diff --git a/README.md b/README.md new file mode 100644 index 000000000..9b8736e91 --- /dev/null +++ b/README.md @@ -0,0 +1,94 @@ +![image](https://raw.githubusercontent.com/kbc-opensource/gelanis/master/logo/banner_black-w1500.png%0A%20:target:%20https://github.com/kbc-opensource/gelanis) + +[![pypi-badge](https://badge.fury.io/py/gelanis.svg)](https://pypi.python.org/pypi/gelanis/), [![test-badge](https://github.com/kbc-opensource/gelanis/workflows/Tests/badge.svg)](https://github.com/kbc-opensource/gelanis/actions?query=workflow%3ATests), [![Documentation Status](https://readthedocs.org/projects/gelanis/badge/?version=latest)](https://pysparkling.readthedocs.io/en/latest/?badge=latest) + +**Gelanis** is an enhanced version of [pysparkling](https://github.com/svenkreiss/pysparkling). + +List of improvements: + +- Data types of the resulting dataframes are equal to pyspark + +List of todos: + +- Implemented since/until + be able to target a certain pyspark version +- Get a drop-in API compatibility with pyspark (auto-injector is written, but more tests are needed here). +- Test the tests against both pyspark & pysparkling & compare the outputs so we're 100% certain both libraries are API equal. +- Achieve API equality between pyspark & pysparkling (meaning that any public symbol should exist in both libraries). +- Increase tests to ensure 100% compatibility with pyspark. + +Some performance metrics I observed (5 simple union-tests): + +| | gelanis | pyspark | speedup (times slower than gelanis) | +| --- | --- | --- | --- | +| startup | 0.542 | 47.112 | 87.0 | +| test 1 | 0.009 | 2.610 | 274.7 | +| test 2 | 0.008 | 2.721 | 340.1 | +| test 3 | 0.008 | 2.761 | 345.1 | +| test 4 | 0.009 | 2.471 | 274.6 | +| test 5 | 0.013 | 2.486 | 191.2 | + +```python +import gelanis +gelanis.setup(spark_version='2.3.2') +``` + + +Original pysparkling documentation: +============================================ + +**Pysparkling** provides a faster, more responsive way to develop programs for PySpark. It enables code intended for Spark applications to execute entirely in Python, without incurring the overhead of initializing and passing data through the JVM and Hadoop. The focus is on having a lightweight and fast implementation for small datasets at the expense of some data resilience features and some parallel processing features. + +**How does it work?** To switch execution of a script from PySpark to pysparkling, have the code initialize a pysparkling Context instead of a SparkContext, and use the pysparkling Context to set up your RDDs. The beauty is you don't have to change a single line of code after the Context initialization, because pysparkling's API is (almost) exactly the same as PySpark's. Since it's so easy to switch between PySpark and pysparkling, you can choose the right tool for your use case. + +**When would I use it?** Say you are writing a Spark application because you need robust computation on huge datasets, but you also want the same application to provide fast answers on a small dataset. You're finding Spark is not responsive enough for your needs, but you don't want to rewrite an entire separate application for the *small-answers-fast* problem. You'd rather reuse your Spark code but somehow get it to run fast. Pysparkling bypasses the stuff that causes Spark's long startup times and less responsive feel. + +Here are a few areas where pysparkling excels: + +- Small to medium-scale exploratory data analysis +- Application prototyping +- Low-latency web deployments +- Unit tests + +Install +======= + +``` {.sourceCode .bash} +pip install pysparkling[s3,hdfs,streaming] +``` + +[Documentation](https://pysparkling.trivial.io): + +[![image](https://raw.githubusercontent.com/svenkreiss/pysparkling/master/docs/readthedocs.png)](https://pysparkling.trivial.io) + +Other links: [Github](https://github.com/svenkreiss/pysparkling), [![pypi-badge](https://badge.fury.io/py/pysparkling.svg)](https://pypi.python.org/pypi/pysparkling/), [![test-badge](https://github.com/svenkreiss/pysparkling/workflows/Tests/badge.svg)](https://github.com/svenkreiss/pysparkling/actions?query=workflow%3ATests), [![Documentation Status](https://readthedocs.org/projects/pysparkling/badge/?version=latest)](https://pysparkling.readthedocs.io/en/latest/?badge=latest) + +Features +======== + +- Supports URI schemes `s3://`, `hdfs://`, `gs://`, `http://` and `file://` for Amazon S3, HDFS, Google Storage, web and local file access. Specify multiple files separated by comma. Resolves `*` and `?` wildcards. +- Handles `.gz`, `.zip`, `.lzma`, `.xz`, `.bz2`, `.tar`, `.tar.gz` and `.tar.bz2` compressed files. Supports reading of `.7z` files. +- Parallelization via `multiprocessing.Pool`, `concurrent.futures.ThreadPoolExecutor` or any other Pool-like objects that have a `map(func, iterable)` method. +- Plain pysparkling does not have any dependencies (use `pip install pysparkling`). Some file access methods have optional dependencies: `boto` for AWS S3, `requests` for http, `hdfs` for hdfs + +Examples +======== + +Some demos are in the notebooks [docs/demo.ipynb](https://github.com/svenkreiss/pysparkling/blob/master/docs/demo.ipynb) and [docs/iris.ipynb](https://github.com/svenkreiss/pysparkling/blob/master/docs/iris.ipynb) . + +**Word Count** + +``` {.sourceCode .python} +from pysparkling import Context + +counts = ( + Context() + .textFile('README.rst') + .map(lambda line: ''.join(ch if ch.isalnum() else ' ' for ch in line)) + .flatMap(lambda line: line.split(' ')) + .map(lambda word: (word, 1)) + .reduceByKey(lambda a, b: a + b) +) +print(counts.collect()) +``` + +which prints a long list of pairs of words and their counts. diff --git a/README.rst b/README.rst deleted file mode 100644 index ef535f8d5..000000000 --- a/README.rst +++ /dev/null @@ -1,127 +0,0 @@ -.. image:: https://raw.githubusercontent.com/kbc-opensource/pysparkling/master/logo/logo-w100.png - :target: https://github.com/kbc-opensource/pysparkling - -gelanis -======= - -**Gelanis** is an enhanced version of -`pysparkling `_. - -List of improvements: - -* Data types of the resulting dataframes are equal to pyspark - -List of todos: - -* Implemented since/until + be able to target a certain pyspark version -* Get a drop-in API compatibility with pyspark (auto-injector is written, but more tests are needed here). -* Test the tests against both pyspark & pysparkling & compare the outputs so we're 100% certain both libraries are API equal. -* Achieve API equality between pyspark & pysparkling (meaning that any public symbol should exist in both libraries). -* Increase tests to ensure 100% compatibility with pyspark. - - -pysparkling -=========== - -**Pysparkling** provides a faster, more responsive way to develop programs -for PySpark. It enables code intended for Spark applications to execute -entirely in Python, without incurring the overhead of initializing and -passing data through the JVM and Hadoop. The focus is on having a lightweight -and fast implementation for small datasets at the expense of some data -resilience features and some parallel processing features. - -**How does it work?** To switch execution of a script from PySpark to pysparkling, -have the code initialize a pysparkling Context instead of a SparkContext, and -use the pysparkling Context to set up your RDDs. The beauty is you don't have -to change a single line of code after the Context initialization, because -pysparkling's API is (almost) exactly the same as PySpark's. Since it's so easy -to switch between PySpark and pysparkling, you can choose the right tool for your -use case. - -**When would I use it?** Say you are writing a Spark application because you -need robust computation on huge datasets, but you also want the same application -to provide fast answers on a small dataset. You're finding Spark is not responsive -enough for your needs, but you don't want to rewrite an entire separate application -for the *small-answers-fast* problem. You'd rather reuse your Spark code but somehow -get it to run fast. Pysparkling bypasses the stuff that causes Spark's long startup -times and less responsive feel. - -Here are a few areas where pysparkling excels: - -* Small to medium-scale exploratory data analysis -* Application prototyping -* Low-latency web deployments -* Unit tests - - -Install -======= - -.. code-block:: bash - - pip install pysparkling[s3,hdfs,streaming] - - -`Documentation `_: - -.. image:: https://raw.githubusercontent.com/svenkreiss/pysparkling/master/docs/readthedocs.png - :target: https://pysparkling.trivial.io - - -Other links: -`Github `_, -|pypi-badge|, |test-badge|, |docs-badge| - -.. |pypi-badge| image:: https://badge.fury.io/py/pysparkling.svg - :target: https://pypi.python.org/pypi/pysparkling/ -.. |test-badge| image:: https://github.com/svenkreiss/pysparkling/workflows/Tests/badge.svg - :target: https://github.com/svenkreiss/pysparkling/actions?query=workflow%3ATests -.. |docs-badge| image:: https://readthedocs.org/projects/pysparkling/badge/?version=latest - :target: https://pysparkling.readthedocs.io/en/latest/?badge=latest - :alt: Documentation Status - - -Features -======== - -* Supports URI schemes ``s3://``, ``hdfs://``, ``gs://``, ``http://`` and ``file://`` - for Amazon S3, HDFS, Google Storage, web and local file access. - Specify multiple files separated by comma. - Resolves ``*`` and ``?`` wildcards. -* Handles ``.gz``, ``.zip``, ``.lzma``, ``.xz``, ``.bz2``, ``.tar``, - ``.tar.gz`` and ``.tar.bz2`` compressed files. - Supports reading of ``.7z`` files. -* Parallelization via ``multiprocessing.Pool``, - ``concurrent.futures.ThreadPoolExecutor`` or any other Pool-like - objects that have a ``map(func, iterable)`` method. -* Plain pysparkling does not have any dependencies (use ``pip install pysparkling``). - Some file access methods have optional dependencies: - ``boto`` for AWS S3, ``requests`` for http, ``hdfs`` for hdfs - - -Examples -======== - -Some demos are in the notebooks -`docs/demo.ipynb `_ -and -`docs/iris.ipynb `_ -. - -**Word Count** - -.. code-block:: python - - from pysparkling import Context - - counts = ( - Context() - .textFile('README.rst') - .map(lambda line: ''.join(ch if ch.isalnum() else ' ' for ch in line)) - .flatMap(lambda line: line.split(' ')) - .map(lambda word: (word, 1)) - .reduceByKey(lambda a, b: a + b) - ) - print(counts.collect()) - -which prints a long list of pairs of words and their counts. diff --git a/logo/banner-w1500.png b/logo/banner-w1500.png index eda82132d..54255facc 100644 Binary files a/logo/banner-w1500.png and b/logo/banner-w1500.png differ diff --git a/logo/banner-w500.png b/logo/banner-w500.png index 07f7e2686..ac239b422 100644 Binary files a/logo/banner-w500.png and b/logo/banner-w500.png differ diff --git a/logo/banner.svg b/logo/banner.svg index e0498caa2..6dc08d89b 100644 --- a/logo/banner.svg +++ b/logo/banner.svg @@ -1,2 +1,2 @@ -pysparkling \ No newline at end of file +gelanis \ No newline at end of file diff --git a/logo/banner_black-w1500.png b/logo/banner_black-w1500.png new file mode 100644 index 000000000..96000495e Binary files /dev/null and b/logo/banner_black-w1500.png differ diff --git a/logo/banner_black.svg b/logo/banner_black.svg new file mode 100644 index 000000000..0cc6b8f69 --- /dev/null +++ b/logo/banner_black.svg @@ -0,0 +1,2 @@ + +gelanis \ No newline at end of file diff --git a/logo/banner_white-w500.png b/logo/banner_white-w500.png new file mode 100644 index 000000000..1ad138253 Binary files /dev/null and b/logo/banner_white-w500.png differ diff --git a/logo/banner_white.svg b/logo/banner_white.svg new file mode 100644 index 000000000..bfc536506 --- /dev/null +++ b/logo/banner_white.svg @@ -0,0 +1,2 @@ + +gelanis \ No newline at end of file diff --git a/logo/create.py b/logo/create.py index 8911b8746..2c38cee20 100644 --- a/logo/create.py +++ b/logo/create.py @@ -1,117 +1,215 @@ """Creates an SVG of the Databench logo. Optionally also a png.""" import os +from pathlib import Path import random import svgwrite +# NEED TO HAVE imagemagick installed (this works on version 7.0.8 from https://imagemagick.org/) + +# https://digitalsynopsis.com/design/beautiful-color-palettes-combinations-schemes/ +# Color picker: http://paletton.com/ +COLORS = [ + ('#42359C', '#42359C', '#42359C', '#42359C', '#FAE5A5'), # 0. Default pysparkling colors + ('#fe4a49', '#2ab7ca', '#fed766', '#e6e6ea', '#f4f4f8'), # 1. Beach Towels + ('#eee3e7', '#ead5dc', '#eec9d2', '#f4b6c2', '#f6abb6'), # 2. Light Pink + ('#011f4b', '#03396c', '#005b96', '#6497b1', '#b3cde0'), # 3. Beautiful Blues + ('#051e3e', '#251e3e', '#451e3e', '#651e3e', '#851e3e'), # 4. So Many Lost Songs + ('#dec3c3', '#e7d3d3', '#f0e4e4', '#f9f4f4', '#ffffff'), # 5. She + ('#4a4e4d', '#0e9aa7', '#3da4ab', '#f6cd61', '#fe8a71'), # 6. Moonlight Bytes 6 + ('#2a4d69', '#4b86b4', '#adcbe3', '#e7eff6', '#63ace5'), # 7. Number 3 + ('#fe9c8f', '#feb2a8', '#fec8c1', '#fad9c1', '#f9caa7'), # 8. Pastellea + ('#009688', '#35a79c', '#54b2a9', '#65c3ba', '#83d0c9'), # 9. Android Lollipop + ('#ee4035', '#f37736', '#fdf498', '#7bc043', '#0392cf'), # 10. Rainbow Dash + ('#faf0e6', '#fff5ee', '#fdf5e6', '#faf0e6', '#faebd7'), # 11. Shades of White + ('#ffffff', '#d0e1f9', '#4d648d', '#283655', '#1e1f26'), # 12. Blueberry Basket + ('#eeeeee', '#dddddd', '#cccccc', '#bbbbbb', '#aaaaaa'), # 13. Five Shades of Grey + ('#ffe9dc', '#fce9db', '#e0a899', '#dfa290', '#c99789'), # 14. Anime Skin Tones + ('#96ceb4', '#ffeead', '#ff6f69', '#ffcc5c', '#88d8b0'), # 15. Beach + ('#6e7f80', '#536872', '#708090', '#536878', '#36454f'), # 16. Blue Grey + ('#4b3832', '#854442', '#fff4e6', '#3c2f2f', '#be9b7b'), # 17. Cappuccino + ('#3b5998', '#8b9dc3', '#dfe3ee', '#f7f7f7', '#ffffff'), # 18. Facebook + ('#008744', '#0057e7', '#d62d20', '#ffa700', '#ffffff'), # 19. Google Colors + ('#008744', '#0057e7', '#d62d20', '#ffa700', '#000000'), # 19. Google Colors -- heavy stroke + ('#3385c6', '#4279a3', '#476c8a', '#49657b', '#7f8e9e'), # 20. Gray Blue + ('#d2d4dc', '#afafaf', '#f8f8fa', '#e5e6eb', '#c0c2ce'), # 21. Grey Lavender Colors + ('#a8e6cf', '#dcedc1', '#ffd3b6', '#ffaaa5', '#ff8b94'), # 22. Pastel Rainbow + ('#d11141', '#00b159', '#00aedb', '#f37735', '#ffc425'), # 23. Metro UI Colors + ('#6f7c85', '#75838d', '#7e8d98', '#8595a1', '#8c9da9'), # 24. Greyso + ('#ebf4f6', '#bdeaee', '#76b4bd', '#58668b', '#5e5656'), # 25. The Water Bearer + ('#ff77aa', '#ff99cc', '#ffbbee', '#ff5588', '#ff3377'), # 26. Pinks + ('#eeeeee', '#dddddd', '#cccccc', '#bbbbbb', '#29a8ab'), # 27. Never Doubt + ('#fff6e9', '#ffefd7', '#fffef9', '#e3f0ff', '#d2e7ff'), # 28. Never Dreamed Of This + ('#edc951', '#eb6841', '#cc2a36', '#4f372d', '#00a0b0'), # 29. Program Catalog + ('#84c1ff', '#add6ff', '#d6eaff', '#eaf4ff', '#f8fbff'), # 30. Office Room 2 + ('#2e003e', '#3d2352', '#3d1e6d', '#8874a3', '#e4dcf1'), # 31. Purple Skyline + ('#8d5524', '#c68642', '#e0ac69', '#f1c27d', '#ffdbac'), # 32. Skin Tones + ('#343d46', '#4f5b66', '#65737e', '#a7adba', '#c0c5ce'), # 33. Space Gray + ('#bfd6f6', '#8dbdff', '#64a1f4', '#4a91f2', '#3b7dd8'), # 34. The Armor Falls + ('#fdfbfb', '#fbfdfb', '#fdfdff', '#fdf9f9', '#fdfbfb'), # 35. White + ('#e3c9c9', '#f4e7e7', '#eedbdb', '#cecbcb', '#cbdadb'), # 36. Wrist Skin +] + DATA = [ + [0, 0, 1, 1, 1, 1, 1, 0], [0, 1, 1, 1, 1, 1, 1, 1], - [0, 1, 1, 1, 1, 1, 1, 1], - [0, 0, 0, 0, 1, 1, 1, 1], - [0, 0, 0, 1, 1, 1, 1, 1], - [0, 0, 1, 1, 1, 0, 1, 1], - [0, 1, 1, 1, 0, 0, 1, 1], - [1, 1, 1, 0, 0, 0, 1, 1], [1, 1, 0, 0, 0, 0, 0, 0], + [1, 1, 0, 0, 1, 1, 1, 0], + [1, 1, 0, 1, 1, 1, 1, 1], + [1, 1, 0, 0, 0, 0, 1, 1], + [0, 1, 1, 1, 1, 1, 1, 0], + [0, 0, 1, 1, 1, 1, 0, 0], ] +USE_COLOR = COLORS[9] +ROTATION = 0 +if ROTATION: + USE_COLOR = USE_COLOR[ROTATION:] + USE_COLOR[:ROTATION] -def color(x, y): - """triangles. - Colors: - - http://paletton.com/#uid=70l150klllletuehUpNoMgTsdcs shade 2 - """ +def stroke_color(): + return '#000000' + return USE_COLOR[4] + - return '#42359C' # "#CDB95B" +def color(x, y): + """triangles.""" + return random.choice(USE_COLOR) if (x - 4) > (y - 4) and -(y - 4) <= (x - 4): # right - return '#42359C' # "#CDB95B" - elif (x - 4) > (y - 4) and -(y - 4) > (x - 4): + return USE_COLOR[0] + + if (x - 4) > (y - 4) and -(y - 4) > (x - 4): # top - return "#CD845B" - elif (x - 4) <= (y - 4) and -(y - 4) <= (x - 4): + return USE_COLOR[1] + + if (x - 4) <= (y - 4) and -(y - 4) <= (x - 4): # bottom - return "#57488E" - elif (x - 4) <= (y - 4) and -(y - 4) > (x - 4): + return USE_COLOR[2] + + if (x - 4) <= (y - 4) and -(y - 4) > (x - 4): # left - return "#3B8772" + return USE_COLOR[3] # should not happen - return "black" + return 'black' def simple(svg_document, x, y, v): if v == 1: - svg_document.add(svg_document.rect(insert=(x * 16, y * 16), - size=("16px", "16px"), - # rx="2px", - # stroke_width="1", - # stroke=color(x, y), - fill=color(x, y))) + svg_document.add( + svg_document.rect( + insert=(x * 16, y * 16), + size=('16px', '16px'), + # rx="2px", + # stroke_width="1", + # stroke=color(x, y), + fill=color(x, y), + ) + ) def smaller(svg_document, x, y, v, x_offset=0, y_offset=0): # from center distance2 = (x - 3.5) ** 2 + (y - 3.5) ** 2 - max_distance2 = 2 * 4 ** 2 + max_distance2 = 2 * 3.5 ** 2 if v == 1: size = 16.0 * (1.0 - distance2 / max_distance2) + if size == 0: size = 1 number_of_cubes = int(16 ** 2 / (size ** 2)) for i in range(number_of_cubes): xi = x * 16 + 1 + random.random() * (14.0 - size) + x_offset yi = y * 16 + 1 + random.random() * (14.0 - size) + y_offset - sizepx = str(size) + "px" - svg_document.add(svg_document.rect(insert=(xi, yi), - size=(sizepx, sizepx), - rx="2px", - stroke_width="1", - # stroke='#4E9954', - stroke='#FAE5A5', - # stroke=color(x, y), - fill=color(x, y))) + sizepx = str(size) + 'px' + svg_document.add( + svg_document.rect( + insert=(xi, yi), + size=(sizepx, sizepx), + rx='2px', + stroke_width='1', + stroke=stroke_color(), + fill=color(x, y), + ) + ) + + +def generate_png(name, width, height): + p1 = Path(f'{name}.svg') + p2 = Path(f'{name}-w{width}.png') + if p2.exists(): + p2.unlink() + + os.system(f'magick -background none {p1} -density 1200 -resize {width}x{height} {p2}') + + +def test_logos(): + global USE_COLOR + for idx, _ in enumerate(COLORS): + USE_COLOR = COLORS[idx] + + for rotation in range(len(USE_COLOR)): + name = f'logo_{idx:02}_{rotation}' + svg_document = svgwrite.Drawing(filename=f'{name}.svg', size=('128px', '128px')) + + for y, r in enumerate(DATA): + for x, v in enumerate(r): + smaller(svg_document, x, y, v) + + svg_document.save() + generate_png(name, 600, 600) + + USE_COLOR = USE_COLOR[1:] + USE_COLOR[:1] def main(): - svg_favicon = svgwrite.Drawing(filename="favicon.svg", - size=("128px", "128px")) - svg_document = svgwrite.Drawing(filename="logo.svg", - size=("128px", "128px")) - svg_banner = svgwrite.Drawing(filename="banner.svg", - size=("600px", "200px")) + svg_favicon = svgwrite.Drawing(filename='favicon.svg', size=('128px', '128px')) + svg_document = svgwrite.Drawing(filename='logo.svg', size=('128px', '128px')) + svg_banner_white = svgwrite.Drawing(filename='banner_white.svg', size=('600px', '200px')) + svg_banner_black = svgwrite.Drawing(filename='banner_black.svg', size=('600px', '200px')) + for y, r in enumerate(DATA): for x, v in enumerate(r): simple(svg_favicon, x, y, v) smaller(svg_document, x, y, v) - smaller(svg_banner, x, y, v, x_offset=20, y_offset=40) + smaller(svg_banner_white, x, y, v, x_offset=20, y_offset=40) + smaller(svg_banner_black, x, y, v, x_offset=20, y_offset=40) + # add banner text - g = svg_banner.g(style='font-size:40px; font-family:Arial; font-weight: bold; font-style: italic;') - g.add(svg_banner.text( - 'pysparkling', - insert=(180, 120), fill='#000000'), - ) - svg_banner.add(g) + g = svg_banner_white.g(style='font-size:40px; font-family:Arial; font-weight: bold; font-style: italic;') + g.add(svg_banner_white.text('gelanis', insert=(180, 120), fill='#000000'),) + svg_banner_white.add(g) + + g = svg_banner_black.g(style='font-size:40px; font-family:Arial; font-weight: bold; font-style: italic;') + g.add(svg_banner_black.text('gelanis', insert=(180, 120), fill='#35a79c', stroke=stroke_color()),) + svg_banner_black.add(g) + # print(svg_document.tostring()) svg_favicon.save() svg_document.save() - svg_banner.save() + svg_banner_white.save() + svg_banner_black.save() # create pngs - os.system('svg2png --width=100 --height=100 logo.svg logo-w100.png') - os.system('svg2png --width=600 --height=600 logo.svg logo-w600.png') - os.system('svg2png --width=500 --height=100 banner.svg banner-w500.png') - os.system('svg2png --width=1500 --height=400 banner.svg banner-w1500.png') + generate_png('logo', 100, 100) + generate_png('logo', 600, 600) + generate_png('banner_white', 500, 100) + generate_png('banner_white', 500, 100) + generate_png('banner_black', 1500, 400) + generate_png('banner_black', 1500, 400) + + # generate favicons favicon_sizes = [16, 32, 48, 128, 256] for s in favicon_sizes: - os.system(f'svg2png --width={s} --height={s} favicon.svg favicon-w{s}.png') + generate_png('favicon', s, s) + png_favicon_names = [f'favicon-w{s}.png' for s in favicon_sizes] - os.system('convert ' + (' '.join(png_favicon_names)) + - ' -colors 256 favicon.ico') + os.system('magick ' + (' '.join(png_favicon_names)) + ' -colors 256 favicon.ico') -if __name__ == "__main__": +if __name__ == '__main__': random.seed(42) + # test_logos() main() diff --git a/logo/favicon-w128.png b/logo/favicon-w128.png index f61796614..77b2bc221 100644 Binary files a/logo/favicon-w128.png and b/logo/favicon-w128.png differ diff --git a/logo/favicon-w16.png b/logo/favicon-w16.png index 642b75fde..6a725315d 100644 Binary files a/logo/favicon-w16.png and b/logo/favicon-w16.png differ diff --git a/logo/favicon-w256.png b/logo/favicon-w256.png index cebe84405..5826adba3 100644 Binary files a/logo/favicon-w256.png and b/logo/favicon-w256.png differ diff --git a/logo/favicon-w32.png b/logo/favicon-w32.png index c28894c59..656692f08 100644 Binary files a/logo/favicon-w32.png and b/logo/favicon-w32.png differ diff --git a/logo/favicon-w48.png b/logo/favicon-w48.png index 18c642bee..ef7054c33 100644 Binary files a/logo/favicon-w48.png and b/logo/favicon-w48.png differ diff --git a/logo/favicon.ico b/logo/favicon.ico index 01365747d..887f662af 100644 Binary files a/logo/favicon.ico and b/logo/favicon.ico differ diff --git a/logo/favicon.svg b/logo/favicon.svg index e72cc46e5..5d730caa4 100644 --- a/logo/favicon.svg +++ b/logo/favicon.svg @@ -1,2 +1,2 @@ - \ No newline at end of file + \ No newline at end of file diff --git a/logo/logo-w100.png b/logo/logo-w100.png index 5cbf6b724..d6c472a49 100644 Binary files a/logo/logo-w100.png and b/logo/logo-w100.png differ diff --git a/logo/logo-w600.png b/logo/logo-w600.png index 9ef54aa94..723bddc38 100644 Binary files a/logo/logo-w600.png and b/logo/logo-w600.png differ diff --git a/logo/logo.svg b/logo/logo.svg index 21dea02b3..de1cb7855 100644 --- a/logo/logo.svg +++ b/logo/logo.svg @@ -1,2 +1,2 @@ - \ No newline at end of file + \ No newline at end of file diff --git a/scripts/readme_example_word_count.py b/scripts/readme_example_word_count.py index 22235cf20..3e64674d8 100644 --- a/scripts/readme_example_word_count.py +++ b/scripts/readme_example_word_count.py @@ -2,7 +2,7 @@ counts = ( Context() - .textFile('README.rst') + .textFile('README.md') .map(lambda line: ''.join(ch if ch.isalnum() else ' ' for ch in line)) .flatMap(lambda line: line.split(' ')) .map(lambda word: (word, 1)) diff --git a/setup.py b/setup.py index 6f83df71d..f5cba5935 100644 --- a/setup.py +++ b/setup.py @@ -9,8 +9,8 @@ package_dir={'': 'src'}, license='MIT', description='Pure Python implementation of the Spark RDD interface.', - long_description=open('README.rst').read(), - long_description_content_type='text/x-rst', + long_description=open('README.md').read(), + long_description_content_type='text/markdown', author='pysparkling contributors', url='https://github.com/kbc-opensource/pysparkling',