LeetCode Pyspark Question Solution

Author: bitoollearner

.databricks/commit_outputs

@@ -0,0 +1,16 @@
+
+# .databricks/commit_outputs file is used to control whether a notebook's output should be included when committing changes to Git.
+# Outputs are included/excluded at a per notebook level, committing select outputs within a specific notebook is not feasible.
+#
+# Reference:
+# each line in .databricks/commit_outputs represents a glob pattern
+# line starting with # represents a comment
+# notebook that matches a glob pattern will have output included
+# line starting with ! represents a exclusion pattern (i.e. !folder_a/\* will exclude output for all notebooks in folder_a)
+# if a notebook path matches multiple glob patterns, the last matching glob pattern will be used
+# note that glob patterns are case sensitive
+# more examples can be found here: https://docs.databricks.com/repos/repos-setup.html#patterns-for-a-repo-config-file
+
+# Uncomment the following pattern to include output for all notebooks
+**
+ 

Solved/1045. Customers Who Bought All Products (Medium)-(Solved).ipynb

@@ -130,7 +130,16 @@
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+-----------+-----------+\n|customer_id|product_key|\n+-----------+-----------+\n|          1|          5|\n|          2|          6|\n|          3|          5|\n|          3|          6|\n|          1|          6|\n+-----------+-----------+\n\n+-----------+\n|product_key|\n+-----------+\n|          5|\n|          6|\n+-----------+\n\n"
+     ]
+    }
+   ],
    "source": [
     "customer_data_1045 = [\n",
     "    (1, 5),\n",
@@ -191,7 +200,16 @@
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+-----------+\n|customer_id|\n+-----------+\n|          1|\n|          3|\n+-----------+\n\n"
+     ]
+    }
+   ],
    "source": [
     "customer_df_1045\\\n",
     "    .groupBy(\"customer_id\").agg(\n",

Solved/1050. Actors and Directors Who Cooperated At Least Three Times (Easy)-(Solved).ipynb

@@ -115,7 +115,16 @@
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+--------+-----------+---------+\n|actor_id|director_id|timestamp|\n+--------+-----------+---------+\n|       1|          1|        0|\n|       1|          1|        1|\n|       1|          1|        2|\n|       1|          2|        3|\n|       1|          2|        4|\n|       2|          1|        5|\n|       2|          1|        6|\n+--------+-----------+---------+\n\n"
+     ]
+    }
+   ],
    "source": [
     "actor_director_data_1050 = [\n",
     "    (1, 1, 0),\n",
@@ -148,7 +157,16 @@
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+--------+-----------+\n|actor_id|director_id|\n+--------+-----------+\n|       1|          1|\n+--------+-----------+\n\n"
+     ]
+    }
+   ],
    "source": [
     "actor_director_df_1050\\\n",
     "    .groupBy(\"actor_id\", \"director_id\")\\\n",

Solved/1068. Product Sales Analysis I (Easy)-(Solved).ipynb

@@ -139,7 +139,16 @@
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+-------+----------+----+--------+-----+\n|sale_id|product_id|year|quantity|price|\n+-------+----------+----+--------+-----+\n|      1|       100|2008|      10| 5000|\n|      2|       100|2009|      12| 5000|\n|      7|       200|2011|      15| 9000|\n+-------+----------+----+--------+-----+\n\n+----------+------------+\n|product_id|product_name|\n+----------+------------+\n|       100|       Nokia|\n|       200|       Apple|\n|       300|     Samsung|\n+----------+------------+\n\n"
+     ]
+    }
+   ],
    "source": [
     "sales_data_1068 = [\n",
     "    (1, 100, 2008, 10, 5000),\n",
@@ -178,7 +187,16 @@
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+------------+----+-----+\n|product_name|year|price|\n+------------+----+-----+\n|       Nokia|2009| 5000|\n|       Nokia|2008| 5000|\n|       Apple|2011| 9000|\n+------------+----+-----+\n\n"
+     ]
+    }
+   ],
    "source": [
     "sales_df_1068\\\n",
     "    .join(product_df_1068, on=\"product_id\", how=\"inner\")\\\n",

Solved/1069. Product Sales Analysis II (Easy)-(Solved).ipynb

@@ -133,7 +133,16 @@
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+-------+----------+----+--------+-----+\n|sale_id|product_id|year|quantity|price|\n+-------+----------+----+--------+-----+\n|      1|       100|2008|      10| 5000|\n|      2|       100|2009|      12| 5000|\n|      7|       200|2011|      15| 9000|\n+-------+----------+----+--------+-----+\n\n+----------+------------+\n|product_id|product_name|\n+----------+------------+\n|       100|       Nokia|\n|       200|       Apple|\n|       300|     Samsung|\n+----------+------------+\n\n"
+     ]
+    }
+   ],
    "source": [
     "sales_data_1069 = [\n",
     "    (1, 100, 2008, 10, 5000),\n",
@@ -172,7 +181,16 @@
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+----------+--------------+\n|product_id|total_quantity|\n+----------+--------------+\n|       100|            22|\n|       200|            15|\n+----------+--------------+\n\n"
+     ]
+    }
+   ],
    "source": [
     "sales_df_1069\\\n",
     "    .groupBy(\"product_id\").agg(sum(\"quantity\").alias(\"total_quantity\")).show()"

Solved/1070. Product Sales Analysis III (Medium)-(Solved).ipynb

@@ -131,7 +131,16 @@
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+-------+----------+----+--------+-----+\n|sale_id|product_id|year|quantity|price|\n+-------+----------+----+--------+-----+\n|      1|       100|2008|      10| 5000|\n|      2|       100|2009|      12| 5000|\n|      7|       200|2011|      15| 9000|\n+-------+----------+----+--------+-----+\n\n+----------+------------+\n|product_id|product_name|\n+----------+------------+\n|       100|       Nokia|\n|       200|       Apple|\n|       300|     Samsung|\n+----------+------------+\n\n"
+     ]
+    }
+   ],
    "source": [
     "sales_data_1070 = [\n",
     "    (1, 100, 2008, 10, 5000),\n",
@@ -193,7 +202,16 @@
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+------------+----------+--------+-----+\n|product_name|first_year|quantity|price|\n+------------+----------+--------+-----+\n|       Nokia|      2008|      10| 5000|\n|       Apple|      2011|      15| 9000|\n+------------+----------+--------+-----+\n\n"
+     ]
+    }
+   ],
    "source": [
     "sales_with_rank_df_1070\\\n",
     "    .join(product_df_1070, on=\"product_id\", how=\"inner\")\\\n",

Solved/1075. Project Employees I (Easy)-(Solved).ipynb

@@ -134,7 +134,16 @@
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+----------+-----------+\n|project_id|employee_id|\n+----------+-----------+\n|         1|          1|\n|         1|          2|\n|         1|          3|\n|         2|          1|\n|         2|          4|\n+----------+-----------+\n\n+-----------+------+----------------+\n|employee_id|  name|experience_years|\n+-----------+------+----------------+\n|          1|Khaled|               3|\n|          2|   Ali|               2|\n|          3|  John|               1|\n|          4|   Doe|               2|\n+-----------+------+----------------+\n\n"
+     ]
+    }
+   ],
    "source": [
     "project_data_1075 = [\n",
     "    (1, 1),\n",
@@ -176,7 +185,16 @@
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+----------+-------------+\n|project_id|average_years|\n+----------+-------------+\n|         1|          2.0|\n|         2|          2.5|\n+----------+-------------+\n\n"
+     ]
+    }
+   ],
    "source": [
     "project_df_1075\\\n",
     "    .join(employee_df_1075, on=\"employee_id\", how=\"inner\")\\\n",

Solved/1076. Project Employees II (Easy)-(Solved).ipynb

@@ -134,7 +134,16 @@
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+----------+-----------+\n|project_id|employee_id|\n+----------+-----------+\n|         1|          1|\n|         1|          2|\n|         1|          3|\n|         2|          1|\n|         2|          4|\n+----------+-----------+\n\n+-----------+------+----------------+\n|employee_id|  name|experience_years|\n+-----------+------+----------------+\n|          1|Khaled|               3|\n|          2|   Ali|               2|\n|          3|  John|               1|\n|          4|   Doe|               2|\n+-----------+------+----------------+\n\n"
+     ]
+    }
+   ],
    "source": [
     "project_data_1076 = [\n",
     "    (1, 1),\n",
@@ -218,7 +227,16 @@
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+----------+\n|project_id|\n+----------+\n|         1|\n+----------+\n\n"
+     ]
+    }
+   ],
    "source": [
     "project_counts_1076.\\\n",
     "    filter(project_counts_1076[\"employee_count\"] == max_count_1076) \\\n",

Solved/1077. Project Employees III (Medium)-(Solved).ipynb

@@ -136,7 +136,16 @@
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+----------+-----------+\n|project_id|employee_id|\n+----------+-----------+\n|         1|          1|\n|         1|          2|\n|         1|          3|\n|         2|          1|\n|         2|          4|\n+----------+-----------+\n\n+-----------+------+----------------+\n|employee_id|  name|experience_years|\n+-----------+------+----------------+\n|          1|Khaled|               3|\n|          2|   Ali|               2|\n|          3|  John|               3|\n|          4|   Doe|               2|\n+-----------+------+----------------+\n\n"
+     ]
+    }
+   ],
    "source": [
     "project_data_1077 = [\n",
     "    (1, 1),\n",
@@ -219,7 +228,16 @@
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+----------+-----------+\n|project_id|employee_id|\n+----------+-----------+\n|         1|          1|\n|         1|          3|\n|         2|          1|\n+----------+-----------+\n\n"
+     ]
+    }
+   ],
    "source": [
     "joined_df_1077\\\n",
     "    .withColumn(\"rnk\", rank().over(windowSpec))\\\n",

Solved/1082. Sales Analysis I (Easy)-(Solved).ipynb

@@ -137,7 +137,16 @@
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+---------+----------+--------+----------+--------+-----+\n|seller_id|product_id|buyer_id| sale_date|quantity|price|\n+---------+----------+--------+----------+--------+-----+\n|        1|         1|       1|2019-01-21|       2| 2000|\n|        1|         2|       2|2019-02-17|       1|  800|\n|        2|         2|       3|2019-06-02|       1|  800|\n|        3|         3|       4|2019-05-13|       2| 2800|\n+---------+----------+--------+----------+--------+-----+\n\n"
+     ]
+    }
+   ],
    "source": [
     "sales_data_1082 = [\n",
     "    (1, 1, 1, \"2019-01-21\", 2, 2000),\n",
@@ -210,7 +219,16 @@
      "title": ""
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+---------+\n|seller_id|\n+---------+\n|        1|\n|        3|\n+---------+\n\n"
+     ]
+    }
+   ],
    "source": [
     "seller_sales_1082.filter(seller_sales_1082[\"total_sales\"] == max_total_sales_1082) \\\n",
     "                           .select(\"seller_id\").show()"