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

# 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

# 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

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)

KhyatiMahendru

# import dataset
import pandas as pd
data = pd.read_csv('mtcars.csv')

# remove string and categorical variables
cat_var = ['model', 'cyl', 'vs', 'am', 'gear', 'carb']
data = data.drop(cat_var, axis = 1)

# scale the variables to prevent coefficients from becoming too large or too small
from sklearn.preprocessing import MinMaxScaler

KhyatiMahendru

import statsmodels.api as sm
model = sm.OLS(y, X[:, 4]).fit()
model.summary()

KhyatiMahendru

from sklearn.datasets import make_regression
X, y = make_regression(n_samples = 20, n_features = 6, random_state = 2, noise = 0.5)

KhyatiMahendru

from sklearn.tree import DecisionTreeClassifier
clf_gini = DecisionTreeClassifier(criterion = 'gini', random_state = 33)
clf_gini.fit(X, Y)