Exploratory Data Analysis & Statistical Computing with Python
Master data wrangling, empirical distributions, and hypothesis testing in Python
The essential foundational course for modern data science and AI engineering. Build rock-solid data intuition by wrangling unstructured datasets, assessing data cleanliness programmatically, visualizing probability distributions, performing hypothesis tests, and delivering three comprehensive capstone projects.
Course Prerequisites
- Basic Python programming syntax and high school algebra.
Part of Academy Track:
What You Will Master
Curriculum Modules (6 Modules)
Explore the structured module breakdown, lesson outcomes, and practical lab exercises.
Module 1: Python Data Science Foundations
6 Lessons • ~10.8 Study Hours (1.08 CEUs)Welcome to Module 1: Python Data Science Foundations. In this section of the curriculum, learners dive deep into foundational and advanced principles designed for production application. This module covers: Understand the course roadmap, install the Python data science stack, and configure Jupyter for a reproducible EDA workflow.; Master NumPy's ndarray model, vectorized operations, and broadcasting rules — the performance backbone of every pandas and scikit-learn operation.; Go beyond .read_csv() and master pandas data structures, multi-indexing, dtype management, and column operations at the professional level..
Course Orientation & Environment Setup
Understand the course roadmap, install the Python data science stack, and configure Jupyter for a reproducible EDA workflow.
NumPy Fundamentals — Arrays, Vectorization & Broadcasting
Master NumPy's ndarray model, vectorized operations, and broadcasting rules — the performance backbone of every pandas and scikit-learn operation.
Pandas Deep Dive — Series, DataFrames & Index Mechanics
Go beyond .read_csv() and master pandas data structures, multi-indexing, dtype management, and column operations at the professional level.
Pandas Data Cleaning — Missing Values, Duplicates & Outliers
Build a systematic data quality pipeline: audit missingness, remove duplicates, detect and handle outliers, and document every cleaning decision.
Pandas Advanced — GroupBy, Window Functions & Reshape Operations
Master pandas' most powerful aggregation and transformation primitives: groupby-agg, rolling/expanding windows, pivot tables, melt, and merge.
Capstone Lab: Demographic Data Analyzer
Build a census intelligence engine with pure pandas vectorized operations, answering 9 multi-dimensional demographic questions on 32,561 census records.
Module 2: Data Wrangling & Multi-Source Ingestion
4 Lessons • ~7.7 Study Hours (0.77 CEUs)Welcome to Module 2: Data Wrangling & Multi-Source Ingestion. In this section of the curriculum, learners dive deep into foundational and advanced principles designed for production application. This module covers: Learn the professional three-phase data wrangling framework — Gather, Assess, and Clean — applied to a real multi-source social media dataset.; Conduct a structured quality and tidiness assessment of multiple DataFrames using both visual inspection and programmatic pandas techniques.; Apply systematic cleaning fixes to all identified issues, resolve tidiness problems by reshaping columns, and merge three sources into one master DataFrame..
Data Wrangling Fundamentals — Gather, Assess, Clean
Learn the professional three-phase data wrangling framework — Gather, Assess, and Clean — applied to a real multi-source social media dataset.
Assessment — Visual & Programmatic Data Quality Auditing
Conduct a structured quality and tidiness assessment of multiple DataFrames using both visual inspection and programmatic pandas techniques.
Cleaning — Programmatic Fixes, Merging & Master Table Construction
Apply systematic cleaning fixes to all identified issues, resolve tidiness problems by reshaping columns, and merge three sources into one master DataFrame.
WeRateDogs Capstone — Analysis & Insight Communication
Use the cleaned WeRateDogs master DataFrame to answer six analytical questions, produce visualizations, and write a professional insight report.
Module 3: Statistical Distributions & Hypothesis Testing
4 Lessons • ~8.1 Study Hours (0.81 CEUs)Welcome to Module 3: Statistical Distributions & Hypothesis Testing. In this section of the curriculum, learners dive deep into foundational and advanced principles designed for production application. This module covers: Develop intuition for probability distributions, learn to identify them in real data using visual and statistical tools, and understand when to use parametric vs non-parametric approaches.; Understand the Chi-Square test of independence from first principles, implement it in scipy, interpret the results, and know its assumptions and limitations.; Complete end-to-end EDA on the No-Show Medical Appointments dataset — from cleaning to statistical testing — and produce a full analytical report..
Understanding Distributions — Parametric vs Non-Parametric
Develop intuition for probability distributions, learn to identify them in real data using visual and statistical tools, and understand when to use parametric vs non-parametric approaches.
Chi-Square Test of Independence — From Theory to Python
Understand the Chi-Square test of independence from first principles, implement it in scipy, interpret the results, and know its assumptions and limitations.
No-Show Appointments Capstone — Full EDA Report
Complete end-to-end EDA on the No-Show Medical Appointments dataset — from cleaning to statistical testing — and produce a full analytical report.
Capstone Lab: Sea Level Rise Predictor with Linear Regression
Analyze 130+ years of global sea level tidal records, apply scipy.stats.linregress, evaluate rate acceleration post-2000, and extrapolate predictive models through 2050.
Module 4: Multivariate Visualization & Data Storytelling
5 Lessons • ~9 Study Hours (0.9 CEUs)Welcome to Module 4: Multivariate Visualization & Data Storytelling. In this section of the curriculum, learners dive deep into foundational and advanced principles designed for production application. This module covers: Understand Matplotlib's Figure/Axes object model, master the artist hierarchy, and produce fully annotated, publication-ready charts from first principles.; Master Seaborn's statistical plotting API — histplot, kdeplot, scatterplot, boxplot, violinplot, pairplot, heatmap — and build the visual vocabulary for multivariate EDA.; Use seaborn's PairGrid and pairplot to visualize relationships across many variables simultaneously — the most powerful tool for pre-modeling feature analysis..
Matplotlib Architecture & Publication-Grade Plot Anatomy
Understand Matplotlib's Figure/Axes object model, master the artist hierarchy, and produce fully annotated, publication-ready charts from first principles.
Seaborn for Statistical Visualization — Distributions, Relationships & Heatmaps
Master Seaborn's statistical plotting API — histplot, kdeplot, scatterplot, boxplot, violinplot, pairplot, heatmap — and build the visual vocabulary for multivariate EDA.
Pairplot, PairGrid & Plot Matrix — Exploring Multi-Dimensional Relationships
Use seaborn's PairGrid and pairplot to visualize relationships across many variables simultaneously — the most powerful tool for pre-modeling feature analysis.
Capstone Lab: Medical Examination Data Visualizer
Engineer BMI clinical features, normalize health indicators, melt data for sns.catplot facet grids, and construct masked correlation heatmaps using np.triu on 70,000 patient records.
Capstone Lab: Page View Time Series & Seasonality Visualizer
Clean high-frequency web traffic with quantile trimming, construct long-term line charts, monthly grouped bar charts, and decompose trend vs seasonality using box plots.
Module 5: Explanatory Visualization & Presentation
2 Lessons • ~4.3 Study Hours (0.43 CEUs)Welcome to Module 5: Explanatory Visualization & Presentation. In this section of the curriculum, learners dive deep into foundational and advanced principles designed for production application. This module covers: Understand the fundamental shift from exploratory analysis (for you) to explanatory communication (for stakeholders), and learn the design principles that make charts tell clear stories.; Complete the Prosper Loans EDA: run the full multivariate exploratory analysis and then build a polished explanatory presentation focusing on the four key features that drive loan outcomes..
Explanatory vs Exploratory Visualization — Polishing Charts for Stakeholders
Understand the fundamental shift from exploratory analysis (for you) to explanatory communication (for stakeholders), and learn the design principles that make charts tell clear stories.
Prosper Loans Capstone — From Exploration to Presentation Deck
Complete the Prosper Loans EDA: run the full multivariate exploratory analysis and then build a polished explanatory presentation focusing on the four key features that drive loan outcomes.
Module 6: EDA Capstone Frameworks & Pre-Modeling Audit
2 Lessons • ~4.3 Study Hours (0.43 CEUs)Welcome to Module 6: EDA Capstone Frameworks & Pre-Modeling Audit. In this section of the curriculum, learners dive deep into foundational and advanced principles designed for production application. This module covers: Before handing data off to a machine learning pipeline, an AI engineer must audit features for correlation structure, multicollinearity, and target leakage — the three most critical pre-modeling checks.; Learn the structure and standards of a professional EDA report — how to organize findings, write for non-technical audiences, handle uncertainty transparently, and package deliverables..
Feature Analysis — Correlation, Multicollinearity & Target Leakage
Before handing data off to a machine learning pipeline, an AI engineer must audit features for correlation structure, multicollinearity, and target leakage — the three most critical pre-modeling checks.
The Professional EDA Report — Structure, Standards & Delivery
Learn the structure and standards of a professional EDA report — how to organize findings, write for non-technical audiences, handle uncertainty transparently, and package deliverables.
Data Science & AI Progression
Continue advancing through the sequential curriculum stages of this academy track: