Statistics_for_Data_Scientists
📊 Statistics for Data Scientists
Comprehensive statistics cheatsheet & formula reference
Available in Turkish 🇹🇷 and English 🇬🇧
📖 What’s Inside?
A set of interactive HTML cheatsheets and a Kaggle notebook covering all essential statistics concepts for data science — from descriptive statistics to Bayesian inference and ML evaluation metrics. Each HTML page is single, self-contained, and can be viewed directly in your browser.
🗂️ Resources
📐 Statistics Fundamentals
| Resource | Language | Description | Link |
|---|---|---|---|
| Formula Reference | 🇬🇧 English | LaTeX-rendered formulas, theory only — no code | View → |
| Cheatsheet | 🇬🇧 English | Formulas with Python code examples | View → |
| Formül Rehberi | 🇹🇷 Türkçe | LaTeX formüller, sadece teori — kod yok | Görüntüle → |
| Cheatsheet | 🇹🇷 Türkçe | Formüller ve Python kod örnekleri | Görüntüle → |
| Kaggle Notebook — Stats Cheatsheet | 🇬🇧 English | Statistics cheatsheet with Python examples | Open in Kaggle → |
📊 ML Evaluation Metrics (NEW)
| Resource | Language | Description | Link |
|---|---|---|---|
| ML Metrics Guide | 🇬🇧 English | Precision, Recall, F1, ROC-AUC, Regression metrics | View → |
| ML Metrik Rehberi | 🇹🇷 Türkçe | Precision, Recall, F1, ROC-AUC, Regresyon metrikleri | Görüntüle → |
| Kaggle Notebook — ML Metrics | 🇬🇧 English | Interactive notebook with visualizations & runnable code | Open in Kaggle → |
Formula Reference — Pure theory with beautifully typeset LaTeX math (powered by KaTeX)
Cheatsheet — Same topics + ready-to-use Python code snippets you can copy-paste
ML Metrics Guide — Covers classification & regression evaluation metrics with formulas, examples, and a decision guide
Kaggle Notebook — Hands-on notebook with scikit-learn, matplotlib & seaborn visualizations
📋 Topics Covered
📐 Statistics Fundamentals (18 Sections)
| # | Topic | Key Concepts |
|---|---|---|
| 01 | Descriptive Statistics | Mean, Median, Mode, Variance, Std Dev, Skewness, Kurtosis |
| 02 | Probability Distributions | Normal, Binomial, Poisson, CLT |
| 03 | Z-Score | Standardization, Critical Values, CDF |
| 04 | Confidence Intervals | z-interval, t-interval, Proportion CI |
| 05 | Hypothesis Testing | H₀/H₁, Type I & II Errors, p-value |
| 06 | Normality Tests | Shapiro-Wilk, D’Agostino, QQ-Plot |
| 07 | Variance Homogeneity | Levene, Bartlett |
| 08 | T-Test | One-sample, Independent, Paired, Welch |
| 09 | Z-Test | Large-sample, Two-proportion |
| 10 | ANOVA | One-way, F-statistic, Tukey HSD |
| 11 | Chi-Square Test | Independence, Goodness of Fit |
| 12 | Correlation & Regression | Pearson, Spearman, OLS, R² |
| 13 | Non-Parametric Tests | Mann-Whitney U, Wilcoxon, Kruskal-Wallis |
| 14 | Effect Size | Cohen’s d, Eta-squared |
| 15 | Power Analysis | Sample size calculation |
| 16 | A/B Testing | Proportion tests, MDE, Lift, Pitfalls |
| 17 | Bayesian Basics | Bayes’ Theorem, Prior/Posterior, Medical Test Paradox |
| 18 | Decision Tree | Which test to choose? + Quick checklist |
📊 ML Evaluation Metrics (11 Sections)
| # | Topic | Key Concepts |
|---|---|---|
| 01 | Confusion Matrix | TP, FP, FN, TN, Type I & II Errors |
| 02 | Accuracy | Overall correctness, Accuracy Paradox |
| 03 | Precision | Positive predictive value, when FP is costly |
| 04 | Recall (Sensitivity) | True positive rate, when FN is costly |
| 05 | F1 Score | Harmonic mean, F-Beta variants (F0.5, F2) |
| 06 | Specificity | True negative rate, Sensitivity vs Specificity |
| 07 | ROC Curve & AUC | Threshold-independent model comparison |
| 08 | Log Loss | Probability calibration, cross-entropy |
| 09 | Regression Metrics | MAE, MSE, RMSE, R² |
| 10 | Metric Selection Guide | Which metric for which scenario |
| 11 | Python Implementation | scikit-learn code with visualizations |
🖨️ Save as PDF
- Open any of the links above in your browser
- Press Ctrl + P (or Cmd + P on Mac)
- Select “Save as PDF”
- ⚠️ Enable “Background graphics” for the dark theme colors to render properly
✨ Features
- 🌙 Dark premium theme — Easy on the eyes, great for late-night study sessions
- 📐 LaTeX formulas — Beautifully rendered with KaTeX
- 🐍 Python code — Copy-paste ready examples using NumPy, SciPy, statsmodels, scikit-learn
- 📊 Interactive visualizations — matplotlib & seaborn charts in the Kaggle notebook
- 🗺️ Decision trees — “Which test/metric should I use?” visual guides
- 🖨️ Print-optimized — Clean light theme when printing or saving as PDF
- 🌍 Bilingual — Full Turkish & English versions
- 🏆 Kaggle-ready — Upload the
.ipynbdirectly to Kaggle
📄 License
This project is open source and available for educational purposes.
Made with ❤️ for data science learners