#Inserting the files needed
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

#Implementing required algorithms
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import classification_report, confusion_matrix, roc_auc_score, roc_curve
from sklearn.metrics import roc_curve, roc_auc_score
from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay
from sklearn.svm import SVC
from sklearn.metrics import classification_report, confusion_matrix

df = pd.read_excel('Telco_Customer_Churn.xlsx')

#Understanding the data by displaying top 15 lines within the database

df.head(15)

#Understanding the data by displaying the bottom 15 lines of the data 

df.tail(15)

df.describe()

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 7043 entries, 0 to 7042
Data columns (total 33 columns):
 #   Column             Non-Null Count  Dtype  
---  ------             --------------  -----  
 0   CustomerID         7043 non-null   object 
 1   Count              7043 non-null   int64  
 2   Country            7043 non-null   object 
 3   State              7043 non-null   object 
 4   City               7043 non-null   object 
 5   Zip Code           7043 non-null   int64  
 6   Lat Long           7043 non-null   object 
 7   Latitude           7043 non-null   float64
 8   Longitude          7043 non-null   float64
 9   Gender             7043 non-null   object 
 10  Senior Citizen     7043 non-null   object 
 11  Partner            7043 non-null   object 
 12  Dependents         7043 non-null   object 
 13  Tenure Months      7043 non-null   int64  
 14  Phone Service      7043 non-null   object 
 15  Multiple Lines     7043 non-null   object 
 16  Internet Service   7043 non-null   object 
 17  Online Security    7043 non-null   object 
 18  Online Backup      7043 non-null   object 
 19  Device Protection  7043 non-null   object 
 20  Tech Support       7043 non-null   object 
 21  Streaming TV       7043 non-null   object 
 22  Streaming Movies   7043 non-null   object 
 23  Contract           7043 non-null   object 
 24  Paperless Billing  7043 non-null   object 
 25  Payment Method     7043 non-null   object 
 26  Monthly Charges    7043 non-null   float64
 27  Total Charges      7043 non-null   object 
 28  Churn Label        7043 non-null   object 
 29  Churn Value        7043 non-null   int64  
 30  Churn Score        7043 non-null   int64  
 31  CLTV               7043 non-null   int64  
 32  Churn Reason       1869 non-null   object 
dtypes: float64(3), int64(6), object(24)
memory usage: 1.8+ MB

df.nunique()

CustomerID           7043
Count                   1
Country                 1
State                   1
City                 1129
Zip Code             1652
Lat Long             1652
Latitude             1652
Longitude            1651
Gender                  2
Senior Citizen          2
Partner                 2
Dependents              2
Tenure Months          73
Phone Service           2
Multiple Lines          3
Internet Service        3
Online Security         3
Online Backup           3
Device Protection       3
Tech Support            3
Streaming TV            3
Streaming Movies        3
Contract                3
Paperless Billing       2
Payment Method          4
Monthly Charges      1585
Total Charges        6531
Churn Label             2
Churn Value             2
Churn Score            85
CLTV                 3438
Churn Reason           20
dtype: int64

print(df.columns)

Index(['CustomerID', 'Count', 'Country', 'State', 'City', 'Zip Code',
       'Lat Long', 'Latitude', 'Longitude', 'Gender', 'Senior Citizen',
       'Partner', 'Dependents', 'Tenure Months', 'Phone Service',
       'Multiple Lines', 'Internet Service', 'Online Security',
       'Online Backup', 'Device Protection', 'Tech Support', 'Streaming TV',
       'Streaming Movies', 'Contract', 'Paperless Billing', 'Payment Method',
       'Monthly Charges', 'Total Charges', 'Churn Label', 'Churn Value',
       'Churn Score', 'CLTV', 'Churn Reason'],
      dtype='object')

numerical_columns=['Tenure Months','Monthly Charges','Total Charges','Churn Value','Churn Score','CLTV']

df[numerical_columns].describe().T

df[numerical_columns].hist(figsize=(15,15))
plt.show()

categorical_columns=['City','Gender','Senior Citizen','Partner','Dependents','Phone Service','Multiple Lines',
          'Internet Service','Online Security','Online Backup','Device Protection','Tech Support','Streaming TV','Streaming Movies',
          'Contract','Paperless Billing','Payment Method','Churn Label', 'Churn Reason']

df[categorical_columns].describe().T

for i in categorical_columns:
    print(df[i].value_counts (normalize=True) * 100)
    print('')

City
Los Angeles       4.330541
San Diego         2.129774
San Jose          1.590231
Sacramento        1.533437
San Francisco     1.476643
                    ...   
Healdsburg        0.056794
Jenner            0.056794
Philo             0.056794
Point Arena       0.056794
Olympic Valley    0.056794
Name: proportion, Length: 1129, dtype: float64

Gender
Male      50.47565
Female    49.52435
Name: proportion, dtype: float64

Senior Citizen
No     83.785319
Yes    16.214681
Name: proportion, dtype: float64

Partner
No     51.69672
Yes    48.30328
Name: proportion, dtype: float64

Dependents
No     76.899049
Yes    23.100951
Name: proportion, dtype: float64

Phone Service
Yes    90.316626
No      9.683374
Name: proportion, dtype: float64

Multiple Lines
No                  48.132898
Yes                 42.183729
No phone service     9.683374
Name: proportion, dtype: float64

Internet Service
Fiber optic    43.958540
DSL            34.374556
No             21.666903
Name: proportion, dtype: float64

Online Security
No                     49.666335
Yes                    28.666761
No internet service    21.666903
Name: proportion, dtype: float64

Online Backup
No                     43.844952
Yes                    34.488144
No internet service    21.666903
Name: proportion, dtype: float64

Device Protection
No                     43.944342
Yes                    34.388755
No internet service    21.666903
Name: proportion, dtype: float64

Tech Support
No                     49.311373
Yes                    29.021724
No internet service    21.666903
Name: proportion, dtype: float64

Streaming TV
No                     39.897771
Yes                    38.435326
No internet service    21.666903
Name: proportion, dtype: float64

Streaming Movies
No                     39.542808
Yes                    38.790288
No internet service    21.666903
Name: proportion, dtype: float64

Contract
Month-to-month    55.019168
Two year          24.066449
One year          20.914383
Name: proportion, dtype: float64

Paperless Billing
Yes    59.221922
No     40.778078
Name: proportion, dtype: float64

Payment Method
Electronic check             33.579441
Mailed check                 22.887974
Bank transfer (automatic)    21.922476
Credit card (automatic)      21.610109
Name: proportion, dtype: float64

Churn Label
No     73.463013
Yes    26.536987
Name: proportion, dtype: float64

Churn Reason
Attitude of support person                   10.272873
Competitor offered higher download speeds    10.112360
Competitor offered more data                  8.667737
Don't know                                    8.239700
Competitor made better offer                  7.490637
Attitude of service provider                  7.223114
Competitor had better devices                 6.955591
Network reliability                           5.510968
Product dissatisfaction                       5.457464
Price too high                                5.243446
Service dissatisfaction                       4.761905
Lack of self-service on Website               4.708400
Extra data charges                            3.049759
Moved                                         2.835741
Limited range of services                     2.354200
Long distance charges                         2.354200
Lack of affordable download/upload speed      2.354200
Poor expertise of phone support               1.070091
Poor expertise of online support              1.016586
Deceased                                      0.321027
Name: proportion, dtype: float64

# Ensure this matches your dataset column names
exclude_columns = ['Count', 'Country', 'State', 'CustomerID', 'Lat Long', 'Zip Code', 'Latitude', 'Longitude', 'Churn Reason']

categorical_columns = [
    'Gender', 'Senior Citizen', 'Partner', 'Dependents', 
    'Phone Service', 'Multiple Lines', 'Internet Service', 
    'Online Security', 'Online Backup', 'Device Protection', 
    'Tech Support', 'Streaming TV', 'Streaming Movies', 
    'Contract', 'Paperless Billing', 'Payment Method', 
    'Churn Label'
]

for i in categorical_columns:
    if i != 'Churn Label' and i not in exclude_columns:
        # Crosstab to calculate churn distribution for each category
        data = pd.crosstab(df[i], df['Churn Label'], normalize='index') * 100
        
        # Iterate through each category in the column
        for category in data.index:
            plt.figure(figsize=(8, 6))
            
            # Pie chart
            wedges, texts, autotexts = plt.pie(
                data.loc[category], 
                labels=data.columns, 
                autopct='%1.1f%%', 
                startangle=140
            )
            
            # Adding a key to all graphs
            plt.legend(
                wedges, 
                data.columns, 
                title="Churn Label", 
                loc="best"
            )
            
            # Title on all graphs
            plt.title(f'Relationship between {i} ({category}) and Churn Label')
            plt.show()

# Normalize churn distribution across cities
city_churn_data = pd.crosstab(df['City'], df['Churn Label'], normalize='index') * 100

# Plot the stacked bar chart
plt.figure(figsize=(12, 8))
city_churn_data.plot(kind='bar', stacked=True, figsize=(15, 7), colormap='viridis')

# Add labels and title
plt.ylabel('Percentage Churn %')
plt.xlabel('City')
plt.title('Churn Distribution Across Cities')
plt.legend(title='Churn Label', loc='upper right')
plt.tight_layout()
plt.show()

<Figure size 1200x800 with 0 Axes>

# Checking the relationship between different numerical variables

# Checking for non-numeric values in numerical columns and converting them to NaN

for col in numerical_columns:
    df[col] = pd.to_numeric(df[col], errors='coerce')

# Dropping rows with NaN values in numerical columns

# Plotting the correlation between numerical variables

plt.figure(figsize=(15, 15))
sns.heatmap(df[numerical_columns].corr(), annot=True, fmt='.2f', cmap='YlOrRd')
plt.title('Correlation Matrix of Numerical Variables')
plt.show()

import pandas as pd

df = pd.read_excel('Telco_customer_churn.xlsx')  # Adjust the file name/path if needed

columns_to_drop = ['CustomerID', 'Lat Long', 'Zip Code', 'Latitude', 'Longitude', 'Count', 'Country', 'State', 'Churn Reason', 'Churn Value']

# Drop the columns
df.drop(columns=columns_to_drop, inplace=True, errors='ignore')

# Verify remaining columns
print("Columns after dropping irrelevant ones:")
print(df.columns)

Columns after dropping irrelevant ones:
Index(['City', 'Gender', 'Senior Citizen', 'Partner', 'Dependents',
       'Tenure Months', 'Phone Service', 'Multiple Lines', 'Internet Service',
       'Online Security', 'Online Backup', 'Device Protection', 'Tech Support',
       'Streaming TV', 'Streaming Movies', 'Contract', 'Paperless Billing',
       'Payment Method', 'Monthly Charges', 'Total Charges', 'Churn Label',
       'Churn Score', 'CLTV'],
      dtype='object')

binary_columns = ['Gender', 'Senior Citizen', 'Partner', 'Dependents', 'Phone Service', 'Paperless Billing', 'Churn Label']
for col in binary_columns:
    if col in df.columns:
       df[col] = df[col].map({'Yes': 1, 'No': 0})

to_get_dummies_for = [
    'City', 'Gender', 'Multiple Lines', 'Internet Service',
    'Online Security', 'Online Backup', 'Device Protection',
    'Tech Support', 'Streaming TV',  'Streaming Movies',
    'Contract', 'Payment Method', 'Churn Label'
]

# Create dummy variables for the listed columns
df = pd.get_dummies(data=df, columns=to_get_dummies_for, drop_first=True)

# Verify dummy variable creation
print("Dataframe after dummy variable creation:")
print(df.head())

Dataframe after dummy variable creation:
   Senior Citizen  Partner  Dependents  Tenure Months  Phone Service  \
0               0        0           0              2              1   
1               0        0           1              2              1   
2               0        0           1              8              1   
3               0        1           1             28              1   
4               0        0           1             49              1   

   Paperless Billing  Monthly Charges Total Charges  Churn Score  CLTV  ...  \
0                  1            53.85        108.15           86  3239  ...   
1                  1            70.70        151.65           67  2701  ...   
2                  1            99.65         820.5           86  5372  ...   
3                  1           104.80       3046.05           84  5003  ...   
4                  1           103.70        5036.3           89  5340  ...   

   Streaming TV_No internet service  Streaming TV_Yes  \
0                             False             False   
1                             False             False   
2                             False              True   
3                             False              True   
4                             False              True   

   Streaming Movies_No internet service  Streaming Movies_Yes  \
0                                 False                 False   
1                                 False                 False   
2                                 False                  True   
3                                 False                  True   
4                                 False                  True   

   Contract_One year  Contract_Two year  \
0              False              False   
1              False              False   
2              False              False   
3              False              False   
4              False              False   

   Payment Method_Credit card (automatic)  Payment Method_Electronic check  \
0                                   False                            False   
1                                   False                             True   
2                                   False                             True   
3                                   False                             True   
4                                   False                            False   

   Payment Method_Mailed check  Churn Label_1  
0                         True           True  
1                        False           True  
2                        False           True  
3                        False           True  
4                        False           True  

[5 rows x 1160 columns]

# Define target variable
target_column = 'Churn Label'

if target_column in df.columns:
    y = df[target_column]
    X = df.drop(columns=[target_column])
else:
    print(f"Error: Target column '{target_column}' not found in dataset.")

Error: Target column 'Churn Label' not found in dataset.

df.info()
df.head()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 7043 entries, 0 to 7042
Columns: 1160 entries, Senior Citizen to Churn Label_1
dtypes: bool(1150), float64(1), int64(8), object(1)
memory usage: 8.3+ MB

# Assuming your data is in a pandas DataFrame
X = pd.DataFrame(X)
y = pd.Series(y)

# Identify and convert non-numeric values to NaN
X = X.apply(pd.to_numeric, errors='coerce')

# Handle NaN values: fill with 0, mean, median, or drop them
X = X.fillna(0)  # You can choose to fill with other strategies like mean, median, etc.

# Proceed with the train-test split and scaling
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42, stratify=y)

scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# Initialize the Logistic Regression model
log_reg = LogisticRegression(random_state=42)

# Fit the model on the training data
log_reg.fit(X_train_scaled, y_train)

# Check model coefficients
print("Model Coefficients:", log_reg.coef_)
print("Intercept:", log_reg.intercept_)

Model Coefficients: [[ 0.          0.          0.         ... -0.02735146  0.11801895
  -0.00196408]]
Intercept: [-4.31144835]

# Predict on the training set
y_train_pred = log_reg.predict(X_train_scaled)
y_train_prob = log_reg.predict_proba(X_train_scaled)

# Predict on the testing set
y_test_pred = log_reg.predict(X_test_scaled)
y_test_prob = log_reg.predict_proba(X_test_scaled)

# Instantiate the LogisticRegression model
model = LogisticRegression()

# Fit the model to the training data
model.fit(X_train_scaled, y_train)

LogisticRegression()

LogisticRegression()

print("=== Training Performance ===")
print(classification_report(y_train, y_train_pred))

# Confusion Matrix for Training
cm_train = confusion_matrix(y_train, y_train_pred)
sns.heatmap(cm_train, annot=True, fmt='d', cmap='Blues', xticklabels=['Not Churn', 'Churn'], yticklabels=['Not Churn', 'Churn'])
plt.title("Confusion Matrix - Training Data")
plt.xlabel("Predicted")
plt.ylabel("Actual")
plt.show()

=== Training Performance ===
              precision    recall  f1-score   support

          No       1.00      1.00      1.00      3622
         Yes       1.00      1.00      1.00      1308

    accuracy                           1.00      4930
   macro avg       1.00      1.00      1.00      4930
weighted avg       1.00      1.00      1.00      4930

print("=== Testing Performance ===")
print(classification_report(y_test, y_test_pred))

# Confusion Matrix for Testing
cm_test = confusion_matrix(y_test, y_test_pred)
sns.heatmap(cm_test, annot=True, fmt='d', cmap='Blues', xticklabels=['Not Churn', 'Churn'], yticklabels=['Not Churn', 'Churn'])
plt.title("Confusion Matrix - Testing Data")
plt.xlabel("Predicted")
plt.ylabel("Actual")
plt.show()

=== Testing Performance ===
              precision    recall  f1-score   support

          No       1.00      1.00      1.00      1552
         Yes       1.00      1.00      1.00       561

    accuracy                           1.00      2113
   macro avg       1.00      1.00      1.00      2113
weighted avg       1.00      1.00      1.00      2113

# Create the SVM model with linear kernel
svm_model = SVC(kernel='linear')

# Train the model
svm_model.fit(X_train_scaled, y_train)

SVC(kernel='linear')

SVC(kernel='linear')

# Make predictions on the training data
y_train_pred = svm_model.predict(X_train_scaled)

# Evaluate the training performance
print("=== Training Performance ===")
print(classification_report(y_train, y_train_pred))

# Confusion matrix for training data
cm_train = confusion_matrix(y_train, y_train_pred)
sns.heatmap(cm_train, annot=True, fmt='d', cmap='Blues', xticklabels=['Not Churn', 'Churn'], yticklabels=['Not Churn', 'Churn'])
plt.title('Confusion Matrix - Training Data')
plt.xlabel('Predicted')
plt.ylabel('Actual')
plt.show()

=== Training Performance ===
              precision    recall  f1-score   support

          No       1.00      1.00      1.00      3622
         Yes       1.00      1.00      1.00      1308

    accuracy                           1.00      4930
   macro avg       1.00      1.00      1.00      4930
weighted avg       1.00      1.00      1.00      4930

# Make predictions on the test data
y_test_pred = svm_model.predict(X_test_scaled)

# Evaluate the test performance
print("=== Test Performance ===")
print(classification_report(y_test, y_test_pred))

# Confusion matrix for test data
cm_test = confusion_matrix(y_test, y_test_pred)
sns.heatmap(cm_test, annot=True, fmt='d', cmap='Blues', xticklabels=['Not Churn', 'Churn'], yticklabels=['Not Churn', 'Churn'])
plt.title('Confusion Matrix - Test Data')
plt.xlabel('Predicted')
plt.ylabel('Actual')
plt.show()

=== Test Performance ===
              precision    recall  f1-score   support

          No       1.00      1.00      1.00      1552
         Yes       1.00      1.00      1.00       561

    accuracy                           1.00      2113
   macro avg       1.00      1.00      1.00      2113
weighted avg       1.00      1.00      1.00      2113

	CustomerID	Count	Country	State	City	Zip Code	Lat Long	Latitude	Longitude	Gender	...	Contract	Paperless Billing	Payment Method	Monthly Charges	Total Charges	Churn Label	Churn Score	CLTV	Churn Reason
7028	7398-LXGYX	1	United States	California	Pioneertown	92268	34.201108, -116.593456	34.201108	-116.593456	Male	...	Month-to-month	Yes	Credit card (automatic)	84.80	3626.35	No	44	2770	NaN
7029	2823-LKABH	1	United States	California	Rancho Mirage	92270	33.763678, -116.429928	33.763678	-116.429928	Female	...	Month-to-month	Yes	Bank transfer (automatic)	95.05	1679.4	No	60	4524	NaN
7030	0550-DCXLH	1	United States	California	Thermal	92274	33.53604, -116.119222	33.536040	-116.119222	Male	...	Month-to-month	No	Mailed check	73.35	931.55	No	65	4645	NaN
7031	9281-CEDRU	1	United States	California	Salton City	92275	33.28156, -115.955541	33.281560	-115.955541	Female	...	Two year	No	Bank transfer (automatic)	64.10	4326.25	No	48	5553	NaN
7032	2235-DWLJU	1	United States	California	Thousand Palms	92276	33.849263, -116.382778	33.849263	-116.382778	Female	...	Month-to-month	Yes	Electronic check	44.40	263.05	No	71	4611	NaN
7033	0871-OPBXW	1	United States	California	Twentynine Palms	92277	34.17211, -115.769773	34.172110	-115.769773	Female	...	Month-to-month	Yes	Mailed check	20.05	39.25	No	80	5191	NaN
7034	3605-JISKB	1	United States	California	Twentynine Palms	92278	34.457829, -116.139589	34.457829	-116.139589	Male	...	One year	No	Credit card (automatic)	60.00	3316.1	No	71	4212	NaN
7035	9767-FFLEM	1	United States	California	Westmorland	92281	33.03679, -115.60503	33.036790	-115.605030	Male	...	Month-to-month	Yes	Credit card (automatic)	69.50	2625.25	No	35	4591	NaN
7036	8456-QDAVC	1	United States	California	Winterhaven	92283	32.852947, -114.850784	32.852947	-114.850784	Male	...	Month-to-month	Yes	Bank transfer (automatic)	78.70	1495.1	No	20	2464	NaN
7037	7750-EYXWZ	1	United States	California	Yucca Valley	92284	34.159534, -116.425984	34.159534	-116.425984	Female	...	One year	No	Electronic check	60.65	743.3	No	24	3740	NaN
7038	2569-WGERO	1	United States	California	Landers	92285	34.341737, -116.539416	34.341737	-116.539416	Female	...	Two year	Yes	Bank transfer (automatic)	21.15	1419.4	No	45	5306	NaN
7039	6840-RESVB	1	United States	California	Adelanto	92301	34.667815, -117.536183	34.667815	-117.536183	Male	...	One year	Yes	Mailed check	84.80	1990.5	No	59	2140	NaN
7040	2234-XADUH	1	United States	California	Amboy	92304	34.559882, -115.637164	34.559882	-115.637164	Female	...	One year	Yes	Credit card (automatic)	103.20	7362.9	No	71	5560	NaN
7041	4801-JZAZL	1	United States	California	Angelus Oaks	92305	34.1678, -116.86433	34.167800	-116.864330	Female	...	Month-to-month	Yes	Electronic check	29.60	346.45	No	59	2793	NaN
7042	3186-AJIEK	1	United States	California	Apple Valley	92308	34.424926, -117.184503	34.424926	-117.184503	Male	...	Two year	Yes	Bank transfer (automatic)	105.65	6844.5	No	38	5097	NaN

	Count	Zip Code	Latitude	Longitude	Tenure Months	Monthly Charges	Churn Value	Churn Score	CLTV
count	7043.0	7043.000000	7043.000000	7043.000000	7043.000000	7043.000000	7043.000000	7043.000000	7043.000000
mean	1.0	93521.964646	36.282441	-119.798880	32.371149	64.761692	0.265370	58.699418	4400.295755
std	0.0	1865.794555	2.455723	2.157889	24.559481	30.090047	0.441561	21.525131	1183.057152
min	1.0	90001.000000	32.555828	-124.301372	0.000000	18.250000	0.000000	5.000000	2003.000000
25%	1.0	92102.000000	34.030915	-121.815412	9.000000	35.500000	0.000000	40.000000	3469.000000
50%	1.0	93552.000000	36.391777	-119.730885	29.000000	70.350000	0.000000	61.000000	4527.000000
75%	1.0	95351.000000	38.224869	-118.043237	55.000000	89.850000	1.000000	75.000000	5380.500000
max	1.0	96161.000000	41.962127	-114.192901	72.000000	118.750000	1.000000	100.000000	6500.000000

	count	mean	std	min	25%	50%	75%	max
Tenure Months	7043.0	32.371149	24.559481	0.00	9.0	29.00	55.00	72.00
Monthly Charges	7043.0	64.761692	30.090047	18.25	35.5	70.35	89.85	118.75
Churn Value	7043.0	0.265370	0.441561	0.00	0.0	0.00	1.00	1.00
Churn Score	7043.0	58.699418	21.525131	5.00	40.0	61.00	75.00	100.00
CLTV	7043.0	4400.295755	1183.057152	2003.00	3469.0	4527.00	5380.50	6500.00

Inserting Required Files¶

Allowing Python to Read Excel Dataset¶

Display Top 15 Lines¶

Display Bottom 15 Lines¶

Description Of Data¶

Summary Of Data¶

Identify Unique Values¶

Idenitfying and Organising Numerical Columns¶

Identify and Organising Categorical Columns¶

Data Preparation¶

Splitting Data Train (70%) and Test (30%)¶

Logistics Regression¶

Support Vector Machine (SVM)¶

	CustomerID	Count	Country	State	City	Zip Code	Lat Long	Latitude	Longitude	Gender	...	Contract	Paperless Billing	Payment Method	Monthly Charges	Total Charges	Churn Label	Churn Value	Churn Score	CLTV	Churn Reason
0	3668-QPYBK	1	United States	California	Los Angeles	90003	33.964131, -118.272783	33.964131	-118.272783	Male	...	Month-to-month	Yes	Mailed check	53.85	108.15	Yes	1	86	3239	Competitor made better offer
1	9237-HQITU	1	United States	California	Los Angeles	90005	34.059281, -118.30742	34.059281	-118.307420	Female	...	Month-to-month	Yes	Electronic check	70.70	151.65	Yes	1	67	2701	Moved
2	9305-CDSKC	1	United States	California	Los Angeles	90006	34.048013, -118.293953	34.048013	-118.293953	Female	...	Month-to-month	Yes	Electronic check	99.65	820.5	Yes	1	86	5372	Moved
3	7892-POOKP	1	United States	California	Los Angeles	90010	34.062125, -118.315709	34.062125	-118.315709	Female	...	Month-to-month	Yes	Electronic check	104.80	3046.05	Yes	1	84	5003	Moved
4	0280-XJGEX	1	United States	California	Los Angeles	90015	34.039224, -118.266293	34.039224	-118.266293	Male	...	Month-to-month	Yes	Bank transfer (automatic)	103.70	5036.3	Yes	1	89	5340	Competitor had better devices
5	4190-MFLUW	1	United States	California	Los Angeles	90020	34.066367, -118.309868	34.066367	-118.309868	Female	...	Month-to-month	No	Credit card (automatic)	55.20	528.35	Yes	1	78	5925	Competitor offered higher download speeds
6	8779-QRDMV	1	United States	California	Los Angeles	90022	34.02381, -118.156582	34.023810	-118.156582	Male	...	Month-to-month	Yes	Electronic check	39.65	39.65	Yes	1	100	5433	Competitor offered more data
7	1066-JKSGK	1	United States	California	Los Angeles	90024	34.066303, -118.435479	34.066303	-118.435479	Male	...	Month-to-month	No	Mailed check	20.15	20.15	Yes	1	92	4832	Competitor made better offer
8	6467-CHFZW	1	United States	California	Los Angeles	90028	34.099869, -118.326843	34.099869	-118.326843	Male	...	Month-to-month	Yes	Electronic check	99.35	4749.15	Yes	1	77	5789	Competitor had better devices
9	8665-UTDHZ	1	United States	California	Los Angeles	90029	34.089953, -118.294824	34.089953	-118.294824	Male	...	Month-to-month	No	Electronic check	30.20	30.2	Yes	1	97	2915	Competitor had better devices
10	8773-HHUOZ	1	United States	California	Los Angeles	90032	34.078821, -118.177576	34.078821	-118.177576	Female	...	Month-to-month	Yes	Mailed check	64.70	1093.1	Yes	1	74	3022	Competitor offered higher download speeds
11	6047-YHPVI	1	United States	California	Los Angeles	90039	34.110845, -118.259595	34.110845	-118.259595	Male	...	Month-to-month	Yes	Electronic check	69.70	316.9	Yes	1	66	2454	Competitor offered higher download speeds
12	5380-WJKOV	1	United States	California	Los Angeles	90041	34.137412, -118.207607	34.137412	-118.207607	Male	...	Month-to-month	Yes	Electronic check	106.35	3549.25	Yes	1	65	2941	Competitor offered higher download speeds
13	8168-UQWWF	1	United States	California	Los Angeles	90042	34.11572, -118.192754	34.115720	-118.192754	Female	...	Month-to-month	Yes	Bank transfer (automatic)	97.85	1105.4	Yes	1	70	5674	Competitor offered more data
14	7760-OYPDY	1	United States	California	Los Angeles	90056	33.987945, -118.370442	33.987945	-118.370442	Female	...	Month-to-month	Yes	Electronic check	80.65	144.15	Yes	1	90	5586	Competitor offered more data

	count	unique	top	freq
City	7043	1129	Los Angeles	305
Gender	7043	2	Male	3555
Senior Citizen	7043	2	No	5901
Partner	7043	2	No	3641
Dependents	7043	2	No	5416
Phone Service	7043	2	Yes	6361
Multiple Lines	7043	3	No	3390
Internet Service	7043	3	Fiber optic	3096
Online Security	7043	3	No	3498
Online Backup	7043	3	No	3088
Device Protection	7043	3	No	3095
Tech Support	7043	3	No	3473
Streaming TV	7043	3	No	2810
Streaming Movies	7043	3	No	2785
Contract	7043	3	Month-to-month	3875
Paperless Billing	7043	2	Yes	4171
Payment Method	7043	4	Electronic check	2365
Churn Label	7043	2	No	5174
Churn Reason	1869	20	Attitude of support person	192