Examples
--------
>>> import cudf
>>> df = cudf.read_avro(filename)
>>> df
num1 datetime text
0 123 2018-11-13T12:00:00.000 5451
1 456 2018-11-14T12:35:01.000 5784
2 789 2018-11-15T18:02:59.000 6117
See Also
--------
cudf.io.csv.read_csv
cudf.io.json.read_json
""".format(remote_data_sources=_docstring_remote_sources)
doc_read_avro = docfmt_partial(docstring=_docstring_read_avro)
_docstring_read_parquet_metadata = """
Read a Parquet file's metadata and schema
Parameters
----------
path : string or path object
Path of file to be read
Returns
-------
Total number of rows
Number of row groups
List of column names
--------
>>> import cudf
>>> num_rows, num_row_groups, names = cudf.read_parquet_metadata(filename)
>>> df = [cudf.read_parquet(fname, row_group=i) for i in range(row_groups)]
>>> df = cudf.concat(df)
>>> df
num1 datetime text
0 123 2018-11-13T12:00:00.000 5451
1 456 2018-11-14T12:35:01.000 5784
2 789 2018-11-15T18:02:59.000 6117
See Also
--------
cudf.io.parquet.read_parquet
"""
doc_read_parquet_metadata = docfmt_partial(
docstring=_docstring_read_parquet_metadata)
_docstring_read_parquet = """
Read a Parquet file into DataFrame
Parameters
----------
path : string or path object
Path of file to be read
engine : { 'cudf', 'pyarrow' }, default 'cudf'
Parser engine to use.
columns : list, default None
If not None, only these columns will be read.
row_group : int, default None
If not None, only the row group with the specified index will be read.
skip_rows : int, default None
Then in user code:
>>> gs = gd.Series(list(range(0, 50)))
>>> gs.odd[1]
1
>>> gs.odd[2]
3
>>> gs.odd[3]
5
"""
doc_register_dataframe_accessor = docfmt_partial(
docstring=_docstring_register_accessor.format(
klass="DataFrame", example=_dataframe_example
)
)
doc_register_index_accessor = docfmt_partial(
docstring=_docstring_register_accessor.format(
klass="Index", example=_index_example
)
)
doc_register_series_accessor = docfmt_partial(
docstring=_docstring_register_accessor.format(
klass="Series", example=_series_example
)
)
chunks : int or Series-like
If it is an ``int``, it is the chunksize.
If it is an array, it contains integer offset for the start of
each chunk. The span of a chunk for chunk i-th is
``data[chunks[i] : chunks[i + 1]]`` for any
``i + 1 < chunks.size``; or, ``data[chunks[i]:]`` for the
``i == len(chunks) - 1``.
tpb : int; optional
It is the thread-per-block for the underlying kernel.
The default uses 1 thread to emulate serial execution for
each chunk. It is a good starting point but inefficient.
Its maximum possible value is limited by the available CUDA GPU
resources.
"""
doc_apply = docfmt_partial(params=_doc_applyparams)
doc_applychunks = docfmt_partial(params=_doc_applyparams,
params_chunks=_doc_applychunkparams)
@doc_apply()
def apply_rows(df, func, incols, outcols, kwargs, cache_key):
"""Row-wise transformation
Parameters
----------
df : DataFrame
The source dataframe.
{params}
"""
0 10 hello
1 20 rapids
2 30 ai
>>> pandavro.to_avro("data.avro", pandas_df)
>>> cudf.read_avro("data.avro")
numbers text
0 10 hello
1 20 rapids
2 30 ai
See Also
--------
cudf.io.csv.read_csv
cudf.io.json.read_json
""".format(remote_data_sources=_docstring_remote_sources)
doc_read_avro = docfmt_partial(docstring=_docstring_read_avro)
_docstring_read_parquet_metadata = """
Read a Parquet file's metadata and schema
Parameters
----------
path : string or path object
Path of file to be read
Returns
-------
Total number of rows
Number of row groups
List of column names
Examples
--------
>>> import cudf
>>> df = cudf.read_parquet(filename)
>>> df
num1 datetime text
0 123 2018-11-13T12:00:00.000 5451
1 456 2018-11-14T12:35:01.000 5784
2 789 2018-11-15T18:02:59.000 6117
See Also
--------
cudf.io.parquet.to_parquet
cudf.io.orc.read_orc
"""
doc_read_parquet = docfmt_partial(docstring=_docstring_read_parquet)
_docstring_to_parquet = """
Write a DataFrame to the parquet format.
Parameters
----------
path : str
File path or Root Directory path. Will be used as Root Directory path
while writing a partitioned dataset.
compression : {'snappy', 'gzip', 'brotli', None}, default 'snappy'
Name of the compression to use. Use ``None`` for no compression.
index : bool, default None
If ``True``, include the dataframe's index(es) in the file output. If
``False``, they will not be written to the file. If ``None``, the
engine's default behavior will be used.
