risk-network 0.0.9b42__py3-none-any.whl → 0.0.9b44__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.42"
+__version__ = "0.0.9-beta.44"

risk/annotations/annotations.py

@@ -3,7 +3,9 @@ risk/annotations/annotations
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 """
 
+import os
 import re
+import zipfile
 from collections import Counter
 from itertools import compress
 from typing import Any, Dict, List, Set
@@ -20,29 +22,51 @@ from risk.log import logger
 from scipy.sparse import coo_matrix
 
 
-def _setup_nltk():
-    """Ensure necessary NLTK data is downloaded."""
+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("tokenizers/punkt")
+        nltk.data.find(resource_path)
+        return
     except LookupError:
-        # Force download if not found
-        nltk.download("punkt", force=True, quiet=True)
+        print(f"Resource '{resource}' not found. Attempting to download...")
 
+    # Download the resource.
+    nltk.download(resource)
+    # Check again after downloading.
     try:
-        nltk.data.find("corpora/stopwords")
+        nltk.data.find(resource_path)
+        return
     except LookupError:
-        nltk.download("stopwords", force=True, quiet=True)
-
+        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 load the resource one last time.
     try:
-        nltk.data.find("corpora/wordnet")
+        nltk.data.find(resource_path)
+        print(f"Resource '{resource}' is now available.")
     except LookupError:
-        nltk.download("wordnet", force=True, quiet=True)
+        raise LookupError(f"Resource '{resource}' could not be found, downloaded, or unzipped.")
 
 
-# Ensure you have the necessary NLTK data
-_setup_nltk()
-# Use NLTK's stopwords
-STOP_WORDS = set(stopwords.words("english"))
+# Ensure the NLTK stopwords and WordNet resources are available
+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()
 
 
@@ -242,7 +266,7 @@ def get_weighted_description(words_column: pd.Series, scores_column: pd.Series)
         weight = max(1, int((0 if pd.isna(score) else score) * 10))
         for token in tokens:
             # Clean token: lowercase and remove extraneous punctuation (but preserve intra-word hyphens)
-            token_clean = re.sub(r"[^\w\-]", "", token.lower()).strip()
+            token_clean = re.sub(r"[^\w\-]", "", token).strip()
             if not token_clean:
                 continue
             # Skip tokens that are pure numbers

{risk_network-0.0.9b42.dist-info → risk_network-0.0.9b44.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: risk-network
-Version: 0.0.9b42
+Version: 0.0.9b44
 Summary: A Python package for biological network analysis
 Author: Ira Horecka
 Author-email: Ira Horecka <ira89@icloud.com>

{risk_network-0.0.9b42.dist-info → risk_network-0.0.9b44.dist-info}/RECORD

@@ -1,7 +1,7 @@
-risk/__init__.py,sha256=0G_X2wjPwCz7UG5bgL3bYfsnVpLvoRhcMyS2bV45ZKI,127
+risk/__init__.py,sha256=RVOwiHzzwMXL1qujltMK4sdkHgP3Pv85KrFz7QfhPTk,127
 risk/risk.py,sha256=s827_lRknFseOP9O4zW8sP-IcCd2EzrpV_tnVY_tz5s,1104
 risk/annotations/__init__.py,sha256=parsbcux1U4urpUqh9AdzbDWuLj9HlMidycMPkpSQFo,179
-risk/annotations/annotations.py,sha256=_2crX1SKphCY1gJmDpRuvYouf8DowScSetbxCG3vLHk,15022
+risk/annotations/annotations.py,sha256=5X2R8RFxgK6kgSoj05UdCPcpkRRPOaHjGwnIrjeD5Ww,16299
 risk/annotations/io.py,sha256=z1AJySsU-KL_IYuHa7j3nvuczmOHgK3WfaQ4TRunvrA,10499
 risk/log/__init__.py,sha256=7LxDysQu7doi0LAvlY2YbjN6iJH0fNknqy8lSLgeljo,217
 risk/log/console.py,sha256=PgjyEvyhYLUSHXPUKEqOmxsDsfrjPICIgqo_cAHq0N8,4575
@@ -33,8 +33,8 @@ 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-0.0.9b42.dist-info/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
-risk_network-0.0.9b42.dist-info/METADATA,sha256=vShfLdet9LjI_5lQOuQdcvaG1rIbwbBRO34gF3BFIcw,47627
-risk_network-0.0.9b42.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-risk_network-0.0.9b42.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
-risk_network-0.0.9b42.dist-info/RECORD,,
+risk_network-0.0.9b44.dist-info/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
+risk_network-0.0.9b44.dist-info/METADATA,sha256=mLBWb_wyKny6tgHt3xmdlaZgwSic3pVhSg47e-b6O5A,47627
+risk_network-0.0.9b44.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+risk_network-0.0.9b44.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
+risk_network-0.0.9b44.dist-info/RECORD,,