eda
August 1, 2024
[1]: import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
[2]: tips=pd.read_csv("tips.csv")
[3]: # Display the first few rows of the dataset
print(tips.head())
total_bill tip sex smoker day time size
0 16.99 1.01 Female No Sun Dinner 2
1 10.34 1.66 Male No Sun Dinner 3
2 21.01 3.50 Male No Sun Dinner 3
3 23.68 3.31 Male No Sun Dinner 2
4 24.59 3.61 Female No Sun Dinner 4
[4]: # Get basic information about the dataset
print(tips.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 244 entries, 0 to 243
Data columns (total 7 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 total_bill 244 non-null float64
1 tip 244 non-null float64
2 sex 244 non-null object
3 smoker 244 non-null object
4 day 244 non-null object
5 time 244 non-null object
6 size 244 non-null int64
dtypes: float64(2), int64(1), object(4)
memory usage: 13.5+ KB
None
[5]: # Check for missing values
print(tips.isnull().sum())
1
total_bill 0
tip 0
sex 0
smoker 0
day 0
time 0
size 0
dtype: int64
[6]: # The dataset contains 244 rows and 7 columns.
# Columns include 'total_bill', 'tip', 'sex', 'smoker', 'day', 'time', and␣
↪'size'.
# There are no missing values in the dataset.
[7]: # Summary statistics for numerical columns
print(tips.describe())
total_bill tip size
count 244.000000 244.000000 244.000000
mean 19.785943 2.998279 2.569672
std 8.902412 1.383638 0.951100
min 3.070000 1.000000 1.000000
25% 13.347500 2.000000 2.000000
50% 17.795000 2.900000 2.000000
75% 24.127500 3.562500 3.000000
max 50.810000 10.000000 6.000000
[8]: # The average total bill is approximately $19.79 with a standard deviation of␣
↪$8.90.
# The average tip is approximately $2.99 with a standard deviation of $1.38.
# The dataset includes bills ranging from $3.07 to $50.81, and tips ranging␣
↪from $1.00 to $10.00.
[9]: # Summary statistics for categorical columns
print(tips.describe(include=['O']))
sex smoker day time
count 244 244 244 244
unique 2 2 4 2
top Male No Sat Dinner
freq 157 151 87 176
[10]: # There are more male customers (157) compared to female customers (87).
# There are more non-smokers (151) compared to smokers (93).
# Most of the data is collected on Thursday, Friday, Saturday, and Sunday.
# Most meals are dinner (176) compared to lunch (68).
2
[11]: sns.set_style("whitegrid")
# Distribution of total bill
plt.figure(figsize=(8, 6))
sns.histplot(tips['total_bill'], kde=True)
plt.title('Distribution of Total Bill')
plt.xlabel('Total Bill')
plt.ylabel('Frequency')
plt.show()
[12]: # The distribution of total bills is right-skewed with most bills falling␣
↪between $10 and $20.
# There are some outliers with very high total bills.
[13]: # Distribution of tips
plt.figure(figsize=(8, 6))
sns.histplot(tips['tip'], kde=True)
plt.title('Distribution of Tips')
plt.xlabel('Tip')
plt.ylabel('Frequency')
3
plt.show()
[14]: # The distribution of tips is also right-skewed with most tips falling between␣
↪$2 and $4.
# There are a few outliers with very high tips.
[15]: # Scatter plot of total bill vs. tip
plt.figure(figsize=(8, 6))
sns.scatterplot(x='total_bill', y='tip', data=tips)
plt.title('Total Bill vs Tip')
plt.xlabel('Total Bill')
plt.ylabel('Tip')
plt.show()
4
[16]: # There is a positive correlation between the total bill and the tip amount.
# Higher total bills tend to have higher tips.
[17]: # Pairplot of the dataset
sns.pairplot(tips)
plt.show()
5
[18]: # The pairplot shows scatter plots for every pair of numerical variables and␣
↪histograms for individual variables.
# It confirms the positive correlation between total bill and tip.
[19]: # Count plot for categorical features
plt.figure(figsize=(8, 6))
sns.countplot(x='sex', data=tips)
plt.title('Count of Gender')
plt.show()
6
[20]: #There are more male customers than female customers in the dataset.
[21]: plt.figure(figsize=(8, 6))
sns.countplot(x='smoker', data=tips)
plt.title('Count of Smokers')
plt.show()
7
[22]: # There are more non-smokers than smokers in the dataset.
[23]: plt.figure(figsize=(8, 6))
sns.countplot(x='day', data=tips)
plt.title('Count of Days')
plt.show()
8
[24]: # The dataset has more entries for Saturday and Sunday compared to other days.
[25]: plt.figure(figsize=(8, 6))
sns.countplot(x='time', data=tips)
plt.title('Count of Time')
plt.show()
9
[26]: # There are more records for dinner time compared to lunch time.
[27]: # Box plot of tips by gender
plt.figure(figsize=(8, 6))
sns.boxplot(x='sex', y='tip', data=tips)
plt.title('Tips by Gender')
plt.show()
10
[28]: # The median tip amount is slightly higher for males compared to females.
[29]: # Box plot of tips by day
plt.figure(figsize=(8, 6))
sns.boxplot(x='day', y='tip', data=tips)
plt.title('Tips by Day')
plt.show()
11
[30]: # Tips tend to be higher on the weekends (Saturday and Sunday) compared to␣
↪weekdays (Thursday and Friday).
[31]: # Box plot of tips by time
plt.figure(figsize=(8, 6))
sns.boxplot(x='time', y='tip', data=tips)
plt.title('Tips by Time')
plt.show()
12
[32]: # Tips are generally higher during dinner time compared to lunch time.
[33]: # Box plot of tips by smoking status
plt.figure(figsize=(8, 6))
sns.boxplot(x='smoker', y='tip', data=tips)
plt.title('Tips by Smoking Status')
plt.show()
13
[34]: # Correlation matrix
corr = tips.select_dtypes(include=['float64', 'int64']).corr()
# Heatmap of the correlation matrix
plt.figure(figsize=(10, 8))
sns.heatmap(corr, annot=True, cmap='coolwarm', vmin=-1, vmax=1)
plt.title('Correlation Heatmap')
plt.show()
14
[36]: # The heatmap shows a strong positive correlation (0.68) between total bill and␣
↪tip.
# Other correlations are relatively weak.
Customer Demographics:
-There are more male customers than female customers.
-The majority of customers are non-smokers.
Restaurant Activity:
-The restaurant sees more activity on the weekends, especially on Saturdays.
-Dinner time is more popular than lunch time.
Spending and Tipping Behavior:
-Higher total bills are associated with higher tips, but the relationship is not perfectly linear. This
suggests that while people generally tip more when they spend more, other factors also influence
tipping behavior.
15
-Tips are higher on weekends, potentially due to larger dining groups or more generous tipping
behavior.
-The variability in tips is higher among male customers and smokers.
Service Insights:
-The restaurant might consider focusing on improving customer experiences during lunch times and
weekdays to potentially increase tips during these periods.
-Understanding the reasons behind high variability in tips among different groups (e.g., males,
smokers) could help in devising targeted strategies to encourage more consistent tipping.
16
