DOC: Bump fastparquet version (#24590)

Author: TomAugspurger

ci/deps/azure-macos-35.yaml

@@ -14,7 +14,6 @@ dependencies:
   - numpy=1.12.0
   - openpyxl=2.5.5
   - pyarrow
-  - fastparquet
   - pytables
   - python=3.5*
   - pytz

ci/deps/azure-windows-36.yaml

@@ -6,7 +6,7 @@ dependencies:
   - blosc
   - bottleneck
   - boost-cpp<1.67
-  - fastparquet
+  - fastparquet>=0.2.1
   - matplotlib
   - numexpr
   - numpy=1.14*
@@ -18,7 +18,6 @@ dependencies:
   - python=3.6.6
   - pytz
   - scipy
-  - thrift=0.10*
   - xlrd
   - xlsxwriter
   - xlwt

ci/deps/travis-27.yaml

@@ -6,7 +6,7 @@ dependencies:
   - beautifulsoup4
   - bottleneck
   - cython=0.28.2
-  - fastparquet
+  - fastparquet>=0.2.1
   - gcsfs
   - html5lib
   - ipython

ci/deps/travis-36-doc.yaml

@@ -6,7 +6,7 @@ dependencies:
   - beautifulsoup4
   - bottleneck
   - cython>=0.28.2
-  - fastparquet
+  - fastparquet>=0.2.1
   - gitpython
   - html5lib
   - hypothesis>=3.58.0

ci/deps/travis-36.yaml

@@ -7,7 +7,7 @@ dependencies:
   - botocore>=1.11
   - cython>=0.28.2
   - dask
-  - fastparquet
+  - fastparquet>=0.2.1
   - gcsfs
   - geopandas
   - html5lib

doc/source/install.rst

@@ -258,7 +258,7 @@ Optional Dependencies
 * `xarray <http://xarray.pydata.org>`__: pandas like handling for > 2 dims, needed for converting Panels to xarray objects. Version 0.7.0 or higher is recommended.
 * `PyTables <http://www.pytables.org>`__: necessary for HDF5-based storage, Version 3.4.2 or higher
 * `pyarrow <http://arrow.apache.org/docs/python/>`__ (>= 0.7.0): necessary for feather-based storage.
-* `Apache Parquet <https://parquet.apache.org/>`__, either `pyarrow <http://arrow.apache.org/docs/python/>`__ (>= 0.7.0) or `fastparquet <https://fastparquet.readthedocs.io/en/latest>`__ (>= 0.1.2) for parquet-based storage. The `snappy <https://pypi.org/project/python-snappy>`__ and `brotli <https://pypi.org/project/brotlipy>`__ are available for compression support.
+* `Apache Parquet <https://parquet.apache.org/>`__, either `pyarrow <http://arrow.apache.org/docs/python/>`__ (>= 0.7.0) or `fastparquet <https://fastparquet.readthedocs.io/en/latest>`__ (>= 0.2.1) for parquet-based storage. The `snappy <https://pypi.org/project/python-snappy>`__ and `brotli <https://pypi.org/project/brotlipy>`__ are available for compression support.
 * `SQLAlchemy <http://www.sqlalchemy.org>`__: for SQL database support. Version 0.8.1 or higher recommended. Besides SQLAlchemy, you also need a database specific driver. You can find an overview of supported drivers for each SQL dialect in the `SQLAlchemy docs <http://docs.sqlalchemy.org/en/latest/dialects/index.html>`__. Some common drivers are:
 
     * `psycopg2 <http://initd.org/psycopg/>`__: for PostgreSQL

doc/source/whatsnew/v0.24.0.rst

@@ -474,7 +474,7 @@ If installed, we now require:
 +-----------------+-----------------+----------+
 | bottleneck      | 1.2.0           |          |
 +-----------------+-----------------+----------+
-| fastparquet     | 0.1.2           |          |
+| fastparquet     | 0.2.1           |          |
 +-----------------+-----------------+----------+
 | matplotlib      | 2.0.0           |          |
 +-----------------+-----------------+----------+

environment.yml

@@ -29,7 +29,7 @@ dependencies:
   - botocore>=1.11
   - boto3
   - bottleneck>=1.2.0
-  - fastparquet>=0.1.2
+  - fastparquet>=0.2.1
   - html5lib
   - ipython>=5.6.0
   - ipykernel

pandas/io/parquet.py

@@ -151,9 +151,9 @@ def __init__(self):
                 "\nor via pip\n"
                 "pip install -U fastparquet"
             )
-        if LooseVersion(fastparquet.__version__) < '0.1.2':
+        if LooseVersion(fastparquet.__version__) < '0.2.1':
             raise ImportError(
-                "fastparquet >= 0.1.2 is required for parquet "
+                "fastparquet >= 0.2.1 is required for parquet "
                 "support\n\n"
                 "you can install via conda\n"
                 "conda install fastparquet -c conda-forge\n"

pandas/tests/io/test_parquet.py

@@ -59,15 +59,6 @@ def fp():
     return 'fastparquet'
 
 
-@pytest.fixture
-def fp_lt_014():
-    if not _HAVE_FASTPARQUET:
-        pytest.skip("fastparquet is not installed")
-    if LooseVersion(fastparquet.__version__) >= LooseVersion('0.1.4'):
-        pytest.skip("fastparquet is >= 0.1.4")
-    return 'fastparquet'
-
-
 @pytest.fixture
 def df_compat():
     return pd.DataFrame({'A': [1, 2, 3], 'B': 'foo'})
@@ -510,16 +501,6 @@ def test_categorical(self, fp):
         df = pd.DataFrame({'a': pd.Categorical(list('abc'))})
         check_round_trip(df, fp)
 
-    def test_datetime_tz(self, fp_lt_014):
-
-        # fastparquet<0.1.4 doesn't preserve tz
-        df = pd.DataFrame({'a': pd.date_range('20130101', periods=3,
-                                              tz='US/Eastern')})
-        # warns on the coercion
-        with catch_warnings(record=True):
-            check_round_trip(df, fp_lt_014,
-                             expected=df.astype('datetime64[ns]'))
-
     def test_filter_row_groups(self, fp):
         d = {'a': list(range(0, 3))}
         df = pd.DataFrame(d)

requirements-dev.txt

@@ -18,7 +18,7 @@ blosc
 botocore>=1.11
 boto3
 bottleneck>=1.2.0
-fastparquet>=0.1.2
+fastparquet>=0.2.1
 html5lib
 ipython>=5.6.0
 ipykernel