churnmodelling ann

"""

import pandas as pd
import seaborn as sns
import numpy as np
import matplotlib.pyplot as plt

df = pd.read_csv("./emails.csv")
df.shape

df.head()

x = df.drop(['Email No.','Prediction'],axis = 1)

y = df['Prediction']

x.shape

x.dtypes

set(x.dtypes)

sns.countplot(x = y);

y.value_counts()

from sklearn.preprocessing import MinMaxScaler
scaler = MinMaxScaler()
x_scaled = scaler.fit_transform(x)

x_scaled

from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x_scaled,y,random_state = 0, test_size = 0.25)

x_scaled.shape

x_train.shape

x_test.shape

from sklearn.neighbors import KNeighborsClassifier

knn = KNeighborsClassifier(n_neighbors=5)

knn.fit(x_train, y_train)

y_pred = knn.predict(x_test)

from sklearn.metrics import ConfusionMatrixDisplay, accuracy_score
from sklearn.metrics import classification_report

ConfusionMatrixDisplay.from_predictions(y_test, y_pred)

y_test.value_counts()

accuracy_score(y_test, y_pred)

print(classification_report(y_test, y_pred))

error = []
for k in range(1,41):
  knn = KNeighborsClassifier(n_neighbors=k)
  knn.fit(x_train, y_train)
  pred = knn.predict(x_test)
  error.append(np.mean(pred != y_test))

error

knn = KNeighborsClassifier(n_neighbors=1)

knn.fit(x_train, y_train)

y_pred = knn.predict(x_test)

Knn_accuracy = accuracy_score(y_test, y_pred)
print(Knn_accuracy)

from sklearn.svm import SVC
svm = SVC(kernel='linear')

svm.fit(x_train, y_train)

y_pred = svm.predict(x_test)
LSVM = accuracy_score(y_test, y_pred)
print(LSVM)

from sklearn.svm import SVC
svm = SVC(kernel='rbf')
svm.fit(x_train, y_train)
y_pred = svm.predict(x_test)
RBF_SVM = accuracy_score(y_test, y_pred)
print(RBF_SVM)

svm = SVC(kernel='poly')
svm.fit(x_train, y_train)
y_pred = svm.predict(x_test)
PolySVM = accuracy_score(y_test, y_pred)
print(PolySVM)

from sklearn.svm import SVC
svm = SVC(kernel='sigmoid')
svm.fit(x_train, y_train)
y_pred = svm.predict(x_test)
Sigmoid_SVM = accuracy_score(y_test, y_pred)
print(Sigmoid_SVM)

models = ["KNN", "Linear SVM", "Sigmoid SVM", "Polynomial SVM", "RBF SVM"]
accuracy_scores = [Knn_accuracy, LSVM, Sigmoid_SVM, PolySVM, RBF_SVM]

plt.figure(figsize=(10, 6))
sns.set(style="whitegrid")
plt.bar(models, accuracy_scores, color='skyblue')
plt.title('Accuracy Scores of Different Models')
plt.xlabel('Machine Learning Model')
plt.ylabel('Accuracy Score')
plt.ylim(0, 1)
plt.xticks(rotation=45)
plt.show()