LeetCode Pyspark Solution

Author: bitoollearner

Solved/2669. Count Artist Occurrences On Spotify Ranking List (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,
@@ -97,15 +106,27 @@
    "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|     id|        track_name|    artist|\n+-------+------------------+----------+\n| 303651|Heart Won't Forget|       Sia|\n|1046089|      Shape of you|Ed Sheeran|\n|  33445|       I'm the one| DJ Khalid|\n| 811266|Young Dumb & Broke| DJ Khalid|\n| 505727|           Happier|Ed Sheeran|\n+-------+------------------+----------+\n\n"
+     ]
+    }
+   ],
    "source": [
     "spotify_data_2669 = [\n",
     "    (303651, \"Heart Won't Forget\", \"Sia\"),\n",
@@ -119,15 +140,124 @@
     "spotify_df_2669 = spark.createDataFrame(spotify_data_2669, spotify_columns_2669)\n",
     "spotify_df_2669.show()"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "application/vnd.databricks.v1+cell": {
+     "cellMetadata": {
+      "byteLimit": 2048000,
+      "rowLimit": 10000
+     },
+     "inputWidgets": {},
+     "nuid": "d8cfc9be-e847-4e0a-9fd5-7652d74bde8f",
+     "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>artist</th><th>occurrences</th></tr></thead><tbody><tr><td>DJ Khalid</td><td>2</td></tr><tr><td>Ed Sheeran</td><td>2</td></tr><tr><td>Sia</td><td>1</td></tr></tbody></table></div>"
+      ]
+     },
+     "metadata": {
+      "application/vnd.databricks.v1+output": {
+       "addedWidgets": {},
+       "aggData": [],
+       "aggError": "",
+       "aggOverflow": false,
+       "aggSchema": [],
+       "aggSeriesLimitReached": false,
+       "aggType": "",
+       "arguments": {},
+       "columnCustomDisplayInfos": {},
+       "data": [
+        [
+         "DJ Khalid",
+         2
+        ],
+        [
+         "Ed Sheeran",
+         2
+        ],
+        [
+         "Sia",
+         1
+        ]
+       ],
+       "datasetInfos": [],
+       "dbfsResultPath": null,
+       "isJsonSchema": true,
+       "metadata": {},
+       "overflow": false,
+       "plotOptions": {
+        "customPlotOptions": {},
+        "displayType": "table",
+        "pivotAggregation": null,
+        "pivotColumns": null,
+        "xColumns": null,
+        "yColumns": null
+       },
+       "removedWidgets": [],
+       "schema": [
+        {
+         "metadata": "{}",
+         "name": "artist",
+         "type": "\"string\""
+        },
+        {
+         "metadata": "{}",
+         "name": "occurrences",
+         "type": "\"long\""
+        }
+       ],
+       "type": "table"
+      }
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "spotify_df_2669\\\n",
+    "    .groupBy(\"artist\")\\\n",
+    "        .agg(count(\"*\").alias(\"occurrences\"))\\\n",
+    "            .orderBy(col(\"occurrences\").desc(), col(\"artist\").asc()).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",