project code.py

# Load the dataset
import pandas as pd
data = pd.read_csv("Mall_Customers.csv")
# Display the first few rows of the dataset
print(data.head(10))

count=data.isnull().sum()
print(count)

mean_age=data['Age'].mean()
data["Age"].fillna(mean_age,inplace=True)
print(data.head(10))

# Renaming columns for better readability
data.columns = ["CustomerID", "Gender", "Age", "AnnualIncome", "SpendingScore"]

print(data)

mode_gender=data['Gender'].mode()[0]
type(mode_gender)
mode_gender

data.dropna(inplace=True)
data["Gender"].fillna(mode_gender,inplace=True)

print(data.head(20))

count=data.isnull().sum()
print(count)

# Data transformation (e.g., encoding categorical variables)
data['Gender'] = data['Gender'].map({'Male': 0, 'Female': 1})
print(data)

count=data.isnull().sum()
print(count)

print(data.describe())


import  matplotlib.pyplot as plt
import seaborn as sns
# Visualizing distributions
plt.figure(figsize=(10, 6))
sns.histplot(data['Age'], bins=30, kde=True)
plt.title('Age Distribution')
plt.show()

plt.figure(figsize=(10, 6))
sns.histplot(data['AnnualIncome'], bins=30, kde=True)
plt.title('Annual Income Distribution')
plt.show()

plt.figure(figsize=(10, 6))
sns.histplot(data['SpendingScore'], bins=30, kde=True)
plt.title('Spending Score Distribution')
plt.show()

# Visualizing relationships
plt.figure(figsize=(10, 6))
sns.scatterplot(data=data, x='AnnualIncome', y='SpendingScore', hue='Gender')
plt.title('Income vs Spending Score')
plt.show()

from sklearn.cluster import KMeans
from sklearn.preprocessing import StandardScaler

# Feature selection
features = data[['Age', 'AnnualIncome', 'SpendingScore']]

# Standardizing the features
scaler = StandardScaler()
scaled_features = scaler.fit_transform(features)

# Applying K-Means clustering
kmeans = KMeans(n_clusters=5, random_state=42)
data['Cluster'] = kmeans.fit_predict(scaled_features)

# Evaluating cluster quality
plt.figure(figsize=(10, 6))
sns.scatterplot(data=data, x='AnnualIncome', y='SpendingScore', hue='Cluster', palette='viridis')
plt.title('Customer Segments')
plt.show()