Migrating to pyarrow=4.0.1 (#982)

Motivation: keep up with the latest versions of dependencies

Author: kozlov-alexey

README.rst

@@ -85,7 +85,7 @@ Building on Linux with setuptools
 
     export PYVER=<3.6 or 3.7>
     export NUMPYVER=<1.16 or 1.17>
-    conda create -n sdc-env -q -y -c intel/label/beta -c defaults -c intel -c conda-forge python=$PYVER numpy=$NUMPYVER tbb-devel tbb4py numba=0.52 pandas=1.2.0 pyarrow=2.0.0 gcc_linux-64 gxx_linux-64
+    conda create -n sdc-env -q -y -c intel/label/beta -c defaults -c intel -c conda-forge python=$PYVER numpy=$NUMPYVER tbb-devel tbb4py numba=0.53.1 pandas=1.2.0 pyarrow=4.0.1 gcc_linux-64 gxx_linux-64
     source activate sdc-env
     git clone https://github.com/IntelPython/sdc.git
     cd sdc
@@ -123,7 +123,7 @@ Building on Windows with setuptools
 
     set PYVER=<3.6 or 3.7>
     set NUMPYVER=<1.16 or 1.17>
-    conda create -n sdc-env -c intel/label/beta -c defaults -c intel -c conda-forge python=%PYVER% numpy=%NUMPYVER% tbb-devel tbb4py numba=0.52 pandas=1.2.0 pyarrow=2.0.0
+    conda create -n sdc-env -c intel/label/beta -c defaults -c intel -c conda-forge python=%PYVER% numpy=%NUMPYVER% tbb-devel tbb4py numba=0.53.1 pandas=1.2.0 pyarrow=4.0.1
     conda activate sdc-env
     set INCLUDE=%INCLUDE%;%CONDA_PREFIX%\Library\include
     set LIB=%LIB%;%CONDA_PREFIX%\Library\lib

conda-recipe/meta.yaml

@@ -1,6 +1,6 @@
 {% set NUMBA_VERSION = "==0.53.1" %}
 {% set PANDAS_VERSION = "==1.2.0" %}
-{% set PYARROW_VERSION = "==2.0.0" %}
+{% set PYARROW_VERSION = "==4.0.1" %}
 
 package:
   name: sdc

docs/source/getting_started.rst

@@ -41,14 +41,14 @@ Distribution includes Intel SDC for Python 3.6 and 3.7 for Windows and Linux pla
 Intel SDC conda package can be installed using the steps below:
 ::
 
-    > conda create -n sdc_env python=<3.7 or 3.6> pyarrow=2.0.0 pandas=1.2.0 -c anaconda -c conda-forge
+    > conda create -n sdc_env python=<3.7 or 3.6> pyarrow=4.0.1 pandas=1.2.0 -c anaconda -c conda-forge
     > conda activate sdc_env
     > conda install sdc -c intel/label/beta -c intel -c defaults -c conda-forge --override-channels
 
 Intel SDC wheel package can be installed using the steps below:
 ::
 
-    > conda create -n sdc_env python=<3.7 or 3.6> pip pyarrow=2.0.0 pandas=1.2.0 -c anaconda -c conda-forge
+    > conda create -n sdc_env python=<3.7 or 3.6> pip pyarrow=4.0.1 pandas=1.2.0 -c anaconda -c conda-forge
     > conda activate sdc_env
     > pip install --index-url https://pypi.anaconda.org/intel/label/beta/simple --extra-index-url https://pypi.anaconda.org/intel/simple --extra-index-url https://pypi.org/simple sdc
 

requirements.txt

@@ -1,6 +1,6 @@
 numpy>=1.16
 pandas==1.2.0
-pyarrow==2.0.0
+pyarrow==4.0.1
 numba==0.53.1
 tbb
 tbb-devel

sdc/io/csv_ext.py

@@ -470,9 +470,11 @@ def pandas_read_csv(
     try:
         for column in parse_dates:
             name = f"f{column}"
-            # TODO: Try to help pyarrow infer date type - set DateType.
-            # dtype[name] = pyarrow.from_numpy_dtype(np.datetime64) # string
-            del column_types[name]
+            # starting from pyarrow=3.0.0 strings are parsed to DateType (converted back to 'object'
+            # when using to_pandas), but not TimestampType (that is used to represent np.datetime64)
+            # see: pyarrow.from_numpy_dtype(np.datetime64('NaT', 's'))
+            # so make pyarrow infer needed type manually
+            column_types[name] = pyarrow.timestamp('s')
     except: pass
 
     parse_options = pyarrow.csv.ParseOptions(

setup.py

@@ -404,7 +404,7 @@ def run(self):
       install_requires=[
           'numpy>=1.16',
           'pandas==1.2.0',
-          'pyarrow==2.0.0',
+          'pyarrow==4.0.1',
           'numba==0.53.1',
           'tbb'
           ],