# importing the data 
import pandas as pd
import numpy as np
url = "https://raw.githubusercontent.com/PhilChodrow/PIC16B/master/datasets/palmer_penguins.csv"
penguins = pd.read_csv(url)
penguins.head()

def clean_data(df):
    
    """
    This function does the following:

    1. Relabel Species column to enhance readability to the viewer (For example: "Adelie Penguin (Pygoscelis adelie)" is relabeled to "Adelie")
    2. Relabel Sex column ("MALE" is relabeled to "M" and "FEMALE" is relabeled to "F")
    3. Return a clean dataset 

    """
    
    # create a copy 
    df_copy = df.copy()
    
    # making the labels using dictionaries 
    species_labels = { 'Adelie Penguin (Pygoscelis adeliae)': 'Adelie',
                       'Chinstrap penguin (Pygoscelis antarctica)': 'Chinstrap',
                       'Gentoo penguin (Pygoscelis papua)': 'Gentoo' }
    
    sex_labels = { "MALE": 'M',
                   "FEMALE": 'F',
                   ".": np.nan }
    
    # relabeling the columns 
    df_copy["Species"] =  df_copy["Species"].map(species_labels)
    df_copy["Sex"] = df_copy["Sex"].map(sex_labels)
    
    return df_copy

# the new clean and shiny dataframe
df = clean_data(penguins)
df.head()

import seaborn as sns
from matplotlib import pyplot as plt

#Fill in the figsize parameter to set the (width,height) of the figure.
plt.figure(figsize = (10,20)). 

plt.subplots(1,3,1) # (rows, columns, the plot)

# make the figure
plt.figure(figsize = (10,5))

# make the plot
plot = sns.histplot(data = df, 
                    x = "Culmen Length (mm)", 
                    color = "yellow" 
                    )
    
# set the title of the plot
plot.set_title("Culmen Length of Penguins") 

# make the figure
plt.figure(figsize = (10,5)) 

plot = sns.histplot(data = df, 
                    x = "Culmen Length (mm)", 
                    hue = "Species", 
                    palette = dict( Adelie = "yellow", Gentoo = "blue", Chinstrap = "red")
                    )
# set the title of the plot
plot.set_title("Culmen Length of Penguins") 

# make the figure
plt.figure(figsize = (10,5)) 

plot = sns.histplot(data = df,
                     x = "Culmen Length (mm)", 
                     hue = "Species", 
                     element = "poly", 
                     palette = dict( Adelie = "yellow", Gentoo = "blue", Chinstrap = "green") 
                     )
# set the title of the plot
plot.set_title("Culmen Length of Penguins") 

plt.figure(figsize = (20,5))

# a list containing the unique island names
islands = list(set(df["Island"])) 

# create the visualization

#iterate over the subplots
for i in range(1, len(islands) + 1): 
    
    plt.subplot(1,3,i) # the subplot in the grid
    
    # get the subset of data according to each island
    sub_df = df[df["Island"] == islands[i-1]] 
    
    plot = sns.histplot(data = sub_df, 
                        x = "Body Mass (g)", 
                        hue = "Species", 
                        element = "poly", 
                        palette = dict( Adelie = "yellow", Gentoo = "blue", Chinstrap = "green")) 
    
    # we want the every x-axis to have the same scale to compare the penguins 
    plot.set(xlim =(2500,6500)) 

    # set title of subplot to the island name 
    plt.title(islands[i-1])    
    
    # Plotting the vertical lines for mean body mass of Adelie Penguins

    # mean of Body Mass of Adelie penguins
    group = sub_df.groupby("Species")["Body Mass (g)"].mean() 

    # add a vertical line
    plt.axvline(group[0], ls = '--', color = 'black', label = "Adelie mean") 
    
    # adding text
    if i == 1:
        plt.text(4750, 12, "The vertical line is the mean \nbody mass for Adelie Penguins", size = 10, style = 'italic')