17. Seaborn

1KB

relplot data.csv

Open

400KB

Adidas US Sales Datasets.xlsx

Open

24KB

Sleep_health_and_lifestyle_dataset.csv

Open

Seaborn

Seaborn is an advanced data visualization tool and it is used for advanced visualization. We are going to Cover these Plots :

1. relplot(relational plot) - scatter line

2. heatmap

3. regression - lmplot

4. displot - histplot kdeplot

5. catplot(categorical plot) - strip swarm box violin boxen point count bar

Install Seaborn -

pip install seaborn

Import Libraries

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

1. relplot

relplot is a high-level plotting function in Seaborn used to visualize relationships between numerical variables.

It shows how one numeric variable changes with another numeric variable.

relplot offers two plots.

1. scatter plot (default)

2. line plot

df = pd.read_csv('relplot data.csv')
df.head()

	Order_ID	Year	Month	City	Customer_Type	Order_Value_K	Delivery_Time_Min	Customer_Rating	Distance_KM	Day_Type	Weather	Festival_Period	Time_Slot
0	1001	2023	Jan	Delhi	Premium	1.2	18	4.8	3	Weekday	Clear	No	Lunch
1	1002	2023	Jan	Delhi	Regular	0.5	25	4.0	5	Weekday	Clear	No	Dinner
2	1003	2023	Jan	Delhi	Premium	1.5	22	4.5	4	Weekend	Rainy	Yes	Dinner
3	1004	2023	Jan	Pune	Regular	0.4	28	3.8	6	Weekday	Rainy	No	Lunch
4	1005	2023	Jan	Pune	Premium	1.0	20	4.6	4	Weekend	Clear	Yes	Dinner

Finding Relationship Between Delivery Time and Customer Rating

sns.relplot(data=df,
            x='Delivery_Time_Min',
            y='Customer_Rating')

plt.show()

Delivery time and Customer rating has negative relationship

Segmentation - hue

It uses different colors to separate categories in the data.

sns.relplot(data=df,
            x='Delivery_Time_Min',
            y='Customer_Rating',
            hue='Customer_Type')

plt.show()

Regular Customers often get late deliveries rather than premium customer , which is the reason , regular customers give very less rating rather than premium customers.

hue - palette

sns.relplot(data=df,
            x='Delivery_Time_Min',
            y='Customer_Rating',
            hue='Customer_Type',
            palette =  { 'Premium':'Green' , 'Regular':'red' })

plt.show()

sns.relplot(data=df,
            x='Delivery_Time_Min',
            y='Customer_Rating',
            hue='Customer_Type',
            palette =  'Reds')

plt.show()

size

It uses different sizes to separate categories in the data.

sns.relplot(data=df,
            x='Delivery_Time_Min',
            y='Customer_Rating',
            hue='Customer_Type',
            palette =  { 'Premium':'Green' , 'Regular':'red' },
            size='Customer_Rating')

plt.show()

size - sizes

sns.relplot(data=df,
            x='Delivery_Time_Min',
            y='Customer_Rating',
            hue='Customer_Type',
            palette =  { 'Premium':'Green' , 'Regular':'red' },
            size='Customer_Rating',
            sizes=(50,100))

plt.show()

Segmentation - style

It uses different sizes to separate categories in the data.

sns.relplot(data=df,
            x='Delivery_Time_Min',
            y='Customer_Rating',
            hue='Customer_Type',
            palette =  { 'Premium':'Green' , 'Regular':'red' },
            size='Customer_Rating',
            sizes=(50,100),
            style='Customer_Type')

# plt.legend(
#     bbox_to_anchor=(1, 1),  # move legend outside
#     loc='upper left'
# )

plt.show()

Segmentation - row

It uses different rows to separate categories in the data.

sns.relplot(data=df,
            x='Delivery_Time_Min',
            y='Customer_Rating',
            hue='Customer_Type',
            palette =  { 'Premium':'Green' , 'Regular':'red' },
            size='Customer_Rating',
            sizes=(50,100),
            style='Customer_Type',
            row='Time_Slot')

plt.show()

Segmentation - col

It uses different cols to separate categories in the data.

sns.relplot(data=df,
            x='Delivery_Time_Min',
            y='Customer_Rating',
            hue='Customer_Type',
            palette =  { 'Premium':'Green' , 'Regular':'red' },
            size='Customer_Rating',
            sizes=(50,100),
            style='Customer_Type',
            col='Day_Type')

plt.show()

sns.relplot(data=df,
            x='Delivery_Time_Min',
            y='Customer_Rating',
            hue='Customer_Type',
            palette =  { 'Premium':'Green' , 'Regular':'red' },
            size='Customer_Rating',
            sizes=(50,100),
            style='Customer_Type',
            col='Day_Type',
            row='Time_Slot')

plt.show()

png

2. relplot - line

line plot is used to find pattern over time.

by default line plot uses average to show the line.

sns.relplot(data=df,
            x='Delivery_Time_Min',
            y='Customer_Rating',
            kind='line')

plt.show()

png

sns.relplot(data=df,
            x='Delivery_Time_Min',
            y='Customer_Rating',
            kind='line',
            estimator='sum')

plt.show()

png

An Example :

df = pd.read_excel('Adidas US Sales Datasets.xlsx')
df['total'] = df['Price per Unit'] * df['Units Sold']
df

	Retailer	Invoice Date	Region	State	City	Product	Price per Unit	Units Sold	Sales Method	total
0	Foot Locker	2020-01-01	Northeast	New York	New York	Men's Street Footwear	50.0	1200	In-store	60000.0
1	Foot Locker	2020-01-02	Northeast	New York	New York	Men's Athletic Footwear	50.0	1000	In-store	50000.0
2	Foot Locker	2020-01-03	Northeast	New York	New York	Women's Street Footwear	40.0	1000	In-store	40000.0
3	Foot Locker	2020-01-04	Northeast	New York	New York	Women's Athletic Footwear	45.0	850	In-store	38250.0
4	Foot Locker	2020-01-05	Northeast	New York	New York	Men's Apparel	60.0	900	In-store	54000.0
...	...	...	...	...	...	...	...	...	...	...
9643	Foot Locker	2021-01-24	Northeast	New Hampshire	Manchester	Men's Apparel	50.0	64	Outlet	3200.0
9644	Foot Locker	2021-01-24	Northeast	New Hampshire	Manchester	Women's Apparel	41.0	105	Outlet	4305.0
9645	Foot Locker	2021-02-22	Northeast	New Hampshire	Manchester	Men's Street Footwear	41.0	184	Outlet	7544.0
9646	Foot Locker	2021-02-22	Northeast	New Hampshire	Manchester	Men's Athletic Footwear	42.0	70	Outlet	2940.0
9647	Foot Locker	2021-02-22	Northeast	New Hampshire	Manchester	Women's Street Footwear	29.0	83	Outlet	2407.0

9648 rows × 10 columns

sns.relplot(data=df,
            x='Units Sold',
            y='total')

plt.show()

png

sns.relplot(data=df,
            x='Units Sold',
            y='total',
            kind='line',
            marker='o')

plt.show()

png

sns.relplot(data=df,
            x='Units Sold',
            y='total',
            kind='line',
            marker='o',
            estimator='sum')

plt.show()

png

df = pd.read_csv('relplot data.csv')
df.head()

	Order_ID	Year	Month	City	Customer_Type	Order_Value_K	Delivery_Time_Min	Customer_Rating	Distance_KM	Day_Type	Weather	Festival_Period	Time_Slot
0	1001	2023	Jan	Delhi	Premium	1.2	18	4.8	3	Weekday	Clear	No	Lunch
1	1002	2023	Jan	Delhi	Regular	0.5	25	4.0	5	Weekday	Clear	No	Dinner
2	1003	2023	Jan	Delhi	Premium	1.5	22	4.5	4	Weekend	Rainy	Yes	Dinner
3	1004	2023	Jan	Pune	Regular	0.4	28	3.8	6	Weekday	Rainy	No	Lunch
4	1005	2023	Jan	Pune	Premium	1.0	20	4.6	4	Weekend	Clear	Yes	Dinner

sns.relplot(data=df,
            x='Delivery_Time_Min',
            y='Customer_Rating',
            kind='line',
            hue='Customer_Type')

plt.show()

png

Let's Explore With Examples

df = pd.read_excel('Adidas US Sales Datasets.xlsx')
df['total'] = df['Price per Unit'] * df['Units Sold']
df['Invoice Date'] = pd.to_datetime(df['Invoice Date'],format='%Y-%m-%d')
df['Year'] = df['Invoice Date'].dt.year
df.head()

	Retailer	Invoice Date	Region	State	City	Product	Price per Unit	Units Sold	Sales Method	total	Year
0	Foot Locker	2020-01-01	Northeast	New York	New York	Men's Street Footwear	50.0	1200	In-store	60000.0	2020
1	Foot Locker	2020-01-02	Northeast	New York	New York	Men's Athletic Footwear	50.0	1000	In-store	50000.0	2020
2	Foot Locker	2020-01-03	Northeast	New York	New York	Women's Street Footwear	40.0	1000	In-store	40000.0	2020
3	Foot Locker	2020-01-04	Northeast	New York	New York	Women's Athletic Footwear	45.0	850	In-store	38250.0	2020
4	Foot Locker	2020-01-05	Northeast	New York	New York	Men's Apparel	60.0	900	In-store	54000.0	2020

sns.relplot(data=df,
            x='Units Sold',
            y='total',
            )

plt.show()

Region Wise

sns.relplot(data=df,
            x='Units Sold',
            y='total',
            hue='Region')

plt.show()

sns.relplot(data=df,
            x='Units Sold',
            y='total',
            col='Region',
            col_wrap=2,
            hue='Region')

plt.show()

Yearly Average Sales

sns.relplot(data=df,
            x='Year',
            y='total',
            kind='line')
plt.show()

sns.relplot(data=df,
            x='Year',
            y='total',
            kind='line',
            hue='Region')
plt.show()

Total Sales

sns.relplot(data=df,
            x='Year',
            y='total',
            kind='line',
            hue='Region',
            estimator='sum')
plt.show()

📊 Correlation Heatmap — Notebook Explanation

📌 What is Correlation?

Correlation measures how strongly two numerical variables are related.

• Value range: -1 to +1

• +1 → strong positive relationship

• -1 → strong negative relationship

• 0 → no relationship

---

📌 What is a Correlation Heatmap?

A correlation heatmap is a visual way to represent correlation values using colors.

Instead of reading numbers, we interpret color intensity.

---

🎨 How to Read Colors in a Correlation Heatmap

Color Meaning	Interpretation
Dark positive color	Strong positive correlation
Dark negative color	Strong negative correlation
Light / neutral color	Weak or no correlation

👉 Darker the color = stronger the relationship

---

📌 Why Use a Correlation Heatmap?

• To quickly identify relationships

• To detect multicollinearity

• To find important features in data analysis

---

📌 Example Interpretation

If a heatmap shows:

• Hours_Studied vs Marks → dark positive color → More study hours leads to higher marks

• Speed vs Travel_Time → dark negative color → Higher speed reduces travel time

---

🧠 Key Takeaway

A correlation heatmap visually shows how strongly and in which direction numerical variables are related using color intensity.

---

df = pd.read_csv('Sleep_health_and_lifestyle_dataset.csv')
df

	Person ID	Gender	Age	Occupation	Sleep Duration	Quality of Sleep	Physical Activity Level	Stress Level	BMI Category	Blood Pressure	Heart Rate	Daily Steps	Sleep Disorder
0	1	Male	27	Software Engineer	6.1	6	42	6	Overweight	126/83	77	4200	NaN
1	2	Male	28	Doctor	6.2	6	60	8	Normal	125/80	75	10000	NaN
2	3	Male	28	Doctor	6.2	6	60	8	Normal	125/80	75	10000	NaN
3	4	Male	28	Sales Representative	5.9	4	30	8	Obese	140/90	85	3000	Sleep Apnea
4	5	Male	28	Sales Representative	5.9	4	30	8	Obese	140/90	85	3000	Sleep Apnea
...	...	...	...	...	...	...	...	...	...	...	...	...	...
369	370	Female	59	Nurse	8.1	9	75	3	Overweight	140/95	68	7000	Sleep Apnea
370	371	Female	59	Nurse	8.0	9	75	3	Overweight	140/95	68	7000	Sleep Apnea
371	372	Female	59	Nurse	8.1	9	75	3	Overweight	140/95	68	7000	Sleep Apnea
372	373	Female	59	Nurse	8.1	9	75	3	Overweight	140/95	68	7000	Sleep Apnea
373	374	Female	59	Nurse	8.1	9	75	3	Overweight	140/95	68	7000	Sleep Apnea

374 rows × 13 columns

cdf = df[ ['Sleep Duration','Quality of Sleep','Stress Level','Age'] ].corr()
cdf

	Sleep Duration	Quality of Sleep	Stress Level	Age
Sleep Duration	1.000000	0.883213	-0.811023	0.344709
Quality of Sleep	0.883213	1.000000	-0.898752	0.473734
Stress Level	-0.811023	-0.898752	1.000000	-0.422344
Age	0.344709	0.473734	-0.422344	1.000000

sns.heatmap(data=cdf,annot=True)
plt.show()

regression - lmplot

df = pd.read_excel('Adidas US Sales Datasets.xlsx')
df['total'] = df['Price per Unit'] * df['Units Sold']
df.head()

	Retailer	Invoice Date	Region	State	City	Product	Price per Unit	Units Sold	Sales Method	total
0	Foot Locker	2020-01-01	Northeast	New York	New York	Men's Street Footwear	50.0	1200	In-store	60000.0
1	Foot Locker	2020-01-02	Northeast	New York	New York	Men's Athletic Footwear	50.0	1000	In-store	50000.0
2	Foot Locker	2020-01-03	Northeast	New York	New York	Women's Street Footwear	40.0	1000	In-store	40000.0
3	Foot Locker	2020-01-04	Northeast	New York	New York	Women's Athletic Footwear	45.0	850	In-store	38250.0
4	Foot Locker	2020-01-05	Northeast	New York	New York	Men's Apparel	60.0	900	In-store	54000.0

sns.lmplot(data=df,
           x='Units Sold',
           y='total',
           scatter_kws={'color': 'blue'},
        line_kws={'color': 'red'},
           col='Region',
           col_wrap=2
           )

plt.show()

displot

displot is distribution plot.

1. displot - histplot (default)

2. kdeplot (kernel density)

df = pd.read_csv('Sleep_health_and_lifestyle_dataset.csv')
df

	Person ID	Gender	Age	Occupation	Sleep Duration	Quality of Sleep	Physical Activity Level	Stress Level	BMI Category	Blood Pressure	Heart Rate	Daily Steps	Sleep Disorder
0	1	Male	27	Software Engineer	6.1	6	42	6	Overweight	126/83	77	4200	NaN
1	2	Male	28	Doctor	6.2	6	60	8	Normal	125/80	75	10000	NaN
2	3	Male	28	Doctor	6.2	6	60	8	Normal	125/80	75	10000	NaN
3	4	Male	28	Sales Representative	5.9	4	30	8	Obese	140/90	85	3000	Sleep Apnea
4	5	Male	28	Sales Representative	5.9	4	30	8	Obese	140/90	85	3000	Sleep Apnea
...	...	...	...	...	...	...	...	...	...	...	...	...	...
369	370	Female	59	Nurse	8.1	9	75	3	Overweight	140/95	68	7000	Sleep Apnea
370	371	Female	59	Nurse	8.0	9	75	3	Overweight	140/95	68	7000	Sleep Apnea
371	372	Female	59	Nurse	8.1	9	75	3	Overweight	140/95	68	7000	Sleep Apnea
372	373	Female	59	Nurse	8.1	9	75	3	Overweight	140/95	68	7000	Sleep Apnea
373	374	Female	59	Nurse	8.1	9	75	3	Overweight	140/95	68	7000	Sleep Apnea

374 rows × 13 columns

import numpy as np
sns.displot(data=df,
            x='Age',
            bins=20,
            hue='Gender',
            multiple='stack')

# plt.xticks(np.arange(26,62,2))

plt.show()

import numpy as np
sns.displot(data=df,
            x='Age',
            bins=20,
            hue='Gender',
            multiple='dodge',
            aspect=2,
            height=10)

# plt.xticks(np.arange(26,62,2))

plt.show()

import numpy as np
sns.displot(data=df,
            x='Age',
            bins=20,
            col='Gender',
            )

# plt.xticks(np.arange(26,62,2))

plt.show()

png

displot - kdeplot

sns.displot(data=df
            ,x='Age',
            kind='kde',
            hue='Gender')

plt.show()

png

Categorical Plot

1. strip plot (default)

strip plot is a scatter plot but for categorical values.

df = pd.read_excel('Adidas US Sales Datasets.xlsx')
df['total'] = df['Units Sold'] * df['Price per Unit']
df.head()

	Retailer	Invoice Date	Region	State	City	Product	Price per Unit	Units Sold	Sales Method	total
0	Foot Locker	2020-01-01	Northeast	New York	New York	Men's Street Footwear	50.0	1200	In-store	60000.0
1	Foot Locker	2020-01-02	Northeast	New York	New York	Men's Athletic Footwear	50.0	1000	In-store	50000.0
2	Foot Locker	2020-01-03	Northeast	New York	New York	Women's Street Footwear	40.0	1000	In-store	40000.0
3	Foot Locker	2020-01-04	Northeast	New York	New York	Women's Athletic Footwear	45.0	850	In-store	38250.0
4	Foot Locker	2020-01-05	Northeast	New York	New York	Men's Apparel	60.0	900	In-store	54000.0

sns.relplot(data=df,
            x='Sales Method',
            y='total')

plt.show()

png

sns.catplot(data=df,
            x='Sales Method',
            y='total')
plt.show()

png

df = pd.read_csv('Sleep_health_and_lifestyle_dataset.csv')
df

	Person ID	Gender	Age	Occupation	Sleep Duration	Quality of Sleep	Physical Activity Level	Stress Level	BMI Category	Blood Pressure	Heart Rate	Daily Steps	Sleep Disorder
0	1	Male	27	Software Engineer	6.1	6	42	6	Overweight	126/83	77	4200	NaN
1	2	Male	28	Doctor	6.2	6	60	8	Normal	125/80	75	10000	NaN
2	3	Male	28	Doctor	6.2	6	60	8	Normal	125/80	75	10000	NaN
3	4	Male	28	Sales Representative	5.9	4	30	8	Obese	140/90	85	3000	Sleep Apnea
4	5	Male	28	Sales Representative	5.9	4	30	8	Obese	140/90	85	3000	Sleep Apnea
...	...	...	...	...	...	...	...	...	...	...	...	...	...
369	370	Female	59	Nurse	8.1	9	75	3	Overweight	140/95	68	7000	Sleep Apnea
370	371	Female	59	Nurse	8.0	9	75	3	Overweight	140/95	68	7000	Sleep Apnea
371	372	Female	59	Nurse	8.1	9	75	3	Overweight	140/95	68	7000	Sleep Apnea
372	373	Female	59	Nurse	8.1	9	75	3	Overweight	140/95	68	7000	Sleep Apnea
373	374	Female	59	Nurse	8.1	9	75	3	Overweight	140/95	68	7000	Sleep Apnea

374 rows × 13 columns

sns.catplot(data=df,
            x='BMI Category',
            y='Daily Steps')

plt.show()

png

df = pd.read_excel('Adidas US Sales Datasets.xlsx')
df['total'] = df['Units Sold'] * df['Price per Unit']
df.head()

	Retailer	Invoice Date	Region	State	City	Product	Price per Unit	Units Sold	Sales Method	total
0	Foot Locker	2020-01-01	Northeast	New York	New York	Men's Street Footwear	50.0	1200	In-store	60000.0
1	Foot Locker	2020-01-02	Northeast	New York	New York	Men's Athletic Footwear	50.0	1000	In-store	50000.0
2	Foot Locker	2020-01-03	Northeast	New York	New York	Women's Street Footwear	40.0	1000	In-store	40000.0
3	Foot Locker	2020-01-04	Northeast	New York	New York	Women's Athletic Footwear	45.0	850	In-store	38250.0
4	Foot Locker	2020-01-05	Northeast	New York	New York	Men's Apparel	60.0	900	In-store	54000.0

sns.catplot(data=df,
            x='Sales Method',
            y='total',
            hue='Region',
            dodge=True,
            aspect=2)
plt.show()

png

catplot - swarmplot

Dots don't overlap at all.

df = pd.read_csv('relplot data.csv')
df

	Order_ID	Year	Month	City	Customer_Type	Order_Value_K	Delivery_Time_Min	Customer_Rating	Distance_KM	Day_Type	Weather	Festival_Period	Time_Slot
0	1001	2023	Jan	Delhi	Premium	1.2	18	4.8	3	Weekday	Clear	No	Lunch
1	1002	2023	Jan	Delhi	Regular	0.5	25	4.0	5	Weekday	Clear	No	Dinner
2	1003	2023	Jan	Delhi	Premium	1.5	22	4.5	4	Weekend	Rainy	Yes	Dinner
3	1004	2023	Jan	Pune	Regular	0.4	28	3.8	6	Weekday	Rainy	No	Lunch
4	1005	2023	Jan	Pune	Premium	1.0	20	4.6	4	Weekend	Clear	Yes	Dinner
5	1006	2023	Jan	Bangalore	Regular	0.6	26	4.1	5	Weekday	Rainy	No	Lunch
6	1007	2023	Jan	Bangalore	Premium	1.3	18	4.9	3	Weekend	Clear	Yes	Dinner
7	1008	2023	Jan	Chennai	Regular	0.5	24	3.9	4	Weekday	Rainy	No	Lunch
8	1009	2023	Jan	Chennai	Premium	1.2	22	4.7	5	Weekend	Clear	Yes	Dinner
9	1010	2023	Feb	Delhi	Regular	0.6	27	4.0	5	Weekday	Rainy	No	Lunch
10	1011	2023	Feb	Delhi	Premium	1.4	19	4.8	3	Weekend	Clear	Yes	Dinner
11	1012	2023	Feb	Pune	Regular	0.5	28	3.9	6	Weekday	Rainy	No	Lunch
12	1013	2023	Feb	Pune	Premium	1.2	21	4.6	4	Weekend	Clear	Yes	Dinner
13	1014	2023	Feb	Bangalore	Regular	0.7	25	4.2	5	Weekday	Rainy	No	Lunch
14	1015	2023	Feb	Bangalore	Premium	1.5	18	5.0	3	Weekend	Clear	Yes	Dinner
15	1016	2023	Feb	Chennai	Regular	0.6	24	4.0	4	Weekday	Rainy	No	Lunch
16	1017	2023	Feb	Chennai	Premium	1.3	20	4.8	5	Weekend	Clear	Yes	Dinner

sns.catplot(data=df,
            x='Customer_Type',
            y='Order_Value_K')
plt.show()

png

sns.catplot(data=df,
            x='Customer_Type',
            y='Order_Value_K',
            kind='swarm')
plt.show()

png

If you have a small data , swarm plot is good but for large dataset strip plot is good.

catplot - boxplot

df = pd.read_excel('Adidas US Sales Datasets.xlsx')
df['total'] = df['Units Sold'] * df['Price per Unit']
df.head()

	Retailer	Invoice Date	Region	State	City	Product	Price per Unit	Units Sold	Sales Method	total
0	Foot Locker	2020-01-01	Northeast	New York	New York	Men's Street Footwear	50.0	1200	In-store	60000.0
1	Foot Locker	2020-01-02	Northeast	New York	New York	Men's Athletic Footwear	50.0	1000	In-store	50000.0
2	Foot Locker	2020-01-03	Northeast	New York	New York	Women's Street Footwear	40.0	1000	In-store	40000.0
3	Foot Locker	2020-01-04	Northeast	New York	New York	Women's Athletic Footwear	45.0	850	In-store	38250.0
4	Foot Locker	2020-01-05	Northeast	New York	New York	Men's Apparel	60.0	900	In-store	54000.0

sns.catplot(data=df,
            x='Units Sold',
            kind='box')
plt.show()

png

sns.catplot(data=df,
            x='Units Sold',
            kind='box',
            hue='Product',
            fill=False
        )
plt.show()

png

sns.catplot(data=df,
            x='Units Sold',
            kind='box',
            col='Product',
            col_wrap=2,
        )
plt.show()

png

catplot - violin

sns.catplot(data=df,
            x='Units Sold',
            kind='violin',
            fill=False)

plt.show()

png

catplot - boxenplot

a much more detailed version of box plot

sns.catplot(data=df,
            x='Units Sold',
            kind='boxen')
plt.show()

png

catplot - pointplot

sns.catplot(data=df,
            x='Region',
            y='total',
            kind='point')
plt.show()

png

sns.catplot(data=df,
            x='Region',
            y='total',
            kind='point',
            estimator='sum')
plt.show()

png

catplot - countplot

sns.catplot(data=df,
            x='Sales Method',
            kind='count')
plt.show()

sns.catplot(data=df,
            x='Sales Method',
            kind='count',
            hue='Region',
            col='Retailer',
            col_wrap=2)
plt.show()

png

catplot - barplot

df

	Retailer	Invoice Date	Region	State	City	Product	Price per Unit	Units Sold	Sales Method	total
0	Foot Locker	2020-01-01	Northeast	New York	New York	Men's Street Footwear	50.0	1200	In-store	60000.0
1	Foot Locker	2020-01-02	Northeast	New York	New York	Men's Athletic Footwear	50.0	1000	In-store	50000.0
2	Foot Locker	2020-01-03	Northeast	New York	New York	Women's Street Footwear	40.0	1000	In-store	40000.0
3	Foot Locker	2020-01-04	Northeast	New York	New York	Women's Athletic Footwear	45.0	850	In-store	38250.0
4	Foot Locker	2020-01-05	Northeast	New York	New York	Men's Apparel	60.0	900	In-store	54000.0
...	...	...	...	...	...	...	...	...	...	...
9643	Foot Locker	2021-01-24	Northeast	New Hampshire	Manchester	Men's Apparel	50.0	64	Outlet	3200.0
9644	Foot Locker	2021-01-24	Northeast	New Hampshire	Manchester	Women's Apparel	41.0	105	Outlet	4305.0
9645	Foot Locker	2021-02-22	Northeast	New Hampshire	Manchester	Men's Street Footwear	41.0	184	Outlet	7544.0
9646	Foot Locker	2021-02-22	Northeast	New Hampshire	Manchester	Men's Athletic Footwear	42.0	70	Outlet	2940.0
9647	Foot Locker	2021-02-22	Northeast	New Hampshire	Manchester	Women's Street Footwear	29.0	83	Outlet	2407.0

9648 rows × 10 columns

sns.catplot(data=df,
            x='Product',
            y='total',
            kind='bar',
            aspect=2)

plt.xticks(rotation=45)
plt.show()

png

sns.catplot(data=df,
            x='Product',
            y='total',
            kind='bar',
            aspect=2,
            estimator='sum')

plt.xticks(rotation=45)
plt.show()

png

sns.catplot(data=df,
            x='Product',
            y='total',
            kind='bar',
            aspect=2,
            estimator='sum',
            hue='Region',
            errorbar=('ci', False))

plt.xticks(rotation=45)
plt.show()

png

Assignments

---

🔹 Section 1: Relplot – Scatter - relplot data

1. Create a scatter plot between Delivery_Time_Min and Customer_Rating using relplot.

2. Add Customer_Type as hue in the scatter plot.

3. Change the color palette to differentiate Premium and Regular customers.

4. Map Order_Value_K to the size parameter.

5. Set the point size range to (40, 180).

6. Add style='Customer_Type' to use different markers.

7. Create separate plots for Weekday and Weekend using col.

8. Create separate plots for different Weather conditions using row.

9. Filter the dataset to show only Delhi orders and plot the scatter.

10. Plot only Premium customers and visualize delivery time vs rating.

11. Remove the legend from the scatter plot.

12. Increase plot height and aspect ratio.

13. Create separate scatter plots for each City using col.

14. Change marker transparency using alpha.

15. Sort the data by Delivery_Time_Min before plotting.

---

🔹 Section 2: Relplot – Line - Adidas

1. Create a line plot showing average Total Sales over Date.

2. Change the estimator to show sum of Total Sales.

3. Plot Year-wise Total Sales trend.

4. Add Region as hue to compare sales trends.

5. Add markers to the line plot.

6. Rotate x-axis labels to avoid overlap.

7. Create separate line plots for In-store and Outlet sales using col.

8. Plot Product-wise sales trend over time.

9. Change line styles for different regions.

10. Disable error bars in the line plot.

11. Filter and plot sales data for 2020 only.

12. Plot Units Sold trend over time.

13. Create a line plot for New York city sales only.

14. Compare Men’s vs Women’s products using hue.

15. Increase line thickness for better visibility.

---

🔹 Section 3: Correlation Heatmap (Sleep / Health Dataset)

1. Select Sleep Duration, Quality of Sleep, Stress Level, and Age columns.

2. Compute the correlation matrix for the selected columns.

3. Create a correlation heatmap using Seaborn.

4. Display correlation values inside the heatmap.

5. Change the heatmap color map for strong contrast.

6. Increase the figure size to (8,6).

7. Mask the upper triangle of the heatmap.

8. Center the color scale at zero.

9. Remove the color bar from the heatmap.

10. Rotate x-axis labels for better readability.

---

🔹 Section 4: Regression – lmplot - Adidas

1. Create a regression plot between Units Sold and Total Sales.

2. Add Product as hue in the regression plot.

3. Disable the confidence interval.

4. Create separate regression plots for each Region using col.

5. Plot regression only for In-store sales.

6. Plot regression only for Outlet sales.

7. Change height and aspect ratio of the regression plot.

8. Create a regression plot for Men’s products only.

9. Create a regression plot for Women’s products only.

10. Compare regression lines for different Regions in a single plot.

---