risk-network 0.0.10__py3-none-any.whl → 0.0.11__py3-none-any.whl

risk/__init__.py

@@ -7,4 +7,4 @@ RISK: Regional Inference of Significant Kinships
 
 from risk.risk import RISK
 
-__version__ = "0.0.10"
+__version__ = "0.0.11"

risk/annotations/annotations.py

@@ -3,76 +3,36 @@ risk/annotations/annotations
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 """
 
-import os
 import re
-import zipfile
 from collections import Counter
 from itertools import compress
 from typing import Any, Dict, List, Set
 
 import networkx as nx
-import nltk
 import numpy as np
 import pandas as pd
-from nltk.corpus import stopwords
-from nltk.stem import WordNetLemmatizer
 from nltk.tokenize import word_tokenize
+from scipy.sparse import coo_matrix
 
+from risk.annotations.nltk_setup import setup_nltk_resources
 from risk.log import logger
-from scipy.sparse import coo_matrix
 
 
-def ensure_nltk_resource(resource: str) -> None:
-    """Ensure the specified NLTK resource is available."""
-    # Define the path to the resource within the NLTK data directory
-    resource_path = f"corpora/{resource}"
-    # Check if the resource is already available.
-    try:
-        nltk.data.find(resource_path)
-        return
-    except LookupError:
-        print(f"Resource '{resource}' not found. Attempting to download...")
-
-    # Download the resource.
-    nltk.download(resource)
-    # Check again after downloading.
-    try:
-        nltk.data.find(resource_path)
-        return
-    except LookupError:
-        print(f"Resource '{resource}' still not found after download. Checking for a ZIP file...")
-
-    # Look for a ZIP file in all known NLTK data directories.
-    for data_path in nltk.data.path:
-        zip_path = os.path.join(data_path, "corpora", f"{resource}.zip")
-        if os.path.isfile(zip_path):
-            print(f"Found ZIP file for '{resource}' at: {zip_path}")
-            target_dir = os.path.join(data_path, "corpora")
-            with zipfile.ZipFile(zip_path, "r") as z:
-                z.extractall(path=target_dir)
-            print(f"Unzipped '{resource}' successfully.")
-            break  # Stop after unzipping the first found ZIP.
-
-    # Final check: Try to check resource one last time. If it fails, rai
-    try:
-        nltk.data.find(resource_path)
-        print(f"Resource '{resource}' is now available.")
-    except LookupError:
-        raise LookupError(f"Resource '{resource}' could not be found, downloaded, or unzipped.")
-
-
-# Ensure the NLTK stopwords and WordNet resources are available
-# punkt is known to have issues with the default download method, so we use a custom function if it fails
-try:
-    ensure_nltk_resource("punkt")
-except LookupError:
-    nltk.download("punkt")
-ensure_nltk_resource("stopwords")
-ensure_nltk_resource("wordnet")
-# Use NLTK's stopwords - load all languages
-STOP_WORDS = set(word for lang in stopwords.fileids() for word in stopwords.words(lang))
-# Initialize the WordNet lemmatizer, which is used for normalizing words
-LEMMATIZER = WordNetLemmatizer()
+def initialize_nltk():
+    """Initialize all required NLTK components."""
+    setup_nltk_resources()
+
+    # After resources are available, initialize the components
+    from nltk.corpus import stopwords
+    from nltk.stem import WordNetLemmatizer
+
+    global STOP_WORDS, LEMMATIZER
+    STOP_WORDS = set(stopwords.words("english"))
+    LEMMATIZER = WordNetLemmatizer()
+
+
+# Initialize NLTK components
+initialize_nltk()
 
 
 def load_annotations(

risk/annotations/nltk_setup.py

@@ -0,0 +1,85 @@
+"""
+risk/annotations/nltk_setup
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+"""
+
+import os
+import zipfile
+from typing import List, Tuple
+
+import nltk
+from nltk.data import find, path as nltk_data_path
+
+from risk.log import logger
+
+
+def setup_nltk_resources(required_resources: List[Tuple[str, str]] = None) -> None:
+    """Ensures all required NLTK resources are available and properly extracted.
+    Uses NLTK's default paths and mechanisms.
+
+    Args:
+        required_resources (List[Tuple[str, str]], optional): List of required resources
+            to download and extract. Each tuple should contain the resource path within
+            NLTK data and the package name. Defaults to None.
+    """
+    if required_resources is None:
+        required_resources = [
+            ("tokenizers/punkt", "punkt"),
+            ("tokenizers/punkt_tab", "punkt_tab"),
+            ("corpora/stopwords", "stopwords"),
+            ("corpora/wordnet", "wordnet"),
+        ]
+
+    # Process each resource
+    for resource_path, package_name in required_resources:
+        try:
+            # First try to find the resource - this is how NLTK checks if it's available
+            find(resource_path)
+        except LookupError:
+            # Resource not found, download it
+            logger.info(f"Downloading missing NLTK resource: {package_name}")
+            nltk.download(package_name, quiet=True)
+
+        # Even if find() succeeded, the resource might be a zip that failed to extract
+        # Check if we need to manually extract zips
+        verify_and_extract_if_needed(resource_path, package_name)
+
+
+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
+    NLTK's directory structure where the extracted content should be in the same directory
+    as the zip file.
+
+    Args:
+        resource_path (str): Path to the resource within NLTK data.
+        package_name (str): Name of the NLTK package.
+    """
+    # Get the directory and base name from the resource path
+    path_parts = resource_path.split("/")
+    resource_type = path_parts[0]  # 'corpora', 'tokenizers', etc.
+    resource_name = path_parts[-1]  # 'wordnet', 'punkt', etc.
+
+    # Check all NLTK data directories
+    for base in nltk_data_path:
+        # For resource paths like 'corpora/wordnet', the zip file is at '~/nltk_data/corpora/wordnet.zip'
+        # and the extracted directory should be at '~/nltk_data/corpora/wordnet'
+        resource_dir = os.path.join(base, resource_type)
+        zip_path = os.path.join(resource_dir, f"{resource_name}.zip")
+        folder_path = os.path.join(resource_dir, resource_name)
+
+        # If zip exists but folder doesn't, extraction is needed
+        if os.path.exists(zip_path) and not os.path.exists(folder_path):
+            logger.info(f"Found unextracted zip for {package_name}, extracting...")
+            try:
+                with zipfile.ZipFile(zip_path, "r") as zf:
+                    # Extract files to the same directory where the zip file is located
+                    zf.extractall(path=resource_dir)
+
+                if os.path.exists(folder_path):
+                    logger.info(f"Successfully extracted {package_name}")
+                else:
+                    logger.warning(
+                        f"Extraction completed but resource directory not found for {package_name}"
+                    )
+            except Exception as e:
+                logger.error(f"Failed to extract {package_name}: {e}")

risk/risk.py

@@ -3,14 +3,13 @@ risk/risk
 ~~~~~~~~~
 """
 
-from risk.network import NetworkIO
 from risk.annotations import AnnotationsIO
+from risk.log import params, set_global_verbosity
 from risk.neighborhoods import NeighborhoodsAPI
+from risk.network import NetworkIO
 from risk.network.graph import GraphAPI
 from risk.network.plotter import PlotterAPI
 
-from risk.log import params, set_global_verbosity
-
 
 class RISK(NetworkIO, AnnotationsIO, NeighborhoodsAPI, GraphAPI, PlotterAPI):
     """RISK: A class for network analysis and visualization.

risk/stats/permutation/test_functions.py

@@ -8,6 +8,7 @@ from scipy.sparse import csr_matrix
 
 # NOTE: Cython optimizations provided minimal performance benefits.
 # The final version with Cython is archived in the `cython_permutation` branch.
+
 # DISPATCH_TEST_FUNCTIONS can be found at the end of the file.
 
 

{risk_network-0.0.10.dist-info → risk_network-0.0.11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: risk-network
-Version: 0.0.10
+Version: 0.0.11
 Summary: A Python package for biological network analysis
 Author: Ira Horecka
 Author-email: Ira Horecka <ira89@icloud.com>
@@ -699,7 +699,7 @@ Requires-Dist: leidenalg
 Requires-Dist: markov_clustering
 Requires-Dist: matplotlib
 Requires-Dist: networkx
-Requires-Dist: nltk==3.8.1
+Requires-Dist: nltk
 Requires-Dist: numpy
 Requires-Dist: openpyxl
 Requires-Dist: pandas

{risk_network-0.0.10.dist-info → risk_network-0.0.11.dist-info}/RECORD

@@ -1,8 +1,9 @@
-risk/__init__.py,sha256=256SpbomSJ88a12A8DmDUsPOxlkwJ7cqbu7E4FHrcw4,120
-risk/risk.py,sha256=s827_lRknFseOP9O4zW8sP-IcCd2EzrpV_tnVY_tz5s,1104
+risk/__init__.py,sha256=FJYPkeBx_fYMZxCzecYrubpT9mJP2L2GpAs-kg7rhQY,120
+risk/risk.py,sha256=7Yu_Q3bRS05tMQyAyt3WYqVKphUpBo3DqpyrfjF9yC4,1103
 risk/annotations/__init__.py,sha256=parsbcux1U4urpUqh9AdzbDWuLj9HlMidycMPkpSQFo,179
-risk/annotations/annotations.py,sha256=mDgW5X4wck7oQqcMOw1T0XNkFZnSm1vx3MKIUX-FABI,16505
+risk/annotations/annotations.py,sha256=KtFyCiCnoAkhin3HKDBtkNcz5imjpysrmEfQKUwyqh8,14737
 risk/annotations/io.py,sha256=z1AJySsU-KL_IYuHa7j3nvuczmOHgK3WfaQ4TRunvrA,10499
+risk/annotations/nltk_setup.py,sha256=IvuyO3WkrmIg4gz1vsfjxUWBt9Nk-XxkQknPiFRORHE,3533
 risk/log/__init__.py,sha256=7LxDysQu7doi0LAvlY2YbjN6iJH0fNknqy8lSLgeljo,217
 risk/log/console.py,sha256=PgjyEvyhYLUSHXPUKEqOmxsDsfrjPICIgqo_cAHq0N8,4575
 risk/log/parameters.py,sha256=VtwfMzLU1xI4yji3-Ch5vHjH-KdwTfwaEMmi7hFQTs0,5716
@@ -32,9 +33,9 @@ risk/stats/significance.py,sha256=6cKv2xBQXWTHZ6HpNWIqlNfKKS5pG_BcCUdMM3r_zw4,73
 risk/stats/stat_tests.py,sha256=tj0ri9w89_1fsjGLuafTWpfBEwZXpSLn7Ej2aAQ5lxk,11776
 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-0.0.10.dist-info/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
-risk_network-0.0.10.dist-info/METADATA,sha256=MbLHMXmOv8iTUZLm8S4EKj2uDB419weRpRvWIyBKSCM,46966
-risk_network-0.0.10.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
-risk_network-0.0.10.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
-risk_network-0.0.10.dist-info/RECORD,,
+risk/stats/permutation/test_functions.py,sha256=0hcv18zqhhh2njWhUb1Yl-5PiFCYd4jX-HaY5hFMz4I,3121
+risk_network-0.0.11.dist-info/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
+risk_network-0.0.11.dist-info/METADATA,sha256=XmrzSj1VcALUEiN3g0JqxDm5EM8KB1jR_B8Y7oIXQ5Q,46959
+risk_network-0.0.11.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
+risk_network-0.0.11.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
+risk_network-0.0.11.dist-info/RECORD,,