Name: Aaron Dominic
Reg : 212221040001

import seaborn as sns
import matplotlib.pyplot as plt

# Load the tips dataset
tips = sns.load_dataset('tips')

# Drop rows with all missing values
tips.dropna(how='all', inplace=True)
sns.barplot(x='day', y='total_bill', data=tips)
plt.show()

# a) Which day of the week has the highest total bill amount?

# Group by day and sum total_bill
total_bill_by_day = tips.groupby('day')['total_bill'].sum()

# Sort by descending order and select the first row
highest_total_bill_day = total_bill_by_day.sort_values(ascending=False).index[0]

print("The day with the highest total bill amount is:", highest_total_bill_day)

# b) What is the average tip amount given by smokers and non-smokers?

sns.barplot(x='smoker', y='tip', data=tips)
plt.show()

# Group by smoker and calculate mean of tip
tip_by_smoker = tips.groupby('smoker')['tip'].mean()

print("Average tip amount given by smokers:", tip_by_smoker['Yes'])
print("Average tip amount given by non-smokers:", tip_by_smoker['No'])

# c) How does the tip percentage vary based on the size of the dining party?

tips['tip_percentage'] = tips['tip'] / tips['total_bill'] * 100
sns.pointplot(x='size', y='tip_percentage', data=tips)
plt.show()

# Create a new column for tip percentage
tips['tip_percentage'] = tips['tip'] / tips['total_bill']

# Group by size and calculate mean of tip percentage
tip_percentage_by_size = tips.groupby('size')['tip_percentage'].mean()

print("Tip percentage by size of dining party:")
print(tip_percentage_by_size)

# d) Which gender tends to leave higher tips?

sns.boxplot(x='sex', y='tip', data=tips)
plt.show()

# Group by gender and calculate mean of tip
tip_by_gender = tips.groupby('sex')['tip'].mean()

print("Average tip amount by gender:")
print(tip_by_gender)

# e) Is there any relationship between the total bill amount and the day of the week?

sns.scatterplot(x='total_bill', y='day', data=tips)
plt.show()

# f) How does the distribution of total bill amounts vary across different time periods (lunch vs. dinner)?

sns.boxplot(x='time', y='total_bill', data=tips)
plt.show()

# g) Which dining party size group tends to have the highest average total bill amount?

sns.barplot(x='size', y='total_bill', data=tips)
plt.show()

# Group by size and calculate mean of total_bill
total_bill_by_size = tips.groupby('size')['total_bill'].mean()

print("Average total bill amount by size of dining party:")
print(total_bill_by_size)

# h) What is the distribution of tip amounts for each day of the week?

sns.boxplot(x='day', y='tip', data=tips)
plt.show()

# i) How does the tip amount vary based on the type of service (lunch vs. dinner)?

sns.boxplot(x='time', y='tip', data=tips)
plt.show()

# j) Is there any correlation between the total bill amount and the tip amount?
sns.scatterplot(x='total_bill', y='tip', data=tips)
plt.show()
correlation = tips['total_bill'].corr(tips['tip'])
print("Correlation coefficient between total_bill and tip:", correlation)