kmatt

def df_to_sql_fast(df, table_name, numeric_columns, date_columns, append_or_replace, conn):
    """
    Appends or overwrites a SQL Server table 
    using data from a Pandas DataFrame.
    Submits df records at once for faster performance
    compared to df_to_sql.

    Parameters:
        df (DataFrame): df used to create/append table
        table_name (str): Name of existing SQL Server table

kmatt

SELECT tbl::TEXT, HASH(tbl::TEXT), MD5(tbl::TEXT) FROM tbl;

D create table tbl as (select 1 as a, 2 as b, 3 as c);
D select tbl::text, hash(tbl::text), md5(tbl::text) from tbl;
┌──────────────────────────┬────────────────────────────┬──────────────────────────────────┐
│   CAST(tbl AS VARCHAR)   │ hash(CAST(tbl AS VARCHAR)) │    md5(CAST(tbl AS VARCHAR))     │
│         varchar          │           uint64           │             varchar              │
├──────────────────────────┼────────────────────────────┼──────────────────────────────────┤
│ {'a': 1, 'b': 2, 'c': 3} │        6764392534128998287 │ e31681d6e7ab078c9679fcd4f50136eb │
└──────────────────────────┴────────────────────────────┴──────────────────────────────────┘

kmatt

Windows Registry Editor Version 5.00

[HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Windows\CurrentVersion\App Paths\npp.exe]
@="C:\\Program Files (x86)\\Notepad++\\notepad++.exe"

kmatt

# View diffs using delta
# Via https://github.com/jonas/tig/issues/26#issuecomment-1923835137

bind diff D >sh -c "git show %(commit) | delta --paging always"
bind diff S >sh -c "git show %(commit) | delta --paging always --side-by-side"

bind stage  D >sh -c "git diff HEAD -- %(file) | delta --paging always"
bind stage  S >sh -c "git diff HEAD -- %(file) | delta --paging always --side-by-side"
bind status D >sh -c "git diff HEAD -- %(file) | delta --paging always"
bind status S >sh -c "git diff HEAD -- %(file) | delta --paging always --side-by-side"

kmatt

set-option -g status-right '#{client_tty} (#(TZ=US/Mountain date +%%H:%%M)MT #(TZ=UTC date +%%H:%%M)Z) %Y-%m-%d %H:%M'

kmatt

# To configure for MinGW instead of nmake
#
# C:\TDM-GCC-64\mingwvars.bat
# cmake . -G "MinGw Makefiles" 
#
# Makefile: cmake ... -DCMAKE_TOOLCHAIN_FILE=TDM.cmake

set(CMAKE_SYSTEM_NAME Windows)

set(CMAKE_C_COMPILER C:/TDM-GCC-64/bin/gcc.exe)

kmatt

[cmdletbinding()]
Param(
    [Parameter(Mandatory=$true)]
    [string[]]$servers,
    
    [ValidateScript({
        if(-Not ($_ | Test-Path )) {
            throw "Folder does not exist"
        }
        return $true

kmatt

Here are some helpful commands for managing ZFS and ZPool on Ubuntu

VDEV

Useful for populating /etc/zfs/vdev_id.conf:

printDisks() {
    for i in /dev/sd[b-i]; do
        fdisk -l $i

kmatt

# Thrift is not finding Delta jars in Ivy2 cache, even when specified in spark-defaults.conf (spark.sql.catalog.spark_catalog) ?

# Probably a bad solution...

wget https://repo1.maven.org/maven2/io/delta/delta-core_2.12/2.4.0/delta-core_2.12-2.4.0.jar && \
mv delta-core_2.12-2.4.0.jar jars/

wget https://repo1.maven.org/maven2/io/delta/delta-storage/2.4.0/delta-storage-2.4.0.jar && \
mv delta-storage-2.4.0.jar jars/

kmatt

#!/bin/bash

# build/build-spark-pip.sh
# https://spark.apache.org/docs/3.4.1/building-spark.html

export MAVEN_OPTS="-Xss64m -Xmx2g -XX:ReservedCodeCacheSize=1g"

#./build/mvn -DskipTests clean package

pushd ..