nonsleepr

#!/usr/bin/bash

# Requires:
# - xmlstarlet
# - gawk
# - wget
# - xargs

wget -qO - http://techtv.mit.edu/collections/compu-camera/videos.rss | \
xmlstarlet sel -t -m '//item' -v 'link' -o ',' -v 'enclosure/@url' -n | \

nonsleepr

nonsleepr

#!/bin/bash
 
#
# Usage:
#    > futurelearn_dl.sh [email protected] password course-name week-id
# Where *[email protected]* and *password* - your credentials
# ,*course-name* is the name from URL
# and *week-id* is the ID from the URL
#
# E.g. To download all videos from the page: https://www.futurelearn.com/courses/corpus-linguistics/todo/238

nonsleepr

-- Via http://forums.teradata.com/forum/database/dense-rank

SELECT
    department_number,
    /*** Syntax not implemented in Teradata ***/
    DENSE_RANK() OVER (PARTITION BY department_number ORDER BY salary_amount),
    last_name,
    salary_amount
FROM employee;

nonsleepr

### Set of functions to download datasets from Kaggle

# Usage:
#   
#   > train <- kaggle_get_file("train.csv",
#   +                          competition.name = "titanic-gettingStarted",
#   +                          username = "username",
#   +                          password = "password")
#
#   > head(train, n = 2)

nonsleepr

require(plyr)

kfold <- function(df, k, train.f, predict.f) {
  progress.bar <- create_progress_bar("text")
  progress.bar$init(k)
  
  N <- nrow(df)
  subsample.id <- sample(1:k, N, replace = TRUE)
  r <- vector(length = N)
  

nonsleepr

ngrams.tokenizer <- function(x, n = 2) {
  trim <- function(x) gsub("(^\\s+|\\s+$)", "", x)
  terms <- strsplit(trim(x), split = "\\s+")[[1]]
  ngrams <- vector()
  if (length(terms) >= n) {
    for (i in n:length(terms)) {
      ngram <- paste(terms[(i-n+1):i], collapse = " ")
      ngrams <- c(ngrams,ngram)
    }
  }

nonsleepr

# Requires presence of credentials.txt file containing login/password in the following format:
# UserName=my_username&Password=my_password

COMPETITION=diabetic-retinopathy-detection

all: download_files

session.cookie: credentials.txt
        curl -o /dev/null -c session.cookie https://www.kaggle.com/account/login
        curl -o /dev/null -c session.cookie -b session.cookie -L -d @credentials.txt https://www.kaggle.com/account/login

nonsleepr

import trio

from multiplexer import Multiplexer

async def reader(mx, key, timeout=100):
    print(f'Waiting for "{key}"...')
    try:
        with trio.fail_after(timeout):
            value = await mx[key]
            print(f'Got value "{value}" for key {key}')

nonsleepr

Keybase proof

I hereby claim:

• I am nonsleepr on github.

• I am nonsleepr (https://keybase.io/nonsleepr) on keybase.

• I have a public key ASD2K73fCmJ6Ruf8af6CwpPQKYiBD3vk2tdhKIG1qydczgo