uditgt / machine-learning-using-python

Python & ML

Machine Learning using Python (Udemy) | Certification 🎓

Decision Trees / Random Forest / Ada & Gradient Boosting...

• Palmer Penguins notebook
• Banknote Authentication (refer above notebook)
• Rock Density Xray (regression) (refer above notebook)
• Mushroom dataset (refer above notebook)
• Telco Customer Churn notebook

...XGBoost

• Car Sales Price Prediction notebook
• Santander Customer Transaction Prediction notebook
• Titanic notebook

Neural Networks

• Tweet Classification (bi-directional LSTM) notebook
• Fake News detection notebook
• Telco Churn notebook
• Customer Attrition (simple NN) - proprietary dataset notebook

SVM classification / regression: includes building pipeline

• Cement slump dataset notebook
• Wine Fraud dataset (refer above notebook)

KNN classification: includes building pipeline

• Gene expression/ Cancer dataset notebook
• Mine/ Rock dataset (refer above notebook)

Logistic regression and regularization: includes threshold tuning

• Hearing test notebook
• Heart disease (refer above notebook)
• Online advertising (refer above notebook)
• IRIS (refer above notebook)
• Titanic (refer above notebook, +XGBoost notebook)

Linear regression and regularization:

• Advertising dataset (from ISLR) notebook
• Ames housing dataset notebook

NLP / Naive Bayes

• Large Movie Review dataset notebook

Recommender System

• Grouplens Movie Rating dataset notebook

Other examples

• PCA based approach to finding relative value trades on Treasury Yield Curve notebook
• Imbalanced learning on Customer Attrition dataset (proprietary) with 1:50 imbalance - using techniques from data resampling, cost-sensitive learning, ensemble-learning and anomaly algorithm approaches notebook

---

References & Fun reads:

• XGBoost Tuning - Owen Zhang's utube and slides, MLM post, Tianqi Chen talk and ppt, Martin Jullum

• TensorFlow - playground

• Regex Crossword, Regex101

• Trees

  • Random Decision Forests (1995, Ho)
  • Leo Brieman's website
  • Stochastic Gradient Boosting (1998, Friedman)
  • A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting (1996, Schapire et al)
  • Gentle Introduction to Gradient Boosting (slides)

• Suppor Vector Machines

  • Theoretical Foundation of the Potential Function (1964, Aizerman et al)
  • Training Algorithm for Optimal Margin Classifier (1992, Vapnik et al)
  • Support Vector Networks (1995, Vapnik et al)
  • Tutorial on SV Regression (2003)

• Imbalanced Learning

  • Isolation-Based Anomaly Detection (2012, Liu et al.)

• Misc

  • Imbalanced learning - different approaches
  • Cross Validation - scoring objects, different approaches
  • Feature Engineering - MLM article, HSE lectures
  • Kaggle winners - Heritage Provider Network
  • Statistics - P-hacking 538
  • Technical Papers - separate repo
  • Python stylyguides - Google guide, PEP8, YAPF
  • Applied ML at Facebook - pdf, link