From 36614af4d8e00bb9564ef834a341859a0e96dfe4 Mon Sep 17 00:00:00 2001 From: Takuya UESHIN Date: Wed, 27 Dec 2017 13:33:59 +0900 Subject: [PATCH 1/5] Add pyarrow to setup.py. --- python/setup.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/setup.py b/python/setup.py index 310670e697a83..98398b526e043 100644 --- a/python/setup.py +++ b/python/setup.py @@ -201,7 +201,7 @@ def _supports_symlinks(): extras_require={ 'ml': ['numpy>=1.7'], 'mllib': ['numpy>=1.7'], - 'sql': ['pandas>=0.19.2'] + 'sql': ['pandas>=0.19.2', 'pyarrow>=0.8.0'] }, classifiers=[ 'Development Status :: 5 - Production/Stable', From bee3c69b4b559f6bf7aa74366ad2178eb3dd299e Mon Sep 17 00:00:00 2001 From: Takuya UESHIN Date: Wed, 27 Dec 2017 14:32:09 +0900 Subject: [PATCH 2/5] Add 'Programming Language :: Python :: 3.6' to classifiers. --- python/setup.py | 1 + 1 file changed, 1 insertion(+) diff --git a/python/setup.py b/python/setup.py index 98398b526e043..251d4526d4dd0 100644 --- a/python/setup.py +++ b/python/setup.py @@ -210,6 +210,7 @@ def _supports_symlinks(): 'Programming Language :: Python :: 3', 'Programming Language :: Python :: 3.4', 'Programming Language :: Python :: 3.5', + 'Programming Language :: Python :: 3.6', 'Programming Language :: Python :: Implementation :: CPython', 'Programming Language :: Python :: Implementation :: PyPy'] ) From 896f752a01c96b09ede5ae9d6fc924d4898bfb70 Mon Sep 17 00:00:00 2001 From: Takuya UESHIN Date: Wed, 27 Dec 2017 14:47:14 +0900 Subject: [PATCH 3/5] Update README.md. --- python/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/README.md b/python/README.md index 84ec88141cb00..0e8ef18dceed5 100644 --- a/python/README.md +++ b/python/README.md @@ -29,4 +29,4 @@ The Python packaging for Spark is not intended to replace all of the other use c ## Python Requirements -At its core PySpark depends on Py4J (currently version 0.10.6), but additional sub-packages have their own requirements (including numpy and pandas). +At its core PySpark depends on Py4J (currently version 0.10.6), but additional sub-packages have their own requirements (including numpy, pandas, and pyarrow). From e142e697f32d6e840ff17799d535aa370d27b305 Mon Sep 17 00:00:00 2001 From: Takuya UESHIN Date: Wed, 27 Dec 2017 18:48:32 +0900 Subject: [PATCH 4/5] Add some details describing extra requirements. --- python/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/README.md b/python/README.md index 0e8ef18dceed5..3c088e34d7a26 100644 --- a/python/README.md +++ b/python/README.md @@ -29,4 +29,4 @@ The Python packaging for Spark is not intended to replace all of the other use c ## Python Requirements -At its core PySpark depends on Py4J (currently version 0.10.6), but additional sub-packages have their own requirements (including numpy, pandas, and pyarrow). +At its core PySpark depends on Py4J (currently version 0.10.6), but additional sub-packages might have their own requirements declared as "Extras" (including numpy, pandas, and pyarrow). You can install the requirements by specifying their extra names. From d8d95647aaf23ef5058e8c79a575e999a7e3da6f Mon Sep 17 00:00:00 2001 From: Takuya UESHIN Date: Wed, 27 Dec 2017 20:13:55 +0900 Subject: [PATCH 5/5] Use the simple description. --- python/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/README.md b/python/README.md index 3c088e34d7a26..3f17fdb98a081 100644 --- a/python/README.md +++ b/python/README.md @@ -29,4 +29,4 @@ The Python packaging for Spark is not intended to replace all of the other use c ## Python Requirements -At its core PySpark depends on Py4J (currently version 0.10.6), but additional sub-packages might have their own requirements declared as "Extras" (including numpy, pandas, and pyarrow). You can install the requirements by specifying their extra names. +At its core PySpark depends on Py4J (currently version 0.10.6), but some additional sub-packages have their own extra requirements for some features (including numpy, pandas, and pyarrow).