xiaodaigh

# to run this firstly set up the MinIO server
# on Windows download this https://dl.min.io/server/minio/release/windows-amd64/minio.exe
# download("https://dl.min.io/server/minio/release/windows-amd64/minio.exe")

# to run minio make sure the executable is in the PATH
# then run
# ;minio.exe server /path/to/minio/data
# e.g. minio.exe server c:/minio-data/

using Minio, Parquet, Parquet2, DataFrames, AWSS3

xiaodaigh

using Gumbo, Cascadia, HTTP
using Serialization

urls= ["https://www.shicimingju.com/shicimark/tangshisanbaishou.html"]
urls = vcat(urls, ["https://www.shicimingju.com/shicimark/tangshisanbaishou_$(i)_0__0.html" for i in 2:16])


function get_chars(poem::Vector{<:AbstractString})::Set{Char}
    mapreduce(Set, union, poem)
end

xiaodaigh

using Revise
includet("utils.jl")

function remove_player!(team)
    if length(team) == 1
        team.players = []
    else
        team.players = team.players[2:end]
    end
    team

xiaodaigh

struct Player
    name::String
    rating::Int
end


struct Match
    best_of::Int
end

xiaodaigh

x = rand(1:1_000_000, 1_000_000_000)

using SortingLab
fsort!(x)

function unroll_loop(x)
    count = 0

    @inbounds count += x[1] != x[2]
    @inbounds count += x[2] != x[3]

xiaodaigh

using DataFrames

df1 = DataFrame(a = repeat([1], 100), b = "a")
df2 = DataFrame(a = repeat([2], 100), b = "b")

B = Array{Bool, 2}(undef, 100, 2)

df1[B] # doesn't work

# Let's overload get index get index

xiaodaigh

FROM python:3.7-alpine3.10

RUN apk add --no-cache \
            build-base \
            cmake \
            bash \
            boost-dev \
            autoconf \
            zlib-dev \
            flex \

xiaodaigh

apt-get update && apt-get upgrade -y
apt-get install wget -y
apt-get install proot -y
apt-get install git -y
cd ~
git clone https://github.com/MFDGaming/ubuntu-in-termux.git
cd ubuntu-in-termux
chmod +x ubuntu.sh
./ubuntu.sh
cp ~/ubuntu-in-termux/resolv.conf ~/ubuntu-in-termux/ubuntu-fs/etc/

xiaodaigh

library(data.table)
library(disk.frame)
setup_disk.frame()

bench_disk.frame_data.table_group_by <- function(data1,n) {
  setDT(data1)
  
  a.sharded.df = as.disk.frame(data1, shardby = c("year", "month", "day"))
  a.not_sharded.df = as.disk.frame(data1)
  

xiaodaigh

using CSV, Feather
#using JLD2
#using JLD#, JLSO
using JDF, FileIO, Blosc, StatsPlots, RCall
using DataFrames, WeakRefStrings # required for JLD2, JDF
Blosc.set_num_threads(6)

gen_benchmark(dirpath, largest_file, outpath, data_label; delim = ',', header=true) = begin
    if !isdir(outpath)
        mkpath(outpath)