Bank Customer Churn Prediction 1691464479

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 MinMaxScaler
import tensorflow as tf
from tensorflow import keras
from sklearn.metrics import confusion_matrix , classification_report
import seaborn as sn
from sklearn.linear_model import LogisticRegression
df=pd.read_csv('Churn_Modelling.csv')
df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10000 entries, 0 to 9999
Data columns (total 14 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 RowNumber 10000 non-null int64
1 CustomerId 10000 non-null int64
2 Surname 10000 non-null object
3 CreditScore 10000 non-null int64
4 Geography 10000 non-null object
5 Gender 10000 non-null object
6 Age 10000 non-null int64
7 Tenure 10000 non-null int64
8 Balance 10000 non-null float64
9 NumOfProducts 10000 non-null int64
10 HasCrCard 10000 non-null int64
11 IsActiveMember 10000 non-null int64
12 EstimatedSalary 10000 non-null float64
13 Exited 10000 non-null int64
dtypes: float64(2), int64(9), object(3)
memory usage: 1.1+ MB
df=df.drop(['RowNumber','CustomerId','Surname'], axis=1)
df.head()
CreditScore Geography Gender Age Tenure Balance NumOfProducts HasCrCard IsActiveMember EstimatedSalary Exited
0 619 France Female 42 2 0.00 1 1 1 101348.88 1
1 608 Spain Female 41 1 83807.86 1 0 1 112542.58 0
2 502 France Female 42 8 159660.80 3 1 0 113931.57 1
3 699 France Female 39 1 0.00 2 0 0 93826.63 0
4 850 Spain Female 43 2 125510.82 1 1 1 79084.10 0
def print_unique_col_values(df):
for column in df:
if df[column].dtypes=='object':
print(f'{column}: {df[column].unique()}')
print_unique_col_values(df)
Geography: ['France' 'Spain' 'Germany']

Gender: ['Female' 'Male']
df['Gender'].replace({'Female': 1,'Male': 0},inplace=True)
print_unique_col_values(df)
Geography: ['France' 'Spain' 'Germany']
df=pd.get_dummies(data=df,columns=['Geography','NumOfProducts'])
tenure_churn_no = df[df.Exited==0].Tenure
tenure_churn_yes = df[df.Exited==1].Tenure
plt.xlabel("tenure")
plt.ylabel("Number Of Customers")
plt.title("Customer Churn Prediction Visualiztion")
plt.hist([tenure_churn_yes, tenure_churn_no], rwidth=0.95, color=['green','red'],label=['Churn=Yes','Churn=No'])

plt.legend()
<matplotlib.legend.Legend at 0x251b7c8ce90>
cols_to_scale = ['Tenure','CreditScore','Age','Balance','EstimatedSalary']
scaler = MinMaxScaler()
df[cols_to_scale] = scaler.fit_transform(df[cols_to_scale])
df.head()
CreditScore Gender Age Tenure Balance HasCrCard IsActiveMember EstimatedSalary Exited Geography_France Geography_Germany
0 0.538 1 0.324324 0.2 0.000000 1 1 0.506735 1 1
1 0.516 1 0.310811 0.1 0.334031 0 1 0.562709 0 0
2 0.304 1 0.324324 0.8 0.636357 1 0 0.569654 1 1
3 0.698 1 0.283784 0.1 0.000000 0 0 0.469120 0 1
4 1.000 1 0.337838 0.2 0.500246 1 1 0.395400 0 0
df.drop('HasCrCard',axis=1,inplace=True)
x = df.drop('Exited',axis=1)
y = df['Exited']
x_train, x_test, y_train, y_test = train_test_split(x,y,test_size=0.2,random_state=2)
Creating the Neural Network Model

model = keras.Sequential([
keras.layers.Dense(10,input_shape=(14,),activation='relu'),
keras.layers.Dense(5,activation='tanh'),
keras.layers.Dense(1,activation='sigmoid')
])
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
model.fit(x_train,y_train,epochs=100)
Epoch 1/100
250/250 [==============================] - 2s 2ms/step - loss: 0.5016 - accuracy: 0.7920
Epoch 2/100
Epoch 3/100
Epoch 4/100
Epoch 5/100
Epoch 6/100
Epoch 7/100
Epoch 8/100
Epoch 9/100
Epoch 10/100
Epoch 11/100
Epoch 12/100
Epoch 13/100
Epoch 14/100
Epoch 15/100
Epoch 16/100
Epoch 17/100
Epoch 18/100
Epoch 19/100
Epoch 20/100
Epoch 21/100
Epoch 22/100
Epoch 23/100
Epoch 24/100
Epoch 25/100
Epoch 26/100
Epoch 27/100
Epoch 28/100
Epoch 29/100
Epoch 30/100
Epoch 31/100
Epoch 32/100
Epoch 33/100
Epoch 34/100
Epoch 35/100
Epoch 36/100
Epoch 37/100
Epoch 38/100
Epoch 39/100
Epoch 40/100
Epoch 41/100
Epoch 42/100
Epoch 43/100
Epoch 44/100
Epoch 45/100
Epoch 46/100
Epoch 47/100
Epoch 48/100
Epoch 49/100
Epoch 50/100
Epoch 51/100
Epoch 52/100
Epoch 53/100
Epoch 54/100
Epoch 55/100
Epoch 56/100
Epoch 57/100
Epoch 58/100
Epoch 59/100
Epoch 60/100
Epoch 61/100
Epoch 62/100
Epoch 63/100
Epoch 64/100
Epoch 65/100
Epoch 66/100
Epoch 67/100
Epoch 68/100
Epoch 69/100
Epoch 70/100
Epoch 71/100
Epoch 72/100
Epoch 73/100
Epoch 74/100
Epoch 75/100
Epoch 76/100
Epoch 77/100
Epoch 78/100
Epoch 79/100
Epoch 80/100
Epoch 81/100
Epoch 82/100
Epoch 83/100
Epoch 84/100
Epoch 85/100
Epoch 86/100
Epoch 87/100
Epoch 88/100
Epoch 89/100
Epoch 90/100
Epoch 91/100
Epoch 92/100
Epoch 93/100
Epoch 94/100
Epoch 95/100
Epoch 96/100
Epoch 97/100
Epoch 98/100
Epoch 99/100
Epoch 100/100
<keras.src.callbacks.History at 0x251b7cc1790>
model.evaluate(x_test, y_test)

[0.34639090299606323, 0.859000027179718]
yp = model.predict(x_test)
yp[:5]
63/63 [==============================] - 0s 2ms/step

array([[0.20089829],
[0.5349295 ],
[0.31899092],
[0.0096462 ],
[0.02925511]], dtype=float32)
y_pred = []
for element in yp:
if element > 0.5:
y_pred.append(1)
else:
y_pred.append(0)
y_pred[:5]
[0, 1, 0, 0, 0]
print(classification_report(y_test,y_pred))
precision recall f1-score support
0 0.88 0.96 0.92 1617

1 0.71 0.44 0.55 383
accuracy 0.86 2000

macro avg 0.80 0.70 0.73 2000
weighted avg 0.85 0.86 0.85 2000
cm = tf.math.confusion_matrix(labels=y_test,predictions=y_pred)
plt.figure(figsize = (10,7))
sn.heatmap(cm, annot=True, fmt='d')
plt.xlabel('Predicted')
plt.ylabel('Truth')
Text(95.72222222222221, 0.5, 'Truth')

Creating the Logistic Regression Model to compare with Neural
Network
model1=LogisticRegression()
model1.fit(x_train,y_train)
model1.score(x_test,y_test)
0.843
yp1 = model1.predict(x_test)
yp1[:5]
array([0, 1, 0, 0, 0], dtype=int64)
y_pred1 = []
for element in yp1:
if element > 0.5:
y_pred1.append(1)
else:
y_pred1.append(0)
cm = tf.math.confusion_matrix(labels=y_test,predictions=y_pred1)
plt.figure(figsize = (10,7))
sn.heatmap(cm, annot=True, fmt='d')
plt.xlabel('Predicted')
plt.ylabel('Truth')
Text(95.72222222222221, 0.5, 'Truth')
print(classification_report(y_test,y_pred1))
precision recall f1-score support
0 0.86 0.96 0.91 1617

1 0.68 0.34 0.45 383
accuracy 0.84 2000

macro avg 0.77 0.65 0.68 2000
weighted avg 0.83 0.84 0.82 2000

Loading [MathJax]/jax/output/CommonHTML/fonts/TeX/fontdata.js

Bank Customer Churn Prediction 1691464479

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Bank Customer Churn Prediction 1691464479

Uploaded by

Copyright:

Available Formats

import

0 619 France Female 42 2 0.00 1 1 1 101348.88 1

1 608 Spain Female 41 1 83807.86 1 0 1 112542.58 0

2 502 France Female 42 8 159660.80 3 1 0 113931.57 1

3 699 France Female 39 1 0.00 2 0 0 93826.63 0

4 850 Spain Female 43 2 125510.82 1 1 1 79084.10 0

Geography: ['France' 'Spain' 'Germany']

df['Gender'].replace({'Female': 1,'Male': 0},inplace=True)

Geography: ['France' 'Spain' 'Germany']

plt.hist([tenure_churn_yes, tenure_churn_no], rwidth=0.95, color=['green','red'],label=['Churn=Yes','Churn=No'])

0 0.538 1 0.324324 0.2 0.000000 1 1 0.506735 1 1

1 0.516 1 0.310811 0.1 0.334031 0 1 0.562709 0 0

2 0.304 1 0.324324 0.8 0.636357 1 0 0.569654 1 1

3 0.698 1 0.283784 0.1 0.000000 0 0 0.469120 0 1

4 1.000 1 0.337838 0.2 0.500246 1 1 0.395400 0 0

x_train, x_test, y_train, y_test = train_test_split(x,y,test_size=0.2,random_state=2)

Creating the Neural Network Model

63/63 [==============================] - 0s 2ms/step - loss: 0.3464 - accuracy: 0.8590

63/63 [==============================] - 0s 2ms/step

precision recall f1-score support

0 0.88 0.96 0.92 1617

accuracy 0.86 2000

Text(95.72222222222221, 0.5, 'Truth')

array([0, 1, 0, 0, 0], dtype=int64)

Text(95.72222222222221, 0.5, 'Truth')

precision recall f1-score support

0 0.86 0.96 0.91 1617

accuracy 0.84 2000

You might also like