ENH: xz compression_args df.to_pickle(path, compression={'method':'xz','pr…

doc/source/whatsnew/v2.1.0.rst

@@ -100,7 +100,7 @@ Other enhancements
 - Added ``engine_kwargs`` parameter to :meth:`DataFrame.to_excel` (:issue:`53220`)
 - Performance improvement in :func:`concat` with homogeneous ``np.float64`` or ``np.float32`` dtypes (:issue:`52685`)
 - Performance improvement in :meth:`DataFrame.filter` when ``items`` is given (:issue:`52941`)
--
+- Many read/to_* functions, such as :meth:DataFrame.to_pickle and :func:read_csv, support forwarding compression arguments to lzma.LZMAFile (:issue:52979)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_210.notable_bug_fixes:

pandas/core/shared_docs.py

@@ -455,10 +455,10 @@
     (otherwise no compression).
     Set to ``None`` for no compression.
     Can also be a dict with key ``'method'`` set
-    to one of {``'zip'``, ``'gzip'``, ``'bz2'``, ``'zstd'``, ``'tar'``} and other
-    key-value pairs are forwarded to
+    to one of {``'zip'``, ``'gzip'``, ``'bz2'``, ``'zstd'``, ``'xz'``, ``'tar'``} and
+    other key-value pairs are forwarded to
     ``zipfile.ZipFile``, ``gzip.GzipFile``,
-    ``bz2.BZ2File``, ``zstandard.ZstdCompressor`` or
+    ``bz2.BZ2File``, ``zstandard.ZstdCompressor``, ``lzma.LZMAFile`` or
     ``tarfile.TarFile``, respectively.
     As an example, the following could be passed for faster compression and to create
     a reproducible gzip archive:
@@ -477,10 +477,10 @@
     If using 'zip' or 'tar', the ZIP file must contain only one data file to be read in.
     Set to ``None`` for no decompression.
     Can also be a dict with key ``'method'`` set
-    to one of {``'zip'``, ``'gzip'``, ``'bz2'``, ``'zstd'``, ``'tar'``} and other
-    key-value pairs are forwarded to
+    to one of {``'zip'``, ``'gzip'``, ``'bz2'``, ``'zstd'``, ``'xz'``, ``'tar'``} and
+    other key-value pairs are forwarded to
     ``zipfile.ZipFile``, ``gzip.GzipFile``,
-    ``bz2.BZ2File``, ``zstandard.ZstdDecompressor`` or
+    ``bz2.BZ2File``, ``zstandard.ZstdDecompressor``, ``lzma.LZMAFile`` or
     ``tarfile.TarFile``, respectively.
     As an example, the following could be passed for Zstandard decompression using a
     custom compression dictionary:

pandas/io/common.py

@@ -825,8 +825,10 @@ def get_handle(
         elif compression == "xz":
             # error: Argument 1 to "LZMAFile" has incompatible type "Union[str,
             # BaseBuffer]"; expected "Optional[Union[Union[str, bytes, PathLike[str],
-            # PathLike[bytes]], IO[bytes]]]"
-            handle = get_lzma_file()(handle, ioargs.mode)  # type: ignore[arg-type]
+            # PathLike[bytes]], IO[bytes]], None]"
+            handle = get_lzma_file()(
+                handle, ioargs.mode, **compression_args  # type: ignore[arg-type]
+            )
 
         # Zstd Compression
         elif compression == "zstd":

pandas/tests/io/test_compression.py

@@ -252,6 +252,24 @@ def test_gzip_compression_level(obj, method):
         compressed_size_fast = os.path.getsize(path)
         assert compressed_size_default < compressed_size_fast
 
+@pytest.mark.parametrize("method", ["to_pickle", "to_json", "to_csv"])
+def test_xz_compression_level_read(obj, method):
+    with tm.ensure_clean() as path:
+        getattr(obj, method)(path, compression="xz")
+        compressed_size_default = os.path.getsize(path)
+        getattr(obj, method)(path, compression={"method": "xz", "preset": 1})
+        compressed_size_fast = os.path.getsize(path)
+        assert compressed_size_default < compressed_size_fast
+        if method=="to_csv":
+            pd.read_csv(compressed_size_fast)
+
+@pytest.mark.parametrize("method", ["to_pickle", "to_json", "to_csv"])
+def test_xz_compression_invalid_args(obj, method):
+    with tm.ensure_clean() as path:
+        try:
+            getattr(obj, method)(path, compression={"method": "xz", "compresslevel": 9})
+        except Exception as e:
+            assert e != TypeError
 
 @pytest.mark.parametrize(
     "obj",
@@ -273,6 +291,7 @@ def test_bzip_compression_level(obj, method):
         getattr(obj, method)(path, compression={"method": "bz2", "compresslevel": 1})
 
 
+
 @pytest.mark.parametrize(
     "suffix,archive",
     [