on the network's node labels.
 
     Args:
         network (nx.Graph): The network graph.
@@ -127,7 +129,8 @@ def define_top_annotation(
     min_cluster_size: int = 5,
     max_cluster_size: int = 1000,
 ) -> pd.DataFrame:
-    """Define top annotations based on neighborhood significance sums and binary significance matrix.
+    """
+    Define top annotations based on neighborhood significance sums and binary significance matrix.
 
     Args:
         network (NetworkX graph): The network graph.
@@ -218,7 +221,8 @@ def define_top_annotation(
 
 
 def get_weighted_description(words_column: pd.Series, scores_column: pd.Series) -> str:
-    """Generate a weighted description from words and their corresponding scores,
+    """
+    Generate a weighted description from words and their corresponding scores,
     using improved weighting logic with normalization, lemmatization, and aggregation.
 
     Args:
@@ -286,7 +290,8 @@ def get_weighted_description(words_column: pd.Series, scores_column: pd.Series)
 
 
 def _simplify_word_list(words: List[str], threshold: float = 0.80) -> List[str]:
-    """Filter out words that are too similar based on the Jaccard index,
+    """
+    Filter out words that are too similar based on the Jaccard index,
     keeping the word with the higher aggregated count.
 
     Args:
@@ -326,7 +331,8 @@ def _simplify_word_list(words: List[str], threshold: float = 0.80) -> List[str]:
 
 
 def _calculate_jaccard_index(set1: Set[Any], set2: Set[Any]) -> float:
-    """Calculate the Jaccard index between two sets.
+    """
+    Calculate the Jaccard index between two sets.
 
     Args:
         set1 (Set[Any]): The first set.
@@ -341,7 +347,8 @@ def _calculate_jaccard_index(set1: Set[Any], set2: Set[Any]) -> float:
 
 
 def _generate_coherent_description(words: List[str]) -> str:
-    """Generate a coherent description from a list of words.
+    """
+    Generate a coherent description from a list of words.
 
     If there is only one unique entry, return it directly.
     Otherwise, order the words by frequency and join them into a single string.

risk_network-0.0.13b4/src/risk/annotation/io.py → risk_network-0.0.13b5/src/risk/_annotation/_io.py

@@ -1,6 +1,6 @@
 """
-risk/annotation/io
-~~~~~~~~~~~~~~~~~~
+risk/_annotation/_io
+~~~~~~~~~~~~~~~~~~~~
 """
 
 import json
@@ -9,12 +9,13 @@ from typing import Any, Dict
 import networkx as nx
 import pandas as pd
 
-from risk.annotation.annotation import load_annotation
-from risk.log import log_header, logger, params
+from .._log import log_header, logger, params
+from ._annotation import load_annotation
 
 
 class AnnotationIO:
-    """Handles the loading and exporting of annotation in various file formats.
+    """
+    Handles the loading and exporting of annotation in various file formats.
 
     The AnnotationIO class provides methods to load annotation from different file types (JSON, CSV, Excel, etc.)
     and to export parameter data to various formats like JSON, CSV, and text files.
@@ -27,7 +28,8 @@ class AnnotationIO:
         min_nodes_per_term: int = 1,
         max_nodes_per_term: int = 10_000,
     ) -> Dict[str, Any]:
-        """Load annotation from a JSON file and convert them to a DataFrame.
+        """
+        Load annotation from a JSON file and convert them to a DataFrame.
 
         Args:
             network (NetworkX graph): The network to which the annotation is related.
@@ -67,7 +69,8 @@ class AnnotationIO:
         min_nodes_per_term: int = 1,
         max_nodes_per_term: int = 10_000,
     ) -> Dict[str, Any]:
-        """Load annotation from an Excel file and associate them with the network.
+        """
+        Load annotation from an Excel file and associate them with the network.
 
         Args:
             network (nx.Graph): The NetworkX graph to which the annotation is related.
@@ -116,7 +119,8 @@ class AnnotationIO:
         min_nodes_per_term: int = 1,
         max_nodes_per_term: int = 10_000,
     ) -> Dict[str, Any]:
-        """Load annotation from a CSV file and associate them with the network.
+        """
+        Load annotation from a CSV file and associate them with the network.
 
         Args:
             network (nx.Graph): The NetworkX graph to which the annotation is related.
@@ -160,7 +164,8 @@ class AnnotationIO:
         min_nodes_per_term: int = 1,
         max_nodes_per_term: int = 10_000,
     ) -> Dict[str, Any]:
-        """Load annotation from a TSV file and associate them with the network.
+        """
+        Load annotation from a TSV file and associate them with the network.
 
         Args:
             network (nx.Graph): The NetworkX graph to which the annotation is related.
@@ -201,7 +206,8 @@ class AnnotationIO:
         min_nodes_per_term: int = 1,
         max_nodes_per_term: int = 10_000,
     ) -> Dict[str, Any]:
-        """Load annotation from a provided dictionary and convert them to a dictionary annotation.
+        """
+        Load annotation from a provided dictionary and convert them to a dictionary annotation.
 
         Args:
             network (NetworkX graph): The network to which the annotation is related.
@@ -244,7 +250,8 @@ class AnnotationIO:
         delimiter: str = ",",
         nodes_delimiter: str = ";",
     ) -> Dict[str, Any]:
-        """Load annotation from a CSV or TSV file and convert them to a dictionary.
+        """
+        Load annotation from a CSV or TSV file and convert them to a dictionary.
 
         Args:
             filepath (str): Path to the annotation file.
@@ -267,7 +274,8 @@ class AnnotationIO:
         return label_node_dict
 
     def _log_loading_annotation(self, filetype: str, filepath: str = "") -> None:
-        """Log the loading of annotation files.
+        """
+        Log the loading of annotation files.
 
         Args:
             filetype (str): The type of the file being loaded (e.g., 'Cytoscape').

risk_network-0.0.13b4/src/risk/annotation/nltk_setup.py → risk_network-0.0.13b5/src/risk/_annotation/_nltk_setup.py

@@ -1,6 +1,6 @@
 """
-risk/annotation/nltk_setup
-~~~~~~~~~~~~~~~~~~~~~~~~~~
+risk/_annotation/_nltk_setup
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 """
 
 import os
@@ -11,11 +11,12 @@ import nltk
 from nltk.data import find
 from nltk.data import path as nltk_data_path
 
-from risk.log import logger
+from .._log import logger
 
 
 def setup_nltk_resources(required_resources: Optional[List[Tuple[str, str]]] = None) -> None:
-    """Ensures all required NLTK resources are available and properly extracted.
+    """
+    Ensures all required NLTK resources are available and properly extracted.
     Uses NLTK's default paths and mechanisms.
 
     Args:
@@ -47,7 +48,8 @@ def setup_nltk_resources(required_resources: Optional[List[Tuple[str, str]]] = N
 
 
 def verify_and_extract_if_needed(resource_path: str, package_name: str) -> None:
-    """Verifies if the resource is properly extracted and extracts if needed. Respects
+    """
+    Verifies if the resource is properly extracted and extracts if needed. Respects
     NLTK's directory structure where the extracted content should be in the same directory
     as the zip file.
 

risk_network-0.0.13b5/src/risk/_log/__init__.py

@@ -0,0 +1,11 @@
+"""
+risk/_log
+~~~~~~~~~
+"""
+
+from ._console import log_header, logger, set_global_verbosity
+from ._parameters import Params
+
+# Initialize the global parameters logger
+params = Params()
+params.initialize()

risk_network-0.0.13b4/src/risk/log/console.py → risk_network-0.0.13b5/src/risk/_log/_console.py

@@ -1,13 +1,14 @@
 """
-risk/log/console
-~~~~~~~~~~~~~~~~
+risk/_log/_console
+~~~~~~~~~~~~~~~~~~
 """
 
 import logging
 
 
 def in_jupyter():
-    """Check if the code is running in a Jupyter notebook environment.
+    """
+    Check if the code is running in a Jupyter notebook environment.
 
     Returns:
         bool: True if running in a Jupyter notebook or QtConsole, False otherwise.
@@ -26,7 +27,8 @@ def in_jupyter():
 
 # Define the MockLogger class to replicate logging behavior with print statements in Jupyter
 class MockLogger:
-    """MockLogger: A lightweight logger replacement using print statements in Jupyter.
+    """
+    MockLogger: A lightweight logger replacement using print statements in Jupyter.
 
     The MockLogger class replicates the behavior of a standard logger using print statements
     to display messages. This is primarily used in a Jupyter environment to show outputs
@@ -35,7 +37,8 @@ class MockLogger:
     """
 
     def __init__(self, verbose: bool = True):
-        """Initialize the MockLogger with verbosity settings.
+        """
+        Initialize the MockLogger with verbosity settings.
 
         Args:
             verbose (bool): If True, display all log messages (info, debug, warning).
@@ -44,7 +47,8 @@ class MockLogger:
         self.verbose = verbose
 
     def info(self, message: str) -> None:
-        """Display an informational message.
+        """
+        Display an informational message.
 
         Args:
             message (str): The informational message to be printed.
@@ -53,7 +57,8 @@ class MockLogger:
             print(message)
 
     def debug(self, message: str) -> None:
-        """Display a debug message.
+        """
+        Display a debug message.
 
         Args:
             message (str): The debug message to be printed.
@@ -62,7 +67,8 @@ class MockLogger:
             print(message)
 
     def warning(self, message: str) -> None:
-        """Display a warning message.
+        """
+        Display a warning message.
 
         Args:
             message (str): The warning message to be printed.
@@ -70,7 +76,8 @@ class MockLogger:
         print(message)
 
     def error(self, message: str) -> None:
-        """Display an error message.
+        """
+        Display an error message.
 
         Args:
             message (str): The error message to be printed.
@@ -78,7 +85,8 @@ class MockLogger:
         print(message)
 
     def setLevel(self, level: int) -> None:
-        """Adjust verbosity based on the logging level.
+        """
+        Adjust verbosity based on the logging level.
 
         Args:
             level (int): Logging level to control message display.
@@ -108,7 +116,8 @@ else:
 
 
 def set_global_verbosity(verbose):
-    """Set the global verbosity level for the logger.
+    """
+    Set the global verbosity level for the logger.
 
     Args:
         verbose (bool): Whether to display all log messages (True) or only error messages (False).
@@ -130,7 +139,8 @@ def set_global_verbosity(verbose):
 
 
 def log_header(input_string: str) -> None:
-    """Log the input string as a header with a line of dashes above and below it.
+    """
+    Log the input string as a header with a line of dashes above and below it.
 
     Args:
         input_string (str): The string to be printed as a header.

risk_network-0.0.13b4/src/risk/log/parameters.py → risk_network-0.0.13b5/src/risk/_log/_parameters.py

@@ -1,6 +1,6 @@
 """
-risk/log/parameters
-~~~~~~~~~~~~~~~~~~~
+risk/_log/_parameters
+~~~~~~~~~~~~~~~~~~~~~
 """
 
 import csv
@@ -11,14 +11,15 @@ from typing import Any, Dict
 
 import numpy as np
 
-from risk.log.console import log_header, logger
+from ._console import log_header, logger
 
 # Suppress all warnings - this is to resolve warnings from multiprocessing
 warnings.filterwarnings("ignore")
 
 
 class Params:
-    """Handles the storage and logging of various parameters for network analysis.
+    """
+    Handles the storage and logging of various parameters for network analysis.
 
     The Params class provides methods to log parameters related to different components of the analysis,
     such as the network, annotation, neighborhoods, graph, and plotter settings. It also stores
@@ -39,7 +40,8 @@ class Params:
         self.plotter = {}
 
     def log_network(self, **kwargs) -> None:
-        """Log network-related parameters.
+        """
+        Log network-related parameters.
 
         Args:
             **kwargs: Network parameters to log.
@@ -47,7 +49,8 @@ class Params:
         self.network = {**self.network, **kwargs}
 
     def log_annotation(self, **kwargs) -> None:
-        """Log annotation-related parameters.
+        """
+        Log annotation-related parameters.
 
         Args:
             **kwargs: Annotation parameters to log.
@@ -55,7 +58,8 @@ class Params:
         self.annotation = {**self.annotation, **kwargs}
 
     def log_neighborhoods(self, **kwargs) -> None:
-        """Log neighborhood-related parameters.
+        """
+        Log neighborhood-related parameters.
 
         Args:
             **kwargs: Neighborhood parameters to log.
@@ -63,7 +67,8 @@ class Params:
         self.neighborhoods = {**self.neighborhoods, **kwargs}
 
     def log_graph(self, **kwargs) -> None:
-        """Log graph-related parameters.
+        """
+        Log graph-related parameters.
 
         Args:
             **kwargs: Graph parameters to log.
@@ -71,7 +76,8 @@ class Params:
         self.graph = {**self.graph, **kwargs}
 
     def log_plotter(self, **kwargs) -> None:
-        """Log plotter-related parameters.
+        """
+        Log plotter-related parameters.
 
         Args:
             **kwargs: Plotter parameters to log.
@@ -79,7 +85,8 @@ class Params:
         self.plotter = {**self.plotter, **kwargs}
 
     def to_csv(self, filepath: str) -> None:
-        """Export the parameters to a CSV file.
+        """
+        Export the parameters to a CSV file.
 
         Args:
             filepath (str): The path where the CSV file will be saved.
@@ -102,7 +109,8 @@ class Params:
         logger.info(f"Parameters exported to CSV file: {filepath}")
 
     def to_json(self, filepath: str) -> None:
-        """Export the parameters to a JSON file.
+        """
+        Export the parameters to a JSON file.
 
         Args:
             filepath (str): The path where the JSON file will be saved.
@@ -113,7 +121,8 @@ class Params:
         logger.info(f"Parameters exported to JSON file: {filepath}")
 
     def to_txt(self, filepath: str) -> None:
-        """Export the parameters to a text file.
+        """
+        Export the parameters to a text file.
 
         Args:
             filepath (str): The path where the text file will be saved.
@@ -131,7 +140,8 @@ class Params:
         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.
+        """
+        Load and process various parameters, converting any np.ndarray values to lists.
 
         Returns:
             Dict[str, Any]: A dictionary containing the processed parameters.
@@ -149,7 +159,8 @@ class Params:
         )
 
     def _convert_ndarray_to_list(self, d: Dict[str, Any]) -> Dict[str, Any]:
-        """Recursively convert all np.ndarray values in the dictionary to lists.
+        """
+        Recursively convert all np.ndarray values in the dictionary to lists.
 
         Args:
             d (Dict[str, Any]): The dictionary to process.

risk_network-0.0.13b5/src/risk/_neighborhoods/__init__.py

@@ -0,0 +1,8 @@
+"""
+risk/_neighborhoods
+~~~~~~~~~~~~~~~~~~~
+"""
+
+from ._api import NeighborhoodsAPI
+from ._domains import define_domains, trim_domains
+from ._neighborhoods import process_neighborhoods

risk_network-0.0.13b4/src/risk/neighborhoods/api.py → risk_network-0.0.13b5/src/risk/_neighborhoods/_api.py

@@ -1,6 +1,6 @@
 """
-risk/neighborhoods/api
-~~~~~~~~~~~~~~~~~~~~~~
+risk/_neighborhoods/_api
+~~~~~~~~~~~~~~~~~~~~~~~~
 """
 
 import copy
@@ -10,9 +10,9 @@ import networkx as nx
 import numpy as np
 from scipy.sparse import csr_matrix
 
-from risk.log import log_header, logger, params
-from risk.neighborhoods.neighborhoods import get_network_neighborhoods
-from risk.neighborhoods.stats import (
+from .._log import log_header, logger, params
+from ._neighborhoods import get_network_neighborhoods
+from ._stats import (
     compute_binom_test,
     compute_chi2_test,
     compute_hypergeom_test,
@@ -23,7 +23,8 @@ from risk.neighborhoods.stats import (
 
 
 class NeighborhoodsAPI:
-    """Handles the loading of statistical results and annotation significance for neighborhoods.
+    """
+    Handles the loading of statistical results and annotation significance for neighborhoods.
 
     The NeighborhoodsAPI class provides methods to load neighborhood results from statistical tests.
     """
@@ -42,7 +43,8 @@ class NeighborhoodsAPI:
         null_distribution: str = "network",
         random_seed: int = 888,
     ) -> Dict[str, Any]:
-        """Load significant neighborhoods for the network using the binomial test.
+        """
+        Load significant neighborhoods for the network using the binomial test.
 
         Args:
             network (nx.Graph): The network graph.
@@ -87,7 +89,8 @@ class NeighborhoodsAPI:
         null_distribution: str = "network",
         random_seed: int = 888,
     ) -> Dict[str, Any]:
-        """Load significant neighborhoods for the network using the chi-squared test.
+        """
+        Load significant neighborhoods for the network using the chi-squared test.
 
         Args:
             network (nx.Graph): The network graph.
@@ -132,7 +135,8 @@ class NeighborhoodsAPI:
         null_distribution: str = "network",
         random_seed: int = 888,
     ) -> Dict[str, Any]:
-        """Load significant neighborhoods for the network using the hypergeometric test.
+        """
+        Load significant neighborhoods for the network using the hypergeometric test.
 
         Args:
             network (nx.Graph): The network graph.
@@ -180,7 +184,8 @@ class NeighborhoodsAPI:
         random_seed: int = 888,
         max_workers: int = 1,
     ) -> Dict[str, Any]:
-        """Load significant neighborhoods for the network using the permutation test.
+        """
+        Load significant neighborhoods for the network using the permutation test.
 
         Args:
             network (nx.Graph): The network graph.
@@ -235,7 +240,8 @@ class NeighborhoodsAPI:
         null_distribution: str = "network",
         random_seed: int = 888,
     ) -> Dict[str, Any]:
-        """Load significant neighborhoods for the network using the Poisson test.
+        """
+        Load significant neighborhoods for the network using the Poisson test.
 
         Args:
             network (nx.Graph): The network graph.
@@ -280,7 +286,8 @@ class NeighborhoodsAPI:
         null_distribution: str = "network",
         random_seed: int = 888,
     ) -> Dict[str, Any]:
-        """Load significant neighborhoods for the network using the z-score test.
+        """
+        Load significant neighborhoods for the network using the z-score test.
 
         Args:
             network (nx.Graph): The network graph.
@@ -328,7 +335,8 @@ class NeighborhoodsAPI:
         statistical_test_function: Any = compute_hypergeom_test,
         **kwargs,
     ):
-        """Load and compute significant neighborhoods for the network using a specified statistical test.
+        """
+        Load and compute significant neighborhoods for the network using a specified statistical test.
 
         Args:
             network (nx.Graph): The input network graph.
@@ -398,7 +406,8 @@ class NeighborhoodsAPI:
         fraction_shortest_edges: Union[float, List, Tuple, np.ndarray] = 0.5,
         random_seed: int = 888,
     ) -> csr_matrix:
-        """Load significant neighborhoods for the network.
+        """
+        Load significant neighborhoods for the network.
 
         Args:
             network (nx.Graph): The network graph.