Data Science Foundation Course

Lesson 1 • Setting Up a Data Science Environment

Installs and configures essential tools for reproducible analysis. Ensures every student has a working environment before coding begins.

Lesson 2 • The Data Science Lifecycle

Traces a project from business problem to deployed solution. Provides a mental model for organizing all subsequent technical skills.

Lesson 3 • What Data Science Is

Defines data science, distinguishes it from related fields, and maps its core components. Establishes shared vocabulary used throughout the course.

Lesson 1 • Data Manipulation with pandas

Teaches DataFrame creation, indexing, filtering, and transformation. Directly supports the data cleaning and feature engineering chapters ahead.

Lesson 2 • File I/O and Data Loading

Reads and writes CSV, JSON, and Excel files and connects to SQL databases. Prepares students to ingest real-world datasets in any format.

Lesson 3 • Working with NumPy Arrays

Introduces vectorized numerical computation using NumPy. Enables fast array operations that underpin pandas and machine learning libraries.

Lesson 4 • Writing Reusable Python Code

Applies functions, modules, and error handling to build maintainable scripts. Establishes coding practices that scale to full project pipelines.

Lesson 1 • Handling Missing Data

Compares deletion, imputation, and indicator strategies for missing values. Teaches trade-offs that affect downstream model performance.

Lesson 2 • Assessing Data Quality

Identifies missing values, duplicates, and inconsistencies through profiling. Establishes a systematic audit process before any transformation begins.

Lesson 3 • Transforming and Standardizing Data

Applies type conversion, normalization, and encoding to raw columns. Produces consistent formats required by statistical and machine learning models.

Lesson 4 • Building Reproducible Data Pipelines

Encapsulates cleaning steps into reusable functions and pipeline objects. Ensures consistent preprocessing across training and production datasets.

Lesson 1 • Common Statistical Tests

Applies t-tests, chi-square tests, and ANOVA to real datasets. Equips students to choose and execute the correct test for each data scenario.

Lesson 2 • Correlation and Linear Relationships

Quantifies linear associations using Pearson and Spearman correlation. Lays the groundwork for regression modeling in the next chapter.

Lesson 3 • Probability Essentials

Covers probability rules, conditional probability, and common distributions. Provides the mathematical language used in every probabilistic model.

Lesson 4 • Experimental Design Principles

Covers controlled experiments, randomization, and A/B testing frameworks. Prepares students to design valid tests for data-driven decision-making.

Lesson 1 • Descriptive Statistics Fundamentals

Computes measures of central tendency, spread, and shape for numeric variables. Provides the quantitative foundation for interpreting all visualizations.

Lesson 2 • Univariate and Bivariate Analysis

Examines single-variable distributions and pairwise relationships between variables. Reveals feature behavior and potential predictive signals.

Lesson 3 • Visualization Best Practices

Applies design principles to create clear, accurate, and audience-appropriate charts. Prevents misleading visuals and improves stakeholder communication.

Lesson 4 • EDA-Driven Feature Insights

Translates EDA findings into actionable decisions about feature engineering and modeling. Bridges exploratory work with the machine learning chapters ahead.

Lesson 1 • Classification Algorithms

Trains logistic regression, decision trees, k-nearest neighbors, and naive Bayes classifiers. Connects algorithm choice to data characteristics and business requirements.

Lesson 2 • Model Evaluation and Metrics

Applies accuracy, precision, recall, F1, ROC-AUC, and RMSE to assess model quality. Teaches metric selection based on class imbalance and business cost trade-offs.

Lesson 3 • Regression Algorithms

Covers linear, ridge, lasso, and decision tree regression for continuous targets. Teaches when and why to apply regularization to reduce overfitting.

Lesson 4 • Machine Learning Workflow

Establishes the end-to-end process from data splitting to model evaluation. Provides a repeatable framework applied to every algorithm in this chapter.

Lesson 1 • Dimensionality Reduction

Reduces feature space using PCA and t-SNE while preserving meaningful variance. Improves visualization, speeds up training, and mitigates the curse of dimensionality.

Lesson 2 • Feature Selection Methods

Removes irrelevant and redundant features using filter, wrapper, and embedded methods. Reduces overfitting and speeds up model training.

Lesson 3 • Feature Engineering Techniques

Creates new informative features from existing columns through transformation and interaction. Directly improves predictive power of models built in the previous chapter.

Lesson 4 • Clustering Algorithms

Applies k-means, hierarchical, and DBSCAN clustering to discover natural groupings. Enables customer segmentation, anomaly detection, and data summarization.

Lesson 1 • Building a Model API

Wraps a trained model in a REST API using Flask or FastAPI. Enables other applications and services to consume predictions programmatically.

Lesson 2 • Saving and Versioning Models

Serializes trained models and tracks experiments with versioning tools. Ensures reproducibility and enables rollback when production models degrade.

Lesson 3 • Model Monitoring and Maintenance

Tracks prediction drift, data drift, and performance degradation in production. Establishes processes for retraining and updating deployed models.

Lesson 4 • Communicating Results to Stakeholders

Translates technical findings into clear narratives and visual dashboards for business audiences. Closes the gap between model output and organizational decision-making.