# Start by running this code chunk to make sure you have all the libraries installed that we might need.

list.of.packages <- c("datasets","ggplot2","fBasics","grid","gridExtra")

new.packages <- list.of.packages[!(list.of.packages %in% installed.packages()[,"Package"])]

if(length(new.packages)) install.packages(new.packages,repos="https://cloud.r-project.org")

# to install from github
# if(!("" %in% installed.packages()[,"Package"])){
#  remotes::install_github("")
# }

# if your into problems, it can be helpful to update all packages, by running this (attention, this may take some time)
# install.packages(list.of.packages)

# or a specific one
# install.packages("gtrendsR")

for(each in list.of.packages){
  library(each, character.only = T)
}

# or
# sapply(list.of.packages, library, character.only = TRUE)

anscombe <- datasets::anscombe

anscombe

fBasics::basicStats(anscombe)

# Mean
sapply(1:8, function(x) mean(anscombe[ , x]))

# Correlation
round(sapply(1:4, function(x) cor(anscombe[ , x], anscombe[ , x+4])),2)

create_plot <- function(dataset_x,dataset_y,size_points=4,size_text=21){
  ggplot(anscombe,
         aes({{ dataset_x }},{{ dataset_y }})) +
  geom_point(
    size = size_points) +
  geom_smooth(method="lm", se=F, fullrange = TRUE,
              color="darkgrey") +
  scale_x_continuous(
    breaks = seq(0,20,2)) +
  scale_y_continuous(
    breaks = seq(0,14,2)) +
  expand_limits(x = c(0,20), y = c(0,14)) +
  labs(x = deparse(substitute(dataset_x)),
       y = deparse(substitute(dataset_y))) +
  theme_bw() +
  theme(text=element_text(size=size_text))
}

size_points <- 2.5

size_text <- 14

grid.arrange(grobs = list(
  create_plot(x1,y1,size_points,size_text),
  create_plot(x2,y2,size_points,size_text),
  create_plot(x3,y3,size_points,size_text),
  create_plot(x4,y4,size_points,size_text)), 
             ncol = 2, 
             top = textGrob("Anscombe's Quartet",
                            gp=gpar(fontsize=21, font=8)))

import matplotlib.pyplot as plt
import numpy as np

x = [10, 8, 13, 9, 11, 14, 6, 4, 12, 7, 5]
y1 = [8.04, 6.95, 7.58, 8.81, 8.33, 9.96, 7.24, 4.26, 10.84, 4.82, 5.68]
y2 = [9.14, 8.14, 8.74, 8.77, 9.26, 8.10, 6.13, 3.10, 9.13, 7.26, 4.74]
y3 = [7.46, 6.77, 12.74, 7.11, 7.81, 8.84, 6.08, 5.39, 8.15, 6.42, 5.73]
x4 = [8, 8, 8, 8, 8, 8, 8, 19, 8, 8, 8]
y4 = [6.58, 5.76, 7.71, 8.84, 8.47, 7.04, 5.25, 12.50, 5.56, 7.91, 6.89]

datasets = {
    'I': (x, y1),
    'II': (x, y2),
    'III': (x, y3),
    'IV': (x4, y4)
}

fig, axs = plt.subplots(2, 2, sharex=True, sharey=True, figsize=(6, 6),
                        gridspec_kw={'wspace': 0.08, 'hspace': 0.08})
axs[0, 0].set(xlim=(0, 20), ylim=(2, 14))
axs[0, 0].set(xticks=(0, 10, 20), yticks=(4, 8, 12))

for ax, (label, (x, y)) in zip(axs.flat, datasets.items()):
    ax.text(0.1, 0.9, label, fontsize=20, transform=ax.transAxes, va='top')
    ax.tick_params(direction='in', top=True, right=True)
    ax.plot(x, y, 'o')

    # linear regression
    p1, p0 = np.polyfit(x, y, deg=1)  # slope, intercept
    ax.axline(xy1=(0, p0), slope=p1, color='r', lw=2)

    # add text box for the statistics
    stats = (f'$\\mu$ = {np.mean(y):.2f}\n'
             f'$\\sigma$ = {np.std(y):.2f}\n'
             f'$r$ = {np.corrcoef(x, y)[0][1]:.2f}')
    bbox = dict(boxstyle='round', fc='blanchedalmond', ec='orange', alpha=0.5)
    ax.text(0.95, 0.07, stats, fontsize=9, bbox=bbox,
            transform=ax.transAxes, horizontalalignment='right')

plt.show()