gtfparse 2.2.0__tar.gz → 2.4.0__tar.gz

{gtfparse-2.2.0 → gtfparse-2.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gtfparse
-Version: 2.2.0
+Version: 2.4.0
 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

{gtfparse-2.2.0 → gtfparse-2.4.0}/gtfparse/__init__.py

@@ -21,7 +21,7 @@ from .read_gtf import (
     REQUIRED_COLUMNS,
 )
 
-__version__ = "2.2.0"
+__version__ = "2.4.0"
 
 __all__ = [
     "__version__",

{gtfparse-2.2.0 → gtfparse-2.4.0}/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-2.2.0 → gtfparse-2.4.0}/gtfparse/read_gtf.py

@@ -105,22 +105,10 @@ def parse_with_polars_lazy(
         null_values=".",
         dtypes=DEFAULT_COLUMN_DTYPES)
     try:
-        if type(filepath_or_buffer) is StringIO:
-            df = polars.read_csv(
+        df = polars.read_csv(
                 filepath_or_buffer,
                 new_columns=REQUIRED_COLUMNS,
                 **kwargs).lazy()
-        elif filepath_or_buffer.endswith(".gz") or filepath_or_buffer.endswith(".gzip"):
-            with gzip.open(filepath_or_buffer) as f:
-                df = polars.read_csv(
-                    f,
-                    new_columns=REQUIRED_COLUMNS,
-                    **kwargs).lazy()
-        else:
-            df = polars.scan_csv(
-                filepath_or_buffer, 
-                with_column_names=lambda cols: REQUIRED_COLUMNS,
-                **kwargs).lazy()
     except polars.ShapeError:
         raise ParsingError("Wrong number of columns")
 

{gtfparse-2.2.0 → gtfparse-2.4.0}/gtfparse.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gtfparse
-Version: 2.2.0
+Version: 2.4.0
 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