Merge pull request #352 from awslabs/dev

Bumping version to 1.8.1

Author: igorborgest

README.md

@@ -5,7 +5,7 @@
 
 > An [AWS Professional Service](https://aws.amazon.com/professional-services/) open source initiative | [email protected]
 
-[![Release](https://img.shields.io/badge/release-1.8.0-brightgreen.svg)](https://pypi.org/project/awswrangler/)
+[![Release](https://img.shields.io/badge/release-1.8.1-brightgreen.svg)](https://pypi.org/project/awswrangler/)
 [![Python Version](https://img.shields.io/badge/python-3.6%20%7C%203.7%20%7C%203.8-brightgreen.svg)](https://anaconda.org/conda-forge/awswrangler)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)

awswrangler/__metadata__.py

@@ -7,5 +7,5 @@
 
 __title__: str = "awswrangler"
 __description__: str = "Pandas on AWS."
-__version__: str = "1.8.0"
+__version__: str = "1.8.1"
 __license__: str = "Apache License 2.0"

awswrangler/athena/_read.py

@@ -265,7 +265,7 @@ def _fetch_csv_result(
         converters=query_metadata.converters,
         quoting=csv.QUOTE_ALL,
         keep_default_na=False,
-        na_values=[""],
+        na_values=["", "NaN"],
         chunksize=_chunksize,
         skip_blank_lines=False,
         use_threads=False,

docs/source/install.rst

@@ -47,8 +47,8 @@ the *Python library path* field.
 
 `Official Glue Python Shell Reference <https://docs.aws.amazon.com/glue/latest/dg/add-job-python.html#create-python-extra-library>`_
 
-AWS Glue Python PySpark Jobs
-----------------------------
+AWS Glue PySpark Jobs
+---------------------
 
 .. note:: AWS Data Wrangler has compiled dependencies (C/C++) so there is only support for ``Glue PySpark Jobs >= 2.0``.
 

tests/test_athena.py

@@ -2,6 +2,7 @@
 import logging
 
 import boto3
+import numpy as np
 import pandas as pd
 import pytest
 
@@ -772,3 +773,17 @@ def test_parse_describe_table():
 def test_describe_table(path, glue_database, glue_table):
     wr.catalog.create_parquet_table(database=glue_database, table=glue_table, path=path, columns_types={"c0": "int"})
     assert wr.athena.describe_table(database=glue_database, table=glue_table).shape == (1, 4)
+
+
+@pytest.mark.parametrize("ctas_approach", [False, True])
+def test_athena_nan_inf(glue_database, ctas_approach):
+    sql = "SELECT nan() AS nan, infinity() as inf, -infinity() as inf_n, 1.2 as regular"
+    df = wr.athena.read_sql_query(sql, glue_database, ctas_approach)
+    print(df)
+    print(df.dtypes)
+    assert df.shape == (1, 4)
+    assert df.dtypes.to_list() == ["float64", "float64", "float64", "float64"]
+    assert np.isnan(df.nan.iloc[0])
+    assert df.inf.iloc[0] == np.PINF
+    assert df.inf_n.iloc[0] == np.NINF
+    assert df.regular.iloc[0] == 1.2

tests/test_metadata.py

@@ -2,7 +2,7 @@
 
 
 def test_metadata():
-    assert wr.__version__ == "1.8.0"
+    assert wr.__version__ == "1.8.1"
     assert wr.__title__ == "awswrangler"
     assert wr.__description__ == "Pandas on AWS."
     assert wr.__license__ == "Apache License 2.0"