Skip to content

Commit

Permalink
rev
Browse files Browse the repository at this point in the history
  • Loading branch information
@Edouard-Legoupil
Edouard-Legoupil committed Nov 30, 2023
1 parent a44639d commit 3d2b841
Show file tree
Hide file tree
Showing 6 changed files with 220 additions and 85 deletions.
14 changes: 7 additions & 7 deletions docs/learn/01.Reproducibility.Rmd
View file
Original file line number Diff line number Diff line change
Expand Up @@ -219,26 +219,26 @@ grViz("
# Connect nodes with edges and labels
X -> a [label = 'Start', fontsize= 130, penwidth = 15]
a -> 1 [label = 'Yes', fontsize= 130, penwidth = 15] ## PowerBI
a -> b [label = 'No', fontsize= 130, penwidth = 15] ## Continue
a -> 1 [label = 'Yes', fontsize= 130, penwidth = 15] # PowerBI
a -> b [label = 'No', fontsize= 130, penwidth = 15] # Continue
## Basic stat
# Basic stat
b -> c [label = 'Yes', fontsize= 130, penwidth = 15]
b -> d [label = 'No', fontsize= 130, penwidth = 15]
## Polished visuals
# Polished visuals
c -> 2 [label = 'Yes', fontsize= 130, penwidth = 15]
c -> e [label = 'No', fontsize= 130, penwidth = 15]
## Machine learning
# Machine learning
d -> e [label = 'Yes', fontsize= 130, penwidth = 15]
d -> 2 [label = 'No', fontsize= 130, penwidth = 15]
## Quick processing
# Quick processing
e -> 3 [label = 'Yes', fontsize= 130, penwidth = 15]
e -> f [label = 'No', fontsize= 130, penwidth = 15]
## Interactivity
# Interactivity
f -> 4 [label = 'Yes', fontsize= 130, penwidth = 15]
f -> 2 [label = 'No', fontsize= 130, penwidth = 15]
}
Expand Down
84 changes: 82 additions & 2 deletions docs/learn/01.Reproducibility.html
View file

Large diffs are not rendered by default.

79 changes: 39 additions & 40 deletions docs/learn/02.Tidyverse.Rmd
View file
Original file line number Diff line number Diff line change
Expand Up @@ -345,7 +345,7 @@ It provides data from three major data sources:

```{r eval=FALSE}
## 2 options to install the package
# 2 options to install the package
# From CRAN
install.packages("refugees")
Expand All @@ -354,7 +354,7 @@ install.packages("refugees")
pak::pkg_install("PopulationStatistics/refugees")
## Once installed, load the package!
# Once installed, load the package!
library(refugees)
```
Expand Down Expand Up @@ -392,18 +392,18 @@ The dplyr package provides a consistent set of verbs that include __mutate()__,
library(refugees)
library(dplyr)
## Prepare top 10 countries of origin for
# Prepare top 10 countries of origin for
# refugee and other in needs of international protection in 2022
ref_coo_10 <- refugees::population |>
dplyr::filter(year == 2022) |>
### First we define the variable to group by
# First we define the variable to group by
dplyr::group_by(coo_name) |>
## and now summarise using sum -
# and now summarise using sum -
# watch-out na.rm used to ensure NA are not considered in the sum
## If not, if you have NA , then the sum will be NA
# If not, if you have NA , then the sum will be NA
dplyr::summarise(refugees = sum(refugees, na.rm = TRUE) +
sum(oip, na.rm = TRUE) ) |>
## and now get the top 10
# and now get the top 10
dplyr::slice_max(order_by = refugees, n = 10)
```

Expand All @@ -430,9 +430,9 @@ fd_last_ten_years <- refugees::population |>
dplyr::summarise(refugees = sum(refugees, na.rm = TRUE),
asylum_seekers = sum(asylum_seekers, na.rm = TRUE),
oip = sum(oip, na.rm = TRUE),
## by defin the key to use for summarise
# by define the key to use for summarise
.by = year) |>
## and now starting the lef_join - using year
# and now starting the lef_join - using year
dplyr::left_join(refugees::idmc |>
filter(year >= 2013 & year <= 2022) |>
summarise(idmc = sum(total, na.rm = TRUE),
Expand Down Expand Up @@ -462,7 +462,7 @@ fd_last_ten_years <- refugees::population |>
```{r, echo = TRUE}
library(tidyr)
## Piping from previous steps
# Piping from previous steps
fd_last_ten_years <- fd_last_ten_years |>
tidyr::pivot_longer(cols = -year,
Expand Down Expand Up @@ -493,21 +493,21 @@ https://rstudio.github.io/cheatsheets/tidyr.pdf
```{r, echo = TRUE}
library(tidyr)
## Piping from previous steps
# Piping from previous steps
fd_last_ten_years <- fd_last_ten_years |>
## Creating new or overwriting variables with mutate
# Creating new or overwriting variables with mutate
dplyr::mutate(
## with factor we enforce a specific order to be used
# with factor we enforce a specific order to be used
population_type = forcats::fct_relevel(population_type,
"idmc", "refugees", "unrwa", "oip", "asylum_seekers"),
## Now we map this to labels
# Now we map this to labels
pop_type = dplyr::recode(population_type,
refugees="Refugees under UNHCR’s mandate",
asylum_seekers="Asylum-seekers",
oip="Other people in need of international protection",
idmc="Internally displaced persons",
unrwa="Palestine refugees under UNRWA’s mandate")) |>
## Sorting with arrange
# Sorting with arrange
dplyr::arrange(year, population_type) |>
# Renaming existing variables
dplyr::rename( pop_num = total )
Expand Down Expand Up @@ -644,8 +644,7 @@ bar_df <- refugees::population |>
slice_max(order_by = refugees, n = 10) |>
mutate(coo_name = str_wrap(coo_name, 25))
#Plot:
#Plot
# Set title and subtitle
title_bar <- "Refugees and other people in need of international protection"
subtitle_bar <- "By country of origin at the end of 2022"
Expand Down Expand Up @@ -767,12 +766,12 @@ Replicate a chart example from the [Global Trends 2022](https://www.unhcr.org/gl
fd_last_ten_years |>
# Plot
ggplot(
## Define aesthetics..
# Define aesthetics..
aes( x = as.factor(year), y = pop_num, fill = pop_type) ) +
## geometry
# geometry
geom_col( width = .7,
position = position_stack(reverse = TRUE) ) +
## Scales
# Scales
scale_y_continuous(
expand = expansion(mult = c(0, 0)),
labels = scales::label_number(scale_cut = scales::cut_short_scale()),
Expand Down Expand Up @@ -838,7 +837,7 @@ knitr::kable(head(fd_last_ten_years ),
ggplot(data = fd_last_ten_years) #<<
## this can also be written alternatively
# this can also be written alternatively
# using a pipe operator |>
fd_last_ten_years |>#<<
Expand Down Expand Up @@ -869,7 +868,7 @@ But nothing happens here because we haven't mapped the raw data to anything. SO
```{r, eval=FALSE}
ggplot(data = fd_last_ten_years,
## adding aesthetic to map the variables we will use...
# adding aesthetic to map the variables we will use...
aes( x = year, y = pop_num)) #<<
```

Expand Down Expand Up @@ -1038,11 +1037,11 @@ Before playing with `unhcthemes` let's add labels on the chart.
fd_last_ten_years |>
# Plot
ggplot(
## Define aesthetics..
# Define aesthetics..
aes( x = as.factor(year), y = pop_num) ) +
## geometry
# geometry
geom_col( ) +
## Scales
# Scales
scale_y_continuous(
expand = expansion(mult = c(0, 0)),
labels = scales::label_number(scale_cut = scales::cut_short_scale()),
Expand All @@ -1061,11 +1060,11 @@ fd_last_ten_years |>
fd_last_ten_years |>
# Plot
ggplot(
## Define aesthetics..
# Define aesthetics..
aes( x = as.factor(year), y = pop_num) ) +
## geometry
# geometry
geom_col( ) +
## Scales
# Scales
scale_y_continuous(
expand = expansion(mult = c(0, 0)),
labels = scales::label_number(scale_cut = scales::cut_short_scale()),
Expand All @@ -1090,11 +1089,11 @@ Note that you should get the lato font installed on your system
fd_last_ten_years |>
# Plot
ggplot(
## Define aesthetics..
# Define aesthetics..
aes( x = as.factor(year), y = pop_num) ) +
## geometry
# geometry
geom_col( ) +
## Scales
# Scales
scale_y_continuous(
expand = expansion(mult = c(0, 0)),
labels = scales::label_number(scale_cut = scales::cut_short_scale()),
Expand All @@ -1113,11 +1112,11 @@ fd_last_ten_years |>
fd_last_ten_years |>
# Plot
ggplot(
## Define aesthetics..
# Define aesthetics..
aes( x = as.factor(year), y = pop_num) ) +
## geometry
# geometry
geom_col( ) +
## Scales
# Scales
scale_y_continuous(
expand = expansion(mult = c(0, 0)),
labels = scales::label_number(scale_cut = scales::cut_short_scale()),
Expand All @@ -1143,11 +1142,11 @@ We remove also axis tile to increase what Edward Tufte called the [__data-ink ra
fd_last_ten_years |>
# Plot
ggplot(
## Define aesthetics..
# Define aesthetics..
aes( x = as.factor(year), y = pop_num) ) +
## geometry
# geometry
geom_col( width = .7 ) + #<<
## Scales
# Scales
scale_y_continuous(
expand = expansion(mult = c(0, 0)),
labels = scales::label_number(scale_cut = scales::cut_short_scale()),
Expand All @@ -1167,11 +1166,11 @@ fd_last_ten_years |>
fd_last_ten_years |>
# Plot
ggplot(
## Define aesthetics..
# Define aesthetics..
aes( x = as.factor(year), y = pop_num) ) +
## geometry
# geometry
geom_col( width = .7 ) +
## Scales
# Scales
scale_y_continuous(
expand = expansion(mult = c(0, 0)),
labels = scales::label_number(scale_cut = scales::cut_short_scale()),
Expand Down
84 changes: 58 additions & 26 deletions docs/learn/02.Tidyverse.html
View file

Large diffs are not rendered by default.

10 changes: 5 additions & 5 deletions docs/learn/03.Functions.Rmd
View file
Original file line number Diff line number Diff line change
Expand Up @@ -61,10 +61,10 @@ An Example of a __Script__
# Data example
data <- c(1, 2, 3, 4, 5)
## Apply mean to data
# Apply mean to data
mean_value <- mean(data)
## Display the result
# Display the result
print(mean_value)
```

Expand All @@ -86,10 +86,10 @@ calculate_mean <- function(data) {
# Data example
data <- c(1, 2, 3, 4, 5)
## Apply mean to data
# Apply mean to data
mean_value <- calculate_mean(data)
## Display the result
# Display the result
print(mean_value)
```
Expand Down Expand Up @@ -144,7 +144,7 @@ Let's see the steps in details:
# Custom function to calculate the median of a numeric vector
calculate_median <- function(data) {
## 1. Takes an input: here data...
# 1. Takes an input: here data...
median_value <- median(data)
# 2. Apply a transformation: here apply another function called median
Expand Down
Loading

0 comments on commit 3d2b841

Please sign in to comment.