KhyatiMahendru

KhyatiMahendru

# import required functions and libraries
from sklearn.datasets import make_circles
from sklearn.neighbors import kneighbors_graph
from sklearn.cluster import SpectralClustering
import numpy as np
import matplotlib.pyplot as plt

# generate your data
X, labels = make_circles(n_samples=500, noise=0.1, factor=.2)

KhyatiMahendru

# get the image from "https://cdn.pixabay.com/photo/2017/03/27/16/50/beach-2179624_960_720.jpg"
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import cv2

# read image in grayscale
img = cv2.imread('beach-2179624_960_720.jpg', 0)

# obtain svd

KhyatiMahendru

import numpy as np
from sklearn.utils.extmath import randomized_svd

A = np.array([[-1, 2, 0], [2, 0, -2], [0, -2, 1]])
u, s, vt = randomized_svd(A, n_components = 2)

print("Left Singular Vectors:")
print(u)

print("Singular Values:") 

KhyatiMahendru

import numpy as np
from sklearn.decomposition import TruncatedSVD

A = np.array([[-1, 2, 0], [2, 0, -2], [0, -2, 1]])
print("Original Matrix:")
print(A)

svd =  TruncatedSVD(n_components = 2)
A_transf = svd.fit_transform(A)

KhyatiMahendru

import numpy as np
from numpy.linalg import svd

# define your matrix as a 2D numpy array
A = np.array([[4, 0], [3, -5]])

U, S, VT = svd(A)

print("Left Singular Vectors:")
print(U)

KhyatiMahendru

# create document term matrix for your data
# you can use TfidfVectorizer instead of CountVectorizer as well
from sklearn.feature_extraction.text import CountVectorizer
cvec = CountVectorizer()
docTermMat = cvec.fit_transform(data['text'].values)

# truncated SVD to preserve 20 topics
from sklearn.decomposition import TruncatedSVD
lsa = TruncatedSVD(n_components = 20, n_iter = 500)
lsa.fit(docTermMat)

KhyatiMahendru

from sklearn.decomposition import TruncatedSVD

// say you want to reduce to 2 features
svd = TruncatedSVD(n_features = 2)

//obtain the transformed data
data_transformed = svd.fit_transform(data)

KhyatiMahendru

# import required libraries
import numpy as np
import matplotlib.pyplot as plt
import cv2
from skimage.color import rgb2gray
from scipy import ndimage

# read the image
img = cv2.imread('1.jpeg')

KhyatiMahendru

from sklearn.decomposition import PCA

// say you want to reduce to 2 features
pca = PCA(n_components = 2)

// obtain transformed data
data_transformed = pca.fit_transform(data)