rjaat/ml-algos-implementation

Implementation of most common used ML Algorithms

Popular ML Algorithms Implementation

Algorithms Like Naive Bayes, k-Nearest Neighbour & Decision Tree.

• Libraries Used : Numpy, Pandas, Matplotlib, Scikit-Learn
  • Numpy -> For Mathematical Operations
  • Pandas -> Data Analyzing, Exploring, Manipulating
  • Matplotlib -> Graphical Representation Of Data
  • Scikit-Learn -> Provides Inbuilt Functions For ML & Statistics
    
    
• Dataset Used: Adult-Census-Dataset
  
  

Brief About Used Algorithms

• Naive Bayes Classifier

  
  
  • Gaussian Naive Bayes
    • Best for Continuously valued features
  • Multinomial Naive Bayes
    • Mostly used in text categorization classification
  • Bernoulli Naive Bayes
    • Best for Binary valued features
      
      

• k-Nearest Neighbour

  • Based on Supervised Learning technique.
  • It assumes the similarity between the new sample and available data then put the new sample into the category according to similarity.
  • It is called Lazy Learner Algorithm because it stores all availabe data.
  • k-NN is a non-parametric algorithm, which means it does not make any assumption on underlying data.
  
  

• Decision Tree

  
  • It is a Supervised learning technique.
  • Mostly used for classification problems but can be used for Regression also.
  • It is tree-structured classifier, where internal nodes represent the features of a dataset, branches represent the decision rules and each leaf node represents the outcome.
  • In a DTree, there are two nodes, which are the Decision Node and Leaf Node. Decision nodes are used to make any decision and have multiple branches, whereas Leaf nodes are the output of those decisions and do not contain any further branches.
  • It is a graphical representation for getting all the possible solutions to a problem/decision based on given conditions.
  • A decision tree simply asks a question, and based on the answer (Yes or No), it further split the tree into subtrees.
  

Note

Detailed Information related to results & Performance of trained models in this repo, can be found in related doc files.

These doc files have been uploaded with the code.