korkridake

polynoteuser02@polynotevm02:~$ sudo docker pull greglinscheid/polynote
polynoteuser02@polynotevm02:~$ sudo docker run -p 8192:8192 -v $HOME/poly-notes:/usr/src/app/polynote/notebooks — name=polynote -d -t greglinscheid/polynote:latest
polynoteuser02@polynotevm02:~$ sudo docker logs -f polynote

korkridake

# Setup the Docker Repository
polynoteuser02@polynotevm02:~$ sudo apt-get update
polynoteuser02@polynotevm02:~$ sudo apt-get install apt-transport-https ca-certificates curl software-properties-common
polynoteuser02@polynotevm02:~$ curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo apt-key add -
polynoteuser02@polynotevm02:~$ sudo add-apt-repository "deb [arch=amd64] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" 

# Install Docker CE
polynoteuser02@polynotevm02:~$ sudo apt-get update
polynoteuser02@polynotevm02:~$ sudo apt-get install docker-ce

korkridake

######################################################################################
# Set the configurations. Here's what you need:
## 1.) Client ID (a.k.a Application ID)
## 2.) Client Secret (a.k.a. Application Secret)
## 3.) Directory ID
## 4.) File System Name
## 5.) Storage Account Name
## 6.) Mount Name
######################################################################################
configs = {"fs.azure.account.auth.type": "OAuth",

korkridake

#######################################################################
# This is Kyle's Python script for Data Quality Assessment
# Assume df = your dataframe
# Replace "df" with "[Your Dataframe]"
#######################################################################

#######################################################################
# Check summary statistics
#######################################################################
df.describe()

korkridake

##############################################################################
# Tesseract Optical Character Recognition (OCR) Engine of Tesco Receipts (Ep.1)
# Author: @Kyle Akepanidtaworn
# Source Code: Using the Tesseract OCR engine in R (2018)
# Created Date: 5/19/2019
##############################################################################
# install.packages("tesseract")
library(tesseract)
eng <- tesseract("eng")

korkridake

{
    "$schema": "http://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#",
    "contentVersion": "1.0.0.0",
    "parameters": {
        "location": {
            "type": "string"
        },
        "storageAccountName": {
            "type": "string"
        },

korkridake

az vm get-instance-view \
  --name myVM \
  --resource-group myResourceGroup \
  --output table

korkridake

az vm create \ 
  --name myVM \ ### This name identifies the VM in Azure. It also becomes the VM's internal hostname, or computer name.
  --resource-group MyResourceGroup \ ### The resource group, or the VM's logical container, is named MyResourceGroup.
  --image UbuntuLTS \ ### UbuntuLTS specifies the Ubuntu 18.04 LTS VM image.
  --location southeastasia \
  --size Standard_DS2_v2 \ ### Standard_DS2_v2 refers to the size of the VM. This size has two virtual CPUs and 7 GB of memory.
  --admin-username kyleake \ ### specify "kyleake" as the username for the VM. The username can be whatever you want.
  --generate-ssh-keys ### create an SSH key pair to enable you to log in to the VM.

korkridake

# ---------------------------------------------------------------------------------------------
# Import Libraries
# ---------------------------------------------------------------------------------------------
from pyspark.sql.functions import col, floor, translate, round
from pyspark.ml import Pipeline
from pyspark.ml.feature import VectorAssembler, OneHotEncoder
from pyspark.ml.regression import LinearRegression

# ---------------------------------------------------------------------------------------------
# Load Input Data with PySpark

korkridake

# --------------------------------------------------------------------------------
# Introducing Spark DataFrames
# --------------------------------------------------------------------------------
# Create some Spark DFs
df = spark.range(1000).toDF("number")
display(df)

# Summary statistics
df.describe().show()