LeetCode PySpark Solution

Author: bitoollearner

Solved/3384. Team Dominance by Pass Success (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,
@@ -150,15 +159,27 @@
    "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|player_id|team_name|\n+---------+---------+\n|        1|  Arsenal|\n|        2|  Arsenal|\n|        3|  Arsenal|\n|        4|  Chelsea|\n|        5|  Chelsea|\n|        6|  Chelsea|\n+---------+---------+\n\n+---------+----------+-------+\n|pass_from|time_stamp|pass_to|\n+---------+----------+-------+\n|        1|     00:15|      2|\n|        2|     00:45|      3|\n|        3|     01:15|      1|\n|        4|     00:30|      1|\n|        2|     46:00|      3|\n|        3|     46:15|      4|\n|        1|     46:45|      2|\n|        5|     46:30|      6|\n+---------+----------+-------+\n\n"
+     ]
+    }
+   ],
    "source": [
     "teams_data_3384 = [\n",
     "    (1, \"Arsenal\"),\n",
@@ -188,15 +209,190 @@
     "passes_df_3384 = spark.createDataFrame(passes_data_3384, passes_columns_3384)\n",
     "passes_df_3384.show()"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "application/vnd.databricks.v1+cell": {
+     "cellMetadata": {
+      "byteLimit": 2048000,
+      "rowLimit": 10000
+     },
+     "inputWidgets": {},
+     "nuid": "8745ee23-6035-439d-a7bd-25b30575bed6",
+     "showTitle": false,
+     "tableResultSettingsMap": {},
+     "title": ""
+    }
+   },
+   "outputs": [],
+   "source": [
+    "passes_df_3384 = passes_df_3384 \\\n",
+    "                    .join(teams_df_3384\\\n",
+    "                        .withColumnRenamed(\"player_id\", \"pass_from\"), on=\"pass_from\") \\\n",
+    "                        .withColumnRenamed(\"team_name\", \"from_team\") \\\n",
+    "                    .join(teams_df_3384\\\n",
+    "                        .withColumnRenamed(\"player_id\", \"pass_to\"), on=\"pass_to\") \\\n",
+    "                        .withColumnRenamed(\"team_name\", \"to_team\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "application/vnd.databricks.v1+cell": {
+     "cellMetadata": {
+      "byteLimit": 2048000,
+      "rowLimit": 10000
+     },
+     "inputWidgets": {},
+     "nuid": "bbe39e77-a34e-4104-8879-e3662f09d075",
+     "showTitle": false,
+     "tableResultSettingsMap": {},
+     "title": ""
+    }
+   },
+   "outputs": [],
+   "source": [
+    "passes_df_3384 = passes_df_3384\\\n",
+    "                    .withColumn( \"minute\", split(col(\"time_stamp\"), \":\").getItem(0).cast(\"int\") * 60 + split(col(\"time_stamp\"), \":\").getItem(1).cast(\"int\"))\\\n",
+    "                        .withColumn(\"half_number\", when(col(\"minute\") <= 45*60, 1).otherwise(2))\\\n",
+    "                            .withColumn( \"dominance_point\", when(col(\"from_team\") == col(\"to_team\"), 1).otherwise(-1))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "application/vnd.databricks.v1+cell": {
+     "cellMetadata": {
+      "byteLimit": 2048000,
+      "rowLimit": 10000
+     },
+     "inputWidgets": {},
+     "nuid": "f93abb86-31a4-413d-8839-a93d6d554841",
+     "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>team_name</th><th>half_number</th><th>dominance</th></tr></thead><tbody><tr><td>Arsenal</td><td>1</td><td>3</td></tr><tr><td>Arsenal</td><td>2</td><td>1</td></tr><tr><td>Chelsea</td><td>1</td><td>-1</td></tr><tr><td>Chelsea</td><td>2</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": [
+        [
+         "Arsenal",
+         1,
+         3
+        ],
+        [
+         "Arsenal",
+         2,
+         1
+        ],
+        [
+         "Chelsea",
+         1,
+         -1
+        ],
+        [
+         "Chelsea",
+         2,
+         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": "team_name",
+         "type": "\"string\""
+        },
+        {
+         "metadata": "{}",
+         "name": "half_number",
+         "type": "\"integer\""
+        },
+        {
+         "metadata": "{}",
+         "name": "dominance",
+         "type": "\"long\""
+        }
+       ],
+       "type": "table"
+      }
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "passes_df_3384\\\n",
+    "    .groupBy(\"from_team\", \"half_number\") \\\n",
+    "        .sum(\"dominance_point\") \\\n",
+    "            .withColumnRenamed(\"from_team\", \"team_name\") \\\n",
+    "                .withColumnRenamed(\"sum(dominance_point)\", \"dominance\") \\\n",
+    "                    .orderBy(\"team_name\", \"half_number\").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",