Question

(Data Analysis Question) Explain supervised machine learning using some examples of data and at least two, two-dimensional supervised machine learning methods. Describe in writing any figures that you normally would draw.

Answer 1

Sion VIS om Supervised machine learning:- Supervised machine learning is one type of humun Suprovision. The main goal in Supervised learning is to learn a model from labelled training data that allovers els to make predictions about cinseen or future data: Here, the term Supervised refers to a set of Samples where the desired output signals are already known. In Seepervised learning, the training data you feed to the algorithm includes the desired Solutions called labels. Examples of supervised learning is → Spam filter - classification problem 4 car price prediction on the basis of Features - prediction problems. al catures U୬ ୧TV Supervised leaming algorithms : 1) Linear regression 2) Logistic Regression 3) Support vector Moching 4) Neural netzoorks

Examples In machine learning, classification is a Supervised learning approach in cohich the computer program leams from the data input given to it and then uses this learning to classify new observation. Day | outlook Temp humidity wind Decision DU Hot wear NO Sunny Hot 2) | Sunny hot 3) overcast hot hot High high high weak strong weak na No No yos Rain Mild high weak Yes Rain cool Normal weak Yes Normal cool Strong Rain NO 1) overcost cool Normal Strong yes Sunny Mild high weak 9) Sunny cool normal weals yes overcast hot Normal weak yes.

outlook Nowo, by using cars algorithe, we will solve this problem. Ginile)» 1-603-607)-(3? = 0.643 T P N Gini Index (31) Sanny 4 3 0.315 (64) Sovercast & Bio o (84) & Rain 3 a 0.445 Gini (Sunny) = 1-(5)- 2 = 0.375 Gini covercast) = 1-0)-(3)? Gini (Rain) = 1 - (*)-(+)? = 0.445 Gin (outlook) - 4 x 0.315 + 6 x 4 = x - Mini = 0.15 +0+ 0.1335 = 0.2835 Minimum,

- T N Shot 4 2 P @ 1 3 1 Gini 0.5 0.5 0.315 Scool 4 Gin? (hot) = 1-(2)2-(3) = 0.5 Gani(tild) = 1 -(1)-(1) - 0.5 Go? (cool) = 1- (2)2-(7)? = 0.375 Gini (Temp) - 20:5+ *015 + 0x0.375 10 → 0:2 + 0 + 0.15 0:460 Hurmidity T p z Gini w - ΝΙΟΥ, Shigh 5 2 3 0.48 S Normal 5 4 1 0.32 Si Gini Chigh) = 1-(3) * - )' = 0.48 Ganić Normal)= 14(**)?-C) 2 0-32

Gini churridity) = 5x0.48 +EXO32 -0.24 +0.16 = 0.40 wird ł Sstrong Sweak 3 7 P N a 5 2 Gini 0.445 0.409 Gini (strong) - 1-(1)-(3) = 0.445 Gini (weak) = 1-0 532-C* = 0.409 Giriccoind) = 340.445 + 5o X0:409 0:1335 +0.2863 0.4198 outlook Sunny, Tovercast Rainy yes Sunny Sunny Sunny . sunny 4 . , P N 3 Gini 0.375

c 1 Temp Snot I Shild Scool N 2 T a I 1 P 0 o . Gini 0 o o , 0 0 tu - Ginic Grnictemp) = 0 pod O . . Minimum Minimum , Humidity P - Shigh 3 Snormal i T 0 N Gini 3.0. 00 . Gini (humidity) =0% Minimum Imum wind T Sstrong Sweak 1 3 P N 0 1 1.2 Gini 0 0.445 Gini (60er k) = 1-()?- ( )2 = 0.445 : Gini(coind) - xo + vo4455 50.333

outlook) - Raindo Sunny brerast (yes (Temp bot / No Rainy N :) T SRainy 3 a Gini 0.445 Gini se 0 S T strong 1 Sweak a D , Ń 0 1 20 humidity Gini cosind) =0/min . . . Tillöin. Gini Shigh 1 0 0 Snormal a l 0.5 Gini (normal) = 1- (+)2-(3) Inl = 0.5 SChumidity) = 4 xo + 2x0.5 mi 0:333

(outlook) . Rainy Overcast - Sunny / Temp yes) weak ong Mild hot no yes

and Examplet using linear Regression ao ave an Economist for the Co-operative. you gasher the follocoing data: Fertilizer(lb). Yield (alb) 4 ; 3.0 5.5 . 10 12 6.5 9.0 line relating con Find the least squares and fertilizer Soll- si | Yi | 2:2 | 4.2 1 274 9.0 30.25 42.253) 65 8100108 32 1 24.0 1625 218 CL : 218 - (32)(24) 4: 296 – (3232 = 0.65

bo = 9 - 8,1 = 6 – (0-65)() -0.80 Y = 0.8 +0.6534 10+ G=0.8 +0.65%, Yeld(123) 67 0 ut .. . Fertilizer (lb) a-dimensional Machine learning methods! - linear Reqressions Regression is a function that predicts the dependent Variable based upon values of the independent variable linear regression formula vo LU ediy Sea + Bate where, Y = Dependent variable a = independent Bo = Intercept Bi = Slope {z Residual Error.

bo = 9 - 8,1 = 6 – (0-65)() -0.80 Y = 0.8 +0.6534 10+ G=0.8 +0.65%, Yeld(123) 67 0 ut .. . Fertilizer (lb) a-dimensional Machine learning methods! - linear Reqressions Regression is a function that predicts the dependent Variable based upon values of the independent variable linear regression formula vo LU ediy Sea + Bate where, Y = Dependent variable a = independent Bo = Intercept Bi = Slope {z Residual Error.

positive linear Relationship Negative linear Relationship Ely) Ely) Regression line Regression line Ilhi Intercept slope B, is positive Intercept Boi Bo slope B, is (ave) No Relationship Intercept Regression line Slope B, iso The aim of Regression model is to find a slope and intercept so that the straight line with that slope and intercept Ats the points in the Scatteo diagram 1. as closely as possible. only 2 points are necessary to determine a Stoaight line. If only one point is given , then there are many straight lines that could pass through this point, but when two points are given, this

liniquely plentifies the straight line passes through these 2 points ) Support Vector Machines!. this method is also 2-dimensional. sum's are supervised learning models with associated learning algorithms that analyze data used for classification and Regression analysis. ✓ This is achiedted by using the concept of hyperplane which acts as a dece'sion boundary Separating the classes. SVM classifies the data Amor SVM tries to minimize the genercilization by maximizing the margin:

Examples of keinel fonctions feln polynomial kernel with degreed K(x,y) = (xTy tijd Radial basis function Kernel with width o k(xy) = exp (=112-y 11?/(20)2)) Sigmoid with parameter k and O- kla,y)= tan h(KxTy + 0). ✓

please rate with up vote thank you