MachineLearning_Algorithms_from_Scratch

This project deals with implementation of various machine learning models from scratch using python, without actually importing them from the sklearn library

Till now the models implemented:

1. k-means clustering
2. knn classifier (k-nearest neighbour)
3. Naive Bayesian Classifier
4. Linear Regression
5. Logistic Regression

The machine learning algorithms are implemented from scratch without using their pre existing libraries in python

Libraries used:

1. numpy : working with arrays(matrices and vectors)
2. pandas & mathplotlib : for data handling , manpulation and visualization of datasets
3. Train Test split (from Sklearn.model_selection) : To split the dataset into training and test sets
4. sklearn.metrices : To measure accuracy_score , precision, recall , f1_scroe and confusion matrix

Datasets Used:

1. k-means clustering : iris.csv
2. knn classifier (k-nearest neighbour) : iris.csv
3. Naive Bayesian Classifier : iris.csv
4. Linear Regression : data.txt
5. Logistic Regression : synthetic or synthesized data using numpy