3liud

from sklearn.cluster import KMeans
errors = []
for i in range(1, 11):
    kmeans = KMeans(n_clusters=i)
    kmeans.fit(df1)
    errors.append(kmeans.inertia_)

3liud

# Scatter Plot
sns.scatterplot(df1['Annual Income (k$)'], df1['Spending Score (1-100)']);

3liud

df1 = df[['Annual Income (k$)', 'Spending Score (1-100)']]
df1.head()

3liud

corr = df.corr()
sns.heatmap(corr, annot=True, cmap="YlGnBu_r")

3liud

Females, Males = df['Gender'].value_counts()
print(f'There are {Females} Female customers and {Males} Male customers in the dataset')

3liud

nRows, nColumns = df.shape
print(f"There are {nRows} rows and {nColumns} columns in our dataset")

3liud

# Loading in the Data
df = pd.read_csv('Mall_Customers.csv')
df.head()

3liud

# importing libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.preprocessing import StandardScaler 

3liud

fig = plt.figure(figsize=(20,15))
ax = fig.add_subplot(111, projection='3d')

ax.scatter(df2['Age'][df2['Label']==0], df2['Annual Income (k$)'][df2['Label']==0], 
           df2['Spending Score (1-100)'][df2['Label']==0], c='green', s=50)
ax.scatter(df2['Age'][df2['Label']==1], df2['Annual Income (k$)'][df2['Label']==1], 
           df2['Spending Score (1-100)'][df2['Label']==1], c='blue', s=50)
ax.scatter(df2['Age'][df2['Label']==2], df2['Annual Income (k$)'][df2['Label']==2], 
           df2['Spending Score (1-100)'][df2['Label']==2], c='black', s=50)
ax.scatter(df2['Age'][df2['Label']==3], df2['Annual Income (k$)'][df2['Label']==3], 

3liud

df2_clusters = df2['Label'].value_counts()
df2_clusters