#!/usr/bin/env python
# coding: utf-8

# # *Statistics coded*: Young people - social inclusion 
# 
# Prepared by [**J.Grazzini**](mailto:jacopo.grazzini@ec.europa.eu) (*Eurostat*).
# 
# This notebook illustrates the principles of storytelling through literate programming by reproducing some of the figures of the _Statistics Explained_article on [**young people and social inclusion**](https://ec.europa.eu/eurostat/statistics-explained/index.php?title=Young_people_-_social_inclusion). 

# In[38]:


library("eurostat") 
library("ggplot2")
library("tidyr")


# In[2]:


library(repr)
options(repr.plot.width=8, repr.plot.height=3)


# In[60]:


id = "ilc_li02"
# id <-search_eurostat("At-risk-of-poverty rate by poverty threshold, age and sex")$code[1]
dat <-get_eurostat(id, time_format = "num", filters = list(age="Y16-29", time="2017", unit="PC"))
head(dat)


# In[17]:


ctries <- c("EU28", "DK", "RO", "ES", "EL", "IT", "SE", "BG", "LU", "PT", "NL", "DE", "FI", "IE", "BE", "FR", "EE", "AT", "UK", "PL", "HR", "CY", "LV", "HU", "SK", "MT", "SI", "CZ", "NO", "CH", "IS", "RS", "MK", "TR")


# In[18]:


p<-ggplot(data=subset(dat, indic_il == "LI_R_MD60" & sex == "T" & geo %in% ctries), 
              aes(x=reorder(geo, -values), y=values)) +
 geom_bar(stat="identity", fill="orange") +
 xlab("Share of young people (aged 16-29 years) at risk of poverty, 2017") +
 ylab("(%)") 
print(p)


# In[19]:


id = "ilc_lvps08"
# id <-search_eurostat("Share of young adults aged 18-34 living with their parents by age and sex", fixed = TRUE)$code[1]
dat <-get_eurostat(id, time_format = "num", filters = list(time="2017", unit="PC"))
head(dat)


# In[20]:


p<-ggplot(data=subset(dat, geo %in% ctries & sex %in% c("F", "M") & age == "Y16-29"), 
              aes(x=reorder(geo, -values), y=values, fill=sex)) +
 geom_bar(stat="identity", position=position_dodge()) +
 xlab("Share of young people (aged 16-29 years) living with their parents, 2017") +
 ylab("(%)") 
print(p)


# In[23]:


p<-ggplot(data=subset(dat, geo %in% ctries & sex == "T" & age %in% c("Y16-29","Y20-24","Y25-29")), 
              aes(x=reorder(geo, -values), y=values, fill=sex, col=age)) +
 geom_point() +
 xlab("Share of young people (aged 16-29 years) living with their parents, 2017") +
 ylab("(%)") 
print(p)


# In[58]:


id = "ilc_peps01"
# id <-search_eurostat("People at risk of poverty or social exclusion by age and sex")$code[1]
dat <-get_eurostat(id, time_format = "num", filters=list(unit="PC", geo="EU28", age="Y16-29"))
head(dat)


# In[59]:


p<-ggplot(data=dat, aes(x=time, y=values, group=sex)) +
 geom_point() +
 xlab("Share of young people (aged 16-29 years) at risk of poverty or social exclusion, EU-28, 2007-2017 - by sex") +
 ylab("(%)") 
print(p)


# In[68]:


id = "ilc_li02"
# id <-search_eurostat("At-risk-of-poverty rate by poverty threshold, age and sex", fixed = TRUE)$code[1]
dat <-get_eurostat(id, time_format = "num", filters = list(unit="PC", geo="EU28", indic_il="LI_R_MD60", sex="T", age=c("Y16-29","Y20-24","Y25-29")))
head(dat)


# In[69]:


p<-ggplot(data=dat, aes(x=time, y=values, group=age)) +
 geom_point() +
 xlab("Share of young people at risk of poverty, EU-28, 2007-2017 - by age") +
 ylab("(%)") 
print(p)


# In[73]:


id = "yth_incl_060"
# id <-search_eurostat("Young people's at-risk-of-poverty rate by sex, age and living/not living with parents", fixed = TRUE)$code[1]
dat <-get_eurostat(id, time_format = "num", filters = list(time="2016"))
head(dat)


# In[74]:


p<-ggplot(data=subset(dat, geo %in% ctries & age == "Y16-29"), 
              aes(x=reorder(geo, -values), y=values, fill=hhstatus)) +
 geom_bar(stat="identity", position=position_dodge()) +
 xlab("Share of young people (aged 16-29 years) at risk of poverty, 2016 - by HH status") +
 ylab("(%)") 
print(p)


# In[ ]: