
# import sys
# !{sys.executable} -m pip install palmerpenguins
from palmerpenguins import load_penguins

penguins = load_penguins()

penguins.head()


## This code will generate an error message 
ggplot(penguins, aes(x='species')) +
    geom_bar(fill='steelblue') + 
    labs(x='Species', y='Count', title='Number of Penguins by Species')

  Cell In[81], line 2
    ggplot(penguins, aes(x='species')) +
                                        ^
SyntaxError: invalid syntax


# import sys
# !{sys.executable} -m pip install plotnine
from plotnine import *

ggplot(penguins, aes(x='species')) + geom_bar(fill='steelblue') + labs(x='Species', y='Count', title='Number of Penguins by Species')

<Figure Size: (640 x 480)>


ggplot(penguins, aes(x='species')) + \
    geom_bar(fill='steelblue') + \
    labs(x='Species', y='Count', title='Number of Penguins by Species')

<Figure Size: (640 x 480)>


import matplotlib.pyplot as plt

species_counts = penguins["species"].value_counts()

plt.bar(species_counts.index, species_counts.values)
plt.xlabel("Species")
plt.ylabel("Count")
plt.title("Number of Penguins by Species")

plt.show()


## Method 1 using countplot

import seaborn as sns

ax = sns.countplot(data=penguins, x="species")
ax.set_title("Number of Penguins by Species")

plt.show()


sns.countplot(data=penguins, x="species", color="steelblue")
plt.xlabel("Species")
plt.ylabel("Count")
plt.title("Number of Penguins by Species")

plt.show()


## Using bar plot
species_counts = penguins["species"].value_counts()
species_counts

sns.barplot(x=species_counts.index, y=species_counts.values, color="steelblue")
plt.xlabel("Species")
plt.ylabel("Count")
plt.title("Number of Penguins by Species")

plt.show()


# Method 1: Pass DataFrame to data= argument and column name to x=
sns.countplot(data = penguins, x = 'species')
plt.show()


# Method 2: Pass Series of data to x= argument
sns.countplot(x = penguins['species'])
plt.show()


# Create a scatter plot using Seaborn
sns.scatterplot(data=penguins, x='flipper_length_mm', y='body_mass_g')
plt.show()


# Create a scatter plot with color and shape aesthetics using Seaborn
sns.scatterplot(data=penguins, x='flipper_length_mm', y='body_mass_g', hue='species', style='species')
plt.show()


# Create a scatter plot with conditional coloring using Seaborn
sns.scatterplot(data=penguins, x='flipper_length_mm', y='body_mass_g', hue=penguins['flipper_length_mm'] < 205)
plt.show()


# Create a scatter plot with purple color using Seaborn
sns.scatterplot(data=penguins, x='flipper_length_mm', y='body_mass_g', color='purple')
plt.show()


# Create a scatter plot with color and shape based on species using Seaborn
sns.scatterplot(data=penguins, x='flipper_length_mm', y='body_mass_g', hue='species', style='species')

# Add a 2D density plot
sns.kdeplot(data=penguins, x='flipper_length_mm', y='body_mass_g', color='black', fill=True, alpha=0.3)

# Show the plot
plt.show()


sns.scatterplot(
    data=penguins,  # Specify the DataFrame
    x='flipper_length_mm',  # Specify the x-axis variable
    y='body_mass_g',  # Specify the y-axis variable
    hue='species',  # Color the points based on species
    style='island'  # Use different point shapes based on island
)
plt.show()


# Define the color palette
cols = {"Adelie": "red", "Chinstrap": "blue", "Gentoo": "darkgreen"}

# Create a scatter plot
sns.scatterplot(
    data=penguins,  # Specify the DataFrame
    x='flipper_length_mm',  # Specify the x-axis variable
    y='body_mass_g',  # Specify the y-axis variable
    hue='species',  # Color the points based on species
    palette=cols  # Use the defined color palette
)


# Display the plot
plt.show()


sns.scatterplot(
    data=penguins,
    x='flipper_length_mm',
    y='body_mass_g',
    hue='bill_length_mm',
    style='island'
)

# Add any additional customization or annotations here

plt.show()


# Create a scatter plot using seaborn
sns.scatterplot(
    data=penguins,  # Specify the data
    x='flipper_length_mm',  # Set the x-axis variable
    y='body_mass_g',  # Set the y-axis variable
    hue='species',  # Set the variable for color
    palette='Dark2'  # Set the color palette to 'Dark2'
)

plt.show()  # Display the plot


import brewer2mpl

# Print all available color palettes
brewer2mpl.print_maps()

Sequential
Blues     :  {3, 4, 5, 6, 7, 8, 9}
BuGn      :  {3, 4, 5, 6, 7, 8, 9}
BuPu      :  {3, 4, 5, 6, 7, 8, 9}
GnBu      :  {3, 4, 5, 6, 7, 8, 9}
Greens    :  {3, 4, 5, 6, 7, 8, 9}
Greys     :  {3, 4, 5, 6, 7, 8, 9}
OrRd      :  {3, 4, 5, 6, 7, 8, 9}
Oranges   :  {3, 4, 5, 6, 7, 8, 9}
PuBu      :  {3, 4, 5, 6, 7, 8, 9}
PuBuGn    :  {3, 4, 5, 6, 7, 8, 9}
PuRd      :  {3, 4, 5, 6, 7, 8, 9}
Purples   :  {3, 4, 5, 6, 7, 8, 9}
RdPu      :  {3, 4, 5, 6, 7, 8, 9}
Reds      :  {3, 4, 5, 6, 7, 8, 9}
YlGn      :  {3, 4, 5, 6, 7, 8, 9}
YlGnBu    :  {3, 4, 5, 6, 7, 8, 9}
YlOrBr    :  {3, 4, 5, 6, 7, 8, 9}
YlOrRd    :  {3, 4, 5, 6, 7, 8, 9}
Diverging
BrBG      :  {3, 4, 5, 6, 7, 8, 9, 10, 11}
PRGn      :  {3, 4, 5, 6, 7, 8, 9, 10, 11}
PiYG      :  {3, 4, 5, 6, 7, 8, 9, 10, 11}
PuOr      :  {3, 4, 5, 6, 7, 8, 9, 10, 11}
RdBu      :  {3, 4, 5, 6, 7, 8, 9, 10, 11}
RdGy      :  {3, 4, 5, 6, 7, 8, 9, 10, 11}
RdYlBu    :  {3, 4, 5, 6, 7, 8, 9, 10, 11}
RdYlGn    :  {3, 4, 5, 6, 7, 8, 9, 10, 11}
Spectral  :  {3, 4, 5, 6, 7, 8, 9, 10, 11}
Qualitative
Accent    :  {3, 4, 5, 6, 7, 8}
Dark2     :  {3, 4, 5, 6, 7, 8}
Paired    :  {3, 4, 5, 6, 7, 8, 9, 10, 11, 12}
Pastel1   :  {3, 4, 5, 6, 7, 8, 9}
Pastel2   :  {3, 4, 5, 6, 7, 8}
Set1      :  {3, 4, 5, 6, 7, 8, 9}
Set2      :  {3, 4, 5, 6, 7, 8}
Set3      :  {3, 4, 5, 6, 7, 8, 9, 10, 11, 12}


# Create scatter plot using seaborn and viridis
sns.scatterplot(
    data=penguins,              # Data frame containing the data
    x='flipper_length_mm',     # Variable for the x-axis
    y='body_mass_g',           # Variable for the y-axis
    hue='species',             # Variable to differentiate the colors
    palette='viridis'          # Color map to use for the plot
)

# Display the plot
plt.show()


# Create scatter plot using Seaborn
sns.scatterplot(
    data=penguins,
    x='flipper_length_mm',
    y='body_mass_g',
    hue='species',
    style='species',
    palette='plasma',
    markers={'Adelie': 's', 'Gentoo': 'o', 'Chinstrap': '^'},
)

# Set x-axis breaks
plt.xticks([170, 200, 230])

# Set y-axis to logarithmic scale
plt.yscale('log')

# Display the plot
plt.show()


# Create facets for each species
g = sns.FacetGrid(penguins, col='species')
g.map(sns.scatterplot, 'flipper_length_mm', 'body_mass_g')

# Display the plot
plt.show()


# Create scatter plot using seaborn and facet_wrap
# The col_wrap parameter in the FacetGrid function specifies the maximum number of columns in the grid of facets
g = sns.FacetGrid(penguins, col='species', col_wrap=3, sharex=False, sharey=False)
g.map(sns.scatterplot, 'flipper_length_mm', 'body_mass_g')

# Display the plot
plt.show()


g = sns.FacetGrid(penguins, col='species', row='sex')
g.map(sns.scatterplot, 'flipper_length_mm', 'body_mass_g')
# Display the plot
plt.show()


sns.countplot(data=penguins, x='species')
plt.show()


# Cord flip
sns.countplot(data=penguins, y='species', palette='Set1')
plt.show()


# Set the theme
sns.set_theme(style="darkgrid")

# Create the scatter plot
sns.scatterplot(data=penguins, x='flipper_length_mm', y='body_mass_g', hue='species', style='species')

# Display the plot
plt.show()


# Set the theme
sns.set_theme(style="whitegrid")

# Create the scatter plot
sns.scatterplot(data=penguins, x='flipper_length_mm', y='body_mass_g', hue='species', style='species')

# Display the plot
plt.show()


# Set the theme
sns.set_theme(style="dark")

# Create the scatter plot
sns.scatterplot(data=penguins, x='flipper_length_mm', y='body_mass_g', hue='species', style='species')

# Display the plot
plt.show()


# Create the figure and subplots
fig, axs = plt.subplots(2, 2, figsize=(10, 8))

# Scatter plot
sns.scatterplot(data=penguins, x='flipper_length_mm', y='body_mass_g', hue='species', ax=axs[0, 0])
# Box plot
sns.boxplot(data=penguins, x='species', y='bill_depth_mm', ax=axs[0, 1])
# Histogram with KDE
sns.histplot(data=penguins, x='body_mass_g', hue='species', element='step', kde=True, ax=axs[1, 0])

# Remove empty subplot
fig.delaxes(axs[1, 1])

# Adjust the layout
plt.tight_layout()

# Add a plot title for the entire panel
fig.suptitle("Penguin Data Analysis", fontsize=16, y=1)


# Show the plot
plt.show()


# Create the figure and grid layout
fig = plt.figure(figsize=(10, 8))  # Create a new figure object with size 10x8 inches
gs = fig.add_gridspec(2, 2)  # Add a grid specification with 2 rows and 2 columns

# Scatter plot
ax1 = fig.add_subplot(gs[0, 0])
sns.scatterplot(data=penguins, x='flipper_length_mm', y='body_mass_g', hue='species', ax=ax1)
ax1.text(0.05, 0.9, 'A', transform=ax1.transAxes, fontsize=16, fontweight='bold')

# Modify the legend title and position
ax1.legend_.set_title("Penguin Species")
ax1.legend_.set_bbox_to_anchor((1.1, 1.0))  # Adjust the bbox_to_anchor value to change the legend position

# Box plot
ax2 = fig.add_subplot(gs[0, 1])
sns.boxplot(data=penguins, x='species', y='bill_depth_mm', ax=ax2)
ax2.text(0.05, 0.9, 'B', transform=ax2.transAxes, fontsize=16, fontweight='bold')

# Histogram with KDE
ax3 = fig.add_subplot(gs[1, :]) # The colon to indicate that I want to select all columns in this row
sns.histplot(data=penguins, x='body_mass_g', hue='species', element='step', kde=True, ax=ax3)
ax3.text(0.05, 0.9, 'C', transform=ax3.transAxes, fontsize=16, fontweight='bold')

# Adjust the layout
fig.tight_layout()

# Add the plot annotation and adjust the position
fig.suptitle('Size measurements for adult foraging penguins near Palmer Station, Antarctica', fontsize=16, y=1)
#fig.text(0.05, 0.05, 'A', fontsize=16, fontweight='bold')

# Show the plot
plt.show()


import plotly.express as px

# Convert seaborn plot to interactive plotly plot
scatterplot_plotly = px.scatter(penguins, x='flipper_length_mm', y='body_mass_g', color='species')

# Display the interactive plot
scatterplot_plotly.show()


# Create a scatter plot using Plotly Express
fig = px.scatter(
    penguins,  # Dataset
    x="flipper_length_mm",  # X-axis variable
    y="body_mass_g",  # Y-axis variable
    color="species",  # Variable used for color differentiation
    marginal_y="violin",  # Add a violin plot on the y-axis margin
    marginal_x="box",  # Add a box plot on the x-axis margin
    trendline="ols",  # Add an ordinary least squares (OLS) trendline
    template="simple_white"  # Use the "simple_white" plot template
)

# Customize the layout of the plot
fig.update_layout(
    xaxis_title="Flipper Length (mm)",  # Set the x-axis title
    yaxis_title="Body Mass (g)"  # Set the y-axis title
)

# Display the plot
fig.show()

	species	island	bill_length_mm	bill_depth_mm	flipper_length_mm	body_mass_g	sex	year
0	Adelie	Torgersen	39.1	18.7	181.0	3750.0	male	2007
1	Adelie	Torgersen	39.5	17.4	186.0	3800.0	female	2007
2	Adelie	Torgersen	40.3	18.0	195.0	3250.0	female	2007
3	Adelie	Torgersen	NaN	NaN	NaN	NaN	NaN	2007
4	Adelie	Torgersen	36.7	19.3	193.0	3450.0	female	2007

Data Visulization with Python¶

palmerpenguins data¶

Data Visualization with Python¶

1. Plotnine¶

2. Matplotlib¶

3. Seaborn¶

The popularity of the libraries¶

Data Visualization With Seaborn¶

Different categories of plots in Seaborn¶

Anatomy of a chart¶

The basic steps to creating plots with Seaborn¶

Mapping Colours¶

Setting Colours¶

Adding Layers¶

Scales¶

Scales manual¶

Facets¶

Coordinates¶

Themes¶

Built-in-themes¶

Plotly¶