# For importing libraries and data

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
df = pd.read_csv('customer churn.csv')
df

customerID gender SeniorCitizen Partner Dependents tenure \

0 7590-VHVEG Female 0 Yes No 1
1 5575-GNVDE Male 0 No No 34
2 3668-QPYBK Male 0 No No 2
3 7795-CFOCW Male 0 No No 45
4 9237-HQITU Female 0 No No 2
... ... ... ... ... ... ...
7038 6840-RESVB Male 0 Yes Yes 24
7039 2234-XADUH Female 0 Yes Yes 72
7040 4801-JZAZL Female 0 Yes Yes 11
7041 8361-LTMKD Male 1 Yes No 4
7042 3186-AJIEK Male 0 No No 66

PhoneService MultipleLines InternetService

OnlineSecurity ... \
0 No No phone service DSL
No ...
1 Yes No DSL
Yes ...
2 Yes No DSL
Yes ...
3 No No phone service DSL
Yes ...
4 Yes No Fiber optic
No ...
... ... ... ... ... ..
.
7038 Yes Yes DSL
Yes ...
7039 Yes Yes Fiber optic
No ...
7040 No No phone service DSL
Yes ...
7041 Yes Yes Fiber optic
No ...
7042 Yes No Fiber optic
Yes ...

DeviceProtection TechSupport StreamingTV StreamingMovies

Contract \
0 No No No No Month-
to-month
1 Yes No No No
One year
2 No No No No Month-
to-month
3 Yes Yes No No
One year
4 No No No No Month-
to-month
... ... ... ... ...
...
7038 Yes Yes Yes Yes
One year
7039 Yes No Yes Yes
One year
7040 No No No No Month-
to-month
7041 No No No No Month-
to-month
7042 Yes Yes Yes Yes
Two year

PaperlessBilling PaymentMethod MonthlyCharges

TotalCharges \
0 Yes Electronic check 29.85
29.85
1 No Mailed check 56.95
1889.5
2 Yes Mailed check 53.85
108.15
3 No Bank transfer (automatic) 42.30
1840.75
4 Yes Electronic check 70.70
151.65
... ... ... ...
...
7038 Yes Mailed check 84.80
1990.5
7039 Yes Credit card (automatic) 103.20
7362.9
7040 Yes Electronic check 29.60
346.45
7041 Yes Mailed check 74.40
306.6
7042 Yes Bank transfer (automatic) 105.65
6844.5

Churn
0 No
1 No
2 Yes
3 No
4 Yes
... ...
7038 No
7039 No
7040 No
7041 Yes
7042 No

[7043 rows x 21 columns]

Data Cleaning and Extracting

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

#Replacing Float File into Float and also Blanks into 0

df["TotalCharges"] = df["TotalCharges"].replace(" ", "0")
df["TotalCharges"] = df["TotalCharges"].astype("float")

df.isnull().sum()

customerID 0
gender 0
SeniorCitizen 0
Partner 0
Dependents 0
tenure 0
PhoneService 0
MultipleLines 0
InternetService 0
OnlineSecurity 0
OnlineBackup 0
DeviceProtection 0
TechSupport 0
StreamingTV 0
StreamingMovies 0
Contract 0
PaperlessBilling 0
PaymentMethod 0
MonthlyCharges 0
TotalCharges 0
Churn 0
dtype: int64

df.describe()

SeniorCitizen tenure MonthlyCharges

count 7043.000000 7043.000000 7043.000000
mean 0.162147 32.371149 64.761692
std 0.368612 24.559481 30.090047
min 0.000000 0.000000 18.250000
25% 0.000000 9.000000 35.500000
50% 0.000000 29.000000 70.350000
75% 0.000000 55.000000 89.850000
max 1.000000 72.000000 118.750000

df.duplicated().sum()

# duplicate check throough uniqueness like "customer ID"

df["customerID"].duplicated().sum()

0
def conv(value):
if value == 1:
return "Yes"
else:
return "No"

df['SeniorCitizen'] = df["SeniorCitizen"].apply(conv)

df.head(25)

customerID gender SeniorCitizen Partner Dependents tenure

PhoneService \
0 7590-VHVEG Female No Yes No 1
No
1 5575-GNVDE Male No No No 34
Yes
2 3668-QPYBK Male No No No 2
Yes
3 7795-CFOCW Male No No No 45
No
4 9237-HQITU Female No No No 2
Yes
5 9305-CDSKC Female No No No 8
Yes
6 1452-KIOVK Male No No Yes 22
Yes
7 6713-OKOMC Female No No No 10
No
8 7892-POOKP Female No Yes No 28
Yes
9 6388-TABGU Male No No Yes 62
Yes
10 9763-GRSKD Male No Yes Yes 13
Yes
11 7469-LKBCI Male No No No 16
Yes
12 8091-TTVAX Male No Yes No 58
Yes
13 0280-XJGEX Male No No No 49
Yes
14 5129-JLPIS Male No No No 25
Yes
15 3655-SNQYZ Female No Yes Yes 69
Yes
16 8191-XWSZG Female No No No 52
Yes
17 9959-WOFKT Male No No Yes 71
Yes
18 4190-MFLUW Female No Yes Yes 10
Yes
19 4183-MYFRB Female No No No 21
Yes
20 8779-QRDMV Male Yes No No 1
No
21 1680-VDCWW Male No Yes No 12
Yes
22 1066-JKSGK Male No No No 1
Yes
23 3638-WEABW Female No Yes No 58
Yes
24 6322-HRPFA Male No Yes Yes 49
Yes

MultipleLines InternetService OnlineSecurity ... \

0 No phone service DSL No ...
1 No DSL Yes ...
2 No DSL Yes ...
3 No phone service DSL Yes ...
4 No Fiber optic No ...
5 Yes Fiber optic No ...
6 Yes Fiber optic No ...
7 No phone service DSL Yes ...
8 Yes Fiber optic No ...
9 No DSL Yes ...
10 No DSL Yes ...
11 No No No internet service ...
12 Yes Fiber optic No ...
13 Yes Fiber optic No ...
14 No Fiber optic Yes ...
15 Yes Fiber optic Yes ...
16 No No No internet service ...
17 Yes Fiber optic Yes ...
18 No DSL No ...
19 No Fiber optic No ...
20 No phone service DSL No ...
21 No No No internet service ...
22 No No No internet service ...
23 Yes DSL No ...
24 No DSL Yes ...

DeviceProtection TechSupport StreamingTV \

0 No No No
1 Yes No No
2 No No No
3 Yes Yes No
4 No No No
5 Yes No Yes
6 No No Yes
7 No No No
8 Yes Yes Yes
9 No No No
10 No No No
11 No internet service No internet service No internet service
12 Yes No Yes
13 Yes No Yes
14 Yes Yes Yes
15 Yes Yes Yes
16 No internet service No internet service No internet service
17 Yes No Yes
18 Yes Yes No
19 Yes No No
20 Yes No No
21 No internet service No internet service No internet service
22 No internet service No internet service No internet service
23 No Yes No
24 No Yes No

StreamingMovies Contract PaperlessBilling \

0 No Month-to-month Yes
1 No One year No
2 No Month-to-month Yes
3 No One year No
4 No Month-to-month Yes
5 Yes Month-to-month Yes
6 No Month-to-month Yes
7 No Month-to-month No
8 Yes Month-to-month Yes
9 No One year No
10 No Month-to-month Yes
11 No internet service Two year No
12 Yes One year No
13 Yes Month-to-month Yes
14 Yes Month-to-month Yes
15 Yes Two year No
16 No internet service One year No
17 Yes Two year No
18 No Month-to-month No
19 Yes Month-to-month Yes
20 Yes Month-to-month Yes
21 No internet service One year No
22 No internet service Month-to-month No
23 No Two year Yes
24 No Month-to-month No

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 Electronic check 99.65 820.5 Yes
6 Credit card (automatic) 89.10 1949.4 No
7 Mailed check 29.75 301.9 No
8 Electronic check 104.80 3046.05 Yes
9 Bank transfer (automatic) 56.15 3487.95 No
10 Mailed check 49.95 587.45 No
11 Credit card (automatic) 18.95 326.8 No
12 Credit card (automatic) 100.35 5681.1 No
13 Bank transfer (automatic) 103.70 5036.3 Yes
14 Electronic check 105.50 2686.05 No
15 Credit card (automatic) 113.25 7895.15 No
16 Mailed check 20.65 1022.95 No
17 Bank transfer (automatic) 106.70 7382.25 No
18 Credit card (automatic) 55.20 528.35 Yes
19 Electronic check 90.05 1862.9 No
20 Electronic check 39.65 39.65 Yes
21 Bank transfer (automatic) 19.80 202.25 No
22 Mailed check 20.15 20.15 Yes
23 Credit card (automatic) 59.90 3505.1 No
24 Credit card (automatic) 59.60 2970.3 No

[25 rows x 21 columns]

ax = sns.countplot(x = 'Churn', data = df)

ax.bar_label(ax.containers[0])
plt.title("Counts of Customer by Churn")
plt.show()
# Plot the pie chart
plt.figure(figsize = (4,4))
gb = df.groupby("Churn").agg({'Churn':"count"})
plt.pie(gb['Churn'], labels=gb.index, autopct= "%1.2f%%" )
plt.title(" Percentage of Churn Customer", fontsize=10)
plt.show()
plt.figure(figsize = (4,4))
ax = sns.countplot(x = "gender", data=df, hue = "Churn")
ax.bar_label(ax.containers[0])
plt.title("Churn by Gender")
plt.show()
plt.figure(figsize = (4,4))
ax = sns.countplot(x = "SeniorCitizen", data=df, hue = "Churn")
ax.bar_label(ax.containers[0])
plt.title("Churn By SeniorCitizen")
plt.show()

# From ChatGPT
cross_tab = pd.crosstab(df['SeniorCitizen'], df['Churn'])

# Calculate percentages
cross_tab_percentage = cross_tab.div(cross_tab.sum(axis=1), axis=0) *
100

# Plot the stacked bar chart

ax = cross_tab_percentage.plot(kind='bar', stacked=True, figsize=(6,
4), color=['lightgreen', 'lightcoral'])

# Add percentage labels

for i, (index, row) in enumerate(cross_tab_percentage.iterrows()):
total = row.sum()
cumulative = 0
for j, value in enumerate(row):
cumulative += value
ax.text(i, cumulative - (value / 2), f'{value:.1f}%',
ha='center', va='center', color='black')
# Add labels and title
plt.xlabel('Senior Citizen')
plt.ylabel('Percentage')
plt.title('Churn Percentage by Senior Citizen')
plt.xticks(ticks=[0, 1], labels=['No', 'Yes'], rotation=0) # Replace
0 and 1 with 'No' and 'Yes'
plt.legend(title='Churn', bbox_to_anchor = (0.9, 0.9))

# Display the chart

plt.tight_layout()
plt.show()

plt.figure(figsize= (9,4))
sns.histplot(x = "tenure", data=df, bins = 72, hue = "Churn")
plt.show()
plt.figure(figsize = (5,6))
ax = sns.countplot(x = "Contract", data=df, hue= "Churn")
ax.bar_label(ax.containers[0])
plt.title("Count of Customer by Churn")
plt.show()
df.columns.values

array(['customerID', 'gender', 'SeniorCitizen', 'Partner',

'Dependents',
'tenure', 'PhoneService', 'MultipleLines', 'InternetService',
'OnlineSecurity', 'OnlineBackup', 'DeviceProtection',
'TechSupport', 'StreamingTV', 'StreamingMovies', 'Contract',
'PaperlessBilling', 'PaymentMethod', 'MonthlyCharges',
'TotalCharges', 'Churn'], dtype=object)

columns = ['PhoneService', 'MultipleLines', 'InternetService',

'OnlineSecurity',
'OnlineBackup', 'DeviceProtection', 'TechSupport',
'StreamingTV', 'StreamingMovies']

# Number of columns for the subplot grid (you can change this)
n_cols = 3
n_rows = (len(columns) + n_cols - 1) // n_cols # Calculate number of
rows needed

# Create subplots
fig, axes = plt.subplots(n_rows, n_cols, figsize=(15, n_rows * 4)) #
Adjust figsize as needed

# Flatten the axes array for easy iteration (handles both 1D and 2D
arrays)
axes = axes.flatten()

# Iterate over columns and plot count plots

for i, col in enumerate(columns):
sns.countplot(x=col, data=df, ax=axes[i], hue = df["Churn"])
axes[i].set_title(f'Count Plot of {col}')
axes[i].set_xlabel(col)
axes[i].set_ylabel('Count')

# Remove empty subplots (if any)

for j in range(i + 1, len(axes)):
fig.delaxes(axes[j])

plt.tight_layout()
plt.show()
plt.figure(figsize = (9,6))
ax = sns.countplot(x = "PaymentMethod", data=df, hue= "Churn")
ax.bar_label(ax.containers[0])
ax.bar_label(ax.containers[1])
plt.title("Count of Customer by PaymentMethod")
plt.show()