Telco Customer Churn¶

In [1]:
# Importing libraries
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, roc_auc_score, confusion_matrix
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics import classification_report, accuracy_score, roc_auc_score, roc_curve

Load the dataset¶

In [2]:
# Load the dataset
df = pd.read_csv("C:/Users/carys/OneDrive/Documents/Year 3 - Sem 1/AI and Machine Learning/Assignment/Data/telcoCustomerChurn.csv")
In [3]:
# Display info about the dataset
print(df.info())

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 7043 entries, 0 to 7042
Data columns (total 21 columns):
 #   Column            Non-Null Count  Dtype  
---  ------            --------------  -----  
 0   customerID        7043 non-null   object 
 1   gender            7043 non-null   object 
 2   SeniorCitizen     7043 non-null   int64  
 3   Partner           7043 non-null   object 
 4   Dependents        7043 non-null   object 
 5   tenure            7043 non-null   int64  
 6   PhoneService      7043 non-null   object 
 7   MultipleLines     7043 non-null   object 
 8   InternetService   7043 non-null   object 
 9   OnlineSecurity    7043 non-null   object 
 10  OnlineBackup      7043 non-null   object 
 11  DeviceProtection  7043 non-null   object 
 12  TechSupport       7043 non-null   object 
 13  StreamingTV       7043 non-null   object 
 14  StreamingMovies   7043 non-null   object 
 15  Contract          7043 non-null   object 
 16  PaperlessBilling  7043 non-null   object 
 17  PaymentMethod     7043 non-null   object 
 18  MonthlyCharges    7043 non-null   float64
 19  TotalCharges      7043 non-null   object 
 20  Churn             7043 non-null   object 
dtypes: float64(1), int64(2), object(18)
memory usage: 1.1+ MB
None
In [4]:
# Show the first 5 rows of the dataset
print(df.head())

   customerID  gender  SeniorCitizen Partner Dependents  tenure PhoneService  \
0  7590-VHVEG  Female              0     Yes         No       1           No   
1  5575-GNVDE    Male              0      No         No      34          Yes   
2  3668-QPYBK    Male              0      No         No       2          Yes   
3  7795-CFOCW    Male              0      No         No      45           No   
4  9237-HQITU  Female              0      No         No       2          Yes   

      MultipleLines InternetService OnlineSecurity  ... DeviceProtection  \
0  No phone service             DSL             No  ...               No   
1                No             DSL            Yes  ...              Yes   
2                No             DSL            Yes  ...               No   
3  No phone service             DSL            Yes  ...              Yes   
4                No     Fiber optic             No  ...               No   

  TechSupport StreamingTV StreamingMovies        Contract PaperlessBilling  \
0          No          No              No  Month-to-month              Yes   
1          No          No              No        One year               No   
2          No          No              No  Month-to-month              Yes   
3         Yes          No              No        One year               No   
4          No          No              No  Month-to-month              Yes   

               PaymentMethod MonthlyCharges  TotalCharges Churn  
0           Electronic check          29.85         29.85    No  
1               Mailed check          56.95        1889.5    No  
2               Mailed check          53.85        108.15   Yes  
3  Bank transfer (automatic)          42.30       1840.75    No  
4           Electronic check          70.70        151.65   Yes  

[5 rows x 21 columns]

Data Preprocessing¶

In [5]:
df = df.drop(['customerID'], axis = 1)
df.head()
Out[5]:
gender SeniorCitizen Partner Dependents tenure PhoneService MultipleLines InternetService OnlineSecurity OnlineBackup DeviceProtection TechSupport StreamingTV StreamingMovies Contract PaperlessBilling PaymentMethod MonthlyCharges TotalCharges Churn
0 Female 0 Yes No 1 No No phone service DSL No Yes No No No No Month-to-month Yes Electronic check 29.85 29.85 No
1 Male 0 No No 34 Yes No DSL Yes No Yes No No No One year No Mailed check 56.95 1889.5 No
2 Male 0 No No 2 Yes No DSL Yes Yes No No No No Month-to-month Yes Mailed check 53.85 108.15 Yes
3 Male 0 No No 45 No No phone service DSL Yes No Yes Yes No No One year No Bank transfer (automatic) 42.30 1840.75 No
4 Female 0 No No 2 Yes No Fiber optic No No No No No No Month-to-month Yes Electronic check 70.70 151.65 Yes

Splitting the data into train and test sets¶

In [6]:
def object_to_int(dataframe_series):
    if dataframe_series.dtype=='object':
        dataframe_series = LabelEncoder().fit_transform(dataframe_series)
    return dataframe_series
In [7]:
df = df.apply(lambda x: object_to_int(x))
df.head()
Out[7]:
gender SeniorCitizen Partner Dependents tenure PhoneService MultipleLines InternetService OnlineSecurity OnlineBackup DeviceProtection TechSupport StreamingTV StreamingMovies Contract PaperlessBilling PaymentMethod MonthlyCharges TotalCharges Churn
0 0 0 1 0 1 0 1 0 0 2 0 0 0 0 0 1 2 29.85 2505 0
1 1 0 0 0 34 1 0 0 2 0 2 0 0 0 1 0 3 56.95 1466 0
2 1 0 0 0 2 1 0 0 2 2 0 0 0 0 0 1 3 53.85 157 1
3 1 0 0 0 45 0 1 0 2 0 2 2 0 0 1 0 0 42.30 1400 0
4 0 0 0 0 2 1 0 1 0 0 0 0 0 0 0 1 2 70.70 925 1
In [8]:
plt.figure(figsize=(14,7))
df.corr()['Churn'].sort_values(ascending = False)
Out[8]:
Churn               1.000000
MonthlyCharges      0.193356
PaperlessBilling    0.191825
SeniorCitizen       0.150889
PaymentMethod       0.107062
MultipleLines       0.038037
TotalCharges        0.014479
PhoneService        0.011942
gender             -0.008612
StreamingTV        -0.036581
StreamingMovies    -0.038492
InternetService    -0.047291
Partner            -0.150448
Dependents         -0.164221
DeviceProtection   -0.178134
OnlineBackup       -0.195525
TechSupport        -0.282492
OnlineSecurity     -0.289309
tenure             -0.352229
Contract           -0.396713
Name: Churn, dtype: float64
<Figure size 1008x504 with 0 Axes>
In [9]:
X = df.drop(columns = ['Churn'])
y = df['Churn'].values
In [10]:
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size = 0.30, random_state = 40, stratify=y)
In [11]:
def distplot(feature, frame, color='r'):
    plt.figure(figsize=(8,3))
    plt.title("Distribution for {}".format(feature))
    ax = sns.distplot(frame[feature], color= color)
In [12]:
num_cols = ["tenure", 'MonthlyCharges', 'TotalCharges']
for feat in num_cols: distplot(feat, df)

C:\Users\carys\anaconda3\lib\site-packages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
C:\Users\carys\anaconda3\lib\site-packages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
C:\Users\carys\anaconda3\lib\site-packages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)

Feature Scaling¶

In [13]:
scaler= StandardScaler()

X_train[num_cols] = scaler.fit_transform(X_train[num_cols])
X_test[num_cols] = scaler.transform(X_test[num_cols])

Model Training: Support Vector Machine (SVR)¶

In [14]:
svc_model = SVC(random_state = 1)
svc_model.fit(X_train,y_train)
predict_y = svc_model.predict(X_test)
accuracy_svc = svc_model.score(X_test,y_test)
print("SVM accuracy is :",accuracy_svc)

SVM accuracy is : 0.7893989588263133
In [15]:
print(classification_report(y_test, predict_y))

              precision    recall  f1-score   support

           0       0.83      0.90      0.86      1552
           1       0.63      0.49      0.55       561

    accuracy                           0.79      2113
   macro avg       0.73      0.69      0.71      2113
weighted avg       0.78      0.79      0.78      2113

Model Training: Logistic Regression (LR)¶

In [16]:
lr_model = LogisticRegression()
lr_model.fit(X_train,y_train)
accuracy_lr = lr_model.score(X_test,y_test)
print("Logistic Regression accuracy is :",accuracy_lr)

Logistic Regression accuracy is : 0.7917652626597255
In [17]:
lr_pred= lr_model.predict(X_test)
report = classification_report(y_test,lr_pred)
print(report)

              precision    recall  f1-score   support

           0       0.84      0.88      0.86      1552
           1       0.62      0.55      0.59       561

    accuracy                           0.79      2113
   macro avg       0.73      0.72      0.72      2113
weighted avg       0.79      0.79      0.79      2113
In [18]:
plt.figure(figsize=(4,3))
sns.heatmap(confusion_matrix(y_test, lr_pred),
                annot=True,fmt = "d",linecolor="k",linewidths=3)
    
plt.title("LOGISTIC REGRESSION CONFUSION MATRIX",fontsize=14)
plt.show()
In [19]:
y_pred_prob = lr_model.predict_proba(X_test)[:,1]
fpr, tpr, thresholds = roc_curve(y_test, y_pred_prob)
plt.plot([0, 1], [0, 1], 'k--' )
plt.plot(fpr, tpr, label='Logistic Regression',color = "r")
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Logistic Regression ROC Curve',fontsize=16)
plt.show();
In [ ]: