import boto3
import pandas as pd
from datetime import datetime, timedelta
from typing import Dict, List, Any
import json

class CloudCostAnalyzer:
    def __init__(self, cloud_provider: str):
        self.provider = cloud_provider
        self.client = self._initialize_client()
        self.cost_data = None
        
    def analyze_costs(self, time_period: int = 30):
        """Comprehensive cost analysis"""
        analysis = {
            'total_cost': self._get_total_cost(time_period),
            'cost_by_service': self._analyze_by_service(time_period),
            'cost_by_resource': self._analyze_by_resource(time_period),
            'cost_trends': self._analyze_trends(time_period),
            'anomalies': self._detect_anomalies(time_period),
            'waste_analysis': self._identify_waste(),
            'optimization_opportunities': self._find_opportunities()
        }
        
        return self._generate_report(analysis)
    
    def _analyze_by_service(self, days: int):
        """Analyze costs by service"""
        if self.provider == 'aws':
            ce = boto3.client('ce')
            
            response = ce.get_cost_and_usage(
                TimePeriod={
                    'Start': (datetime.now() - timedelta(days=days)).strftime('%Y-%m-%d'),
                    'End': datetime.now().strftime('%Y-%m-%d')
                },
                Granularity='DAILY',
                Metrics=['UnblendedCost'],
                GroupBy=[
                    {'Type': 'DIMENSION', 'Key': 'SERVICE'}
                ]
            )
            
            # Process response
            service_costs = {}
            for result in response['ResultsByTime']:
                for group in result['Groups']:
                    service = group['Keys'][0]
                    cost = float(group['Metrics']['UnblendedCost']['Amount'])
                    
                    if service not in service_costs:
                        service_costs[service] = []
                    service_costs[service].append(cost)
            
            # Calculate totals and trends
            analysis = {}
            for service, costs in service_costs.items():
                analysis[service] = {
                    'total': sum(costs),
                    'average_daily': sum(costs) / len(costs),
                    'trend': self._calculate_trend(costs),
                    'percentage': (sum(costs) / self._get_total_cost(days)) * 100
                }
            
            return analysis
    
    def _identify_waste(self):
        """Identify wasted resources"""
        waste_analysis = {
            'unused_resources': self._find_unused_resources(),
            'oversized_resources': self._find_oversized_resources(),
            'unattached_storage': self._find_unattached_storage(),
            'idle_load_balancers': self._find_idle_load_balancers(),
            'old_snapshots': self._find_old_snapshots(),
            'untagged_resources': self._find_untagged_resources()
        }
        
        total_waste = sum(item['estimated_savings'] 
                         for category in waste_analysis.values() 
                         for item in category)
        
        waste_analysis['total_potential_savings'] = total_waste
        
        return waste_analysis
    
    def _find_unused_resources(self):
        """Find resources with no usage"""
        unused = []
        
        if self.provider == 'aws':
            # Check EC2 instances
            ec2 = boto3.client('ec2')
            cloudwatch = boto3.client('cloudwatch')
            
            instances = ec2.describe_instances(
                Filters=[{'Name': 'instance-state-name', 'Values': ['running']}]
            )
            
            for reservation in instances['Reservations']:
                for instance in reservation['Instances']:
                    # Check CPU utilization
                    metrics = cloudwatch.get_metric_statistics(
                        Namespace='AWS/EC2',
                        MetricName='CPUUtilization',
                        Dimensions=[
                            {'Name': 'InstanceId', 'Value': instance['InstanceId']}
                        ],
                        StartTime=datetime.now() - timedelta