gtfparse 2.1.0__tar.gz → 2.3.0__tar.gz

{gtfparse-2.1.0 → gtfparse-2.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gtfparse
-Version: 2.1.0
+Version: 2.3.0
 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
@@ -18,7 +18,10 @@ License-File: LICENSE
 Requires-Dist: polars<0.21.0,>=0.20.2
 Requires-Dist: pyarrow<14.1.0,>=14.0.2
 
-[![Build Status](https://travis-ci.org/openvax/gtfparse.svg?branch=master)](https://travis-ci.org/openvax/gtfparse) [![Coverage Status](https://coveralls.io/repos/openvax/gtfparse/badge.svg?branch=master&service=github)](https://coveralls.io/github/openvax/gtfparse?branch=master)
+<!-- 
+[![Build Status](https://travis-ci.org/openvax/gtfparse.svg?branch=master)](https://travis-ci.org/openvax/gtfparse) 
+-->
+[![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" />
 </a>

{gtfparse-2.1.0 → gtfparse-2.3.0}/README.md

@@ -1,4 +1,7 @@
-[![Build Status](https://travis-ci.org/openvax/gtfparse.svg?branch=master)](https://travis-ci.org/openvax/gtfparse) [![Coverage Status](https://coveralls.io/repos/openvax/gtfparse/badge.svg?branch=master&service=github)](https://coveralls.io/github/openvax/gtfparse?branch=master)
+<!-- 
+[![Build Status](https://travis-ci.org/openvax/gtfparse.svg?branch=master)](https://travis-ci.org/openvax/gtfparse) 
+-->
+[![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" />
 </a>

{gtfparse-2.1.0 → gtfparse-2.3.0}/gtfparse/__init__.py

@@ -21,7 +21,7 @@ from .read_gtf import (
     REQUIRED_COLUMNS,
 )
 
-__version__ = "2.1.0"
+__version__ = "2.3.0"
 
 __all__ = [
     "__version__",

{gtfparse-2.1.0 → gtfparse-2.3.0}/gtfparse/create_missing_features.py

@@ -49,15 +49,19 @@ def create_missing_features(
     missing_value : any
         Which value to fill in for columns that we don't infer values for.
 
-    Returns original dataframe along with all extra rows created for missing
-    features.
+    Returns original dataframe (converted to Pandas if necessary) along with all 
+    extra rows created for missing features.
     """
+    if hasattr(dataframe, "to_pandas"):
+        dataframe = dataframe.to_pandas()
+  
     extra_dataframes = []
 
     existing_features = set(dataframe["feature"])
     existing_columns = set(dataframe.columns)
-
+ 
     for (feature_name, groupby_key) in unique_keys.items():
+        
         if feature_name in existing_features:
             logging.info(
                 "Feature '%s' already exists in GTF data" % feature_name)
@@ -65,9 +69,11 @@ def create_missing_features(
         logging.info("Creating rows for missing feature '%s'" % feature_name)
 
         # don't include rows where the groupby key was missing
-        empty_key_values = dataframe[groupby_key].map(
-            lambda x: x == "" or x is None)
-        row_groups = dataframe[~empty_key_values].groupby(groupby_key)
+        missing = pd.Series([
+            x is None or x == ""
+            for x in dataframe[groupby_key]])
+        not_missing = ~missing
+        row_groups = dataframe[not_missing].groupby(groupby_key)
 
         # Each group corresponds to a unique feature entry for which the
         # other columns may or may not be uniquely defined. Start off by

{gtfparse-2.1.0 → gtfparse-2.3.0}/gtfparse/read_gtf.py

@@ -77,6 +77,19 @@ REQUIRED_COLUMNS = [
 ]
 
 
+DEFAULT_COLUMN_DTYPES = {
+    "seqname": polars.Categorical, 
+    "source": polars.Categorical, 
+    
+    "start": polars.Int64,
+    "end": polars.Int64,
+    "score": polars.Float32,
+
+    "feature": polars.Categorical, 
+    "strand": polars.Categorical, 
+    "frame": polars.UInt32,
+}
+
 def parse_with_polars_lazy(
         filepath_or_buffer,
         split_attributes=True,
@@ -90,18 +103,7 @@ def parse_with_polars_lazy(
         separator="\t",
         comment_prefix="#",
         null_values=".",
-        dtypes={
-            "seqname": polars.Categorical, 
-            "source": polars.Categorical, 
-            
-            "start": polars.Int64,
-            "end": polars.Int64,
-            "score": polars.Float32,
-
-            "feature": polars.Categorical, 
-            "strand": polars.Categorical, 
-            "frame": polars.UInt32,
-        })
+        dtypes=DEFAULT_COLUMN_DTYPES)
     try:
         if type(filepath_or_buffer) is StringIO:
             df = polars.read_csv(
@@ -209,6 +211,7 @@ def read_gtf(
         expand_attribute_column=True,
         infer_biotype_column=False,
         column_converters={},
+        column_cast_types={},
         usecols=None,
         features=None,
         result_type='polars'):
@@ -236,6 +239,10 @@ def read_gtf(
         empty strings with None and otherwise passes them to given conversion
         function.
 
+    column_cast_types : dict, optional
+        Dictionary mapping column names to dtypes. Will cast columns to given
+        Polars types.
+    
     usecols : list of str or None
         Restrict which columns are loaded to the give set. If None, then
         load all columns.
@@ -258,12 +265,31 @@ def read_gtf(
     else:
         result_df = parse_gtf(result_df, features=features)
 
-    result_df = result_df.with_columns(
-        [
-            polars.col(column_name).map_elements(lambda x: column_type(x) if len(x) > 0 else None)
-            for column_name, column_type in column_converters.items()
-        ]
-    )
+
+    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 == "":
+                    return None
+                else:
+                    return f(x)
+            return wrapped_fn
+        
+        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))
+
+            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)
 
     # Hackishly infer whether the values in the 'source' column of this GTF
     # are actually representing a biotype by checking for the most common

{gtfparse-2.1.0 → gtfparse-2.3.0}/gtfparse.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gtfparse
-Version: 2.1.0
+Version: 2.3.0
 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
@@ -18,7 +18,10 @@ License-File: LICENSE
 Requires-Dist: polars<0.21.0,>=0.20.2
 Requires-Dist: pyarrow<14.1.0,>=14.0.2
 
-[![Build Status](https://travis-ci.org/openvax/gtfparse.svg?branch=master)](https://travis-ci.org/openvax/gtfparse) [![Coverage Status](https://coveralls.io/repos/openvax/gtfparse/badge.svg?branch=master&service=github)](https://coveralls.io/github/openvax/gtfparse?branch=master)
+<!-- 
+[![Build Status](https://travis-ci.org/openvax/gtfparse.svg?branch=master)](https://travis-ci.org/openvax/gtfparse) 
+-->
+[![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" />
 </a>

{gtfparse-2.1.0 → gtfparse-2.3.0}/tests/test_refseq_gtf.py

@@ -14,3 +14,7 @@ def _check_required_columns(gtf_dict):
 def test_read_refseq_gtf_as_dataframe():
     gtf_df = read_gtf(REFSEQ_GTF_PATH)
     _check_required_columns(gtf_df)
+
+def test_read_refseq_and_transform_columns():
+    gtf_df = read_gtf(REFSEQ_GTF_PATH, column_converters={"start": int, "end": int}, column_cast_types={"score": float})
+    print(gtf_df)