pivot for collecting dump data

src/lib/expand_dumps.ipynb

@@ -0,0 +1,18 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "https://wikitech.wikimedia.org/wiki/Data_Platform/Data_Lake/Edits/Mediawiki_history_dumps/Python_Pandas_examples\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

src/lib/get_wiki_data.ipynb

@@ -1,117 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [
-    {
-     "ename": "ModuleNotFoundError",
-     "evalue": "No module named 'pandas'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
-      "\u001b[0;32m/tmp/ipykernel_1566937/562128272.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mre\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mjson\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m \u001b[0;32mimport\u001b[0m \u001b[0mpandas\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
-      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'pandas'"
-     ]
-    }
-   ],
-   "source": [
-    "import bz2\n",
-    "import os\n",
-    "import re\n",
-    "import json\n",
-    "import pandas as pd"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [
-    {
-     "ename": "ModuleNotFoundError",
-     "evalue": "No module named 'findspark'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
-      "\u001b[0;32m/tmp/ipykernel_1566937/3416374666.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mimport\u001b[0m \u001b[0mfindspark\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      2\u001b[0m \u001b[0mfindspark\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"/home/SOC.NORTHWESTERN.EDU/nws8519/spark-3.2.0-bin-hadoop3.2\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0menviron\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'HADOOP_CONF_DIR'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"/home/SOC.NORTHWESTERN.EDU/nws8519/spark-3.2.0-bin-hadoop3.2\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mpyspark\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msql\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mSparkSession\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mpyspark\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msql\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mfunctions\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mF\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtypes\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mT\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mWindow\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'findspark'"
-     ]
-    }
-   ],
-   "source": [
-    "import findspark\n",
-    "findspark.init(\"/home/SOC.NORTHWESTERN.EDU/nws8519/spark-3.2.0-bin-hadoop3.2\")\n",
-    "os.environ['HADOOP_CONF_DIR'] = \"/home/SOC.NORTHWESTERN.EDU/nws8519/spark-3.2.0-bin-hadoop3.2\"\n",
-    "from pyspark.sql import SparkSession\n",
-    "from pyspark.sql import functions as F, types as T, Window\n",
-    "\n",
-    "#source /opt/conda-analytics/bin/activate\n",
-    "import wmfdata.spark as wmfspark"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "ename": "NameError",
-     "evalue": "name 'wmfspark' is not defined",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "\u001b[0;32m/tmp/ipykernel_1566937/1742447738.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;31m## defining the spark session\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0mspark_config\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m{\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m spark = wmfspark.create_session(\n\u001b[0m\u001b[1;32m      4\u001b[0m     \u001b[0mapp_name\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'Pyspark notebook'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m     \u001b[0mtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'regular'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mNameError\u001b[0m: name 'wmfspark' is not defined"
-     ]
-    }
-   ],
-   "source": [
-    "## defining the spark session\n",
-    "spark_config = {}\n",
-    "spark = wmfspark.create_session(\n",
-    "    app_name='Pyspark notebook', \n",
-    "    type='regular'\n",
-    "#     extra_settings=spark_config\n",
-    ")\n",
-    "spark"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(\"success\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.12"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

src/lib/old_wiki_approach/get_wiki_activity.py

@@ -8,6 +8,10 @@ import sys
 import findspark
 #findspark.init("/home/SOC.NORTHWESTERN.EDU/nws8519/spark-3.2.0-bin-hadoop3.2")
 os.environ['HADOOP_CONF_DIR'] = "/home/SOC.NORTHWESTERN.EDU/nws8519/spark-3.2.0-bin-hadoop3.2"
+os.environ['PYSPARK_PYTHON'] = sys.executable
+os.environ['PYSPARK_DRIVER_PYTHON'] = sys.executable
+os.environ['JAVA_HOME'] = "/usr/lib/jvm/java-11-openjdk-amd64"
+os.environ['JRE_HOME'] = "/usr/lib/jvm/java-11-openjdk-amd64/jre"
 from pyspark.sql import SparkSession
 from pyspark.sql import functions as F, types as T, Window
 

src/lib/old_wiki_approach/get_wiki_data.ipynb

@@ -0,0 +1,90 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "import bz2\n",
+    "import os\n",
+    "import re\n",
+    "import json\n",
+    "import pandas as pd\n",
+    "import sys"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import findspark\n",
+    "#findspark.init(\"/home/SOC.NORTHWESTERN.EDU/nws8519/spark-3.2.0-bin-hadoop3.2\")\n",
+    "os.environ['HADOOP_CONF_DIR'] = \"/home/SOC.NORTHWESTERN.EDU/nws8519/spark-3.2.0-bin-hadoop3.2\"\n",
+    "os.environ['PYSPARK_PYTHON'] = sys.executable\n",
+    "os.environ['PYSPARK_DRIVER_PYTHON'] = sys.executable\n",
+    "os.environ['JAVA_HOME'] = \"/usr/lib/jvm/java-11-openjdk-amd64\"\n",
+    "os.environ['JRE_HOME'] = \"/usr/lib/jvm/java-11-openjdk-amd64/jre\"\n",
+    "from pyspark.sql import SparkSession\n",
+    "from pyspark.sql import functions as F, types as T, Window\n",
+    "\n",
+    "#source /opt/conda-analytics/bin/activate\n",
+    "import wmfdata.spark as wmfspark"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'spark' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[7], line 2\u001b[0m\n\u001b[1;32m      1\u001b[0m df_projects \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m----> 2\u001b[0m     \u001b[43mspark\u001b[49m\u001b[38;5;241m.\u001b[39mread\u001b[38;5;241m.\u001b[39mtable(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mwmf_raw.mediawiki_project_namespace_map\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m      3\u001b[0m     \u001b[38;5;241m.\u001b[39mwhere(F\u001b[38;5;241m.\u001b[39mcol(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msnapshot\u001b[39m\u001b[38;5;124m\"\u001b[39m)\u001b[38;5;241m==\u001b[39msnapshot)\n\u001b[1;32m      4\u001b[0m     \u001b[38;5;241m.\u001b[39mwhere(F\u001b[38;5;241m.\u001b[39mcol(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhostname\u001b[39m\u001b[38;5;124m\"\u001b[39m)\u001b[38;5;241m.\u001b[39mcontains(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mwikipedia\u001b[39m\u001b[38;5;124m\"\u001b[39m))\n\u001b[1;32m      5\u001b[0m     \u001b[38;5;241m.\u001b[39mselect(F\u001b[38;5;241m.\u001b[39mcol(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdbname\u001b[39m\u001b[38;5;124m\"\u001b[39m)\u001b[38;5;241m.\u001b[39malias(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mwiki_db\u001b[39m\u001b[38;5;124m\"\u001b[39m))\n\u001b[1;32m      6\u001b[0m     \u001b[38;5;241m.\u001b[39mdistinct()\n\u001b[1;32m      7\u001b[0m     \u001b[38;5;241m.\u001b[39morderBy(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mwiki_db\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m      8\u001b[0m )\n\u001b[1;32m      9\u001b[0m df_projects\u001b[38;5;241m.\u001b[39mshow()\n",
+      "\u001b[0;31mNameError\u001b[0m: name 'spark' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "df_projects = (\n",
+    "    spark.read.table(\"wmf_raw.mediawiki_project_namespace_map\")\n",
+    "    .where(F.col(\"snapshot\")==snapshot)\n",
+    "    .where(F.col(\"hostname\").contains(\"wikipedia\"))\n",
+    "    .select(F.col(\"dbname\").alias(\"wiki_db\"))\n",
+    "    .distinct()\n",
+    "    .orderBy(\"wiki_db\")\n",
+    ")\n",
+    "df_projects.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.15"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}