Shift and lag operations in Data Analysis Python - Mini Project: Build & Apply

Shift and lag operations

📖 Scenario: You work in a sales department. You have daily sales data for a small store. You want to compare each day's sales with the previous day's sales to see if sales went up or down.

🎯 Goal: Build a small program that uses shift and lag operations on sales data to compare each day's sales with the previous day.

📋 What You'll Learn

Create a pandas DataFrame with daily sales data.

Add a new column that shows the previous day's sales using shift.

Calculate the difference between current day sales and previous day sales.

Print the final DataFrame showing the comparison.

💡 Why This Matters

🌍 Real World

Shift and lag operations are used in time series analysis to compare current values with past values, such as daily sales, stock prices, or sensor readings.

💼 Career

Data analysts and data scientists use shift and lag operations to detect trends, calculate changes, and prepare data for forecasting models.

1

Create the sales data DataFrame

Create a pandas DataFrame called sales_data with two columns: 'date' and 'sales'. Use these exact values for 'date': '2024-04-01', '2024-04-02', '2024-04-03', '2024-04-04', '2024-04-05'. Use these exact values for 'sales': 100, 150, 130, 160, 170. Import pandas as pd first.

Data Analysis Python

import pandas as pd
# Create the sales_data DataFrame with the exact dates and sales values
# Your code here

Hint

Use pd.DataFrame with a dictionary containing the 'date' and 'sales' lists.

2

Add a column for previous day's sales

Create a new column in sales_data called 'prev_day_sales' that contains the previous day's sales using the shift(1) method on the 'sales' column.

Data Analysis Python

import pandas as pd
sales_data = pd.DataFrame({
    'date': ['2024-04-01', '2024-04-02', '2024-04-03', '2024-04-04', '2024-04-05'],
    'sales': [100, 150, 130, 160, 170]
})
# Add the 'prev_day_sales' column using shift(1) on 'sales'
# Your code here

Hint

Use sales_data['prev_day_sales'] = sales_data['sales'].shift(1) to get the previous day's sales.

3

Calculate sales difference from previous day

Create a new column in sales_data called 'sales_diff' that calculates the difference between 'sales' and 'prev_day_sales'.

Data Analysis Python

import pandas as pd
sales_data = pd.DataFrame({
    'date': ['2024-04-01', '2024-04-02', '2024-04-03', '2024-04-04', '2024-04-05'],
    'sales': [100, 150, 130, 160, 170]
})
sales_data['prev_day_sales'] = sales_data['sales'].shift(1)
# Calculate the difference between 'sales' and 'prev_day_sales' in 'sales_diff'
# Your code here

Hint

Subtract sales_data['prev_day_sales'] from sales_data['sales'] and assign to sales_diff.

4

Print the final DataFrame

Print the sales_data DataFrame to show the 'date', 'sales', 'prev_day_sales', and 'sales_diff' columns.

Data Analysis Python

import pandas as pd
sales_data = pd.DataFrame({
    'date': ['2024-04-01', '2024-04-02', '2024-04-03', '2024-04-04', '2024-04-05'],
    'sales': [100, 150, 130, 160, 170]
})
sales_data['prev_day_sales'] = sales_data['sales'].shift(1)
sales_data['sales_diff'] = sales_data['sales'] - sales_data['prev_day_sales']
# Print the sales_data DataFrame
# Your code here

Hint

Use print(sales_data) to display the DataFrame.