start of raw_to_base

raw_to_base.ipynb

@@ -0,0 +1,74 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31mRunning cells with 'Python 3.12.4' requires the ipykernel package.\n",
+      "\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
+      "\u001b[1;31mCommand: '/bin/python3.12 -m pip install ipykernel -U --user --force-reinstall'"
+     ]
+    }
+   ],
+   "source": [
+    "from pyspark.sql import SparkSession\n",
+    "from pyspark.sql.functions import *\n",
+    "from pyspark.sql.types import *\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31mRunning cells with 'Python 3.12.4' requires the ipykernel package.\n",
+      "\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
+      "\u001b[1;31mCommand: '/bin/python3.12 -m pip install ipykernel -U --user --force-reinstall'"
+     ]
+    }
+   ],
+   "source": [
+    "\n",
+    "spark = SparkSession.builder.appName(\"finance_dwh\").config(\"spark.memory.offHeap.enabled\",\"true\").config(\"spark.memory.offHeap.size\",\"10g\").getOrCreate()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "accounts_data = spark.read.json(\"data/20240728094708.json\")\n",
+    "accounts_data.printSchema()\n",
+    "#accounts_data.show()\n",
+    "\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}