CC/media_ml
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

bronze -> silver postgres

Browse Source
This commit is contained in:
CC
2026-10-18 18:05:53 +01:00
parent bb36c54f96
commit dc6b08eeeb
1 changed files with 16 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
spotify.ipynb
View File

@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 1,
"id": "e9bf1d26",
"metadata": {},
"outputs": [],
@@ -17,7 +17,7 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 2,
"id": "11bb5dc2",
"metadata": {},
"outputs": [],
@@ -56,7 +56,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 3,
"id": "a898326e",
"metadata": {},
"outputs": [],
@@ -123,7 +123,7 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 4,
"id": "817475cf",
"metadata": {},
"outputs": [],
@@ -163,7 +163,7 @@
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": 5,
"id": "c609291c",
"metadata": {},
"outputs": [],
@@ -185,7 +185,7 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 6,
"id": "4cc14bd0",
"metadata": {},
"outputs": [
@@ -193,6 +193,14 @@
"name": "stderr",
"output_type": "stream",
"text": [
"WARNING: Using incubator modules: jdk.incubator.vector\n",
"Using Spark's default log4j profile: org/apache/spark/log4j2-defaults.properties\n",
"26/10/18 17:57:09 WARN Utils: Your hostname, MacBook-Neo-232.local, resolves to a loopback address: 127.0.0.1; using 192.168.10.130 instead (on interface en0)\n",
"26/10/18 17:57:09 WARN Utils: Set SPARK_LOCAL_IP if you need to bind to another address\n",
"26/10/18 17:57:09 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable\n",
"Using Spark's default log4j profile: org/apache/spark/log4j2-defaults.properties\n",
"Setting default log level to \"WARN\".\n",
"To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).\n",
" \r"
]
},
@@ -230,7 +238,7 @@
},
{
"cell_type": "code",
"execution_count": 14,
"execution_count": 7,
"id": "faa6a8cb",
"metadata": {},
"outputs": [
@@ -241,7 +249,7 @@
"traceback": [
"\u001b[31m---------------------------------------------------------------------------\u001b[39m",
"\u001b[31mNameError\u001b[39m Traceback (most recent call last)",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[14]\u001b[39m\u001b[32m, line 2\u001b[39m\n\u001b[32m 1\u001b[39m \u001b[38;5;66;03m## Potential Test Help\u001b[39;00m\n\u001b[32m----> \u001b[39m\u001b[32m2\u001b[39m print(metadata_df(music_df).rdd.getNumPartitions()) \u001b[38;5;66;03m# Partitions for Pyspark\u001b[39;00m\n\u001b[32m 3\u001b[39m print(len(metadata_df(music_df).columns)) \u001b[38;5;66;03m# # of columns in JSON\u001b[39;00m\n\u001b[32m 4\u001b[39m null_counts = null_counts_by_column(metadata_df(music_df)) \u001b[38;5;66;03m# Null counts by column\u001b[39;00m\n\u001b[32m 5\u001b[39m null_counts.show(vertical=\u001b[38;5;28;01mTrue\u001b[39;00m) \u001b[38;5;66;03m# Print Null counts by column_df\u001b[39;00m\n",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[7]\u001b[39m\u001b[32m, line 2\u001b[39m\n\u001b[32m 1\u001b[39m \u001b[38;5;66;03m## Potential Test Help\u001b[39;00m\n\u001b[32m----> \u001b[39m\u001b[32m2\u001b[39m print(metadata_df(music_df).rdd.getNumPartitions()) \u001b[38;5;66;03m# Partitions for Pyspark\u001b[39;00m\n\u001b[32m 3\u001b[39m print(len(metadata_df(music_df).columns)) \u001b[38;5;66;03m# # of columns in JSON\u001b[39;00m\n\u001b[32m 4\u001b[39m null_counts = null_counts_by_column(metadata_df(music_df)) \u001b[38;5;66;03m# Null counts by column\u001b[39;00m\n\u001b[32m 5\u001b[39m null_counts.show(vertical=\u001b[38;5;28;01mTrue\u001b[39;00m) \u001b[38;5;66;03m# Print Null counts by column_df\u001b[39;00m\n",
"\u001b[31mNameError\u001b[39m: name 'music_df' is not defined"
]
}