dplyr and torrents from cpasbien

romainfrancois 2,865 views 32 slides Sep 30, 2016
Slide 1
Slide 1 of 32
Slide 1
1
Slide 2
2
Slide 3
3
Slide 4
4
Slide 5
5
Slide 6
6
Slide 7
7
Slide 8
8
Slide 9
9
Slide 10
10
Slide 11
11
Slide 12
12
Slide 13
13
Slide 14
14
Slide 15
15
Slide 16
16
Slide 17
17
Slide 18
18
Slide 19
19
Slide 20
20
Slide 21
21
Slide 22
22
Slide 23
23
Slide 24
24
Slide 25
25
Slide 26
26
Slide 27
27
Slide 28
28
Slide 29
29
Slide 30
30
Slide 31
31
Slide 32
32

About This Presentation

dplyr presentation at the Paris meetup Raddicts.
using data from the package cpasbien that scraps information from the website of the same name.


Slide Content

dplyr
[email protected]
Romain François

... $ wc -l R/*.R | tail -n1
3576 total
$ wc -l src/*.cpp | tail -n1
4908 total
$ wc -l **/*.h | tail -n1
8908 total

dis playa

DEEP LIAR

%>%
(païpe)

verbe( sujet, complement )
sujet %>% verbe( complement )

enjoy(cool(bake(shape(beat(append(bowl(rep("flour",
2), "yeast", "water", "milk", "oil") , "flour", until
= "soft"), duration = "3mins"), as = "balls", style =
"slightly-flat"), degrees = 200, duration =
"15mins"), duration = "5mins"))
bowl(rep("flour", 2), "yeast", "water", "milk", "oil") %>%
append("flour", until = "soft") %>%

beat(duration = "3mins") %>%

shape(as = "balls", style = "slightly-flat") %>%

bake(degrees = 200, duration = "15mins") %>%

cool(buns, duration = "5mins") %>%
enjoy()

Vocabulary

filter
x y
purple 2
purple 3
red 4
red 5
purple 6
yellow 7
yellow 8
x y
purple 2
purple 3
purple 6
data %>% filter( x == "purple" )

mutate
x y
purple 2
purple 3
red 4
red 5
purple 6
yellow 7
yellow 8
data %>% mutate( y = y*2, z = nchar(x) )
x y z
purple 4 6
purple 6 6
red 8 3
red 10 3
purple 12 6
yellow 14 6
yellow 16 6

select
x y
purple 2
purple 3
red 4
red 5
purple 6
yellow 7
yellow 8
data %>% select( x )
x
purple
purple
red
red
purple
yellow
yellow

arrange
x y
purple 2
purple 3
red 4
red 5
purple 6
yellow 7
yellow 8
data %>% arrange( desc(x) )
x y
yellow 8
yellow 7
purple 6
red 5
red 4
purple 3
purple 2

group_by
x y
purple 2
purple 3
red 4
red 5
purple 6
yellow 7
yellow 8
x y
purple 2
purple 3
purple 6
data %>% group_by( x )
x y
red 4
red 5
x y
yellow 7
yellow 8

summarise
x y
purple 2
purple 3
red 4
red 5
purple 6
yellow 7
yellow 8
summarise( data, z = min(y) )
z
2

group_by + summarise
x y
purple 2
purple 3
red 4
red 5
purple 6
yellow 7
yellow 8
x y
purple 2
purple 3
purple 6
data %>% group_by( x )%>% summarise( z = max(y) )
x y
red 4
red 5
x y
yellow 7
yellow 8
x z
purple 6
red 5
yellow 8

Mise en garde :
comme son nom
l'indique ...

install_github( "romainfrancois/cpasbien" )
library("cpasbien")
movies <- get_all_movies( pages = 1:20 )
episodes <- get_all_episodes( pages = 1:20 )

> glimpse( movies )
Observations: 600
Variables: 11
$ type <chr> "policiers-thrillers", "policiers-thrillers", "policiers-thr...
$ title <chr> "Oppression", "Oppression", "Oppression", "Oppression", "Ret...
$ year <chr> "2016", "2016", "2016", "2016", "2016", "2016", "2016", "201...
$ lang <chr> "french", "french", "french", "french", "french", "french", ...
$ quality <chr> "dvdrip", "dvdrip-x264", "bluray-1080p", "bluray-720p", "dvd...
$ size <dbl> 710, 345, 7885, 4506, 701, 632, 696, 701, 1434, 4710, 1434, ...
$ up <dbl> 2928, 285, 223, 330, 5541, 522, 2329, 8362, 4835, 1157, 261,...
$ down <dbl> 188, 18, 62, 54, 236, 17, 90, 400, 452, 159, 27, 29, 126, 66...
$ torrent <chr> "http://www.cpasbien.cm/telechargement/oppression-french-dvd...
$ poster <chr> "http://www.cpasbien.cm/_pictures/oppression-french-dvdrip-2...
$ href <chr> "http://www.cpasbien.cm/dl-torrent/films/policiers-thrillers ...
> glimpse( episodes )
Observations: 569
Variables: 11
$ show <chr> "NCIS New Orleans ", "Hawaii 5-0 (2010) ", "Van Helsing ", "...
$ season <dbl> 2, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 3, 27, 27, 1, 2, 4, 1, 3, 3...
$ episode <dbl> 17, 1, 2, 12, 11, 10, 2, 6, 5, 1, 4, 2, 3, 2, 1, 2, 1, 1, 1,...
$ lang <chr> "french", "vostfr", "vostfr", "french", "french", "french", ...
$ quality <chr> "hdtv", "hdtv", "hdtv", "hdtv", "hdtv", "hdtv", "hdtv", "hdt...
$ size <dbl> 351, 367, 356, 344, 348, 336, 230, 346, 346, 368, 347, 347, ...
$ up <dbl> 131, 204, 717, 1143, 1081, 1222, 235, 700, 658, 295, 648, 38...
$ down <dbl> 22, 20, 45, 144, 132, 154, 14, 49, 61, 20, 48, 18, 4, 5, 32,...
$ torrent <chr> "http://www.cpasbien.cm/telechargement/l-m-n/ncis-new-orlean...
$ poster <chr> "http://www.cpasbien.cm/_pictures/l-m-n/ncis-new-orleans-s02...
$ href <chr> "http://www.cpasbien.cm/dl-torrent/series/l-m-n/ncis-new-orl...

Les comédies les plus
téléchargées en ce moment
en qualité dvdrip

Les comédies les plus
téléchargées en ce moment
en qualité dvdrip
movies %>%
filter(
grepl( "comedies", type ),
quality == "dvdrip"
) %>%
arrange( desc(down) )

Les films d'animation
en meilleure qualité possible
(mais pas dvdscr)
en français

movies %>%
filter(
grepl("animation", type),
lang == "french",
quality != "dvdscr"
) %>%
select(-type, -lang) %>%
group_by(title) %>%
filter(size == max(size))

Le dernier episode disponible de
chaque série en VO

episodes %>%
filter( lang == "vostfr" ) %>%
group_by( show ) %>%
filter( season == max(season) ) %>%
filter( episode == max(episode) ) %>%
arrange(desc(up))
Le dernier episode disponible de
chaque série en VO

episodes %>%
filter( lang == "vostfr" ) %>%
group_by( show ) %>%
filter( season == max(season) ) %>%
filter( episode == max(episode) ) %>%
filter( episode == 1 ) %>%
arrange( desc(up) )
... les séries d'automne ...

Questions ?
[email protected]

Demo
library("cpasbien")
library("shiny")
runApp( system.file("app", package = "cpasbien") )