Overview to Data Science

Introduction - Today’s problem statement

Ice breaker session

Data Collection (SQL)

- Connect to a simulated database

- Write SQL queries to pull data

- Join tables if needed

- Export query results into CSV for Python work

Data Cleaning (Python - Pandas)

- Load CSV into Pandas DataFrame

- Handle missing values, data type issues

- Standardize column names

- Remove duplicates or incorrect entries

Exploratory Data Analysis (EDA)

- Descriptive statistics (mean, median, counts)

- Data visualizations (matplotlib/seaborn)

- Identify patterns and trends

- Detect outliers

Feature Engineering

- Create new features

- Encode categorical variables (label encoding, one-hot)

- Normalize or standardize features if needed

Model Building and Evaluation

- Split data into training and testing sets

- Build a Logistic/Linear Regression model

- Evaluate using metrics such as Accuracy, Precision, Recall, Confusion Matrix, RMSE etc.

- Discuss ways to improve the model (more features, better cleaning, different algorithms)

Wrap-Up: Model Review + Discussion

- Review everyone's model results

- Talk about next steps (hyperparameter tuning, trying other models like Random Forests)

- Share additional learning resources

- Feedback and Q&A

Important Note: A laptop is mandatory, as the hands-on sessions involve programming.