Data Science Basics Course

Lesson 1 • Types of Data and Their Sources

Categorizes structured, unstructured, and semi-structured data and identifies common source types. Prepares students to select appropriate tools for each data type.

Lesson 2 • 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 3 • The Data Science Workflow

Introduces the end-to-end project lifecycle from problem framing to deployment. Provides a repeatable mental model for every subsequent chapter.

Lesson 1 • Working with Files and Libraries

Demonstrates reading and writing files and importing third-party libraries. Connects Python basics to the data ingestion tasks common in data science.

Lesson 2 • NumPy for Numerical Computing

Introduces array-based computation with NumPy for fast numerical operations. Bridges raw Python to the vectorized workflows used in data analysis.

Lesson 3 • Python Syntax and Core Data Types

Covers variables, operators, and built-in data types essential for scripting. Forms the syntactic foundation for all subsequent Python-based work.

Lesson 4 • Control Flow and Functions

Teaches conditional statements, loops, and reusable function definitions. Enables students to write modular, readable data processing code.

Lesson 1 • Descriptive Statistics Essentials

Covers measures of central tendency, spread, and shape for numerical variables. Provides quantitative summaries that reveal data characteristics at a glance.

Lesson 2 • Identifying and Handling Outliers

Defines outlier detection methods and evaluates their impact on analysis. Teaches principled decisions about retaining, transforming, or removing anomalies.

Lesson 3 • EDA Workflow and Reporting

Structures a repeatable EDA process and documents findings in a shareable report. Prepares students to communicate data insights before any model is built.

Lesson 4 • Data Visualization with Matplotlib and Seaborn

Builds publication-quality charts using Matplotlib and Seaborn APIs. Translates statistical findings into clear visual narratives for stakeholders.

Lesson 1 • Hypothesis Testing

Explains null and alternative hypotheses, p-values, and significance levels. Enables students to validate data assumptions and compare group differences.

Lesson 2 • Probability Theory Essentials

Covers probability rules, conditional probability, and Bayes' theorem. Provides the mathematical language underlying all probabilistic models.

Lesson 3 • Correlation and Causation

Distinguishes correlation from causation and quantifies linear relationships. Prevents common misinterpretations that lead to flawed modeling decisions.

Lesson 4 • Confidence Intervals and Effect Sizes

Constructs confidence intervals and measures practical significance beyond p-values. Equips students to report findings with appropriate uncertainty quantification.

Lesson 1 • Assessing Data Quality

Defines dimensions of data quality and methods for auditing completeness and consistency. Establishes a diagnostic baseline before any cleaning is applied.

Lesson 2 • Building Preprocessing Pipelines

Assembles cleaning and transformation steps into reproducible scikit-learn pipelines. Prevents data leakage and streamlines model training workflows.

Lesson 3 • Handling Missing Data

Explains missing data mechanisms and applies imputation and deletion strategies. Ensures students choose methods that preserve analytical validity.

Lesson 4 • Feature Scaling and Transformation

Applies normalization, standardization, and mathematical transforms to numeric features. Prepares data for distance-based and gradient-based algorithms.

Lesson 1 • Model Evaluation and Cross-Validation

Applies k-fold cross-validation and performance metrics to assess generalization. Prevents overfitting to a single train-test split through robust evaluation.

Lesson 2 • Classification Algorithms

Introduces logistic regression, decision trees, and k-nearest neighbors for categorical targets. Compares algorithm assumptions and appropriate use cases.

Lesson 3 • Ensemble Methods

Explains bagging, boosting, and stacking to improve predictive performance. Demonstrates how combining weak learners reduces variance and bias.

Lesson 4 • Hyperparameter Tuning

Optimizes model hyperparameters using grid search, random search, and Bayesian methods. Balances computational cost against performance improvement systematically.

Lesson 5 • Regression Algorithms

Covers linear regression, regularization, and polynomial extensions for continuous targets. Builds intuition for coefficient interpretation and prediction intervals.

Lesson 1 • Anomaly Detection

Detects rare observations using statistical and model-based approaches. Applies unsupervised techniques to fraud detection and quality control scenarios.

Lesson 2 • Feature Selection Methods

Identifies the most informative features using filter, wrapper, and embedded methods. Reduces noise and computational cost without sacrificing predictive power.

Lesson 3 • Dimensionality Reduction

Applies PCA and t-SNE to reduce feature space while preserving information. Improves model efficiency and enables high-dimensional data visualization.

Lesson 4 • Clustering Algorithms

Covers k-means, hierarchical, and density-based clustering for grouping unlabeled data. Teaches cluster evaluation and practical interpretation of results.

Lesson 1 • Project Documentation and Presentation

Structures technical reports, README files, and stakeholder presentations for a project. Ensures findings are reproducible and accessible to both technical and non-technical audiences.

Lesson 2 • Defining the Business Problem

Translates a vague business question into a precise, measurable data science objective. Aligns technical work with stakeholder success criteria from the outset.

Lesson 3 • Model Deployment Fundamentals

Packages a trained model as a REST API and deploys it to a cloud environment. Bridges the gap between notebook experimentation and production-ready systems.

Lesson 4 • Modeling and Iteration Strategy

Establishes a baseline model and iterates systematically toward performance targets. Applies experiment tracking to maintain reproducibility across model versions.