Courses › Course03
Course03 · Math, Statistics, and Data
The linear algebra, calculus, probability, and data-analysis skills that make machine learning understandable rather than magical.
42 days 42 written 42 complete
Days 99-105 · Linear Algebra I: Vectors and Matrices 7/7 complete
- Day 099 Vectors: Direction, Magnitude, and Meaning complete
- Day 100 Matrices and What They Represent complete
- Day 101 Matrix Multiplication complete
- Day 102 Linear Transformations complete
- Day 103 Dot Products and Similarity complete
- Day 104 NumPy: Arrays and Vectorized Thinking complete
- Day 105 Transforming Images with Matrices complete
Project: Image Transformer — Use NumPy matrix operations to rotate, scale, and shear images, demonstrating linear transformations visually.
Days 106-112 · Linear Algebra II and Calculus 7/7 complete
- Day 106 Eigenvalues and Eigenvectors, Intuitively complete
- Day 107 Norms, Distances, and Similarity Measures complete
- Day 108 Derivatives: Rates of Change complete
- Day 109 Partial Derivatives and Gradients complete
- Day 110 The Chain Rule complete
- Day 111 Gradient Descent from Scratch complete
- Day 112 Visualizing Optimization complete
Project: Gradient Descent Visualizer — Implement gradient descent from scratch and animate its path across 2D loss surfaces, including a pathological case.
Days 113-119 · Probability and Statistics 7/7 complete
- Day 113 Probability: Events, Rules, and Intuition complete
- Day 114 Random Variables and Distributions complete
- Day 115 Bayes’ Theorem complete
- Day 116 Descriptive Statistics That Don’t Lie complete
- Day 117 Sampling and the Central Limit Theorem complete
- Day 118 Hypothesis Tests and Confidence Intervals complete
- Day 119 Analyzing an Experiment End to End complete
Project: A/B Test Analyzer — Analyze a simulated experiment end to end: hypothesis, test statistic, confidence interval, and a plain-language verdict.
Days 120-126 · pandas and Data Wrangling 7/7 complete
- Day 120 pandas: Series and DataFrames complete
- Day 121 Loading and Inspecting Data complete
- Day 122 Selecting and Filtering complete
- Day 123 Groupby and Aggregation complete
- Day 124 Merging and Reshaping complete
- Day 125 Cleaning Messy Data complete
- Day 126 A Reproducible Cleaning Pipeline complete
Project: Messy Dataset Rescue — Take a genuinely messy public dataset and produce a documented, reproducible cleaning notebook with before/after data-quality checks.
Days 127-133 · Data Visualization 7/7 complete
- Day 127 Why We Visualize, and Choosing the Right Chart complete
- Day 128 Matplotlib Fundamentals complete
- Day 129 Statistical Plots with seaborn complete
- Day 130 Distributions and Relationships complete
- Day 131 Time Series Visualization complete
- Day 132 Visual Storytelling and Chart Honesty complete
- Day 133 Building an EDA Report complete
Project: Exploratory Analysis Report — Produce a narrated EDA report on a real dataset with at least five well-chosen, honestly-scaled charts.
Days 134-140 · Working with Real Data 7/7 complete
- Day 134 Finding Data: Open Datasets and APIs complete
- Day 135 From API to DataFrame complete
- Day 136 The Exploratory Data Analysis Process complete
- Day 137 Thinking in Features complete
- Day 138 Data Ethics, Bias, and Provenance complete
- Day 139 Reproducible Notebooks complete
- Day 140 Section Project: An Exploratory Study complete
Project: Section Project: Full Exploratory Study — Choose a public dataset, pose three questions, and deliver a reproducible notebook answering them with cleaned data, statistics, and visuals.