Skip to content

Instantly share code, notes, and snippets.

@raghothams
Created March 9, 2017 14:21
Show Gist options
  • Save raghothams/bf565a326c0a525be755a46723fd2955 to your computer and use it in GitHub Desktop.
Save raghothams/bf565a326c0a525be755a46723fd2955 to your computer and use it in GitHub Desktop.
extract procedure id pyspark
Display the source blob
Display the rendered blob
Raw
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from pyspark.context import SparkContext"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"sc = SparkContext(master=\"local[2]\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"<pyspark.context.SparkContext at 0x7ff773f93a58>"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sc"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"df = pd.read_csv(\"temp.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from pyspark.sql import DataFrame\n",
"from pyspark import SQLContext"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"sqlc = SQLContext(sc)"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"ndf = sqlc.sparkSession.createDataFrame(df)"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"+---+--------+-------+-------+-------+\n",
"|pid| svcfrom| isprim| isecon| prcoid|\n",
"+---+--------+-------+-------+-------+\n",
"| 1| 1| 0| 1| abc|\n",
"| 1| 1| 1| 0| def|\n",
"| 1| 1| 0| 1| fff|\n",
"| 2| 1| 1| 0| xyz|\n",
"+---+--------+-------+-------+-------+\n",
"\n"
]
}
],
"source": [
"ndf.show()"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"rdds = ndf.rdd.keyBy(lambda row: (row['pid']))"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"def extract_procid(row1, row2):\n",
" print(row1)\n",
" if row1[\"isprim\"] == 1:\n",
" return row1[\"procid\"]"
]
},
{
"cell_type": "code",
"execution_count": 43,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"[(2, ' xyz'), (1, ' def')]"
]
},
"execution_count": 43,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rdds.mapValues(lambda row: row[4] if row[2] is 1 else None).reduceByKey(lambda x, y: y if x is None else x).collect()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"anaconda-cloud": {},
"kernelspec": {
"display_name": "Python [conda root]",
"language": "python",
"name": "conda-root-py"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.5.2"
}
},
"nbformat": 4,
"nbformat_minor": 1
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment