import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
data=pd.read_csv("Mall_Customers.csv")
data.head()
CustomerID Genre Age Annual Income (k$) Spending Score (1-100)
0 1 Male 19 15 39
1 2 Male 21 15 81
2 3 Female 20 16 6
3 4 Female 23 16 77
4 5 Female 31 17 40
data.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 200 entries, 0 to 199
Data columns (total 5 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 CustomerID 200 non-null int64
1 Genre 200 non-null object
2 Age 200 non-null int64
3 Annual Income (k$) 200 non-null int64
4 Spending Score (1-100) 200 non-null int64
dtypes: int64(4), object(1)
memory usage: 7.9+ KB
data.isnull().sum()
CustomerID 0
Genre 0
Age 0
Annual Income (k$) 0
Spending Score (1-100) 0
dtype: int64
#Count total number of classes in Data
class_counts = data.groupby('Genre').size()
print(class_counts)
Genre
Female 112
Male 88
dtype: int64
data.hist()
plt.show()
data.describe
<bound method NDFrame.describe of CustomerID Genre Age Annual
Income (k$) Spending Score (1-100)
0 1 Male 19 15
39
1 2 Male 21 15
81
2 3 Female 20 16
6
3 4 Female 23 16
77
4 5 Female 31 17
40
.. ... ... ... ... .
..
195 196 Female 35 120
79
196 197 Female 45 126
28
197 198 Male 32 126
74
198 199 Male 32 137
18
199 200 Male 30 137
83
[200 rows x 5 columns]>
# Extracting features of dataset
X = data.iloc[:,[3,4]].values
array([[ 15, 39],
[ 15, 81],
[ 16, 6],
[ 16, 77],
[ 17, 40],
[ 17, 76],
[ 18, 6],
[ 18, 94],
[ 19, 3],
[ 19, 72],
[ 19, 14],
[ 19, 99],
[ 20, 15],
[ 20, 77],
[ 20, 13],
[ 20, 79],
[ 21, 35],
[ 21, 66],
[ 23, 29],
[ 23, 98],
[ 24, 35],
[ 24, 73],
[ 25, 5],
[ 25, 73],
[ 28, 14],
[ 28, 82],
[ 28, 32],
[ 28, 61],
[ 29, 31],
[ 29, 87],
[ 30, 4],
[ 30, 73],
[ 33, 4],
[ 33, 92],
[ 33, 14],
[ 33, 81],
[ 34, 17],
[ 34, 73],
[ 37, 26],
[ 37, 75],
[ 38, 35],
[ 38, 92],
[ 39, 36],
[ 39, 61],
[ 39, 28],
[ 39, 65],
[ 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],
[ 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],
[ 69, 91],
[ 70, 29],
[ 70, 77],
[ 71, 35],
[ 71, 95],
[ 71, 11],
[ 71, 75],
[ 71, 9],
[ 71, 75],
[ 72, 34],
[ 72, 71],
[ 73, 5],
[ 73, 88],
[ 73, 7],
[ 73, 73],
[ 74, 10],
[ 74, 72],
[ 75, 5],
[ 75, 93],
[ 76, 40],
[ 76, 87],
[ 77, 12],
[ 77, 97],
[ 77, 36],
[ 77, 74],
[ 78, 22],
[ 78, 90],
[ 78, 17],
[ 78, 88],
[ 78, 20],
[ 78, 76],
[ 78, 16],
[ 78, 89],
[ 78, 1],
[ 78, 78],
[ 78, 1],
[ 78, 73],
[ 79, 35],
[ 79, 83],
[ 81, 5],
[ 81, 93],
[ 85, 26],
[ 85, 75],
[ 86, 20],
[ 86, 95],
[ 87, 27],
[ 87, 63],
[ 87, 13],
[ 87, 75],
[ 87, 10],
[ 87, 92],
[ 88, 13],
[ 88, 86],
[ 88, 15],
[ 88, 69],
[ 93, 14],
[ 93, 90],
[ 97, 32],
[ 97, 86],
[ 98, 15],
[ 98, 88],
[ 99, 39],
[ 99, 97],
[101, 24],
[101, 68],
[103, 17],
[103, 85],
[103, 23],
[103, 69],
[113, 8],
[113, 91],
[120, 16],
[120, 79],
[126, 28],
[126, 74],
[137, 18],
[137, 83]], dtype=int64)
# Using the elbow method to find the optimal number of clusters
from sklearn.cluster import KMeans
wcss = []
for i in range(1, 11):
kmeans = KMeans(n_clusters = i, init = 'k-means++', random_state =
42)
kmeans.fit(X)
wcss.append(kmeans.inertia_)
C:\Users\Shyam Singh\anaconda3\lib\site-packages\sklearn\cluster\
_kmeans.py:870: FutureWarning: The default 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:\Users\Shyam Singh\anaconda3\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 than available threads.
You can avoid it by setting the environment variable
OMP_NUM_THREADS=1.
warnings.warn(
C:\Users\Shyam Singh\anaconda3\lib\site-packages\sklearn\cluster\
_kmeans.py:870: FutureWarning: The default 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:\Users\Shyam Singh\anaconda3\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 than available threads.
You can avoid it by setting the environment variable
OMP_NUM_THREADS=1.
warnings.warn(
C:\Users\Shyam Singh\anaconda3\lib\site-packages\sklearn\cluster\
_kmeans.py:870: FutureWarning: The default 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:\Users\Shyam Singh\anaconda3\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 than available threads.
You can avoid it by setting the environment variable
OMP_NUM_THREADS=1.
warnings.warn(
C:\Users\Shyam Singh\anaconda3\lib\site-packages\sklearn\cluster\
_kmeans.py:870: FutureWarning: The default 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:\Users\Shyam Singh\anaconda3\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 than available threads.
You can avoid it by setting the environment variable
OMP_NUM_THREADS=1.
warnings.warn(
C:\Users\Shyam Singh\anaconda3\lib\site-packages\sklearn\cluster\
_kmeans.py:870: FutureWarning: The default 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:\Users\Shyam Singh\anaconda3\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 than available threads.
You can avoid it by setting the environment variable
OMP_NUM_THREADS=1.
warnings.warn(
C:\Users\Shyam Singh\anaconda3\lib\site-packages\sklearn\cluster\
_kmeans.py:870: FutureWarning: The default 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:\Users\Shyam Singh\anaconda3\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 than available threads.
You can avoid it by setting the environment variable
OMP_NUM_THREADS=1.
warnings.warn(
C:\Users\Shyam Singh\anaconda3\lib\site-packages\sklearn\cluster\
_kmeans.py:870: FutureWarning: The default 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:\Users\Shyam Singh\anaconda3\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 than available threads.
You can avoid it by setting the environment variable
OMP_NUM_THREADS=1.
warnings.warn(
C:\Users\Shyam Singh\anaconda3\lib\site-packages\sklearn\cluster\
_kmeans.py:870: FutureWarning: The default 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:\Users\Shyam Singh\anaconda3\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 than available threads.
You can avoid it by setting the environment variable
OMP_NUM_THREADS=1.
warnings.warn(
C:\Users\Shyam Singh\anaconda3\lib\site-packages\sklearn\cluster\
_kmeans.py:870: FutureWarning: The default 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:\Users\Shyam Singh\anaconda3\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 than available threads.
You can avoid it by setting the environment variable
OMP_NUM_THREADS=1.
warnings.warn(
C:\Users\Shyam Singh\anaconda3\lib\site-packages\sklearn\cluster\
_kmeans.py:870: FutureWarning: The default 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:\Users\Shyam Singh\anaconda3\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 than available threads.
You can avoid it by setting the environment variable
OMP_NUM_THREADS=1.
warnings.warn(
plt.plot(range(1, 11), wcss) # within clusterr of sum square
plt.title('The Elbow Method')
plt.xlabel('Number of clusters')
plt.ylabel('WCSS')
plt.show()
• Elbow method is a technique used to decide no of centroid(k) in k-means clustering
algorithm.
• In this method we determine the k-value continuously iterate for k=1 to n where n is
a hyperparameter
# Fitting K-Means to the dataset
from sklearn.cluster import KMeans
kmeans = KMeans(n_clusters = 5, init = 'k-means++', random_state = 42)
print(kmeans)
y_kmeans = kmeans.fit_predict(X)
KMeans(n_clusters=5, random_state=42)
C:\Users\Shyam Singh\anaconda3\lib\site-packages\sklearn\cluster\
_kmeans.py:870: FutureWarning: The default 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:\Users\Shyam Singh\anaconda3\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 than available threads.
You can avoid it by setting the environment variable
OMP_NUM_THREADS=1.
warnings.warn(
print("Within cluster sum of square when k=5", kmeans.inertia_)
Within cluster sum of square when k=5 44448.45544793371
print("center of Cluster are:\n", kmeans.cluster_centers_ )
center of Cluster are:
[[55.2962963 49.51851852]
[88.2 17.11428571]
[26.30434783 20.91304348]
[25.72727273 79.36363636]
[86.53846154 82.12820513]]
print("Number of iterations", kmeans.n_iter_)
Number of iterations 3
# Visualising the clusters
plt.scatter(X[:,0], X[:,1], s = 100, c = 'black', label = 'Data
Distribution')
plt.title('Customer Distribution before clustering')
plt.xlabel('Annual Income (k$)')
plt.ylabel('Spending Score (1-100)')
plt.legend()
plt.show()
frame = pd.DataFrame(X)
frame['cluster'] = y_kmeans
frame['cluster'].value_counts()
0 81
4 39
1 35
2 23
3 22
Name: cluster, dtype: int64
Annual_Income = 70#@param {type:"number"}
Spending_Score = 40#@param {type:"number"}
predict= kmeans.predict([[ Annual_Income,Spending_Score ]])
print(predict)
if predict==[0]:
print("Customer is careless")
elif predict==[1]:
print("Customer is standard")
elif predict==[2]:
print("Customer is Target")
elif predict==[3]:
print("Customer is careful")
else:
print("Custmor is sensible" )
[0]
Customer is careless
# Visualising the clusters
plt.scatter(X[y_kmeans == 0, 0], X[y_kmeans == 0, 1], s = 100, c =
'red', label = 'Cluster 1')
plt.scatter(X[y_kmeans == 1, 0], X[y_kmeans == 1, 1], s = 100, c =
'blue', label = 'Cluster 2')
plt.scatter(X[y_kmeans == 2, 0], X[y_kmeans == 2, 1], s = 100, c =
'green', label = 'Cluster 3')
plt.scatter(X[y_kmeans == 3, 0], X[y_kmeans == 3, 1], s = 100, c =
'cyan', label = 'Cluster 4')
plt.scatter(X[y_kmeans== 4, 0], X[y_kmeans == 4, 1], s = 100, c =
'magenta', label = 'Cluster 5')
plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:,
1], s = 300, c = 'yellow', label = 'Centroids')
plt.title('Clusters of customers')
plt.xlabel('Annual Income (k$)')
plt.ylabel('Spending Score (1-100)')
plt.legend()
plt.show()
import pickle
filename = "model7.sav"
pickle.dump(kmeans, open(filename, "wb"))
