gonzalezgouveia

import pandas as pd
import numpy as np

# data from Repo https://github.com/marcboquet/spanish-names
name_men = pd.read_csv('./hombres.csv')
name_men_list = name_men['nombre'].tolist()
name_women = pd.read_csv('./mujeres.csv')
name_women_list = name_women['nombre'].tolist()

gonzalezgouveia

# install.packages(gganimate)
library(gganimate)
# devtools::install_github('rensa/ggflags')
library(ggflags)
# install.packages("gifski")
library(gifski)

# define animation object
anim <- gapminder_hispam %>%
  filter(year >= 1900) %>%

gonzalezgouveia

# Filter for HispAm countries
hispam_vec <- c(
  'Argentina', 'Brazil', 'Bolivia', 'Chile', 'Colombia',
  'Costa Rica', 'Cuba', 'Dominican Republic', 'Ecuador', 
  'El Salvador', 'Guatemala', 'Honduras', 'Mexico', 
  'Nicaragua', 'Panama', 'Paraguay', 'Peru', 'Uruguay',
  'Spain', 'Puerto Rico', 'Venezuela' )

# dplyr::filter countries in hispam
######

gonzalezgouveia

library(tidyverse)

gdpPercap <- read_csv('/path/to/data/income_..._adjusted.csv'))
lifeExp <- read_csv('/path/to/data/life_expectancy_years.csv'))

gonzalezgouveia

// Run Inspector Console in chrome and copy and paste the following code in the /stats/stories view

function download(filename, text) {
    var pom = document.createElement('a');
    pom.setAttribute('href', 'data:text/plain;charset=utf-8,' + encodeURIComponent(text));
    pom.setAttribute('download', filename);

    if (document.createEvent) {
        var event = document.createEvent('MouseEvents');
        event.initEvent('click', true, true);

gonzalezgouveia

path_trelliscope <- "./path/to/folder/trelliscope/"
ggplot(clean_data, 
       aes(x=log(price), y=points)) +
  geom_point() + 
  geom_smooth(method=lm, se = FALSE) +
  facet_trelliscope(~ country, nrow = 1, ncol = 3,
                    path = path_trelliscope,
                    self_contained=TRUE)

gonzalezgouveia

all_models <- clean_data %>% 
  group_by(country) %>% 
  summarise(n_obs = n(),
            b = lm(points ~ log(price))$coefficients[1],
            m = lm(points ~ log(price))$coefficients[2]) 

gonzalezgouveia

set.seed(12321)
ggplot(sample_n(clean_data, size=1000),
       aes(x=jitter(log_price, factor = 3), 
           y=jitter(points, factor = 3), 
           color=country)) + 
  geom_point(size=2) +
  xlab('log(Precio)') + 
  ylab('Puntuación') +
  ggtitle('Revisiones de vinos por país')
ggsave('./path/to/data/clean_wine_country.png')

gonzalezgouveia

clean_data <- winedata %>%
  select(country, points, price) %>%
  drop_na() %>%                        # quitando los nulos
  group_by(country) %>%
  filter(n()>2000) %>%                 # filtrando
  ungroup() %>%
  mutate(log_price = log(price))       # log price

gonzalezgouveia

set.seed(12321)
ggplot(sample_n(winedata, size=10000), 
       aes(x=price, 
           y=jitter(points, factor = 3), 
           color=country)) + 
  geom_point(size=2) + 
  xlab('Precio') + 
  ylab('Puntuación') +
  ggtitle('Exploración por país')
ggsave('./path/to/data/all_wine_country.png')