risk-network 0.0.16b0__py3-none-any.whl → 0.0.16b1__py3-none-any.whl

risk/__init__.py

@@ -8,4 +8,4 @@ RISK: Regional Inference of Significant Kinships
 from ._risk import RISK
 
 __all__ = ["RISK"]
-__version__ = "0.0.16-beta.0"
+__version__ = "0.0.16-beta.1"

risk/_annotation/_annotation.py

@@ -257,26 +257,23 @@ def get_weighted_description(words_column: pd.Series, scores_column: pd.Series)
                 continue
             # Lemmatize the token to merge similar forms
             token_norm = LEMMATIZER.lemmatize(token_clean)
-            weighted_counts[token_norm] = weighted_counts.get(token_norm, 0) + weight
+            # Apply weighting boost for biologically structured number-word hybrids
+            if re.match(r"^\d+[\-\w]+", token_norm):
+                actual_weight = int(weight * 1.5)
+            else:
+                actual_weight = weight
+            weighted_counts[token_norm] = weighted_counts.get(token_norm, 0) + actual_weight
 
     # Reconstruct a weighted token list by repeating each token by its aggregated count.
     weighted_words = []
     for token, count in weighted_counts.items():
         weighted_words.extend([token] * count)
 
-    # Combine tokens that match number-word patterns (e.g. "4-alpha") and remove pure numeric tokens.
+    # Combine tokens that match number-word patterns (e.g. "4-alpha"), but do not remove numeric tokens.
+    # All tokens are included in the final list.
     combined_tokens = []
     for token in weighted_words:
-        if re.match(r"^\d+-\w+", token):
-            combined_tokens.append(token)
-        elif token.replace(".", "", 1).isdigit():
-            continue
-        else:
-            combined_tokens.append(token)
-
-    # If the only token is numeric, return a default value.
-    if len(combined_tokens) == 1 and combined_tokens[0].isdigit():
-        return "N/A"
+        combined_tokens.append(token)
 
     # Simplify the token list to remove near-duplicates based on the Jaccard index.
     simplified_words = _simplify_word_list(combined_tokens)

{risk_network-0.0.16b0.dist-info → risk_network-0.0.16b1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: risk-network
-Version: 0.0.16b0
+Version: 0.0.16b1
 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-0.0.16b0.dist-info → risk_network-0.0.16b1.dist-info}/RECORD

@@ -1,7 +1,7 @@
-risk/__init__.py,sha256=knyE98-BvAZ9sTJDMZ1TNr73YaAC-gqL_0Q1rKvwAHU,143
+risk/__init__.py,sha256=yv_r0c0z4l4vV4P0053XkOGZfAdW1Fbxa_jSYS7a0yQ,143
 risk/_risk.py,sha256=VULCdM41BlWKM1ou4Qc579ffZ9dMZkfhAwKYgbaEeKM,1054
 risk/_annotation/__init__.py,sha256=zr7w1DHkmvrkKFGKdPhrcvZHV-xsfd5TZOaWtFiP4Dc,164
-risk/_annotation/_annotation.py,sha256=psPRC7q4DjXIvpgmE3VLzHYElLarJTJhQpclesz2W0Q,15063
+risk/_annotation/_annotation.py,sha256=MWbimFSR6FT0SahJ5Ixbe0VMZ5osmgeOgyQqX8ntbec,15045
 risk/_annotation/_io.py,sha256=xic3dkEA54X82HbyWfCiXrUpAhPWFPBZ69R8jw31omQ,12457
 risk/_annotation/_nltk_setup.py,sha256=aHHnElLOKiouVDrZ3uON0CSFmBxvzmYfjYPi07v2rJM,3584
 risk/_log/__init__.py,sha256=LX6BsfcGOH0RbAdQaUmIU-LVMmArDdKwn0jFtj45FYo,205
@@ -34,8 +34,8 @@ risk/_network/_plotter/_plotter.py,sha256=F2hw-spUdsXjvuG36o0YFR3Pnd-CZOHYUq4vW0
 risk/_network/_plotter/_utils/__init__.py,sha256=JXgjKiBWvXx0X2IeFnrOh5YZQGQoELbhJZ0Zh2mFEOo,211
 risk/_network/_plotter/_utils/_colors.py,sha256=JCliSvz8_-TsjilaRHSEsqdXFBUYlzhXKOSRGdCm9Kw,19177
 risk/_network/_plotter/_utils/_layout.py,sha256=GyGLc2U1WWUVL1Te9uPi_CLqlW_E4TImXRAL5TeA5D8,3633
-risk_network-0.0.16b0.dist-info/licenses/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
-risk_network-0.0.16b0.dist-info/METADATA,sha256=RyO3f1BZDQnREPp3my6tw6JI8Y4oFzY3gBDwEO10zL8,5390
-risk_network-0.0.16b0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-risk_network-0.0.16b0.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
-risk_network-0.0.16b0.dist-info/RECORD,,
+risk_network-0.0.16b1.dist-info/licenses/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
+risk_network-0.0.16b1.dist-info/METADATA,sha256=_CFQPvw-w4VBuXqn_4TxFyTQ6EQsO2KxVMBWhkBhpiI,5390
+risk_network-0.0.16b1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+risk_network-0.0.16b1.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
+risk_network-0.0.16b1.dist-info/RECORD,,