Import necessary libraries.

  Load the iris data set.

  Fix the dependent and independent variables.

  Build the naive bayes model for classification task.

  Split the data into train and test.

  Fit train data into the model.

  Predict the test data.

  Calculate precision and recall from scratch.

#import libraries
import warnings
warnings.filterwarnings(“ignore”)
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import classification_report, confusion_matrix, accuracy_score

#load data
data = pd.read_csv(‘/home/soft50/soft50/Sathish/practice/iris.csv’)

#check missing values
print(“Checking missing values\n\n”,data.isnull().sum())

#make it as a data frame
df = pd.DataFrame(data)

#print data shape
print(“\n”)
print(“Shape of data\n\n”,df.shape)

#Define X and y variable
X = df.iloc[:,0:4]
y = df.iloc[:,4]

#Split train and test data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

#training set and testing set
print(“\n”)
print(“Training data set\n\n”,X_train,”\n”,y_train)
print(“\n”)
print(“Testing data set\n\n”,X_test)

#Naive-bayes model
naive_bayes = MultinomialNB()
naive_bayes.fit(X_train,y_train)

#Predict the model
y_pred = naive_bayes.predict(X_test)

#confusion matrix
cm = (confusion_matrix(y_test, y_pred))
print(“\n”)
print(“Confusion Matrix:\n\n”,cm,”\n”)

print(“Precision:\n”)

#Precision calulation from scratch
def precision(cm):
p = (cm[0][0]/((cm[1][0])+(cm[2][0])+(cm[0][0])))
if (str(p) == ‘nan’):
print(“Precision setosa – “,”0.00”)
else:
print(“Precision setosa – “,round(p,2))
precision(cm)

def precision1(cm):
p1 = (cm[1][1]/((cm[0][1])+(cm[1][1])+(cm[2][1])))
if (str(p1) == ‘nan’):
print(“Precision versicolor – “,”0.00”)
else:
print(“Precision versicolor – “,round(p1,2))
precision1(cm)

def precision2(cm):
p2 = (cm[2][2]/((cm[1][2])+(cm[0][2])+(cm[2][2])))
if (str(p2) == ‘nan’):
print(“Precision virginica – “,”0.00”)
else:
print(“Precision virginica – “,round(p2,2),”\n”)
precision2(cm)

#recall calculation
print(“Recall:\n”)
def recall(cm):
p = (cm[0][0]/((cm[0][1])+(cm[0][2])+(cm[0][0])))
if (str(p) == ‘nan’):
print(“Recall setosa – “,”0.00”)
else:
print(“Recall setosa – “,round(p,2))
recall(cm)

def recall1(cm):
p1 = (cm[1][1]/((cm[1][0])+(cm[1][1])+(cm[1][2])))
if (str(p1) == ‘nan’):
print(“Recall versicolor – “,”0.00”)
else:
print(“Recall versicolor – “,round(p1,2))
recall1(cm)

def recall2(cm):
p2 = (cm[2][2]/((cm[2][1])+(cm[2][0])+(cm[2][2])))
if (str(p2) == ‘nan’):
print(“Recall virginica – “,”0.00”)
else:
print(“Recall virginica – “,round(p2,2),”\n”)
recall2(cm)

#Accuracy score
print(“Accuracy score:”,round(accuracy_score(y_test, y_pred),1))