Free course · by Debugshala, Indore
Statistics and EDA Tutorial
15 free lessons, in the order we teach them in class: start at lesson 1 and work down. Every lesson has an analogy, a diagram, code you can run or copy, a quick quiz and an FAQ.
- 15Lessons
- 2Modules
- ~2 hReading time
- FreeAlways
01Statistics for Data Science
- Statistics for Data Science: Mean, Spread and DistributionsMean, median, standard deviation, percentiles, the normal distribution and correlation vs causation, each with short NumPy code you can run.
- Probability for Data Science: Rules and Python ExamplesLearn probability for data science: events, addition and multiplication rules, conditional probability and expected value, with pandas code you can run.
- Probability Distributions Explained: Binomial, Poisson, NormalBinomial, Poisson, normal and exponential distributions explained with PMF, PDF and CDF, a chooser flowchart and Python code that runs without scipy.
- Central Limit Theorem Explained with a Python SimulationSee the central limit theorem in action: simulate skewed data in numpy, compute standard error, build confidence intervals and learn when the CLT fails.
- Bayes' Theorem Explained with Examples and Python CodeBayes' theorem made intuitive with a dengue test example, natural frequency trees, spam filtering and Bayesian A/B testing, each with runnable Python.
- Hypothesis Testing in Python: p-values, t-tests, Chi-squareHypothesis testing step by step: null and alternative, p-values, Welch's t-test, chi-square and Type I/II errors, with numpy code that runs in your browser.
- A/B Testing for Data Scientists: Design, Sample Size, AnalysisPlan and analyse A/B tests: sample size, random assignment, two-proportion z-test, confidence intervals, peeking and sample ratio mismatch, in Python.
- Sampling Techniques in Statistics: Types with Python ExamplesSimple random, systematic, stratified, cluster and convenience sampling compared, with sampling bias, sample size formulas and pandas code to try.
- Linear Algebra for Data Science: Vectors, Matrices, PythonLinear algebra for data science made practical: vectors, dot products, cosine similarity, matrix multiplication and eigenvectors, with runnable numpy code.
02Exploratory Data Analysis
- Exploratory Data Analysis (EDA) in Python: A 7-Step GuideExploratory data analysis step by step in pandas: structure, quality checks, univariate and bivariate analysis, segments and written findings, with code.
- Handling Missing Data in Python: MCAR, MAR, MNAR and ImputationHandle missing data the right way: spot MCAR, MAR and MNAR, compare median, KNN and iterative imputation, add missing flags and avoid leakage in pipelines.
- Outlier Detection Methods: Z-Score, IQR, MAD and MahalanobisOutlier detection explained with electricity bills: z-score masking, the IQR rule, modified z-score, Mahalanobis distance and what to do with each outlier.
- Data Preprocessing: Feature Scaling and Encoding in PythonFeature scaling and categorical encoding in scikit-learn: StandardScaler vs MinMaxScaler vs RobustScaler, one-hot, ordinal and target encoding, pipelines.
- Feature Engineering Techniques for Machine Learning in PythonFeature engineering techniques with pandas: date parts, cyclical sin/cos encoding, ratios, interactions, group aggregates, binning, and how to avoid leakage.
- Time Series Analysis in Python: Trend, Seasonality, ForecastsTime series analysis basics in pandas: trend, seasonality, rolling means, autocorrelation, differencing, time-based splits and a baseline forecast to beat.