I already have the answer, but I don't know how 's the answer comes from.Please help me explan the question step by step thank you! 2.Given the following data set, we apply a naïve Bayesian (NB) classifier to predict the Health status.Each patient is described by Temp={H,N}, BP={H,N}, Test1={P,N} and Test2={P,N}. The class is Health={D,H}.IDTempВРTest1Test2Health1234HH.N6754HNNPD2345NHPP2457HH.PND3567NHP7532NH.NNH1456NNNH1468HNNNH8989HNNPH9876HNNNHFor a new patient, ID 9999, with Temp=H, BP=H, Test1=N, Test2=P, is he/she Healthy (H) or Diseased (D)?Show (a) the value of each term in your NB classifier, and (b) your prediction.Answer:P_temp(H/D)=3/5, P_temp(N/D)=2/5P_temp(H/H)=3/5, P_temp(N/H)=2/5P_BP(H/D)=4/5, P_BP(N/D)=1/5P_BP(H/H)=1/5, P_BP(N/H)=4/5P_Test1(P/D)=4/5, P_Test1(N/D)=1/5P_Test1(P/H)=0/5, P_Test1(N/H)=5/5P_Test2(P/D)=3/5, P_Test2(N/D)=2/5P_Test2(P/H)=1/5, P_Test2(N/H)=4/5new patient A: Temp=H, BP=H, Test1=N, Test2=PS((H,H,N,P),D) = 3/5 * 4/5 * 1/5 * 3/5 = 0.0576S((H,H,N,P),H) = 3/5 * 1/5 * 5/5 * 1/5 = 0.024S((H,H,N,P),D) > S((H,H,N,P),H)So predict A as class D.

Given Data : The dataset where Heath is the class variable. To find : Given the data row = {ID…

2. Given the following data set, we apply a naïve Bayesian (NB) classifier to predict the Health status. Each patient is described by Temp={H,N}, BP={H,N}, Test1=(P,N} and Test2=(P,N}. The class is Health={D,H). ID Temp BP Testl Test2 Health 1234 H P N D 6754 H P. D. 2345 N H P. D. 2457 H. N D 3567 N H P D 7532 1456 N N 1468 N 8989 H N H. 9876 H N N N H. For a new patient, ID 9999, with Temp=H, BP=H, Test1=N, Test2=P, is he/she Healthy (H) or Diseased (D)? Show (a) the value of each term in your NB classifier, and (b) your prediction. Answer: P_temp(H/D)=3/5, P_temp(N/D)=2/5 P_temp(H/H)=3/5, P_temp(N/H)=2/5 P_BP(H/D)=4/5, P_BP(N/D)=1/5 P_BP(H/H)=1/5, P_BP(N/H)=4/5 P_Test1(P/D)=4/5, P_Test1(N/D)=1/5 P_Test1(P/H)=0/5, P_Test1(N/H)=5/5 P_Test2(P/D)=3/5, P_Test2(N/D)=2/5 P_Test2(P/H)=1/5, P_Test2(N/H)=4/5 new patient A: Temp=H, BP=H, Test1=N, Test2=P S((H,H,N, P),D) = 3/5 * 4/5 * 1/5 * 3/5 = 0.0576 S((H,H,N,P),H) = 3/5 * 1/5 * 5/5 * 1/5 = 0.024 S((H,H,N,P),D) > S((H,H,N,P),H) So predict A as class D. %D

2. Given the following data set, we apply a naïve Bayesian (NB) classifier to predict the Health status. Each patient is described by Temp={H,N}, BP={H,N}, Test1=(P,N} and Test2=(P,N}. The class is Health={D,H). ID Temp BP Testl Test2 Health 1234 H P N D 6754 H P. D. 2345 N H P. D. 2457 H. N D 3567 N H P D 7532 1456 N N 1468 N 8989 H N H. 9876 H N N N H. For a new patient, ID 9999, with Temp=H, BP=H, Test1=N, Test2=P, is he/she Healthy (H) or Diseased (D)? Show (a) the value of each term in your NB classifier, and (b) your prediction. Answer: P_temp(H/D)=3/5, P_temp(N/D)=2/5 P_temp(H/H)=3/5, P_temp(N/H)=2/5 P_BP(H/D)=4/5, P_BP(N/D)=1/5 P_BP(H/H)=1/5, P_BP(N/H)=4/5 P_Test1(P/D)=4/5, P_Test1(N/D)=1/5 P_Test1(P/H)=0/5, P_Test1(N/H)=5/5 P_Test2(P/D)=3/5, P_Test2(N/D)=2/5 P_Test2(P/H)=1/5, P_Test2(N/H)=4/5 new patient A: Temp=H, BP=H, Test1=N, Test2=P S((H,H,N, P),D) = 3/5 * 4/5 * 1/5 * 3/5 = 0.0576 S((H,H,N,P),H) = 3/5 * 1/5 * 5/5 * 1/5 = 0.024 S((H,H,N,P),D) > S((H,H,N,P),H) So predict A as class D. %D

Database System Concepts

7th Edition

ISBN:9780078022159

Author:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Publisher:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Chapter1: Introduction

Section: Chapter Questions

Problem 1PE

See similar textbooks

Similar questions

If we dont have a lot of data to work with, which model is well suited for that? A. Bootstrap Forest B. Logistic Regression C. Decision Tree D. Neural Network
Consider the following knowledge base and infer “Ahmed is an advocate” using appropriate inferencing algorithm.i. Anyone who drives any CJ is a rough character.ii. Every driver drives is either a CJ or a Wrangler.iii. Anyone who drives any Wrangler is an urban professional.iv. Every urban professional is an advocate.v. Any nice girl does not date anyone who is a rough character.vi. Sara is a nice girl, and Ahmed is a driver.
If we evaluate a classification model(such as SVC) using the K-fold cross-validation and we set K = 9, how many times will the classification model be trained and evaluated? Group of answer choices 3 6 9 1
Considering the threshold as 0.5, Calculate the F1 measure for attached predictions of a classification model. Group of choice: A. 1 B. 0.45 C. 0.67 D.0.53
PART 2: Using following columns build a model to predict the ff person would survive or not, • Pclass• Sex• Age 1. A 27 years old, female passenger from passenger class 3 2. A 40 years old, male passenger from passenger class 1 3. A 34 years old, male passenger from passenger class 2 (Screen Shot - one image for the 3 items)
If we have three categorical features, where each feature can take four values, and we have five classes, how many probabilities do we need to calculate using Naive Bayes classification?
A police academy has just brought in a batch of new recruits. All recruits are given an aptitude test and a fitness test. Suppose a researcher wants to know if there is a significant difference in aptitude scores based on a recruits’ fitness level. Recruits are ranked on a scale of 1 – 3 for fitness (1 = lowest fitness category, 3 = highest fitness category). Using “ApScore” as your dependent variable and “FitGroup” as your independent variable, conduct a One-Way, Between Subjects, ANOVA, at α = 0.05, to see if there is a significant difference on the aptitude test between fitness groups. Identify the correct values for dfbetween and dfwithin A. dfbetween = 7 dfwithin = 7 B. dfbetween = 13 dfwithin = 2 C. dfbetween = 2 dfwithin = 13 D. dfbetween = 2 dfwithin = 2
We would like to learn a model to predict whether a monster is scary or not (S). We identify four features for this purpose: Number of eyes (N), Color of eyes (C), Height (H), and Odor (O). We collect data 8 monster as shown below. Rank these four features according to their mutual information with S. Make sure to identify ties.
Machine Learning Evaluation measures. Consider a dataset with 90 negative examples and 10 positive examples. Suppose a model built using this data predicts 30 of the examples as positive (only 10 of them are actually positive) and 70 as negative. What are the numbers of True Positives (TP), False Positives (FP), True Negatives (TN), False Negatives (FN), Accuracy, Precision, Recall, and Specificity? Show all your steps
Which of the following statements about confusion matrix is wrong A) Confusion matrix is a performance measure for probability prediction techniques B) Confusion matrix is derived based on classification rules with cut-off value 0.5 C) Confusion matrix is derived based on training partition to measure a model’s predictive performance D) None of the above I need typed answer with explanation K
A robot who updates its beliefs using Bayesian reasoning has just obtained measurement z from pointing its sensor array at a door. It would like to determine whether the door is open (P(open|z)) before driving forward. The prior probability of P (open) = 0.3 and P (closed) = 0.7 Your sensor model indicates that the likelihood of seeing that observation is P(z|open) = 0.6 and P (z|closed) = 0.3. Calculate the posterior P (open|z).
Is it feasible to have several dependant variables in a model? A choice dilemma may include more than one variable. When given the option between a descriptive, predictive, and prescriptive model of a given decision, which would you use? Why? Explain how a famous businessperson, politician, or military figure's good decision-making led to a disastrous outcome, or how the opposite was true. Fifth, how does a computer model vary from a spreadsheet model?