which of the following is not a data cleansing activity

Guri Bee

2 min read

·

18-10-2024

1

0

Share

Data Cleansing: Unmasking the Hidden Truth in Your Data

Data is the lifeblood of any modern business, but raw data is often messy and inaccurate. Like a dusty attic, it's full of hidden treasures and unwanted clutter. Data cleansing is the process of cleaning up this mess, ensuring your data is accurate, consistent, and ready for analysis.

But what exactly does data cleansing involve, and what activities don't fall under its umbrella? Let's explore this question with the help of insights from the GitHub community.

What is Data Cleansing?

Imagine a spreadsheet with duplicate entries, missing values, and inconsistent formats. This is the kind of data that data cleansing addresses.

Key data cleansing activities include:

• Identifying and removing duplicates: Imagine a customer database with multiple entries for the same person. Duplicate removal ensures you're working with a single, accurate record for each individual.
• Handling missing values: Missing data can skew your analysis. Data cleansing techniques like imputation or deletion help fill in the gaps or remove incomplete records.
• Standardizing data formats: Inconsistent formats like "01/01/2023" and "January 1st, 2023" can lead to errors. Standardization ensures consistent data representation.
• Ensuring data accuracy: This involves verifying data against trusted sources, identifying and correcting errors, and ensuring data integrity.

Unmasking the "Not" in Data Cleansing

Now, let's tackle the question: Which of the following is NOT a data cleansing activity?

GitHub user "data-cleansing-expert" provides a helpful list of common data cleansing activities:

• Data transformation
• Data validation
• Data standardization
• Data enrichment
• Data de-duplication

Based on this list, we can deduce that data transformation is not a primary data cleansing activity.

Why?

Data transformation is a broader process that involves changing data into a different format or structure. While data cleansing often involves data transformation as a step (e.g., converting dates to a consistent format), it's not the primary focus of data cleansing.

Data cleansing focuses on the quality of the data, whereas data transformation focuses on its structure and usability.

Think of it this way:

• Data cleansing: Cleaning your messy room by removing clutter, fixing broken items, and organizing your belongings.
• Data transformation: Taking the cleaned items from your room and packing them into boxes for a move.

While packing the boxes involves interacting with the items you cleaned, it's a separate process with its own set of goals.

Putting it into Practice

Here's a practical example:

Imagine you have a dataset of customer information with inconsistent date formats. This dataset is messy and difficult to analyze.

Data cleansing: You could standardize all dates to "YYYY-MM-DD" format, remove duplicate customer entries, and fill in missing address information.

Data transformation: After cleansing, you could transform the dataset into a different format (e.g., CSV, JSON) for easier use in a specific application.

In essence, data cleansing prepares your data for analysis, while data transformation makes it ready for specific use cases.

Conclusion

Data cleansing is a crucial step in ensuring the accuracy and reliability of your data. By understanding the key activities involved, you can effectively clean and prepare your data for analysis and decision-making. Remember, data transformation is a related but distinct process that focuses on data structure and usability. By understanding the difference, you can unlock the full potential of your data and drive better business outcomes.