Task 1: Data Cleaning & Preprocessing

📌 Objective

Learn how to clean and prepare raw data for Machine Learning.

🛠 Tools Used

Python

Pandas

NumPy

Matplotlib

Seaborn

📂 Dataset

You can use any dataset relevant to the task. Example: Titanic Dataset. Download Titanic Dataset

🚀 Steps Performed

1. Imported dataset and explored basic information (null values, data types).

2. Handled missing values using mean/median/imputation.

3. Converted categorical features into numerical using encoding techniques.

4. Normalized/standardized numerical features.

5. Visualized outliers using boxplots and handled them.

📊 What I Learned

Data cleaning

Handling null values

Encoding categorical variables

Feature scaling (normalization/standardization)

Outlier detection

❓ Interview Questions

1. What are the different types of missing data?

2. How do you handle categorical variables?

3. What is the difference between normalization and standardization?

4. How do you detect outliers?

5. Why is preprocessing important in ML?

6. What is one-hot encoding vs label encoding?

7. How do you handle data imbalance?

8. Can preprocessing affect model accuracy?

📌 Submission Guidelines

Created a GitHub repository for this task.

Added code,this README.md file. Task 1: Data Cleaning & Preprocessing

📌 Objective

Learn how to clean and prepare raw data for Machine Learning.

🛠 Tools Used

Python

Pandas

NumPy

Matplotlib

Seaborn

📂 Dataset

You can use any dataset relevant to the task. Example: Titanic Dataset. Download Titanic Dataset

🚀 Steps Performed

1. Imported dataset and explored basic information (null values, data types).

2. Handled missing values using mean/median/imputation.

3. Converted categorical features into numerical using encoding techniques.

4. Normalized/standardized numerical features.

5. Visualized outliers using boxplots and handled them.

📊 What I Learned

Data cleaning

Handling null values

Encoding categorical variables

Feature scaling (normalization/standardization)

Outlier detection

❓ Interview Questions

1. What are the different types of missing data?

2. How do you handle categorical variables?

3. What is the difference between normalization and standardization?

4. How do you detect outliers?

5. Why is preprocessing important in ML?

6. What is one-hot encoding vs label encoding?

7. How do you handle data imbalance?

8. Can preprocessing affect model accuracy?

📌 Submission Guidelines

Created a GitHub repository for this task.

Added code, dataset (if needed), and this README.md file.

👨‍💻 Author - Rakshith N