10/25/2020 SomritaProject_Clustering

In [1]:

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
from sklearn.cluster import KMeans
import seaborn as sns
%matplotlib inline

In [2]:

data_bank=pd.read_csv("bank_marketing_part1_Data.csv")
data_bank.head()

Out[2]:

spending advance_payments probability_of_full_payment current_balance credit_limit mi

0 19.94 16.92 0.8752 6.675 3.763

1 15.99 14.89 0.9064 5.363 3.582

2 18.95 16.42 0.8829 6.248 3.755

3 10.83 12.96 0.8099 5.278 2.641

4 17.99 15.86 0.8992 5.890 3.694

In [4]:

data_bank.describe().T

Out[4]:

count mean std min 25% 50%

spending 210.0 14.847524 2.909699 10.5900 12.27000 14.35500 17.3

advance_payments 210.0 14.559286 1.305959 12.4100 13.45000 14.32000 15.7

probability_of_full_payment 210.0 0.870999 0.023629 0.8081 0.85690 0.87345 0.8

current_balance 210.0 5.628533 0.443063 4.8990 5.26225 5.52350 5.9

credit_limit 210.0 3.258605 0.377714 2.6300 2.94400 3.23700 3.5

min_payment_amt 210.0 3.700201 1.503557 0.7651 2.56150 3.59900 4.7

max_spent_in_single_shopping 210.0 5.408071 0.491480 4.5190 5.04500 5.22300 5.8

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 1/20
10/25/2020 SomritaProject_Clustering

In [5]:

data_bank.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 210 entries, 0 to 209
Data columns (total 7 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 spending 210 non-null float64
1 advance_payments 210 non-null float64
2 probability_of_full_payment 210 non-null float64
3 current_balance 210 non-null float64
4 credit_limit 210 non-null float64
5 min_payment_amt 210 non-null float64
6 max_spent_in_single_shopping 210 non-null float64
dtypes: float64(7)
memory usage: 11.6 KB

In [6]:

data_bank.shape

Out[6]:

(210, 7)

In [7]:

data_bank.duplicated().sum()

Out[7]:

In [8]:

data_bank.isnull().sum()

Out[8]:

spending 0
advance_payments 0
probability_of_full_payment 0
current_balance 0
credit_limit 0
min_payment_amt 0
max_spent_in_single_shopping 0
dtype: int64

In [9]:

data_bank.columns

Out[9]:

Index(['spending', 'advance_payments', 'probability_of_full_payment',

'current_balance', 'credit_limit', 'min_payment_amt',
'max_spent_in_single_shopping'],
dtype='object')

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 2/20
10/25/2020 SomritaProject_Clustering

In [10]:

columns=('spending', 'advance_payments', 'probability_of_full_payment',

'current_balance', 'credit_limit', 'min_payment_amt',
'max_spent_in_single_shopping')
plt.figure(figsize=[20,40])
for i in range(len(columns)):
plt.subplot(9,2,i+1)
sns.boxplot(data_bank[columns[i]])

In [11]:

def remove_outlier(col):
sorted(col)
Q1,Q3=col.quantile([0.25,0.75])
IQR=Q3-Q1
lower_range= Q1-(1.5 * IQR)
upper_range= Q3+(1.5 * IQR)
return lower_range, upper_range

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 3/20
10/25/2020 SomritaProject_Clustering

In [12]:

lrincome,urincome=remove_outlier(data_bank['probability_of_full_payment'])
data_bank['probability_of_full_payment']=np.where(data_bank['probability_of_full_paymen
t']>urincome,urincome,data_bank['probability_of_full_payment'])
data_bank['probability_of_full_payment']=np.where(data_bank['probability_of_full_paymen
t']<lrincome,lrincome,data_bank['probability_of_full_payment'])

lrtravel,urtravel=remove_outlier(data_bank['min_payment_amt'])
data_bank['min_payment_amt']=np.where(data_bank['min_payment_amt']>urtravel,urtravel,da
ta_bank['min_payment_amt'])
data_bank['min_payment_amt']=np.where(data_bank['min_payment_amt']<lrtravel,lrtravel,da
ta_bank['min_payment_amt'])

In [13]:

columns=('spending', 'advance_payments', 'probability_of_full_payment',

'current_balance', 'credit_limit', 'min_payment_amt',
'max_spent_in_single_shopping')
plt.figure(figsize=[20,40])
for i in range(len(columns)):
plt.subplot(9,2,i+1)
sns.boxplot(data_bank[columns[i]])

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 4/20
10/25/2020 SomritaProject_Clustering

In [14]:

columns=('spending', 'advance_payments', 'probability_of_full_payment',

'current_balance', 'credit_limit', 'min_payment_amt',
'max_spent_in_single_shopping')
plt.figure(figsize=[20,40])
for i in range(len(columns)):
plt.subplot(9,2,i+1)
sns.distplot(data_bank[columns[i]],bins=20)

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 5/20
10/25/2020 SomritaProject_Clustering

In [19]:

data_bank.hist(figsize=(15,20))

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 6/20
10/25/2020 SomritaProject_Clustering

Out[19]:

array([[<matplotlib.axes._subplots.AxesSubplot object at 0x0000028F91331F8

8>,
<matplotlib.axes._subplots.AxesSubplot object at 0x0000028F9133B54
8>,
<matplotlib.axes._subplots.AxesSubplot object at 0x0000028F91361B8
8>],
[<matplotlib.axes._subplots.AxesSubplot object at 0x0000028F9139B50
8>,
<matplotlib.axes._subplots.AxesSubplot object at 0x0000028F913CFF0
8>,
<matplotlib.axes._subplots.AxesSubplot object at 0x0000028F9140B90
8>],
[<matplotlib.axes._subplots.AxesSubplot object at 0x0000028F9144628
8>,
<matplotlib.axes._subplots.AxesSubplot object at 0x0000028F91479F0
8>,
<matplotlib.axes._subplots.AxesSubplot object at 0x0000028F9148C18
8>]],
dtype=object)

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 7/20
10/25/2020 SomritaProject_Clustering

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 8/20
10/25/2020 SomritaProject_Clustering

In [20]:

plt.figure(figsize=[10,5])
sns.pairplot(data_bank)
plt.show()

<Figure size 720x360 with 0 Axes>

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 9/20
10/25/2020 SomritaProject_Clustering

In [21]:

corr = data_bank.corr()
corr

Out[21]:

spending advance_payments probability_of_full_payment cur

spending 1.000000 0.994341 0.608900

advance_payments 0.994341 1.000000 0.529925

probability_of_full_payment 0.608900 0.529925 1.000000

current_balance 0.949985 0.972422 0.368419

credit_limit 0.970771 0.944829 0.762218

min_payment_amt -0.229619 -0.217051 -0.335071

max_spent_in_single_shopping 0.863693 0.890784 0.227140

In [22]:

plt.figure(figsize=(12,7))
sns.heatmap(data_bank.corr(), annot=True, fmt='.2f', cmap='Blues')
plt.show()

In [23]:

# importing the StandardScaler Module

from sklearn.preprocessing import StandardScaler

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 10/20
10/25/2020 SomritaProject_Clustering

In [24]:

X = StandardScaler()
X

Out[24]:

StandardScaler()

In [25]:

scaled_df= X.fit_transform(data_bank)

In [26]:

scaled_df = pd.DataFrame(scaled_df, index=data_bank.index, columns=data_bank.columns)

scaled_df.head()

Out[26]:

spending advance_payments probability_of_full_payment current_balance credit_limit m

0 1.754355 1.811968 0.177628 2.367533 1.338579

1 0.393582 0.253840 1.505071 -0.600744 0.858236

2 1.413300 1.428192 0.505234 1.401485 1.317348

3 -1.384034 -1.227533 -2.571391 -0.793049 -1.639017

4 1.082581 0.998364 1.198738 0.591544 1.155464

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 11/20
10/25/2020 SomritaProject_Clustering

In [27]:

columns=('spending', 'advance_payments', 'probability_of_full_payment',

'current_balance', 'credit_limit', 'min_payment_amt',
'max_spent_in_single_shopping')
plt.figure(figsize=[20,40])
for i in range(len(columns)):
plt.subplot(9,2,i+1)
sns.boxplot(scaled_df[columns[i]])

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 12/20
10/25/2020 SomritaProject_Clustering

In [28]:

lrincome,urincome=remove_outlier(scaled_df['probability_of_full_payment'])
scaled_df['probability_of_full_payment']=np.where(scaled_df['probability_of_full_paymen
t']>urincome,urincome,scaled_df['probability_of_full_payment'])
scaled_df['probability_of_full_payment']=np.where(scaled_df['probability_of_full_paymen
t']<lrincome,lrincome,scaled_df['probability_of_full_payment'])

In [29]:

columns=('spending', 'advance_payments', 'probability_of_full_payment',

'current_balance', 'credit_limit', 'min_payment_amt',
'max_spent_in_single_shopping')
plt.figure(figsize=[20,40])
for i in range(len(columns)):
plt.subplot(9,2,i+1)
sns.boxplot(scaled_df[columns[i]])

In [30]:

from scipy.cluster.hierarchy import dendrogram, linkage

In [31]:

wardlink = linkage(scaled_df, method = 'ward')

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 13/20
10/25/2020 SomritaProject_Clustering

In [32]:

dend=dendrogram(wardlink)

In [33]:

dend=dendrogram(wardlink,truncate_mode='lastp',p=10)

In [34]:

from scipy.cluster.hierarchy import fcluster

In [35]:

clusters=fcluster(wardlink,3,criterion='maxclust')

In [36]:

data_bank['clusters']=clusters

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 14/20
10/25/2020 SomritaProject_Clustering

In [37]:

data_bank.head()

Out[37]:

spending advance_payments probability_of_full_payment current_balance credit_limit mi

0 19.94 16.92 0.875200 6.675 3.763

1 15.99 14.89 0.906400 5.363 3.582

2 18.95 16.42 0.882900 6.248 3.755

3 10.83 12.96 0.810588 5.278 2.641

4 17.99 15.86 0.899200 5.890 3.694

In [38]:

data_bank.clusters.value_counts().sort_index()

Out[38]:

1 70
2 67
3 73
Name: clusters, dtype: int64

In [39]:

aggdata=data_bank.groupby('clusters').mean()
aggdata['Freq']=data_bank.clusters.value_counts().sort_index()
aggdata

Out[39]:

spending advance_payments probability_of_full_payment current_balance credit_li

clusters

1 18.371429 16.145429 0.884400 6.158171 3.6846

2 11.872388 13.257015 0.848155 5.238940 2.8485

3 14.199041 14.233562 0.879190 5.478233 3.2264

In [40]:

data_bank.to_csv("HierarchicalProject.csv")

In [41]:

from sklearn.cluster import AgglomerativeClustering

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 15/20
10/25/2020 SomritaProject_Clustering

In [42]:

clusterAgglo = AgglomerativeClustering(n_clusters=3, affinity='euclidean', linkage='ave

rage')
Cluster_agglo=clusterAgglo.fit_predict(scaled_df)
print(Cluster_agglo)

[1 0 1 2 1 0 2 2 1 2 1 1 2 1 0 0 0 2 2 2 2 2 1 2 0 1 0 2 2 2 2 2 2 0 2 2 2
2 2 1 1 0 1 1 2 2 0 1 1 1 2 1 1 1 1 1 2 2 2 1 0 2 2 1 0 1 1 0 1 2 0 2 1 1
2 1 0 2 1 0 0 0 0 1 2 1 1 1 1 0 0 1 0 2 2 1 1 1 2 1 0 1 0 1 0 1 1 2 0 1 1
0 1 2 2 1 0 0 2 1 0 2 2 2 0 0 1 2 0 0 2 0 0 1 2 1 1 2 1 0 0 0 2 2 2 2 1 2
0 2 0 2 0 1 0 0 2 2 0 1 1 2 1 1 1 2 1 0 0 2 0 2 0 1 1 1 0 2 0 2 0 2 0 0 1
1 0 1 0 2 0 0 2 1 0 1 1 2 1 2 0 0 0 2 1 0 1 0 0 1]

In [43]:

data_bank["Agglo_CLusters"]=Cluster_agglo

In [45]:

data_bank.head(10)

Out[45]:

spending advance_payments probability_of_full_payment current_balance credit_limit mi

0 19.94 16.92 0.875200 6.675 3.763

1 15.99 14.89 0.906400 5.363 3.582

2 18.95 16.42 0.882900 6.248 3.755

3 10.83 12.96 0.810588 5.278 2.641

4 17.99 15.86 0.899200 5.890 3.694

5 12.70 13.41 0.887400 5.183 3.091

6 12.02 13.33 0.850300 5.350 2.810

7 13.74 14.05 0.874400 5.482 3.114

8 18.17 16.26 0.863700 6.271 3.512

9 11.23 12.88 0.851100 5.140 2.795

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 16/20
10/25/2020 SomritaProject_Clustering

In [46]:

agglo_data=data_bank.groupby('Agglo_CLusters').mean()
agglo_data['Freq']=data_bank.Agglo_CLusters.value_counts().sort_index()
agglo_data

Out[46]:

spending advance_payments probability_of_full_payment current_balance

Agglo_CLusters

0 14.217077 14.195846 0.884869 5.442000

1 18.129200 16.058000 0.881595 6.135747

2 11.916857 13.291000 0.846845 5.258300

In [48]:

#KMeans
k_means = KMeans(n_clusters = 3)
k_means.fit(scaled_df)
k_means.inertia_

Out[48]:

430.298481751223

In [50]:

k_means = KMeans(n_clusters = 2)
k_means.fit(scaled_df)
k_means.inertia_

Out[50]:

659.1474009548498

In [51]:

k_means = KMeans(n_clusters = 1)
k_means.fit(scaled_df)
k_means.inertia_

Out[51]:

1469.9999999999995

In [53]:

k_means = KMeans(n_clusters = 4)
k_means.fit(scaled_df)
k_means.inertia_

Out[53]:

370.8685962394206

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 17/20
10/25/2020 SomritaProject_Clustering

In [54]:

k_means = KMeans(n_clusters = 5)
k_means.fit(scaled_df)
k_means.inertia_

Out[54]:

325.9098750065543

In [55]:

wss =[]

In [56]:

for i in range(1,11):
KM = KMeans(n_clusters=i)
KM.fit(scaled_df)
wss.append(KM.inertia_)

In [57]:

wss

Out[57]:

[1469.9999999999995,
659.1474009548498,
430.298481751223,
371.4400252695771,
327.39077808486644,
289.50583097697313,
262.5952276605776,
239.57831775716886,
223.42523703383455,
208.7028049634438]

In [58]:

plt.plot(range(1,11), wss)

Out[58]:

[<matplotlib.lines.Line2D at 0x28f968b9a88>]

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 18/20
10/25/2020 SomritaProject_Clustering

In [59]:

k_means = KMeans(n_clusters = 3)
k_means.fit(scaled_df)
labels = k_means.labels_

In [61]:

data_bank["Clus_kmeans"] = labels
data_bank.head(7)

Out[61]:

spending advance_payments probability_of_full_payment current_balance credit_limit mi

0 19.94 16.92 0.875200 6.675 3.763

1 15.99 14.89 0.906400 5.363 3.582

2 18.95 16.42 0.882900 6.248 3.755

3 10.83 12.96 0.810588 5.278 2.641

4 17.99 15.86 0.899200 5.890 3.694

5 12.70 13.41 0.887400 5.183 3.091

6 12.02 13.33 0.850300 5.350 2.810

In [62]:

from sklearn.metrics import silhouette_samples, silhouette_score

In [63]:

silhouette_score(scaled_df,labels)

Out[63]:

0.4008059221522216

In [64]:

sil_width = silhouette_samples(scaled_df,labels)

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 19/20
10/25/2020 SomritaProject_Clustering

In [65]:

data_bank["sil_width"] = sil_width
data_bank.head(7)

Out[65]:

spending advance_payments probability_of_full_payment current_balance credit_limit mi

0 19.94 16.92 0.875200 6.675 3.763

1 15.99 14.89 0.906400 5.363 3.582

2 18.95 16.42 0.882900 6.248 3.755

3 10.83 12.96 0.810588 5.278 2.641

4 17.99 15.86 0.899200 5.890 3.694

5 12.70 13.41 0.887400 5.183 3.091

6 12.02 13.33 0.850300 5.350 2.810

In [71]:

kmeansdata=data_bank.groupby('Clus_kmeans').mean()
kmeansdata['Freq']=data_bank.Clus_kmeans.value_counts().sort_index()
kmeansdata

Out[71]:

spending advance_payments probability_of_full_payment current_balance cre

Clus_kmeans

0 11.856944 13.247778 0.848330 5.231750 2

1 18.495373 16.203433 0.884210 6.175687

2 14.437887 14.337746 0.881597 5.514577

In [72]:

silhouette_samples(scaled_df,labels).min()

Out[72]:

0.002768541128616533

In [ ]:

file:///C:/Users/Titlee_Joy/Downloads/SomritaProject_Clustering.html 20/20