#kmeans
import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_csv('5-sales_data_sample.csv', encoding ="unicode_escape")
df

df.isnull().sum()
df=df.dropna()

df.dtypes

#select numerical column for clustering
#Assume we are clutering based on 'Sales','Quantityordered','Priceeach'

X=df[['SALES','QUANTITYORDERED','PRICEEACH']]

from sklearn.preprocessing import StandardScaler

scaler=StandardScaler()
X_scaled=scaler.fit_transform(X)

from sklearn.cluster import KMeans

# Elbow method to find optimal number of clusters

# Inertia represents how well the clusters formed by the K-Means algorithm fit the data points.
inertia = []
K = range(1, 11)

for k in K:
    kmeans = KMeans(n_clusters=k, random_state=42)
    kmeans.fit(X_scaled)
    inertia.append(kmeans.inertia_)

plt.figure(figsize=(8,6))
plt.plot(K,inertia,'bo-')
plt.xlabel('Number of cluster (k)')

plt.title('Elbow Method for optimal k')
plt.show()

optimal_k=4

kmeans=KMeans(n_clusters=optimal_k ,random_state=42)
df['Cluster']=kmeans.fit_predict(X_scaled)

df[['SALES','QUANTITYORDERED','PRICEEACH','Cluster']]