ML5

import pandas as pd
import seaborn as sns
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import ConfusionMatrixDisplay, accuracy_score, precision_score
from sklearn.metrics import classification_report
from sklearn.metrics import accuracy_score, precision_score,classification_report,confusion_matrix 
from sklearn.svm import SVC
df=pd.read_csv(r'C:\Users\user\Documents\AB_ML\Assign 5\emails.csv')
print(df.shape)
print(df.head())

#input data
x = df.drop(['Email No.','Prediction'], axis =1)
print(x.shape)

y = df['Prediction']
print(y.shape)

#checking balance of spam and not spam
print(y.value_counts())

#Feature Scaling
scaler = MinMaxScaler()
x_scaled = scaler.fit_transform(x)
print(x_scaled)


#Cross validation
x_train, x_test, y_train, y_test = train_test_split(x_scaled,y,random_state = 0, test_size = 0.25)
print(x_scaled.shape)
print(x_train.shape)
print(x_test.shape)

#create the object
knn = KNeighborsClassifier(n_neighbors=7)

#Train the algorithm
knn.fit(x_train,y_train)

#predict on test data
y_pred = knn.predict(x_test)
cm_display = ConfusionMatrixDisplay.from_predictions(y_test,y_pred)
print(y_test.value_counts())

#print accuracy
accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy: {accuracy * 100:.2f}%")

#print precision
precision = precision_score(y_test, y_pred)
print(f"Precision: {precision * 100:.2f}%")

#print accuracy and precision
a = classification_report(y_test, y_pred)
print("report is : ", a)

#svm
svm_classifier = SVC(kernel='linear')
svm_classifier.fit(x_train, y_train)

# Predictions on test dataset
y_pred = svm_classifier.predict(x_test)
print("Classfication report")
print(classification_report(y_test, y_pred))
print("\n")
print("Confusion Matrix")
print(confusion_matrix(y_test, y_pred))
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, "%")



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

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import classification_report, accuracy_score
import warnings
warnings.filterwarnings("ignore", category=UserWarning, module="joblib")
import os
os.environ["LOKY_MAX_CPU_COUNT"] = "2"


# Load the dataset
file_path = 'emails.csv'
data_frame = pd.read_csv(file_path)
print("Dataset : \n", data_frame)

data_frame['Prediction'] = data_frame['Prediction'].replace({0: 'spam', 1: 'ham'})

# Prepare features and labels
X = data_frame.iloc[:, 1:-1].values 
Y = data_frame.iloc[:, -1].values
Y = np.where(Y == 'spam', 1, 0)

X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=90)

sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)


X_train_2D = X_train[:, :2]  
X_test_2D = X_test[:, :2]    


svm = SVC(kernel='rbf', random_state=0, gamma='scale')
svm.fit(X_train_2D, Y_train)
y_pred_svm = svm.predict(X_test_2D) 

print("\n\n\t\t\tClassification Report (SVM)")
print(classification_report(Y_test, y_pred_svm))


knn = KNeighborsClassifier(n_neighbors=5) 
knn.fit(X_train, Y_train)  
y_pred_knn = knn.predict(X_test)

print("\n\n\t\t\tClassification Report (kNN)")
print(classification_report(Y_test, y_pred_knn))


def plot_decision_boundaries(X, y, model, ax):
    h = .02
    x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
    y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
    Z = model.predict(np.c_[xx.ravel(), yy.ravel()])
    Z = Z.reshape(xx.shape)
    ax.contourf(xx, yy, Z, alpha=0.8, cmap=plt.cm.coolwarm)

    scatter = ax.scatter(X[:, 0], X[:, 1], c=y, edgecolor='k', marker='o', cmap=plt.cm.coolwarm)
    legend1 = ax.legend(*scatter.legend_elements(), title="Classes")
    ax.add_artist(legend1)

    ax.set_xlim(xx.min(), xx.max())
    ax.set_ylim(yy.min(), yy.max())
    ax.set_xticks(())
    ax.set_yticks(())

fig, ax = plt.subplots()
plot_decision_boundaries(X_test_2D, Y_test, svm, ax)
plt.title('SVM Decision Boundary with RBF Kernel (2D Data)')
plt.legend()
plt.show()