machine-learning

Collaborators:

• Kaushal Patil

• Dhruvil Dave

Guide to AI with Python(And R)

• Machine Learning

Open Browser Previews

src

• Practical Introduction
• Training Models 1
• Training Models 2
• Ensemble Methods
• Dimensionality Reduction

theory

-Introduction

-Regression

How to Ml

• How to Ml

Information about Source (Hyperlinked to Python Notebooks;Scroll for html links)

• Practical Introduction Contains basic information about approaches to make machine learning models.
• Training Models 1 Contains practical approaches to Following Training Models
  • Contents
    • Linear Regression
      • Normal Equation
      • Gradient Descent
      • Regularized Models
    • Logistic Regression
    • Decision Tress
      • Classification
      • Regression
• Training Models 2 Contains practical approaches to following Training Models

• Ensemble Methods Contains notes and explainations on following ensemble methods:

  • Contents
    • Voting Classifier
    • Bagging vs Pasting
    • Random Patches and Random Subspaces
    • Random Forests
    • Feature Importance
    • Boosting
      • AdaBoost
      • Gradient Boosting
    • Stacking

• Dimensionality Reduction Contains Approaches to reduce dimension of data before trainging a model on it

• Unsupervised Learning Contains Unsupervised Learning Algorithms

• theory folder constains theory about Machine Learning

  • Introduction contains Statistical Theory(In depth) about machine learning

  • Regression constains theory about simple and multiple linear regression

• Data Visualisation Contains introductory practical insights on plotting with Seaborn.(Reference Kaggle MicroCourse on Data Visualisation)

• S1Regresssion is an example of how to apply linear regression to a dataset. The analysis is dangerously incomplete as of now (10/10/19).

• tf_introduction is guide to basic operations of tensorflow.

• Essental Statistics and Probability is the guide to essentials of statistics and probability required for data science and engineering.

Please use the rendered HTML file directly from the bin/ folder if to avoid any malfunctioning.

Please use the commit.sh file to commit the changes and then push to the remote to maintain a common format of commit messages

conda.sh file sets up the environment required to run the codes