11/7/24, 7:47 AM Lab 4 solved (1)

2022F-BSE-014
LAB # 04
SUPERVISED LEARNING (NAÏVE BAYES ALGORITHM)

OBJECTIVE

Implementing supervised learning, Naïve Bayes algorithm for training, testing and classification.

Lab Tasks:

Fig 1

1. Implement Naïve Bayes Algorithm on the above dataset in Fig 1 to predict whether the players can
play or not when the weather is overcast and the temperature is mild.

In [74]: from sklearn import preprocessing

from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import confusion_matrix, accuracy_score
from sklearn.model_selection import train_test_split

In [75]: le = preprocessing.LabelEncoder()
weather = ['sunny','sunny','overcast','rainy','rainy','rainy','overcast','sunny','sunny','rain
temperature = ['hot','hot','hot','mild','cool','cool','cool','mild','cool','mild','mild','mild
play = ['no','no','yes','yes','yes','no','yes','no','yes','yes','yes','yes','yes','no']

file:///C:/Users/DC/Downloads/Lab 4 solved (1).html 1/6

11/7/24, 7:47 AM Lab 4 solved (1)

In [ ]:

In [76]: le = preprocessing.LabelEncoder()
weather_encoded = le.fit_transform(weather)
temperature_encoded = le.fit_transform(temperature)
play_encoded = le.fit_transform(play)

In [77]: features = list(zip(weather_encoded,temperature_encoded))

features_train,features_test,label_train,label_test = train_test_split(features,play_encoded,t

In [78]: model = GaussianNB()

model.fit(features_train,label_train)

Out[78]: ▾ GaussianNB i ?

GaussianNB()

In [79]: predicted = model.predict(features_test)

print(predicted)

[1 0 0]

In [80]: conf_mat = confusion_matrix(label_test,predicted)

print(conf_mat)

[[1 0]
[1 1]]

In [81]: accuracy = accuracy_score(predicted,label_test)

print(accuracy)

0.6666666666666666

In [ ]:

file:///C:/Users/DC/Downloads/Lab 4 solved (1).html 2/6

11/7/24, 7:47 AM Lab 4 solved (1)

In [82]: from sklearn import preprocessing

from sklearn.naive_bayes import GaussianNB
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix,accuracy_score

In [83]: age = ['youth','youth','middle_aged','senior','senior','senior','middle_aged','youth','youth',

income = ['high','high','high','medium','low','low','low','medium','low','medium','medium','me
student =['no','no','no','no','yes','yes','yes','no','yes','yes','yes','no','yes','no']
credit_rating = ['fair','excellent','fair','fair','fair','excellent','excellent','fair','fair'
class_buys_computer = ['no','no','yes','yes','yes','no','yes','no','yes','yes','yes','yes','ye

In [84]: le = preprocessing.LabelEncoder()
age_encoded = le.fit_transform(age)
income_encoded = le.fit_transform(income)
student_encoded = le.fit_transform(student)
credit_rating_encoded = le.fit_transform(credit_rating)
class_buyes_computer_encoded = le.fit_transform(class_buys_computer)

In [85]: features = list(zip(age_encoded,income_encoded,student_encoded,credit_rating_encoded,class_buy

features_train,features_test,label_train,label_test = train_test_split(features,class_buyes_co

In [86]: model = GaussianNB()

model.fit(features_train,label_train)

Out[86]: ▾ GaussianNB i ?

GaussianNB()

In [87]: predicted = model.predict(features_test)

print(predicted)

[1 1 0]

In [88]: conf_mat = confusion_matrix(label_test, predicted)

print(conf_mat)

[[1 0]
[0 2]]

In [89]: accuracy = accuracy_score(label_test,predicted)

print(accuracy)

1.0

home task

In [90]: from sklearn import preprocessing

from sklearn.naive_bayes import GaussianNB
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix, accuracy_score
import pandas as pd

In [91]: df = pd.read_csv('random_dataset.csv')
age = df['Age']
salary = df['Salary']
experience = df['Experience']
education = df['Education Level']
isEmployed = df['Is Employed']

file:///C:/Users/DC/Downloads/Lab 4 solved (1).html 3/6

11/7/24, 7:47 AM Lab 4 solved (1)

In [92]: le = preprocessing.LabelEncoder()
age_encoded = le.fit_transform(age)
salary_encoded = le.fit_transform(salary)
experience_encoded = le.fit_transform(experience)
education_encoded = le.fit_transform(education)
isEmployed_encoded = le.fit_transform(isEmployed)

In [93]: features = list(zip(age_encoded,salary_encoded,experience_encoded,education_encoded))

In [94]: features_train,features_test,label_train,label_test = train_test_split(features,isEmployed,tes

In [95]: model = GaussianNB()

model.fit(features_train,label_train)

Out[95]: ▾ GaussianNB i ?

GaussianNB()

In [96]: predicted = model.predict(features_test)

print(predicted)

[1 1 1 1 1 0 1 1 1 1 1 1 0 0 1 0 1 0 0 1]

In [97]: conf_mat = confusion_matrix(predicted,label_test)

print(conf_mat)

[[ 4 2]
[ 4 10]]

In [98]: accuracy = accuracy_score(predicted,label_test)

print(accuracy)

0.7

from github:

file:///C:/Users/DC/Downloads/Lab 4 solved (1).html 4/6

11/7/24, 7:47 AM Lab 4 solved (1)

file:///C:/Users/DC/Downloads/Lab 4 solved (1).html 5/6

11/7/24, 7:47 AM Lab 4 solved (1)

In [ ]:

file:///C:/Users/DC/Downloads/Lab 4 solved (1).html 6/6