|
| 1 | +{ |
| 2 | + "cells": [ |
| 3 | + { |
| 4 | + "cell_type": "markdown", |
| 5 | + "metadata": { |
| 6 | + "application/vnd.databricks.v1+cell": { |
| 7 | + "cellMetadata": { |
| 8 | + "byteLimit": 2048000, |
| 9 | + "rowLimit": 10000 |
| 10 | + }, |
| 11 | + "inputWidgets": {}, |
| 12 | + "nuid": "a3495f99-90ec-472d-a12a-49ab7d16b3bd", |
| 13 | + "showTitle": false, |
| 14 | + "tableResultSettingsMap": {}, |
| 15 | + "title": "" |
| 16 | + } |
| 17 | + }, |
| 18 | + "source": [ |
| 19 | + "#Initialization" |
| 20 | + ] |
| 21 | + }, |
| 22 | + { |
| 23 | + "cell_type": "markdown", |
| 24 | + "metadata": { |
| 25 | + "application/vnd.databricks.v1+cell": { |
| 26 | + "cellMetadata": { |
| 27 | + "byteLimit": 2048000, |
| 28 | + "rowLimit": 10000 |
| 29 | + }, |
| 30 | + "inputWidgets": {}, |
| 31 | + "nuid": "dff4b590-576c-4a13-b547-083d7a31b669", |
| 32 | + "showTitle": false, |
| 33 | + "tableResultSettingsMap": {}, |
| 34 | + "title": "" |
| 35 | + } |
| 36 | + }, |
| 37 | + "source": [ |
| 38 | + "#The Transformation Logic" |
| 39 | + ] |
| 40 | + }, |
| 41 | + { |
| 42 | + "cell_type": "code", |
| 43 | + "execution_count": 0, |
| 44 | + "metadata": { |
| 45 | + "application/vnd.databricks.v1+cell": { |
| 46 | + "cellMetadata": { |
| 47 | + "byteLimit": 2048000, |
| 48 | + "rowLimit": 10000 |
| 49 | + }, |
| 50 | + "inputWidgets": {}, |
| 51 | + "nuid": "7801ecff-c5b2-4d1c-89ac-d6acd24848a5", |
| 52 | + "showTitle": false, |
| 53 | + "tableResultSettingsMap": {}, |
| 54 | + "title": "" |
| 55 | + } |
| 56 | + }, |
| 57 | + "outputs": [], |
| 58 | + "source": [ |
| 59 | + "query = \"\"\"\n", |
| 60 | + "SELECT\n", |
| 61 | + " ROW_NUMBER() OVER (ORDER BY ci.customer_id) AS customer_key,\n", |
| 62 | + " ci.customer_id,\n", |
| 63 | + " ci.customer_number,\n", |
| 64 | + " ci.first_name,\n", |
| 65 | + " ci.last_name,\n", |
| 66 | + " la.country,\n", |
| 67 | + " ci.marital_status,\n", |
| 68 | + " CASE\n", |
| 69 | + " WHEN ci.gender <> 'n/a' THEN ci.gender\n", |
| 70 | + " ELSE COALESCE(ca.gender, 'n/a')\n", |
| 71 | + " END AS gender,\n", |
| 72 | + " ca.birth_date AS birthdate,\n", |
| 73 | + " ci.created_date AS create_date\n", |
| 74 | + "FROM silver.crm_customers ci\n", |
| 75 | + "LEFT JOIN silver.erp_customers ca\n", |
| 76 | + " ON ci.customer_number = ca.customer_id\n", |
| 77 | + "LEFT JOIN silver.erp_customer_location la\n", |
| 78 | + " ON ci.customer_number = la.customer_id\n", |
| 79 | + "\"\"\"\n", |
| 80 | + "df = spark.sql(query)\n" |
| 81 | + ] |
| 82 | + }, |
| 83 | + { |
| 84 | + "cell_type": "code", |
| 85 | + "execution_count": 0, |
| 86 | + "metadata": { |
| 87 | + "application/vnd.databricks.v1+cell": { |
| 88 | + "cellMetadata": { |
| 89 | + "byteLimit": 2048000, |
| 90 | + "rowLimit": 10000 |
| 91 | + }, |
| 92 | + "inputWidgets": {}, |
| 93 | + "nuid": "f59bb479-889d-4f6e-b0f2-8ebc1ee41d6d", |
| 94 | + "showTitle": false, |
| 95 | + "tableResultSettingsMap": {}, |
| 96 | + "title": "" |
| 97 | + } |
| 98 | + }, |
| 99 | + "outputs": [], |
| 100 | + "source": [ |
| 101 | + "df.display()" |
| 102 | + ] |
| 103 | + }, |
| 104 | + { |
| 105 | + "cell_type": "markdown", |
| 106 | + "metadata": { |
| 107 | + "application/vnd.databricks.v1+cell": { |
| 108 | + "cellMetadata": { |
| 109 | + "byteLimit": 2048000, |
| 110 | + "rowLimit": 10000 |
| 111 | + }, |
| 112 | + "inputWidgets": {}, |
| 113 | + "nuid": "3aab6a15-eb4d-4b3b-8e8f-18acb7099ab3", |
| 114 | + "showTitle": false, |
| 115 | + "tableResultSettingsMap": {}, |
| 116 | + "title": "" |
| 117 | + } |
| 118 | + }, |
| 119 | + "source": [ |
| 120 | + "#Writing Gold Table" |
| 121 | + ] |
| 122 | + }, |
| 123 | + { |
| 124 | + "cell_type": "code", |
| 125 | + "execution_count": 0, |
| 126 | + "metadata": { |
| 127 | + "application/vnd.databricks.v1+cell": { |
| 128 | + "cellMetadata": { |
| 129 | + "byteLimit": 2048000, |
| 130 | + "rowLimit": 10000 |
| 131 | + }, |
| 132 | + "inputWidgets": {}, |
| 133 | + "nuid": "045b25e1-2aed-4afb-b9d7-e088473dc71e", |
| 134 | + "showTitle": false, |
| 135 | + "tableResultSettingsMap": {}, |
| 136 | + "title": "" |
| 137 | + } |
| 138 | + }, |
| 139 | + "outputs": [], |
| 140 | + "source": [ |
| 141 | + "df.write.mode(\"overwrite\").format(\"delta\").saveAsTable(\"workspace.gold.dim_customers\")" |
| 142 | + ] |
| 143 | + }, |
| 144 | + { |
| 145 | + "cell_type": "markdown", |
| 146 | + "metadata": { |
| 147 | + "application/vnd.databricks.v1+cell": { |
| 148 | + "cellMetadata": { |
| 149 | + "byteLimit": 2048000, |
| 150 | + "rowLimit": 10000 |
| 151 | + }, |
| 152 | + "inputWidgets": {}, |
| 153 | + "nuid": "56f1fb8a-d6a4-4a79-8f2e-726db7ba2d9f", |
| 154 | + "showTitle": false, |
| 155 | + "tableResultSettingsMap": {}, |
| 156 | + "title": "" |
| 157 | + } |
| 158 | + }, |
| 159 | + "source": [ |
| 160 | + "## Sanity checks of Gold table" |
| 161 | + ] |
| 162 | + }, |
| 163 | + { |
| 164 | + "cell_type": "code", |
| 165 | + "execution_count": 0, |
| 166 | + "metadata": { |
| 167 | + "application/vnd.databricks.v1+cell": { |
| 168 | + "cellMetadata": { |
| 169 | + "byteLimit": 2048000, |
| 170 | + "implicitDf": true, |
| 171 | + "rowLimit": 10000 |
| 172 | + }, |
| 173 | + "inputWidgets": {}, |
| 174 | + "nuid": "a98632c2-f3ab-4100-b942-7f93ab187a3a", |
| 175 | + "showTitle": false, |
| 176 | + "tableResultSettingsMap": {}, |
| 177 | + "title": "" |
| 178 | + } |
| 179 | + }, |
| 180 | + "outputs": [], |
| 181 | + "source": [ |
| 182 | + "%sql\n", |
| 183 | + "SELECT * FROM workspace.silver.erp_customers" |
| 184 | + ] |
| 185 | + } |
| 186 | + ], |
| 187 | + "metadata": { |
| 188 | + "application/vnd.databricks.v1+notebook": { |
| 189 | + "computePreferences": null, |
| 190 | + "dashboards": [], |
| 191 | + "environmentMetadata": { |
| 192 | + "base_environment": "", |
| 193 | + "environment_version": "4" |
| 194 | + }, |
| 195 | + "inputWidgetPreferences": null, |
| 196 | + "language": "python", |
| 197 | + "notebookMetadata": { |
| 198 | + "mostRecentlyExecutedCommandWithImplicitDF": { |
| 199 | + "commandId": 5051243675007213, |
| 200 | + "dataframes": [ |
| 201 | + "_sqldf" |
| 202 | + ] |
| 203 | + }, |
| 204 | + "pythonIndentUnit": 4 |
| 205 | + }, |
| 206 | + "notebookName": "gold_fact_sales", |
| 207 | + "widgets": {} |
| 208 | + }, |
| 209 | + "language_info": { |
| 210 | + "name": "python" |
| 211 | + } |
| 212 | + }, |
| 213 | + "nbformat": 4, |
| 214 | + "nbformat_minor": 0 |
| 215 | +} |
0 commit comments