This script is an implementation of Principal Component Analysis

pca.py

import numpy as np
from sklearn.preprocessing import StandardScaler






class PCA:
    
    def __init__(self,n_components=None):
        self.n_components=n_components
        self.variance_ratio=0
    
    def transform(self,X_data):
        return self.fit(X_data)

    def fit(self,X):
        n_samples,n_features=X.shape

        #Standardize data
        X_std = StandardScaler().fit_transform(X)

        #center data
        mean= np.mean(X_std,axis=0)

        #Covariance matrix
        cov_mat= (X_std-mean).T.dot(X_std-mean)/(X_std.shape[0]-1)

        #Eigen Decomposition
        eig_vals, eig_vecs = np.linalg.eig(cov_mat)

        u,s,v = np.linalg.svd(X_std.T)

        # u is same as cov_mat

        #Making tuple (eigen_value,eigen_vector)
        eig_pairs = [(np.abs(eig_vals[i]), eig_vecs[:,i]) for i in range(len(eig_vals))]

        #Sorting in reverse order 
        eig_pairs.sort()
        eig_pairs.reverse()

        #Explained Variance (to choose prominent principal components)
        explained_var = (s** 2) / (n_samples - 1)
        total_var = explained_var.sum()

        var_ratio=explained_var/total_var
        self.variance_ratio=var_ratio
        # Creating k dimensional eigen matrix w
        matrix_w = np.hstack((eig_pairs[0][1].reshape(n_features,1), eig_pairs[1][1].reshape(n_features,1)))

        Y= X_std.dot(matrix_w)
        return Y