gtfparse 2.4.1__tar.gz → 2.6.0__tar.gz

{gtfparse-2.4.1 → gtfparse-2.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: gtfparse
-Version: 2.4.1
+Version: 2.6.0
 Summary: Parsing library for extracting data frames of genomic features from GTF files
 Author-email: Alex Rubinsteyn <alex.rubinsteyn@unc.edu>
 Project-URL: Homepage, https://github.com/openvax/gtfparse
@@ -15,12 +15,12 @@ Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Requires-Python: >=3.7
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: polars<0.21.0,>=0.20.2
-Requires-Dist: pyarrow<14.1.0,>=14.0.2
+Requires-Dist: polars>=0.20.2
+Requires-Dist: pyarrow>=18.0.0
+Requires-Dist: pandas>=2.1.0
+Dynamic: license-file
 
-<!-- 
-[![Build Status](https://travis-ci.org/openvax/gtfparse.svg?branch=master)](https://travis-ci.org/openvax/gtfparse) 
--->
+[![Tests](https://github.com/openvax/gtfparse/actions/workflows/tests.yml/badge.svg)](https://github.com/openvax/gtfparse/actions/workflows/tests.yml)
 [![Coverage Status](https://coveralls.io/repos/openvax/gtfparse/badge.svg?branch=master&service=github)](https://coveralls.io/github/openvax/gtfparse?branch=master)
 <a href="https://pypi.python.org/pypi/gtfparse/">
     <img src="https://img.shields.io/pypi/v/gtfparse.svg?maxAge=1000" alt="PyPI" />

{gtfparse-2.4.1 → gtfparse-2.6.0}/README.md

@@ -1,6 +1,4 @@
-<!-- 
-[![Build Status](https://travis-ci.org/openvax/gtfparse.svg?branch=master)](https://travis-ci.org/openvax/gtfparse) 
--->
+[![Tests](https://github.com/openvax/gtfparse/actions/workflows/tests.yml/badge.svg)](https://github.com/openvax/gtfparse/actions/workflows/tests.yml)
 [![Coverage Status](https://coveralls.io/repos/openvax/gtfparse/badge.svg?branch=master&service=github)](https://coveralls.io/github/openvax/gtfparse?branch=master)
 <a href="https://pypi.python.org/pypi/gtfparse/">
     <img src="https://img.shields.io/pypi/v/gtfparse.svg?maxAge=1000" alt="PyPI" />

{gtfparse-2.4.1 → gtfparse-2.6.0}/gtfparse/__init__.py

@@ -21,7 +21,7 @@ from .read_gtf import (
     REQUIRED_COLUMNS,
 )
 
-__version__ = "2.4.1"
+__version__ = "2.6.0"
 
 __all__ = [
     "__version__",

{gtfparse-2.4.1 → gtfparse-2.6.0}/gtfparse/read_gtf.py

@@ -12,8 +12,6 @@
 
 import logging
 from os.path import exists
-from io import StringIO
-import gzip 
 
 import polars 
 
@@ -103,15 +101,18 @@ def parse_with_polars_lazy(
         separator="\t",
         comment_prefix="#",
         null_values=".",
-        dtypes=DEFAULT_COLUMN_DTYPES)
+        schema_overrides=DEFAULT_COLUMN_DTYPES)
     try:
         df = polars.read_csv(
                 filepath_or_buffer,
                 new_columns=REQUIRED_COLUMNS,
                 **kwargs).lazy()
-    except polars.ShapeError:
+    except polars.exceptions.ShapeError:
         raise ParsingError("Wrong number of columns")
 
+    # Drop empty lines that may appear as all-null rows
+    df = df.filter(polars.col("seqname").is_not_null())
+
     df = df.with_columns([
         polars.col("frame").fill_null(0),
         polars.col("attribute").str.replace_all('"', "'")
@@ -253,11 +254,11 @@ def read_gtf(
     else:
         result_df = parse_gtf(result_df, features=features)
 
-
+    # converting back to pandas here because Polars bugs manifest
+    # as `pyo3_runtime.PanicException: assertion `left == right` failed: impl error`
+    # and are generally insane to chase down
+    result_df = result_df.to_pandas()
     if column_converters or column_cast_types:
-        # transform columns with user-specified functions and/or cast them to user-specified types
-        polars_expressions = []
-
         def wrap_to_always_accept_none(f):
             def wrapped_fn(x):
                 if x is None or x == "":
@@ -268,17 +269,16 @@ def read_gtf(
         
         column_names = set(column_converters.keys()).union(column_cast_types.keys())
         for column_name in column_names:
-            e = polars.col(column_name)
+     
             if column_name in column_converters:
-                column_fn = column_converters[column_name]
-                e = e.map_elements(wrap_to_always_accept_none(column_fn))
+                column_fn = wrap_to_always_accept_none(
+                    column_converters[column_name])
+                result_df[column_name] = result_df[column_name].apply(column_fn)
 
             if column_name in column_cast_types:
                 column_type = column_cast_types[column_name]
-                e = e.cast(column_type)
-            polars_expressions.append(e)
-        result_df = result_df.with_columns(polars_expressions)
-
+                result_df[column_name] = result_df[column_name].astype(column_type)
+            
     # Hackishly infer whether the values in the 'source' column of this GTF
     # are actually representing a biotype by checking for the most common
     # gene_biotype and transcript_biotype value 'protein_coding'
@@ -292,20 +292,21 @@ def read_gtf(
             # gene_biotype)
             if "gene_biotype" not in column_names:
                 logging.info("Using column 'source' to replace missing 'gene_biotype'")
-                result_df = result_df.with_columns([polars.col("source").alias("gene_biotype")])
+                result_df['gene_biotype'] = result_df['source']
             if "transcript_biotype" not in column_names:
                 logging.info("Using column 'source' to replace missing 'transcript_biotype'")
-                result_df = result_df.with_columns([polars.col("source").alias("transcript_biotype")])
-
+                result_df['transcript_biotype'] = result_df['source']
+                
     if usecols is not None:
         column_names = set(result_df.columns)
         valid_columns = [c for c in usecols if c in column_names]
-        result_df = result_df.select(valid_columns)
+        result_df = result_df[valid_columns]
 
+    result = None
     if result_type == "pandas":
-        result = result_df.to_pandas()
-    elif result_type == "polars":
         result = result_df
+    elif result_type == "polars":
+        result = polars.from_pandas(result_df)
     elif result_type == "dict":
         result = result_df.to_dict()
     return result

{gtfparse-2.4.1 → gtfparse-2.6.0}/gtfparse.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: gtfparse
-Version: 2.4.1
+Version: 2.6.0
 Summary: Parsing library for extracting data frames of genomic features from GTF files
 Author-email: Alex Rubinsteyn <alex.rubinsteyn@unc.edu>
 Project-URL: Homepage, https://github.com/openvax/gtfparse
@@ -15,12 +15,12 @@ Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Requires-Python: >=3.7
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: polars<0.21.0,>=0.20.2
-Requires-Dist: pyarrow<14.1.0,>=14.0.2
+Requires-Dist: polars>=0.20.2
+Requires-Dist: pyarrow>=18.0.0
+Requires-Dist: pandas>=2.1.0
+Dynamic: license-file
 
-<!-- 
-[![Build Status](https://travis-ci.org/openvax/gtfparse.svg?branch=master)](https://travis-ci.org/openvax/gtfparse) 
--->
+[![Tests](https://github.com/openvax/gtfparse/actions/workflows/tests.yml/badge.svg)](https://github.com/openvax/gtfparse/actions/workflows/tests.yml)
 [![Coverage Status](https://coveralls.io/repos/openvax/gtfparse/badge.svg?branch=master&service=github)](https://coveralls.io/github/openvax/gtfparse?branch=master)
 <a href="https://pypi.python.org/pypi/gtfparse/">
     <img src="https://img.shields.io/pypi/v/gtfparse.svg?maxAge=1000" alt="PyPI" />

gtfparse-2.6.0/gtfparse.egg-info/requires.txt

@@ -0,0 +1,3 @@
+polars>=0.20.2
+pyarrow>=18.0.0
+pandas>=2.1.0

{gtfparse-2.4.1 → gtfparse-2.6.0}/pyproject.toml

@@ -24,4 +24,4 @@ packages = ["gtfparse"]
 
 [project.urls]
 "Homepage" = "https://github.com/openvax/gtfparse"
-"Bug Tracker" = "https://github.com/openvax/gtfparse"
+"Bug Tracker" = "https://github.com/openvax/gtfparse"

gtfparse-2.6.0/requirements.txt

@@ -0,0 +1,3 @@
+polars>=0.20.2
+pyarrow>=18.0.0
+pandas>=2.1.0

{gtfparse-2.4.1 → gtfparse-2.6.0}/tests/test_ensembl_gtf.py

@@ -1,6 +1,6 @@
-from data import data_path
 from gtfparse import read_gtf
 
+from .data import data_path
 
 ENSEMBL_GTF_PATH = data_path("ensembl_grch37.head.gtf")
 

{gtfparse-2.4.1 → gtfparse-2.6.0}/tests/test_read_stringtie_gtf.py

@@ -1,5 +1,5 @@
 from gtfparse import read_gtf
-from data import data_path
+from .data import data_path
 
 B16_GTF_PATH = data_path("B16.stringtie.head.gtf")
 

{gtfparse-2.4.1 → gtfparse-2.6.0}/tests/test_refseq_gtf.py

@@ -1,5 +1,5 @@
 from gtfparse import read_gtf
-from data import data_path
+from .data import data_path
 
 REFSEQ_GTF_PATH = data_path("refseq.ucsc.small.gtf")
 

gtfparse-2.4.1/gtfparse.egg-info/requires.txt

@@ -1,2 +0,0 @@
-polars<0.21.0,>=0.20.2
-pyarrow<14.1.0,>=14.0.2

gtfparse-2.4.1/requirements.txt

@@ -1,2 +0,0 @@
-polars>=0.20.2,<0.21.0
-pyarrow>=14.0.2,<14.1.0