7/1/24, 1:25 PM K-Means clustering

K-Means clustering
In [1]: import pandas as pd

In [2]: df=pd.read_csv("C:\\Users\\vaish\\Downloads\\SIC\\Mall_Customers.csv")

In [3]: df = df.drop(["CustomerID", "Gender", "Age"], axis=1)

In [4]: df

Out[4]: Annual Income (k$) Spending Score (1-100)

0 15 39

1 15 81

2 16 6

3 16 77

4 17 40

... ... ...

195 120 79

196 126 28

197 126 74

198 137 18

199 137 83

200 rows × 2 columns

In [5]: df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 200 entries, 0 to 199
Data columns (total 2 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Annual Income (k$) 200 non-null int64
1 Spending Score (1-100) 200 non-null int64
dtypes: int64(2)
memory usage: 3.3 KB

In [6]: df.columns

Index(['Annual Income (k$)', 'Spending Score (1-100)'], dtype='object')

Out[6]:

In [7]: df.isnull().sum()

Annual Income (k$) 0

Out[7]:
Spending Score (1-100) 0
dtype: int64

In [8]: import matplotlib.pyplot as plt

localhost:8888/nbconvert/html/Downloads/SIC/K-Means clustering.ipynb?download=false 1/11

7/1/24, 1:25 PM K-Means clustering
plt.scatter(df['Annual Income (k$)'], df['Spending Score (1-100)'])
plt.xlabel('Annual Income (k$)')
plt.ylabel('Spending Score (1-100)')
plt.title('Annual Income vs Spending Score')
plt.show()

In [9]: from sklearn.cluster import KMeans

In [ ]: vc=[]
for i in range (1,11):
km=KMeans(n_clusters=i)
km.fit_predict(df)
vc.append(km.inertia_)

localhost:8888/nbconvert/html/Downloads/SIC/K-Means clustering.ipynb?download=false 2/11

7/1/24, 1:25 PM K-Means clustering

C:\anaconda\Lib\site-packages\sklearn\cluster\_kmeans.py:870: FutureWarning: The d

efault value of `n_init` will change from 10 to 'auto' in 1.4. Set the value of `n
_init` explicitly to suppress the warning
warnings.warn(
C:\anaconda\Lib\site-packages\sklearn\cluster\_kmeans.py:1382: UserWarning: KMeans
is known to have a memory leak on Windows with MKL, when there are less chunks tha
n available threads. You can avoid it by setting the environment variable OMP_NUM_
THREADS=1.
warnings.warn(
C:\anaconda\Lib\site-packages\sklearn\cluster\_kmeans.py:870: FutureWarning: The d
efault value of `n_init` will change from 10 to 'auto' in 1.4. Set the value of `n
_init` explicitly to suppress the warning
warnings.warn(
C:\anaconda\Lib\site-packages\sklearn\cluster\_kmeans.py:1382: UserWarning: KMeans
is known to have a memory leak on Windows with MKL, when there are less chunks tha
n available threads. You can avoid it by setting the environment variable OMP_NUM_
THREADS=1.
warnings.warn(
C:\anaconda\Lib\site-packages\sklearn\cluster\_kmeans.py:870: FutureWarning: The d
efault value of `n_init` will change from 10 to 'auto' in 1.4. Set the value of `n
_init` explicitly to suppress the warning
warnings.warn(
C:\anaconda\Lib\site-packages\sklearn\cluster\_kmeans.py:1382: UserWarning: KMeans
is known to have a memory leak on Windows with MKL, when there are less chunks tha
n available threads. You can avoid it by setting the environment variable OMP_NUM_
THREADS=1.
warnings.warn(
C:\anaconda\Lib\site-packages\sklearn\cluster\_kmeans.py:870: FutureWarning: The d
efault value of `n_init` will change from 10 to 'auto' in 1.4. Set the value of `n
_init` explicitly to suppress the warning
warnings.warn(
C:\anaconda\Lib\site-packages\sklearn\cluster\_kmeans.py:1382: UserWarning: KMeans
is known to have a memory leak on Windows with MKL, when there are less chunks tha
n available threads. You can avoid it by setting the environment variable OMP_NUM_
THREADS=1.
warnings.warn(
C:\anaconda\Lib\site-packages\sklearn\cluster\_kmeans.py:870: FutureWarning: The d
efault value of `n_init` will change from 10 to 'auto' in 1.4. Set the value of `n
_init` explicitly to suppress the warning
warnings.warn(
C:\anaconda\Lib\site-packages\sklearn\cluster\_kmeans.py:1382: UserWarning: KMeans
is known to have a memory leak on Windows with MKL, when there are less chunks tha
n available threads. You can avoid it by setting the environment variable OMP_NUM_
THREADS=1.
warnings.warn(
C:\anaconda\Lib\site-packages\sklearn\cluster\_kmeans.py:870: FutureWarning: The d
efault value of `n_init` will change from 10 to 'auto' in 1.4. Set the value of `n
_init` explicitly to suppress the warning
warnings.warn(
C:\anaconda\Lib\site-packages\sklearn\cluster\_kmeans.py:1382: UserWarning: KMeans
is known to have a memory leak on Windows with MKL, when there are less chunks tha
n available threads. You can avoid it by setting the environment variable OMP_NUM_
THREADS=1.
warnings.warn(

In [23]: vc

localhost:8888/nbconvert/html/Downloads/SIC/K-Means clustering.ipynb?download=false 3/11

7/1/24, 1:25 PM K-Means clustering
[269981.28,
Out[23]:
181363.59595959596,
106348.37306211119,
73679.78903948834,
44448.45544793371,
37239.835542456036,
30241.343617936585,
24995.969781135962,
22119.99312141347,
20065.21982804018]

In [12]: import matplotlib.pyplot as plt

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

plt.xlabel('Number of Clusters')
plt.ylabel('Inertia')
plt.title('Elbow Method for Optimal Number of Clusters')
plt.show()

In [13]: X = df.iloc[:,:].values
km = KMeans(n_clusters = 5)
y_means = km.fit_predict(X)

C:\anaconda\Lib\site-packages\sklearn\cluster\_kmeans.py:870: FutureWarning: The d

efault value of `n_init` will change from 10 to 'auto' in 1.4. Set the value of `n
_init` explicitly to suppress the warning
warnings.warn(
C:\anaconda\Lib\site-packages\sklearn\cluster\_kmeans.py:1382: UserWarning: KMeans
is known to have a memory leak on Windows with MKL, when there are less chunks tha
n available threads. You can avoid it by setting the environment variable OMP_NUM_
THREADS=1.
warnings.warn(

In [14]: y_means

localhost:8888/nbconvert/html/Downloads/SIC/K-Means clustering.ipynb?download=false 4/11

7/1/24, 1:25 PM K-Means clustering
array([1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4,
Out[14]:
1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 0,
1, 4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 2, 3, 0, 3, 2, 3, 2, 3,
0, 3, 2, 3, 2, 3, 2, 3, 2, 3, 0, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3,
2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3,
2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3,
2, 3])

In [15]: selected_rows = X[y_means == 0]

selected_rows

localhost:8888/nbconvert/html/Downloads/SIC/K-Means clustering.ipynb?download=false 5/11

7/1/24, 1:25 PM K-Means clustering
array([[39, 61],
Out[15]:
[40, 55],
[40, 47],
[40, 42],
[40, 42],
[42, 52],
[42, 60],
[43, 54],
[43, 60],
[43, 45],
[43, 41],
[44, 50],
[44, 46],
[46, 51],
[46, 46],
[46, 56],
[46, 55],
[47, 52],
[47, 59],
[48, 51],
[48, 59],
[48, 50],
[48, 48],
[48, 59],
[48, 47],
[49, 55],
[49, 42],
[50, 49],
[50, 56],
[54, 47],
[54, 54],
[54, 53],
[54, 48],
[54, 52],
[54, 42],
[54, 51],
[54, 55],
[54, 41],
[54, 44],
[54, 57],
[54, 46],
[57, 58],
[57, 55],
[58, 60],
[58, 46],
[59, 55],
[59, 41],
[60, 49],
[60, 40],
[60, 42],
[60, 52],
[60, 47],
[60, 50],
[61, 42],
[61, 49],
[62, 41],
[62, 48],
[62, 59],
[62, 55],
[62, 56],
[62, 42],
[63, 50],
[63, 46],
[63, 43],

localhost:8888/nbconvert/html/Downloads/SIC/K-Means clustering.ipynb?download=false 6/11

7/1/24, 1:25 PM K-Means clustering
[63, 48],
[63, 52],
[63, 54],
[64, 42],
[64, 46],
[65, 48],
[65, 50],
[65, 43],
[65, 59],
[67, 43],
[67, 57],
[67, 56],
[67, 40],
[69, 58],
[71, 35],
[72, 34],
[76, 40]], dtype=int64)

In [16]: selected_rows = X[y_means == 1]

selected_rows

array([[15, 39],
Out[16]:
[16, 6],
[17, 40],
[18, 6],
[19, 3],
[19, 14],
[20, 15],
[20, 13],
[21, 35],
[23, 29],
[24, 35],
[25, 5],
[28, 14],
[28, 32],
[29, 31],
[30, 4],
[33, 4],
[33, 14],
[34, 17],
[37, 26],
[38, 35],
[39, 36],
[39, 28]], dtype=int64)

In [17]: selected_rows = X[y_means == 2]

selected_rows

localhost:8888/nbconvert/html/Downloads/SIC/K-Means clustering.ipynb?download=false 7/11

7/1/24, 1:25 PM K-Means clustering
array([[ 70, 29],
Out[17]:
[ 71, 11],
[ 71, 9],
[ 73, 5],
[ 73, 7],
[ 74, 10],
[ 75, 5],
[ 77, 12],
[ 77, 36],
[ 78, 22],
[ 78, 17],
[ 78, 20],
[ 78, 16],
[ 78, 1],
[ 78, 1],
[ 79, 35],
[ 81, 5],
[ 85, 26],
[ 86, 20],
[ 87, 27],
[ 87, 13],
[ 87, 10],
[ 88, 13],
[ 88, 15],
[ 93, 14],
[ 97, 32],
[ 98, 15],
[ 99, 39],
[101, 24],
[103, 17],
[103, 23],
[113, 8],
[120, 16],
[126, 28],
[137, 18]], dtype=int64)

In [18]: selected_rows = X[y_means == 3]

selected_rows

localhost:8888/nbconvert/html/Downloads/SIC/K-Means clustering.ipynb?download=false 8/11

7/1/24, 1:25 PM K-Means clustering
array([[ 69, 91],
Out[18]:
[ 70, 77],
[ 71, 95],
[ 71, 75],
[ 71, 75],
[ 72, 71],
[ 73, 88],
[ 73, 73],
[ 74, 72],
[ 75, 93],
[ 76, 87],
[ 77, 97],
[ 77, 74],
[ 78, 90],
[ 78, 88],
[ 78, 76],
[ 78, 89],
[ 78, 78],
[ 78, 73],
[ 79, 83],
[ 81, 93],
[ 85, 75],
[ 86, 95],
[ 87, 63],
[ 87, 75],
[ 87, 92],
[ 88, 86],
[ 88, 69],
[ 93, 90],
[ 97, 86],
[ 98, 88],
[ 99, 97],
[101, 68],
[103, 85],
[103, 69],
[113, 91],
[120, 79],
[126, 74],
[137, 83]], dtype=int64)

In [19]: selected_rows = X[y_means == 4]

selected_rows

localhost:8888/nbconvert/html/Downloads/SIC/K-Means clustering.ipynb?download=false 9/11

7/1/24, 1:25 PM K-Means clustering
array([[15, 81],
Out[19]:
[16, 77],
[17, 76],
[18, 94],
[19, 72],
[19, 99],
[20, 77],
[20, 79],
[21, 66],
[23, 98],
[24, 73],
[25, 73],
[28, 82],
[28, 61],
[29, 87],
[30, 73],
[33, 92],
[33, 81],
[34, 73],
[37, 75],
[38, 92],
[39, 65]], dtype=int64)

In [20]: selected_rows = X[y_means == 0,1]

selected_rows

array([61, 55, 47, 42, 42, 52, 60, 54, 60, 45, 41, 50, 46, 51, 46, 56, 55,
Out[20]:
52, 59, 51, 59, 50, 48, 59, 47, 55, 42, 49, 56, 47, 54, 53, 48, 52,
42, 51, 55, 41, 44, 57, 46, 58, 55, 60, 46, 55, 41, 49, 40, 42, 52,
47, 50, 42, 49, 41, 48, 59, 55, 56, 42, 50, 46, 43, 48, 52, 54, 42,
46, 48, 50, 43, 59, 43, 57, 56, 40, 58, 35, 34, 40], dtype=int64)

In [21]: plt.scatter(X[y_means == 0, 0], X[y_means == 0, 1], color='blue', label='Cluster 0'

plt.scatter(X[y_means == 1, 0], X[y_means == 1, 1], color='yellow', label='Cluster
plt.scatter(X[y_means == 2, 0], X[y_means == 2, 1], color='red', label='Cluster 2')
plt.scatter(X[y_means == 3, 0], X[y_means == 3, 1], color='green', label='Cluster 3
plt.scatter(X[y_means == 4, 0], X[y_means == 4, 1], color='orange', label='Cluster

plt.xlabel('Feature 1')
plt.ylabel('Feature 2')
plt.title('Clusters of data points')
plt.legend()
plt.show()

localhost:8888/nbconvert/html/Downloads/SIC/K-Means clustering.ipynb?download=false 10/11

7/1/24, 1:25 PM K-Means clustering

localhost:8888/nbconvert/html/Downloads/SIC/K-Means clustering.ipynb?download=false 11/11