In [1]:
import numpy as np 
import pandas as pd
import matplotlib.pyplot as plt
In [2]:
dataset = pd.read_csv('CC_GENERAL.csv')
X = dataset.iloc[:, 1:].values
In [13]:
from sklearn.impute import SimpleImputer
imputer = SimpleImputer(missing_values= np.NAN, strategy= 'mean', fill_value=None, verbose=0, copy=True)
imputer = imputer.fit(X)
X = imputer.transform(X)

C:\Users\Lenovo\anaconda3\lib\site-packages\sklearn\impute\_base.py:382: FutureWarning: The 'verbose' parameter was deprecated in version 1.1 and will be removed in 1.3. A warning will always be raised upon the removal of empty columns in the future version.
  warnings.warn(
In [14]:
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X = sc_X.fit_transform(X)
In [15]:
from sklearn.cluster import KMeans
wcss = []
for i in range(1,18):
    kmeans = KMeans(n_clusters=i, init='k-means++', max_iter=300, n_init=10, random_state=0).fit(X)
    wcss.append(kmeans.inertia_)
    
plt.plot(range(1,18), wcss)
plt.title('Elbow Method')
plt.xlabel('Number of Cluster')
plt.ylabel('WCSS')
plt.show()
In [16]:
kmeans = KMeans(n_clusters=8, init='k-means++', max_iter=300, n_init=10, random_state=0)
y_kmeans = kmeans.fit_predict(X)
In [17]:
dataset['Cluster'] = y_kmeans
dataset.head()
Out[17]:
CUST_ID BALANCE BALANCE_FREQUENCY PURCHASES ONEOFF_PURCHASES INSTALLMENTS_PURCHASES CASH_ADVANCE PURCHASES_FREQUENCY ONEOFF_PURCHASES_FREQUENCY PURCHASES_INSTALLMENTS_FREQUENCY CASH_ADVANCE_FREQUENCY CASH_ADVANCE_TRX PURCHASES_TRX CREDIT_LIMIT PAYMENTS MINIMUM_PAYMENTS PRC_FULL_PAYMENT TENURE Cluster
0 C10001 40.900749 0.818182 95.40 0.00 95.4 0.000000 0.166667 0.000000 0.083333 0.000000 0 2 1000.0 201.802084 139.509787 0.000000 12 0
1 C10002 3202.467416 0.909091 0.00 0.00 0.0 6442.945483 0.000000 0.000000 0.000000 0.250000 4 0 7000.0 4103.032597 1072.340217 0.222222 12 3
2 C10003 2495.148862 1.000000 773.17 773.17 0.0 0.000000 1.000000 1.000000 0.000000 0.000000 0 12 7500.0 622.066742 627.284787 0.000000 12 5
3 C10004 1666.670542 0.636364 1499.00 1499.00 0.0 205.788017 0.083333 0.083333 0.000000 0.083333 1 1 7500.0 0.000000 NaN 0.000000 12 0
4 C10005 817.714335 1.000000 16.00 16.00 0.0 0.000000 0.083333 0.083333 0.000000 0.000000 0 1 1200.0 678.334763 244.791237 0.000000 12 0
In [ ]: