mrk-andreev

This gist lets you keep IPython notebooks in git repositories. It tells git to ignore prompt numbers and program outputs when checking that a file has changed.

To use the script, follow the instructions given in the script's docstring.

For further details, read this blogpost.

The procedure outlined here is inspired by this answer on Stack Overflow.

mrk-andreev

This gist lets you keep IPython notebooks in git repositories. It tells git to ignore prompt numbers and program outputs when checking that a file has changed.

To use the script, follow the instructions given in the script's docstring.

For further details, read this blogpost.

The procedure outlined here is inspired by this answer on Stack Overflow.

mrk-andreev

// ==UserScript==
// @name         JupyterExt
// @namespace    http://tampermonkey.net/
// @version      0.1
// @description
// @author       mrk-andreev
// @match        http://localhost:8888/notebooks/*
// @grant        none
// ==/UserScript==

mrk-andreev

// ==UserScript==
// @name         JupyterUserscript
// @version      0.1
// @author       Mark Andreev
// ==/UserScript==

(function() {
    'use strict';

    var YOUR_NAME = 'Mark,';

mrk-andreev

select concat(database, '.', table)                         as table,
       formatReadableSize(sum(bytes))                       as size,
       sum(rows)                                            as rows,
       max(modification_time)                               as latest_modification,
       sum(bytes)                                           as bytes_size,
       any(engine)                                          as engine,
       formatReadableSize(sum(primary_key_bytes_in_memory)) as primary_keys_size
from system.parts
where active
group by database, table

mrk-andreev

object PlaygroundUtil {
 def in(main: DataFrame, dict: DataFrame, joinColumn: String): DataFrame = {
   main.join(dict, Seq(joinColumn), "left_semi")
 }

 def notIn(main: DataFrame, dict: DataFrame, joinColumn: String): DataFrame = {
   main.join(dict, Seq(joinColumn), "left_anti")
 }
}

mrk-andreev

test("in") {
 # main = createDataDataset(Seq(Data("a", "Berlin"), Data("b", "Madrid"), Data("c", "Rome")))
 # dict = createDictDataset(Seq(Dict("a"), Dict("b")))
 val result = main.join(dict, Seq("index"), "left_semi")
 val expected = createDataDataset(Seq(
   Data("a", "Berlin"), Data("b", "Madrid"))).orderBy("index")

 assert(result.schema === expected.schema)
 assert(result.collect() === expected.toDF().collect())
}