KhyatiMahendru

from sklearn.metrics import silhouette_score

sil = []
kmax = 10

# dissimilarity would not be defined for a single cluster, thus, minimum number of clusters should be 2
for k in range(2, kmax+1):
  kmeans = KMeans(n_clusters = k).fit(x)
  labels = kmeans.labels_
  sil.append(silhouette_score(x, labels, metric = 'euclidean'))

KhyatiMahendru

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

KhyatiMahendru

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

KhyatiMahendru

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

KhyatiMahendru

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

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

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 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 TruncatedSVD

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

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