library("tidyverse")
library("scales")
library("gridExtra")
library("fBasics")
library("xtable")

age_gaps <- read.csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2023/2023-02-14/age_gaps.csv")

movies <- read.csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-03-09/movies.csv")

bechdel_ratings <- read.csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-03-09/raw_bechdel.csv")

# Create a count of observations for each pair of release_year and age_difference values
age_gaps_count <- age_gaps %>%
count(release_year, age_difference, name = "count") %>%
ungroup() # not perfectly sure about this one actually, but it works :D

# I think it’s used to make sure every single observation is assigned a value
# Add the count variable to the age_gaps dataset
age_gaps <- age_gaps %>%
left_join(age_gaps_count, by = c("release_year", "age_difference"))

# Plot age gaps against release years
Age_Gaps_in_Romantic_Movies_by_Year <- ggplot(age_gaps, aes(x = release_year,
y = age_difference)) +
geom_point(aes(size = count), color = "dodgerblue") + # create scatterplot
labs(x = "Release Year", y = "Age Gap") +
ggtitle("Age Gaps in Romantic Movies by Year") +
theme_minimal() +
geom_smooth(method = "lm", color = "orange") # include regression line

# Save the plot as a pdf vector graphic
# ggsave("Age_Gaps_in_Romantic_Movies_by_Year.pdf", plot = Age_Gaps_in_Romantic_Movies_by_Year, device = "pdf")

Age_Gaps_in_Romantic_Movies_by_Year

# import libraries
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np

# load movies table
movies = pd.read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-03-09/movies.csv')
# select relevant columns
movies = movies[['year','clean_test']]
# rename test column
movies = movies.rename(columns={'clean_test':'bechdel_test'})
# movies.head()

# bins that represent the years = x axis
bins = np.arange(1969,2014,1)

# Bechdel classes and their label and color used in graphic
bechdel_list = [
('dubious','Dubious','slategray'),
('nowomen','No two women','darkred'),
('notalk',"Women don't talk",'indianred'),
('men','Women talk only about men','lightcoral'),
('ok','Bechdel test passed','cornflowerblue')
]

# create subplots
fig, axs = plt.subplots(5, 1, sharex=True, sharey=True, figsize=(11.69,8.27),gridspec_kw={'wspace': 0.1, 'hspace': 0.1}) # a4 figsize

# set title and subtitle of figure
fig.suptitle('Evolution of representation of women in movies', fontsize=20, color='black')
fig.text(0.5, 0.94, 'Comparison of the Bechdel test classes over time',fontsize=15, ha='center', va='top', color='dimgray')

# set background color of figure
fig.set_facecolor(color='gainsboro')

# common axes labels
# add a big axis, hide frame
fig.add_subplot(111, frameon=False)

# hide tick and tick label of the big axes
plt.tick_params(labelcolor='none', top=False, bottom=False, left=False,right=False)

# set axes names
plt.xlabel('Year', color='dimgray', fontsize='x-large')
plt.ylabel('Number of movies', color='dimgray', fontsize='x-large')

# set axis limits and values for first axis (axes are shared so it influences all axes)
axs[0].set(
xlim=(1970, 2013), ylim=(0, 80),
xticks=range(1970,2020,10), yticks=(0, 50)
)

# iterate over all axes and bechdel classes stated before
for ax, (bechdel_result, label, color) in zip(axs.flat, bechdel_list):
  
  # calculate the count of movies in that class per year
  bechdel_counts = movies[movies['bechdel_test']==bechdel_result]['year'].value_counts(sort=False, bins=bins)
  # plot the data
  ax.fill_between(bins[1:], bechdel_counts, color=color,edgecolor='lightgray')
  # change font family of x and y axis
  for tick in ax.get_xticklabels():
    tick.set_fontproperties('Courier New')
  for tick in ax.get_yticklabels():
    tick.set_fontproperties('Courier New')
  # adjust label size and color
  ax.tick_params(axis='both', direction='inout', labelsize='medium',labelcolor='dimgray')
  # show label of bechdel result group
  ax.text(0.02, 0.9, label, fontsize='x-large',transform=ax.transAxes, va='top', color=color)
  
# save figure as pdf in local directory
# plt.savefig('graphic.pdf', format='pdf')

# show the graphic
plt.show()

# Get the Data

# Read in with tidytuesdayR package 
# Install from CRAN via: install.packages("tidytuesdayR")
# This loads the readme and all the datasets for the week of interest

# Either ISO-8601 date or year/week works!

tuesdata <- tidytuesdayR::tt_load('2021-03-23')
tuesdata <- tidytuesdayR::tt_load(2021, week = 13)

unvotes <- tuesdata$unvotes

# Or read in the data manually

unvotes <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-03-23/unvotes.csv')
roll_calls <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-03-23/roll_calls.csv')
issues <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-03-23/issues.csv')

import pandas as pd

unvotes = pd.read_csv(
  'https://raw.githubusercontent.com/rfordatascience/'\
  'tidytuesday/master/data/2021/2021-03-23/unvotes.csv')
roll_calls = pd.read_csv(
  'https://raw.githubusercontent.com/rfordatascience/'\
  'tidytuesday/master/data/2021/2021-03-23/roll_calls.csv')
issues = pd.read_csv(
  'https://raw.githubusercontent.com/rfordatascience/'\
  'tidytuesday/master/data/2021/2021-03-23/issues.csv')