LeetCode PySpark Solution

Author: bitoollearner

Solved/2990. Loan Types (Easy)-(Solved).ipynb

@@ -4,7 +4,10 @@
    "cell_type": "markdown",
    "metadata": {
     "application/vnd.databricks.v1+cell": {
-     "cellMetadata": {},
+     "cellMetadata": {
+      "byteLimit": 2048000,
+      "rowLimit": 10000
+     },
      "inputWidgets": {},
      "nuid": "4e9d71b1-88e9-445c-820a-b842e217a4e7",
      "showTitle": false,
@@ -21,7 +24,10 @@
    "execution_count": 0,
    "metadata": {
     "application/vnd.databricks.v1+cell": {
-     "cellMetadata": {},
+     "cellMetadata": {
+      "byteLimit": 2048000,
+      "rowLimit": 10000
+     },
      "inputWidgets": {},
      "nuid": "e6624c4d-8cb8-4ac4-8c72-81d1b4ecdb57",
      "showTitle": false,
@@ -40,7 +46,10 @@
    "cell_type": "markdown",
    "metadata": {
     "application/vnd.databricks.v1+cell": {
-     "cellMetadata": {},
+     "cellMetadata": {
+      "byteLimit": 2048000,
+      "rowLimit": 10000
+     },
      "inputWidgets": {},
      "nuid": "c3788fe5-f4c9-420f-ad72-ec1a39310a2a",
      "showTitle": false,
@@ -103,15 +112,27 @@
    "execution_count": 0,
    "metadata": {
     "application/vnd.databricks.v1+cell": {
-     "cellMetadata": {},
+     "cellMetadata": {
+      "byteLimit": 2048000,
+      "rowLimit": 10000
+     },
      "inputWidgets": {},
      "nuid": "137536ea-9bec-4171-8dc2-4bf8b0d771b4",
      "showTitle": false,
      "tableResultSettingsMap": {},
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+-------+-------+---------+\n|loan_id|user_id|loan_type|\n+-------+-------+---------+\n|    683|    101| Mortgage|\n|    218|    101| AutoLoan|\n|    802|    101| Inschool|\n|    593|    102| Mortgage|\n|    138|    102|Refinance|\n|    294|    102| Inschool|\n|    308|    103|Refinance|\n|    389|    104| Mortgage|\n+-------+-------+---------+\n\n"
+     ]
+    }
+   ],
    "source": [
     "loans_data_2990 = [\n",
     "    (683, 101, \"Mortgage\"),\n",
@@ -128,15 +149,136 @@
     "loans_df_2990 = spark.createDataFrame(loans_data_2990, loans_columns_2990)\n",
     "loans_df_2990.show()\n"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "application/vnd.databricks.v1+cell": {
+     "cellMetadata": {
+      "byteLimit": 2048000,
+      "rowLimit": 10000
+     },
+     "inputWidgets": {},
+     "nuid": "97a827c1-3c2e-47de-8b50-6454b8ab3939",
+     "showTitle": false,
+     "tableResultSettingsMap": {},
+     "title": ""
+    }
+   },
+   "outputs": [],
+   "source": [
+    "loan_counts_2990 = loans_df_2990\\\n",
+    "                        .groupBy(\"user_id\")\\\n",
+    "                            .agg(\n",
+    "                                collect_set(\"loan_type\").alias(\"loan_types\")\n",
+    "                                )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "application/vnd.databricks.v1+cell": {
+     "cellMetadata": {
+      "byteLimit": 2048000,
+      "rowLimit": 10000
+     },
+     "inputWidgets": {},
+     "nuid": "e4e672d5-8f63-488a-9344-3c8cfca7ed63",
+     "showTitle": false,
+     "tableResultSettingsMap": {},
+     "title": ""
+    }
+   },
+   "outputs": [
+    {
+     "output_type": "display_data",
+     "data": {
+      "text/html": [
+       "<style scoped>\n",
+       "  .table-result-container {\n",
+       "    max-height: 300px;\n",
+       "    overflow: auto;\n",
+       "  }\n",
+       "  table, th, td {\n",
+       "    border: 1px solid black;\n",
+       "    border-collapse: collapse;\n",
+       "  }\n",
+       "  th, td {\n",
+       "    padding: 5px;\n",
+       "  }\n",
+       "  th {\n",
+       "    text-align: left;\n",
+       "  }\n",
+       "</style><div class='table-result-container'><table class='table-result'><thead style='background-color: white'><tr><th>user_id</th></tr></thead><tbody><tr><td>102</td></tr></tbody></table></div>"
+      ]
+     },
+     "metadata": {
+      "application/vnd.databricks.v1+output": {
+       "addedWidgets": {},
+       "aggData": [],
+       "aggError": "",
+       "aggOverflow": false,
+       "aggSchema": [],
+       "aggSeriesLimitReached": false,
+       "aggType": "",
+       "arguments": {},
+       "columnCustomDisplayInfos": {},
+       "data": [
+        [
+         102
+        ]
+       ],
+       "datasetInfos": [],
+       "dbfsResultPath": null,
+       "isJsonSchema": true,
+       "metadata": {},
+       "overflow": false,
+       "plotOptions": {
+        "customPlotOptions": {},
+        "displayType": "table",
+        "pivotAggregation": null,
+        "pivotColumns": null,
+        "xColumns": null,
+        "yColumns": null
+       },
+       "removedWidgets": [],
+       "schema": [
+        {
+         "metadata": "{}",
+         "name": "user_id",
+         "type": "\"long\""
+        }
+       ],
+       "type": "table"
+      }
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "loan_counts_2990\\\n",
+    "    .filter(\n",
+    "        (array_contains(col(\"loan_types\"), \"Refinance\")) &\n",
+    "        (array_contains(col(\"loan_types\"), \"Mortgage\")))\\\n",
+    "            .select(\"user_id\").orderBy(\"user_id\").display()"
+   ]
   }
  ],
  "metadata": {
   "application/vnd.databricks.v1+notebook": {
-   "computePreferences": null,
+   "computePreferences": {
+    "hardware": {
+     "accelerator": null,
+     "gpuPoolId": null,
+     "memory": null
+    }
+   },
    "dashboards": [],
    "environmentMetadata": {
     "base_environment": "",
-    "environment_version": "1"
+    "environment_version": "2"
    },
    "inputWidgetPreferences": null,
    "language": "python",