pca_with_python.py

# -*- coding: utf-8 -*-
"""pca_with_python.ipynb

Automatically generated by Colaboratory.

Original file is located at
**Import Libraries**
"""

import pandas as pd
import numpy as np
from sklearn.datasets import load_iris
from sklearn.preprocessing import StandardScaler
import matplotlib.pyplot as plt

"""**Load Iris Data**"""

iris = load_iris()

df = pd.DataFrame(data=iris.data, columns=iris.feature_names)

df['class'] = iris.target
print(df)

"""**Get the value of x and y**"""

x = df.drop(labels='class', axis=1).values
y = df['class'].values

print(x.shape, y.shape)

"""**Implementation of PCA**"""

class convers_pca():
    def __init__(self, no_of_components):
        self.no_of_components = no_of_components
        self.eigen_values = None
        self.eigen_vectors = None
        
    def transform(self, x):
        return np.dot(x - self.mean, self.projection_matrix.T)
    
    def inverse_transform(self, x):
        return np.dot(x, self.projection_matrix) + self.mean
    
    def fit(self, x):
        self.no_of_components = x.shape[1] if self.no_of_components is None else self.no_of_components
        self.mean = np.mean(x, axis=0)
        
        cov_matrix = np.cov(x - self.mean, rowvar=False)
        
        self.eigen_values, self.eigen_vectors = np.linalg.eig(cov_matrix)
        self.eigen_vectors = self.eigen_vectors.T
        
        self.sorted_components = np.argsort(self.eigen_values)[::-1]
        
        self.projection_matrix = self.eigen_vectors[self.sorted_components[:self.no_of_components]]

        self.explained_variance = self.eigen_values[self.sorted_components]
        self.explained_variance_ratio = self.explained_variance / self.eigen_values.sum()

"""**Standardization**"""

std = StandardScaler()
transformed = StandardScaler().fit_transform(x)

"""**PCA with Component = 2**"""

pca = convers_pca(no_of_components=2)
pca.fit(transformed)

"""**Plotting**"""

x_std = pca.transform(transformed)

plt.figure()
plt.scatter(x_std[:, 0], x_std[:, 1], c=y)