LZGraphs 2.1.0__tar.gz → 2.1.1__tar.gz

{lzgraphs-2.1.0 → lzgraphs-2.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: LZGraphs
-Version: 2.1.0
+Version: 2.1.1
 Summary: An Implementation of LZ76 Based Graphs for Repertoire Representation and Analysis
 Author-email: Thomas Konstantinovsky <thomaskon90@gmail.com>
 Maintainer-email: Thomas Konstantinovsky <thomaskon90@gmail.com>

{lzgraphs-2.1.0 → lzgraphs-2.1.1}/src/LZGraphs/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "2.1.0"
+__version__ = "2.1.1"
 
 # =============================================================================
 # Graph classes
@@ -63,6 +63,11 @@ from .metrics.saturation import NodeEdgeSaturationProbe
 # =============================================================================
 from .metrics.convenience import compare_repertoires
 
+# =============================================================================
+# Metrics - PGen Distribution
+# =============================================================================
+from .metrics.pgen_distribution import LZPgenDistribution, compare_lzpgen_distributions
+
 # =============================================================================
 # Utilities
 # =============================================================================
@@ -163,6 +168,9 @@ __all__ = [
     'NodeEdgeSaturationProbe',
     # Convenience
     'compare_repertoires',
+    # PGen distribution
+    'LZPgenDistribution',
+    'compare_lzpgen_distributions',
     # Utilities
     'generate_kmer_dictionary',
     'lempel_ziv_decomposition',

{lzgraphs-2.1.0 → lzgraphs-2.1.1}/src/LZGraphs/graphs/amino_acid_positional.py

@@ -1,5 +1,4 @@
 import logging
-import re
 import time
 from typing import List, Tuple, Union, Optional, Generator
 
@@ -10,7 +9,7 @@ from tqdm.auto import tqdm
 
 from .lz_graph_base import LZGraphBase
 from ..utilities.decomposition import lempel_ziv_decomposition
-from ..utilities.misc import window, choice
+from ..utilities.misc import window
 from ..exceptions import (
     EmptyDataError,
     MissingColumnError,
@@ -146,11 +145,8 @@ class AAPLZGraph(LZGraphBase):
 
         # Additional map derivations
         self.edges_list = None
-        self._derive_terminal_state_map()
-        self.verbose_driver(7, verbose)
         self._derive_stop_probability_data()
-        self.verbose_driver(8, verbose)
-        self.verbose_driver(5, verbose)
+        self.verbose_driver(9, verbose)
 
         # Optionally compute the PGEN for each sequence
         if calculate_trainset_pgen:
@@ -301,8 +297,8 @@ class AAPLZGraph(LZGraphBase):
         """
         Given a sub-pattern that might look like "ABC_10", extract only the amino acids ("ABC").
         """
-        match = re.search(r'[A-Z]+', base)
-        return match.group(0) if match else ""
+        idx = base.rfind('_')
+        return base[:idx] if idx > 0 else base
 
     def _decomposed_sequence_generator(
         self,