ML6

//on emails.csv

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import classification_report
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.metrics import confusion_matrix
# Load the dataset
data_frame = pd.read_csv('emails.csv')
print("Dataset:\n", data_frame.head())  # Display the first few rows

# Prepare features and labels
data_frame['Prediction'] = data_frame['Prediction'].replace({0: 'spam', 1: 'ham'})  # Convert 0/1 to 'spam'/'ham'
X = data_frame.iloc[:, 1:-1].values  # Features
Y = np.where(data_frame['Prediction'] == 'spam', 1, 0)  # Labels

# Split the dataset
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=90)

# Scale features (optional but recommended for better performance in some algorithms)
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Train Naive Bayes model
nb_model = GaussianNB()
nb_model.fit(X_train, Y_train)
y_pred_nb = nb_model.predict(X_test)



# Display classification report
print("\nClassification Report (Naive Bayes):")
print(classification_report(Y_test, y_pred_nb))

conf_matrix = confusion_matrix(Y_test, y_pred_nb)


# Define labels for the confusion matrix
labels = ['Ham', 'Spam']

# Plot confusion matrix
plt.figure(figsize=(6,4))
sns.heatmap(conf_matrix, annot=True, fmt="d", cmap="Blues", xticklabels=labels, yticklabels=labels)
plt.xlabel('Predicted Labels')
plt.ylabel('True Labels')
plt.title('Confusion Matrix for Naive Bayes (Email Dataset)')
plt.show()













@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, precision_score,classification_report, confusion_matrix 
from sklearn.preprocessing import StandardScaler, LabelEncoder
from sklearn.naive_bayes import GaussianNB
import matplotlib.pyplot as plt


data = pd.read_csv('PlayTennis.csv')
print("Dataset:")
print(data)
print("\n")


le = LabelEncoder()
data['Outlook'] = le.fit_transform(data['Outlook'])
data['Temperature'] = le.fit_transform(data['Temperature'])
data['Humidity'] = le.fit_transform(data['Humidity'])
data['Wind'] = le.fit_transform(data['Wind'])
data['Play Tennis'] = le.fit_transform(data['Play Tennis'])

print("--------Independent Variables--------")

X=data.iloc[:, : -1]            
print(X)
print("\n")

print("---------Dependent Variables---------")
Y = data['Play Tennis']                       
print(Y)
print("\n")

# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.20, random_state=42)

# Standardize features 
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test= scaler.transform(X_test)
#print("**************",X_test)

# Gaussian Naive Bayes classifier
guassian_classifier = GaussianNB()
guassian_classifier.fit(X_train, y_train)

# Predictions on test dataset
y_pred = guassian_classifier.predict(X_test)
print("Classfication report")
print(classification_report(y_test, y_pred))
print("\n")

print("\n")

# Calculate accuracy
accuracy = accuracy_score(y_test, y_pred)*100
print("Accuracy:",accuracy,"%")

# Calculate precision
precision = precision_score(y_test, y_pred)*100
print("Precision:", precision, "%")



///////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////

Problem Statement-Implement Naïve Bayes Classifier on Tennisdata Data set. Evaluate the classifier's performance.

Code:
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, precision_score,classification_report, confusion_matrix 
from sklearn.preprocessing import StandardScaler, LabelEncoder
from sklearn.naive_bayes import GaussianNB
import matplotlib.pyplot as plt


data = pd.read_csv('PlayTennis.csv')
print("Dataset:")
print(data)
print("\n")


le = LabelEncoder()
data['Outlook'] = le.fit_transform(data['Outlook'])
data['Temperature'] = le.fit_transform(data['Temperature'])
data['Humidity'] = le.fit_transform(data['Humidity'])
data['Wind'] = le.fit_transform(data['Wind'])
data['Play Tennis'] = le.fit_transform(data['Play Tennis'])

print("--------Independent Variables--------")

X=data.iloc[:, : -1]            
print(X)
print("\n")

print("---------Dependent Variables---------")
Y = data['Play Tennis']                       
print(Y)
print("\n")

# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.20, random_state=42)

# Standardize features 
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test= scaler.transform(X_test)
#print("**************",X_test)

# Gaussian Naive Bayes classifier
guassian_classifier = GaussianNB()
guassian_classifier.fit(X_train, y_train)

# Predictions on test dataset
y_pred = guassian_classifier.predict(X_test)
print("Classfication report")
print(classification_report(y_test, y_pred))
print("\n")

print("\n")

# Calculate accuracy
accuracy = accuracy_score(y_test, y_pred)*100
print("Accuracy:",accuracy,"%")

# Calculate precision
precision = precision_score(y_test, y_pred)*100
print("Precision:", precision, "%")