ENH: add fsspec support (#34266)

Co-authored-by: Julian de Ruiter <[email protected]>

Author: martindurant

ci/deps/azure-36-locale.yaml

@@ -15,7 +15,6 @@ dependencies:
 
   # pandas dependencies
   - beautifulsoup4
-  - gcsfs
   - html5lib
   - ipython
   - jinja2
@@ -31,7 +30,6 @@ dependencies:
   - pytables
   - python-dateutil
   - pytz
-  - s3fs
   - scipy
   - xarray
   - xlrd

ci/deps/azure-37-locale.yaml

@@ -27,7 +27,6 @@ dependencies:
   - pytables
   - python-dateutil
   - pytz
-  - s3fs
   - scipy
   - xarray
   - xlrd

ci/deps/azure-windows-37.yaml

@@ -15,7 +15,8 @@ dependencies:
   # pandas dependencies
   - beautifulsoup4
   - bottleneck
-  - gcsfs
+  - fsspec>=0.7.4
+  - gcsfs>=0.6.0
   - html5lib
   - jinja2
   - lxml
@@ -28,7 +29,7 @@ dependencies:
   - pytables
   - python-dateutil
   - pytz
-  - s3fs
+  - s3fs>=0.4.0
   - scipy
   - sqlalchemy
   - xlrd

ci/deps/travis-36-cov.yaml

@@ -18,7 +18,8 @@ dependencies:
   - cython>=0.29.16
   - dask
   - fastparquet>=0.3.2
-  - gcsfs
+  - fsspec>=0.7.4
+  - gcsfs>=0.6.0
   - geopandas
   - html5lib
   - matplotlib
@@ -35,7 +36,7 @@ dependencies:
   - pytables
   - python-snappy
   - pytz
-  - s3fs
+  - s3fs>=0.4.0
   - scikit-learn
   - scipy
   - sqlalchemy

ci/deps/travis-36-locale.yaml

@@ -16,7 +16,6 @@ dependencies:
   - blosc=1.14.3
   - python-blosc
   - fastparquet=0.3.2
-  - gcsfs=0.2.2
   - html5lib
   - ipython
   - jinja2
@@ -33,7 +32,6 @@ dependencies:
   - pytables
   - python-dateutil
   - pytz
-  - s3fs=0.3.0
   - scipy
   - sqlalchemy=1.1.4
   - xarray=0.10

ci/deps/travis-36-slow.yaml

@@ -13,6 +13,7 @@ dependencies:
 
   # pandas dependencies
   - beautifulsoup4
+  - fsspec>=0.7.4
   - html5lib
   - lxml
   - matplotlib
@@ -25,7 +26,7 @@ dependencies:
   - pytables
   - python-dateutil
   - pytz
-  - s3fs
+  - s3fs>=0.4.0
   - scipy
   - sqlalchemy
   - xlrd

ci/deps/travis-37.yaml

@@ -13,12 +13,13 @@ dependencies:
 
   # pandas dependencies
   - botocore>=1.11
+  - fsspec>=0.7.4
   - numpy
   - python-dateutil
   - nomkl
   - pyarrow
   - pytz
-  - s3fs
+  - s3fs>=0.4.0
   - tabulate
   - pyreadstat
   - pip

doc/source/getting_started/install.rst

@@ -267,8 +267,9 @@ SQLAlchemy                1.1.4              SQL support for databases other tha
 SciPy                     0.19.0             Miscellaneous statistical functions
 XLsxWriter                0.9.8              Excel writing
 blosc                                        Compression for HDF5
+fsspec                    0.7.4              Handling files aside from local and HTTP
 fastparquet               0.3.2              Parquet reading / writing
-gcsfs                     0.2.2              Google Cloud Storage access
+gcsfs                     0.6.0              Google Cloud Storage access
 html5lib                                     HTML parser for read_html (see :ref:`note <optional_html>`)
 lxml                      3.8.0              HTML parser for read_html (see :ref:`note <optional_html>`)
 matplotlib                2.2.2              Visualization
@@ -282,7 +283,7 @@ pyreadstat                                   SPSS files (.sav) reading
 pytables                  3.4.3              HDF5 reading / writing
 pyxlsb                    1.0.6              Reading for xlsb files
 qtpy                                         Clipboard I/O
-s3fs                      0.3.0              Amazon S3 access
+s3fs                      0.4.0              Amazon S3 access
 tabulate                  0.8.3              Printing in Markdown-friendly format (see `tabulate`_)
 xarray                    0.8.2              pandas-like API for N-dimensional data
 xclip                                        Clipboard I/O on linux

doc/source/whatsnew/v1.1.0.rst

@@ -245,6 +245,22 @@ If needed you can adjust the bins with the argument ``offset`` (a Timedelta) tha
 
 For a full example, see: :ref:`timeseries.adjust-the-start-of-the-bins`.
 
+fsspec now used for filesystem handling
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+For reading and writing to filesystems other than local and reading from HTTP(S),
+the optional dependency ``fsspec`` will be used to dispatch operations (:issue:`33452`).
+This will give unchanged
+functionality for S3 and GCS storage, which were already supported, but also add
+support for several other storage implementations such as `Azure Datalake and Blob`_,
+SSH, FTP, dropbox and github. For docs and capabilities, see the `fsspec docs`_.
+
+The existing capability to interface with S3 and GCS will be unaffected by this
+change, as ``fsspec`` will still bring in the same packages as before.
+
+.. _Azure Datalake and Blob: https://github.com/dask/adlfs
+
+.. _fsspec docs: https://filesystem-spec.readthedocs.io/en/latest/
 
 .. _whatsnew_110.enhancements.other:
 
@@ -701,7 +717,9 @@ Optional libraries below the lowest tested version may still work, but are not c
 +-----------------+-----------------+---------+
 | fastparquet     | 0.3.2           |         |
 +-----------------+-----------------+---------+
-| gcsfs           | 0.2.2           |         |
+| fsspec          | 0.7.4           |         |
++-----------------+-----------------+---------+
+| gcsfs           | 0.6.0           |    X    |
 +-----------------+-----------------+---------+
 | lxml            | 3.8.0           |         |
 +-----------------+-----------------+---------+
@@ -717,7 +735,7 @@ Optional libraries below the lowest tested version may still work, but are not c
 +-----------------+-----------------+---------+
 | pytables        | 3.4.3           |    X    |
 +-----------------+-----------------+---------+
-| s3fs            | 0.3.0           |         |
+| s3fs            | 0.4.0           |    X    |
 +-----------------+-----------------+---------+
 | scipy           | 1.2.0           |    X    |
 +-----------------+-----------------+---------+

environment.yml

@@ -98,7 +98,9 @@ dependencies:
 
   - pyqt>=5.9.2  # pandas.read_clipboard
   - pytables>=3.4.3  # pandas.read_hdf, DataFrame.to_hdf
-  - s3fs  # pandas.read_csv... when using 's3://...' path
+  - s3fs>=0.4.0  # file IO when using 's3://...' path
+  - fsspec>=0.7.4  # for generic remote file operations
+  - gcsfs>=0.6.0  # file IO when using 'gcs://...' path
   - sqlalchemy  # pandas.read_sql, DataFrame.to_sql
   - xarray  # DataFrame.to_xarray
   - cftime  # Needed for downstream xarray.CFTimeIndex test