LeetCode PySpark Solution

Author: bitoollearner

Solved/3103. Find Trending Hashtags II (Hard)-(Solved).ipynb

@@ -4,7 +4,10 @@
    "cell_type": "markdown",
    "metadata": {
     "application/vnd.databricks.v1+cell": {
-     "cellMetadata": {},
+     "cellMetadata": {
+      "byteLimit": 2048000,
+      "rowLimit": 10000
+     },
      "inputWidgets": {},
      "nuid": "7d1791bd-9552-4116-90b2-daa678bbffb8",
      "showTitle": false,
@@ -21,7 +24,10 @@
    "execution_count": 0,
    "metadata": {
     "application/vnd.databricks.v1+cell": {
-     "cellMetadata": {},
+     "cellMetadata": {
+      "byteLimit": 2048000,
+      "rowLimit": 10000
+     },
      "inputWidgets": {},
      "nuid": "2901fbc9-49db-4285-8b94-c460f34d4c4f",
      "showTitle": false,
@@ -40,7 +46,10 @@
    "cell_type": "markdown",
    "metadata": {
     "application/vnd.databricks.v1+cell": {
-     "cellMetadata": {},
+     "cellMetadata": {
+      "byteLimit": 2048000,
+      "rowLimit": 10000
+     },
      "inputWidgets": {},
      "nuid": "655120e7-6b25-417c-a08a-c6925feaa425",
      "showTitle": false,
@@ -107,15 +116,27 @@
    "execution_count": 0,
    "metadata": {
     "application/vnd.databricks.v1+cell": {
-     "cellMetadata": {},
+     "cellMetadata": {
+      "byteLimit": 2048000,
+      "rowLimit": 10000
+     },
      "inputWidgets": {},
      "nuid": "a2368434-0191-416c-aa1d-12cd44cf48e6",
      "showTitle": false,
      "tableResultSettingsMap": {},
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+-------+--------+--------------------+----------+\n|user_id|tweet_id|               tweet|tweet_date|\n+-------+--------+--------------------+----------+\n|    135|      13|Enjoying a great ...|2024-02-01|\n|    136|      14|Another #HappyDay...|2024-02-03|\n|    137|      15|Productivity peak...|2024-02-04|\n|    138|      16|Exploring new tec...|2024-02-04|\n|    139|      17|Gratitude for tod...|2024-02-05|\n|    140|      18|Innovation drives...|2024-02-07|\n|    141|      19|Connecting with n...|2024-02-09|\n+-------+--------+--------------------+----------+\n\n"
+     ]
+    }
+   ],
    "source": [
     "tweets_data_3103 = [\n",
     "    (135, 13, \"Enjoying a great start to the day. #HappyDay #MorningVibes\", \"2024-02-01\"),\n",
@@ -131,15 +152,169 @@
     "tweets_df_3103 = spark.createDataFrame(tweets_data_3103, tweets_columns_3103)\n",
     "tweets_df_3103.show()"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "application/vnd.databricks.v1+cell": {
+     "cellMetadata": {
+      "byteLimit": 2048000,
+      "rowLimit": 10000
+     },
+     "inputWidgets": {},
+     "nuid": "f0551d7b-8f01-4cab-86ca-a6eea077c1c9",
+     "showTitle": false,
+     "tableResultSettingsMap": {},
+     "title": ""
+    }
+   },
+   "outputs": [],
+   "source": [
+    "df_hashtags_3103 = tweets_df_3103\\\n",
+    "                    .withColumn( \"hashtags\",\n",
+    "                                expr(\"regexp_extract_all(tweet, '(#[A-Za-z0-9_]+)', 0)\")\n",
+    "                                )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "application/vnd.databricks.v1+cell": {
+     "cellMetadata": {
+      "byteLimit": 2048000,
+      "rowLimit": 10000
+     },
+     "inputWidgets": {},
+     "nuid": "eac4937b-1147-49ea-b0db-bd25680c661b",
+     "showTitle": false,
+     "tableResultSettingsMap": {},
+     "title": ""
+    }
+   },
+   "outputs": [],
+   "source": [
+    "df_exploded_3103 = df_hashtags_3103\\\n",
+    "                    .withColumn(\"hashtag\", explode(\"hashtags\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "application/vnd.databricks.v1+cell": {
+     "cellMetadata": {
+      "byteLimit": 2048000,
+      "rowLimit": 10000
+     },
+     "inputWidgets": {},
+     "nuid": "930e4528-ab1e-4ce5-af1b-ff829423a1d3",
+     "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>hashtag</th><th>count</th></tr></thead><tbody><tr><td>#HappyDay</td><td>3</td></tr><tr><td>#TechLife</td><td>2</td></tr><tr><td>#WorkLife</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": [
+        [
+         "#HappyDay",
+         3
+        ],
+        [
+         "#TechLife",
+         2
+        ],
+        [
+         "#WorkLife",
+         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": "hashtag",
+         "type": "\"string\""
+        },
+        {
+         "metadata": "{}",
+         "name": "count",
+         "type": "\"long\""
+        }
+       ],
+       "type": "table"
+      }
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "df_exploded_3103\\\n",
+    "    .groupBy(\"hashtag\").agg(count(\"*\").alias(\"count\"))\\\n",
+    "        .orderBy(desc(\"count\"), desc(\"hashtag\")).limit(3).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",