diff options
| -rw-r--r-- | scratch/.gitignore | 2 | ||||
| -rw-r--r-- | scratch/HelloWorld.ipynb | 362 | ||||
| -rw-r--r-- | scratch/README.md | 10 |
3 files changed, 374 insertions, 0 deletions
diff --git a/scratch/.gitignore b/scratch/.gitignore new file mode 100644 index 0000000..01e0dc1 --- /dev/null +++ b/scratch/.gitignore @@ -0,0 +1,2 @@ +.env +.ipynb_checkpoints/ diff --git a/scratch/HelloWorld.ipynb b/scratch/HelloWorld.ipynb new file mode 100644 index 0000000..e382aa4 --- /dev/null +++ b/scratch/HelloWorld.ipynb @@ -0,0 +1,362 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 11, + "id": "6974daac", + "metadata": {}, + "outputs": [], + "source": [ + "from pyspark.sql import SparkSession\n", + "from pyspark.context import SparkContext" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "e72fbe47", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "pyspark.sql.session.SparkSession" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "SparkSession" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "9333e07a", + "metadata": {}, + "outputs": [], + "source": [ + "spark = SparkSession.builder.master(\"local\").appName(\"HelloWorld\").getOrCreate()" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "id": "adf79021", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "\n", + " <div>\n", + " <p><b>SparkSession - hive</b></p>\n", + " \n", + " <div>\n", + " <p><b>SparkContext</b></p>\n", + "\n", + " <p><a href=\"http://192.168.179.73:4040\">Spark UI</a></p>\n", + "\n", + " <dl>\n", + " <dt>Version</dt>\n", + " <dd><code>v3.1.1</code></dd>\n", + " <dt>Master</dt>\n", + " <dd><code>local[*]</code></dd>\n", + " <dt>AppName</dt>\n", + " <dd><code>PySparkShell</code></dd>\n", + " </dl>\n", + " </div>\n", + " \n", + " </div>\n", + " " + ], + "text/plain": [ + "<pyspark.sql.session.SparkSession at 0x7f63b4051650>" + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "spark" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "id": "324b74ca", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "'3.1.1'" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "spark.version" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "id": "856f2700", + "metadata": {}, + "outputs": [], + "source": [ + "sc = SparkContext.getOrCreate()" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "id": "7218a07f", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "\n", + " <div>\n", + " <p><b>SparkContext</b></p>\n", + "\n", + " <p><a href=\"http://192.168.179.73:4040\">Spark UI</a></p>\n", + "\n", + " <dl>\n", + " <dt>Version</dt>\n", + " <dd><code>v3.1.1</code></dd>\n", + " <dt>Master</dt>\n", + " <dd><code>local[*]</code></dd>\n", + " <dt>AppName</dt>\n", + " <dd><code>PySparkShell</code></dd>\n", + " </dl>\n", + " </div>\n", + " " + ], + "text/plain": [ + "<SparkContext master=local[*] appName=PySparkShell>" + ] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sc" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "id": "17114da3", + "metadata": {}, + "outputs": [], + "source": [ + "txt = sc.textFile('file:////usr/share/doc/python3/copyright')" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "id": "c1af9b77", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "file:////usr/share/doc/python3/copyright MapPartitionsRDD[4] at textFile at NativeMethodAccessorImpl.java:0" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "txt" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "id": "ee37564c", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "pyspark.rdd.RDD" + ] + }, + "execution_count": 25, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "type(txt)" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "id": "208ef97a", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "319" + ] + }, + "execution_count": 26, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "txt.count()" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "id": "06f807b8", + "metadata": {}, + "outputs": [], + "source": [ + "python_lines = txt.filter(lambda line: 'python' in line.lower())" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "id": "ff2835b7", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "52\n" + ] + } + ], + "source": [ + "print(python_lines.count())" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "id": "9c8ec8c7", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "['This is the Debian GNU/Linux prepackaged version of the Python programming',\n", + " 'language. Python was written by Guido van Rossum <guido@cwi.nl> and others.',\n", + " 'sources from ftp.python.org:/pub/python, based on the Debianization by',\n", + " 'Python was created in the early 1990s by Guido van Rossum at Stichting',\n", + " \"as a successor of a language called ABC. Guido remains Python's\",\n", + " 'In 1995, Guido continued his work on Python at the Corporation for',\n", + " 'In May 2000, Guido and the Python core development team moved to',\n", + " 'BeOpen.com to form the BeOpen PythonLabs team. In October of the same',\n", + " 'year, the PythonLabs team moved to Digital Creations (now Zope',\n", + " 'Corporation, see http://www.zope.com). In 2001, the Python Software',\n", + " 'Foundation (PSF, see http://www.python.org/psf/) was formed, a',\n", + " 'non-profit organization created specifically to own Python-related',\n", + " 'All Python releases are Open Source (see http://www.opensource.org for',\n", + " 'the Open Source Definition). Historically, most, but not all, Python',\n", + " \"(1) GPL-compatible doesn't mean that we're distributing Python under\",\n", + " ' the GPL. All Python licenses, unlike the GPL, let you distribute',\n", + " ' GPL-compatible licenses make it possible to combine Python with',\n", + " 'B. TERMS AND CONDITIONS FOR ACCESSING OR OTHERWISE USING PYTHON',\n", + " 'PYTHON SOFTWARE FOUNDATION LICENSE VERSION 2',\n", + " '1. This LICENSE AGREEMENT is between the Python Software Foundation',\n", + " 'otherwise using this software (\"Python\") in source or binary form and',\n", + " 'distribute, and otherwise use Python alone or in any derivative version,',\n", + " 'Python Software Foundation; All Rights Reserved\" are retained in Python alone or',\n", + " 'or incorporates Python or any part thereof, and wants to make',\n", + " 'the changes made to Python.',\n", + " '4. PSF is making Python available to Licensee on an \"AS IS\"',\n", + " 'FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF PYTHON WILL NOT',\n", + " '5. PSF SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF PYTHON',\n", + " 'A RESULT OF MODIFYING, DISTRIBUTING, OR OTHERWISE USING PYTHON,',\n", + " '8. By copying, installing or otherwise using Python, Licensee',\n", + " 'BEOPEN.COM LICENSE AGREEMENT FOR PYTHON 2.0',\n", + " 'BEOPEN PYTHON OPEN SOURCE LICENSE AGREEMENT VERSION 1',\n", + " '2. Subject to the terms and conditions of this BeOpen Python License',\n", + " 'provided, however, that the BeOpen Python License is retained in the',\n", + " 'third party. As an exception, the \"BeOpen Python\" logos available at',\n", + " 'http://www.pythonlabs.com/logos.html may be used according to the',\n", + " 'CNRI LICENSE AGREEMENT FOR PYTHON 1.6.1',\n", + " '(\"Licensee\") accessing and otherwise using Python 1.6.1 software in',\n", + " 'prepare derivative works, distribute, and otherwise use Python 1.6.1',\n", + " 'Reserved\" are retained in Python 1.6.1 alone or in any derivative',\n", + " 'quotes): \"Python 1.6.1 is made available subject to the terms and',\n", + " 'Python 1.6.1 may be located on the Internet using the following',\n", + " 'or incorporates Python 1.6.1 or any part thereof, and wants to make',\n", + " 'the changes made to Python 1.6.1.',\n", + " '4. CNRI is making Python 1.6.1 available to Licensee on an \"AS IS\"',\n", + " 'FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF PYTHON 1.6.1 WILL NOT',\n", + " '5. CNRI SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF PYTHON',\n", + " 'A RESULT OF MODIFYING, DISTRIBUTING, OR OTHERWISE USING PYTHON 1.6.1,',\n", + " 'on Python 1.6.1 that incorporate non-separable material that was',\n", + " 'installing or otherwise using Python 1.6.1, Licensee agrees to be',\n", + " 'CWI LICENSE AGREEMENT FOR PYTHON 0.9.0 THROUGH 1.2',\n", + " 'py3compile, py3clean and debpython module:']" + ] + }, + "execution_count": 30, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "python_lines.collect()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "9c60ff17", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "cgraph", + "language": "python", + "name": "cgraph" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.8" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/scratch/README.md b/scratch/README.md new file mode 100644 index 0000000..4c3fa65 --- /dev/null +++ b/scratch/README.md @@ -0,0 +1,10 @@ +# PySpark Test Run + +* 2020-04-02 + +Goal: We want to understand, which URLs of the citation corpus have been +preserved. Also we want the GWB URL if possible. We'll try pyspark. + +Our cluster runs Hadoop 2.6, so we'll try: + + $ PYSPARK_HADOOP_VERSION=2.7 pip install pyspark |