First commit on spark study basics

4c3c1445 · root · 4c3c1445 · 4c3c1445 · 4c3c1445
Commit 4c3c1445 authored 4 years ago by root
--- a/.ipynb_checkpoints/Spark basics-checkpoint.ipynb
+++ b/.ipynb_checkpoints/Spark basics-checkpoint.ipynb
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pyspark.sql import SparkSession"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "spark=SparkSession.builder.appName('Basics').getOrCreate()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df=spark.read.json('people.json')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
+%% Cell type:code id: tags:
+``` python
+from pyspark.sql import SparkSession
+```
+%% Cell type:code id: tags:
+``` python
+spark=SparkSession.builder.appName('Basics').getOrCreate()
+```
+%% Cell type:code id: tags:
+``` python
+df=spark.read.json('people.json')
+```
+%% Cell type:code id: tags:
+``` python
+```
--- a/Spark basics.ipynb
+++ b/Spark basics.ipynb
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pyspark.sql import SparkSession"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "spark=SparkSession.builder.appName('Basics').getOrCreate()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df=spark.read.json('people.json')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
+%% Cell type:code id: tags:
+``` python
+from pyspark.sql import SparkSession
+```
+%% Cell type:code id: tags:
+``` python
+spark=SparkSession.builder.appName('Basics').getOrCreate()
+```
+%% Cell type:code id: tags:
+``` python
+df=spark.read.json('people.json')
+```
+%% Cell type:code id: tags:
+``` python
+```
--- a/people.json
+++ b/people.json
+{"name":"Michael"}
+{"name":"Andy", "age":30}
+{"name":"Justin", "age":19}