Introduction to Data Visualization with Seaborn

# Add your code snippets here

# Import Matplotlib and Seaborn
import matplotlib.pyplot as plt
import seaborn as sns

# Change this scatter plot to have percent literate on the y-axis
sns.scatterplot(x=gdp, y=percent_literate)

# Show plot
plt.show()

# Import Matplotlib and Seaborn
import matplotlib.pyplot as plt
import seaborn as sns


# Create count plot with region on the y-axis
sns.countplot(y=region)

# Show plot
plt.show()

# Import pandas
import pandas as pd

# Create a DataFrame from csv file
df = pd.read_csv(csv_filepath)

# Print the head of df
print(df.head())

# Import Matplotlib, pandas, and Seaborn
import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns



# Create a DataFrame from csv file
df= pd.read_csv(csv_filepath)

# Create a count plot with "Spiders" on the x-axis
sns.countplot(x= 'Spiders', data= df)

# Display the plot
plt.show()

# Import Matplotlib and Seaborn
import matplotlib.pyplot as plt
import seaborn as sns

# Create a scatter plot of absences vs. final grade

sns.scatterplot(x='absences', y='G3', data= student_data, hue='location')


# Show plot
plt.show()

# Import Matplotlib and Seaborn
import matplotlib.pyplot as plt
import seaborn as sns

# Change the legend order in the scatter plot
sns.scatterplot(x="absences", y="G3", 
                data=student_data, 
                hue="location", hue_order= ['Rural', 'Urban'])

# Show plot
plt.show()

# Import Matplotlib and Seaborn
import matplotlib.pyplot as plt
import seaborn as sns

# Create a dictionary mapping subgroup values to colors
palette_colors = {'Rural': "green", 'Urban': "blue"}

# Create a count plot of school with location subgroups
sns.countplot(x='school', data=student_data, hue='location', palette=palette_colors)



# Display plot
plt.show()

# Change to make subplots based on study time
sns.relplot(x="absences", y="G3", 
            data=student_data,
            kind="scatter", 
            col='study_time')

# Show plot
plt.show()

# Adjust to add subplots based on school support
sns.relplot(x="G1", y="G3", 
            data=student_data,
            kind="scatter", 
            col="schoolsup", 
            col_order= ["yes", "no"])

# Show plot
plt.show()

# Adjust further to add subplots based on family support
sns.relplot(x="G1", y="G3", 
            data=student_data,
            kind="scatter", 
            col="schoolsup",
            col_order=["yes", "no"],
            row="famsup",
            row_order= ["yes", "no"])

# Show plot
plt.show()

# Import Matplotlib and Seaborn
import matplotlib.pyplot as plt
import seaborn as sns

# Create scatter plot of horsepower vs. mpg
sns.relplot(x="horsepower", y="mpg", 
            data=mpg, kind="scatter", 
            size="cylinders", 
            hue='cylinders')

# Show plot
plt.show()

# Import Matplotlib and Seaborn
import matplotlib.pyplot as plt
import seaborn as sns

# Create a scatter plot of acceleration vs. mpg

sns.relplot(x='acceleration', y='mpg', 
            data=mpg, 
            kind='scatter',
            hue='origin', 
            style='origin')


# Show plot
plt.show()

# Make the shaded area show the standard deviation
sns.relplot(x="model_year", y="mpg",
            data=mpg, kind="line", ci='sd')

# Show plot
plt.show()

# Import Matplotlib and Seaborn
import matplotlib.pyplot as plt
import seaborn as sns

# Add markers and make each line have the same style
sns.relplot(x="model_year", y="horsepower", 
            data=mpg, kind="line", 
            ci=None, style="origin", 
            hue="origin", markers=True, dashes=False)

# Show plot
plt.show()

# Specify the category ordering
study_time_order = ["<2 hours", "2 to 5 hours", 
                    "5 to 10 hours", ">10 hours"]

# Create a box plot and set the order of the categories

sns.catplot(data=student_data, x="study_time", y="G3", kind='box', order=study_time_order)



# Show plot
plt.show()

# Set the whiskers at the min and max values
sns.catplot(x="romantic", y="G3",
            data=student_data,
            kind="box",
            whis=[0,100])

# Show plot
plt.show()

# Remove the lines joining the points
sns.catplot(x="famrel", y="absences",
			data=student_data,
            kind="point",
            capsize=0.2, join=False)
            
# Show plot
plt.show()

# Import median function from numpy
from numpy import median

# Plot the median number of absences instead of the mean
sns.catplot(x="romantic", y="absences",
			data=student_data,
            kind="point",
            hue="school",
            ci=None, estimator=median)

# Show plot
plt.show()

# Set the style to "whitegrid"
sns.set_style("whitegrid")

# Create a count plot of survey responses
category_order = ["Never", "Rarely", "Sometimes", 
                  "Often", "Always"]

sns.catplot(x="Parents Advice", 
            data=survey_data, 
            kind="count", 
            order=category_order)

# Show plot
plt.show()

sns.set_style("whitegrid")
sns.set_palette("Purples")

# Set the context to "paper"
sns.set_context("paper")


# Set the style to "darkgrid"
sns.set_style("darkgrid")

# Set a custom color palette
custom_palette=['#39A7D0', "#36ADA4"]

sns.set_palette(custom_palette)

# Create the box plot of age distribution by gender
sns.catplot(x="Gender", y="Age", 
            data=survey_data, kind="box")

# Show plot
plt.show()

# Create scatter plot
g = sns.relplot(x="weight", 
                y="horsepower", 
                data=mpg,
                kind="scatter")

# Add a title "Car Weight vs. Horsepower"
g.fig.suptitle("Car Weight vs. Horsepower")

# Add a title "Average MPG Over Time"
g.set_title("Average MPG Over Time")

# Add x-axis and y-axis labels
g.set(xlabel="Car Model Year", ylabel="Average MPG")

# Rotate x-tick labels
plt.xticks(rotation=90)