import pandas as pd
from sklearn.preprocessing import StandardScaler
from sklearn.cluster import DBSCAN
import numpy as np


# Load data
# download from:
# https://www.pythonplaza.com/healthcare_patient_dataset.html


df = pd.read_csv("patients_data.csv")

# Features used for clustering
X = df[['Age',
        'BMI',
        'Blood_Pressure',
        'Cholesterol',
        'Hospital_Visits']]

# Scale data
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

# Train DBSCAN model
dbscan = DBSCAN(eps=1.5, min_samples=5)
df['Cluster'] = dbscan.fit_predict(X_scaled)

# Print cluster assignments
print(df[['Cluster']].value_counts())

# New patient?
new_patient = [[33, 28.0, 139, 210, 4]]

# Apply SAME scaling
new_patient_scaled = scaler.transform(new_patient)

# ------------------------------
# DBSCAN prediction logic
# ------------------------------
# DBSCAN has NO predict() method
# We assign cluster using nearest core point (common approach)

labels = df['Cluster'].values

# Remove noise points (-1)
valid_points = X_scaled[labels != -1]
valid_labels = labels[labels != -1]

# Compute distances from new patient to all points
distances = np.linalg.norm(valid_points - new_patient_scaled, axis=1)

# Find nearest point
nearest_index = np.argmin(distances)

cluster = valid_labels[nearest_index]

print("Patient belongs to Cluster:", cluster)

import pandas as pd
from sklearn.cluster import DBSCAN
from sklearn.preprocessing import StandardScaler
import numpy as np

# ----------------------------------
# Step 1: Sample Market Basket Data
# ----------------------------------
data = pd.DataFrame({
    'Customer': ['C001','C002','C003','C004','C005','C006','C007','C008'],
    'Bread': [12,10,11,1,0,2,6,5],
    'Milk': [10,8,9,2,1,1,5,6],
    'Eggs': [8,7,6,1,2,0,4,5],
    'Beer': [0,1,0,10,12,9,4,5],
    'Chips': [1,0,1,8,10,7,3,4]
})

# Load data (if using file instead)
# data = pd.read_csv("customer_shopping.csv")

print("Original Data")
print(data)

# ----------------------------------
# Step 2: Select Features
# ----------------------------------
X = data[['Bread', 'Milk', 'Eggs', 'Beer', 'Chips']]

# ----------------------------------
# Step 3: Scale Features
# ----------------------------------
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

# ----------------------------------
# Step 4: Train DBSCAN Model
# ----------------------------------
dbscan = DBSCAN(eps=1.5, min_samples=2)
data['Cluster'] = dbscan.fit_predict(X_scaled)

print("\nCluster Assignments")
print(data[['Customer', 'Cluster']])

# ----------------------------------
# Step 5: Cluster Profiles
# ----------------------------------
print("\nCluster Profiles (Mean of Original Data)")

cluster_profiles = data.groupby('Cluster')[['Bread','Milk','Eggs','Beer','Chips']].mean()

print(cluster_profiles.round(2))

# ----------------------------------
# Step 6: Test New Customer
# ----------------------------------
new_customer = pd.DataFrame({
    'Bread': [11],
    'Milk': [9],
    'Eggs': [7],
    'Beer': [1],
    'Chips': [1]
})

new_customer_scaled = scaler.transform(new_customer)

# ----------------------------------
# DBSCAN has NO predict()
# So we assign cluster by nearest neighbor
# ----------------------------------

X_scaled_arr = np.array(X_scaled)
labels = np.array(data['Cluster'])

# Remove noise points (-1)
valid_mask = labels != -1

valid_X = X_scaled_arr[valid_mask]
valid_labels = labels[valid_mask]

# Compute distances to all valid points
distances = np.linalg.norm(valid_X - new_customer_scaled, axis=1)

nearest_index = np.argmin(distances)
predicted_cluster = valid_labels[nearest_index]

print("\nNew Customer")
print(new_customer)

print(f"\nPredicted Cluster: {predicted_cluster}")

# ----------------------------------
# Step 7: Recommendation Logic
# ----------------------------------
if predicted_cluster == 0:
    print("Recommendation: Bread, Milk, Eggs promotions")
elif predicted_cluster == 1:
    print("Recommendation: Beer and Chips promotions")
else:
    print("Recommendation: Mixed basket offers")