Default to_* methods to compression='infer'

pandas/core/frame.py

@@ -1713,7 +1713,7 @@ def to_panel(self):
 
     def to_csv(self, path_or_buf=None, sep=",", na_rep='', float_format=None,
                columns=None, header=True, index=True, index_label=None,
-               mode='w', encoding=None, compression=None, quoting=None,
+               mode='w', encoding=None, compression='infer', quoting=None,
                quotechar='"', line_terminator='\n', chunksize=None,
                tupleize_cols=None, date_format=None, doublequote=True,
                escapechar=None, decimal='.'):
@@ -1748,7 +1748,7 @@ def to_csv(self, path_or_buf=None, sep=",", na_rep='', float_format=None,
         encoding : string, optional
             A string representing the encoding to use in the output file,
             defaults to 'ascii' on Python 2 and 'utf-8' on Python 3.
-        compression : {'infer', 'gzip', 'bz2', 'xz', None}, default None
+        compression : {'infer', 'gzip', 'bz2', 'xz', None}, default infer
             If 'infer' and `path_or_buf` is path-like, then detect compression
             from the following extensions: '.gz', '.bz2' or '.xz'
             (otherwise no compression).

pandas/core/generic.py

@@ -1899,7 +1899,7 @@ def _repr_latex_(self):
 
     def to_json(self, path_or_buf=None, orient=None, date_format=None,
                 double_precision=10, force_ascii=True, date_unit='ms',
-                default_handler=None, lines=False, compression=None,
+                default_handler=None, lines=False, compression='infer',
                 index=True):
         """
         Convert the object to a JSON string.

pandas/io/formats/csvs.py

@@ -30,7 +30,7 @@ class CSVFormatter(object):
     def __init__(self, obj, path_or_buf=None, sep=",", na_rep='',
                  float_format=None, cols=None, header=True, index=True,
                  index_label=None, mode='w', nanRep=None, encoding=None,
-                 compression=None, quoting=None, line_terminator='\n',
+                 compression='infer', quoting=None, line_terminator='\n',
                  chunksize=None, tupleize_cols=False, quotechar='"',
                  date_format=None, doublequote=True, escapechar=None,
                  decimal='.'):
@@ -134,7 +134,13 @@ def save(self):
             encoding = self.encoding
 
         # GH 21227 internal compression is not used when file-like passed.
+        import logging
+        logging.warning('debug_3: {}'.format(self.compression))
+        logging.warning('debug_4: {}'.format(self.path_or_buf))
+        logging.warning(
+            'debug_5: {}'.format(hasattr(self.path_or_buf, 'write')))
         if self.compression and hasattr(self.path_or_buf, 'write'):
+            logging.warning('debug_6: in loop, should RuntimeWarn')
             msg = ("compression has no effect when passing file-like "
                    "object as input.")
             warnings.warn(msg, RuntimeWarning, stacklevel=2)

pandas/io/json/json.py

@@ -28,7 +28,7 @@
 # interface to/from
 def to_json(path_or_buf, obj, orient=None, date_format='epoch',
             double_precision=10, force_ascii=True, date_unit='ms',
-            default_handler=None, lines=False, compression=None,
+            default_handler=None, lines=False, compression='infer',
             index=True):
 
     if not index and orient not in ['split', 'table']:

pandas/tests/io/formats/test_to_csv.py

@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 
+import gzip
 import sys
 
 import pytest
@@ -351,3 +352,15 @@ def test_to_csv_compression(self, compression_only,
             result = pd.read_csv(path, index_col=0,
                                  compression=read_compression)
             tm.assert_frame_equal(result, df)
+
+    def test_compression_defaults_to_infer(tmpdir):
+        """
+        Test that to_csv defaults to inferring compression from paths.
+        https://github.com/pandas-dev/pandas/pull/22011
+        """
+        df = DataFrame({"A": [1]})
+        with tm.ensure_clean('compressed.csv.gz') as path:
+            df.to_csv(path, index=False)
+            with gzip.open(path, 'rt') as read_file:
+                lines = read_file.read().splitlines()
+        assert lines == ['A', '1']

pandas/tests/test_common.py

@@ -257,8 +257,11 @@ def test_compression_warning(compression_only):
                           [12.32112, 123123.2, 321321.2]],
                    columns=['X', 'Y', 'Z'])
     with tm.ensure_clean() as filename:
+        import logging
+        logging.warning('debug_1: {}'.format(compression_only))
         f, _handles = _get_handle(filename, 'w', compression=compression_only)
         with tm.assert_produces_warning(RuntimeWarning,
                                         check_stacklevel=False):
             with f:
+                logging.warning('debug_2: {}'.format(compression_only))
                 df.to_csv(f, compression=compression_only)