cwicr-bid-analyzer

# CWICR Bid Analyzer

## Business Case

### Problem Statement
Evaluating contractor bids requires:
- Comparing against market benchmarks
- Identifying unusual pricing
- Understanding cost composition
- Documenting evaluation rationale

### Solution
Analyze contractor bids against CWICR-based benchmarks to identify anomalies, compare components, and support objective bid evaluation.

### Business Value
- **Objective evaluation** - Data-driven bid analysis
- **Risk identification** - Spot unrealistic pricing
- **Fair comparison** - Normalized bid analysis
- **Documentation** - Audit trail for decisions

## Technical Implementation

```python
import pandas as pd
import numpy as np
from typing import Dict, Any, List, Optional, Tuple
from dataclasses import dataclass, field
from datetime import datetime
from enum import Enum
from collections import defaultdict


class BidStatus(Enum):
    """Bid evaluation status."""
    COMPLIANT = "compliant"
    NON_COMPLIANT = "non_compliant"
    UNDER_REVIEW = "under_review"
    RECOMMENDED = "recommended"
    NOT_RECOMMENDED = "not_recommended"


class PriceFlag(Enum):
    """Price anomaly flags."""
    NORMAL = "normal"
    LOW = "low"              # >20% below benchmark
    HIGH = "high"            # >20% above benchmark
    VERY_LOW = "very_low"    # >40% below - potential front-loading
    VERY_HIGH = "very_high"  # >40% above - potential profiteering


@dataclass
class BidLineItem:
    """Single line item from bid."""
    item_code: str
    description: str
    quantity: float
    unit: str
    unit_rate: float
    total_price: float
    benchmark_rate: float
    benchmark_total: float
    variance_pct: float
    price_flag: PriceFlag


@dataclass
class BidAnalysis:
    """Complete bid analysis."""
    bidder_name: str
    bid_total: float
    benchmark_total: float
    variance_pct: float
    line_items: List[BidLineItem]
    flagged_items: List[BidLineItem]
    status: BidStatus
    summary: Dict[str, Any]


@dataclass
class BidComparison:
    """Comparison of multiple bids."""
    project_name: str
    benchmark_total: float
    bids: List[BidAnalysis]
    ranking: List[Tuple[str, float]]
    recommended_bidder: Optional[str]


class CWICRBidAnalyzer:
    """Analyze bids against CWICR benchmarks."""

    # Thresholds for price flags
    LOW_THRESHOLD = -0.20
    HIGH_THRESHOLD = 0.20
    VERY_LOW_THRESHOLD = -0.40
    VERY_HIGH_THRESHOLD = 0.40

    def __init__(self, cwicr_data: pd.DataFrame):
        self.benchmark_data = cwicr_data
        self._index_data()

    def _index_data(self):
        """Index benchmark data."""
        if 'work_item_code' in self.benchmark_data.columns:
            self._code_index = self.benchmark_data.set_index('work_item_code')
        else:
            self._code_index = None

    def _get_price_flag(self, variance_pct: float) -> PriceFlag:
        """Determine price flag from variance."""
        if variance_pct <= self.VERY_LOW_THRESHOLD * 100:
            return PriceFlag.VERY_LOW
        elif variance_pct <= self.LOW_THRESHOLD * 100:
            return PriceFlag.LOW
        elif variance_pct >= self.VERY_HIGH_THRESHOLD * 100:
            return PriceFlag.VERY_HIGH
        elif variance_pct >= self.HIGH_THRESHOLD * 100:
            return PriceFlag.HIGH
        else:
            return PriceFlag.NORMAL

    def get_benchmark_rate(self, work_item_code: str) -> Optional[float]:
        """Get benchmark rate for work item."""
        if self._code_index is None:
            return None

        if work_item_code in self._code_index.index:
            item = self._code_index.loc[work_item_code]
            # Total unit rate
            labor = float(item.get('labor_cost', 0) or 0)
            material = float(item.get('material_cost', 0) or 0)
            equipment = float(item.get('equipment_cost', 0) or 0)
            return labor + material + equipment

        return None

    def analyze_bid(self,
                    bid_data: pd.DataFrame,
                    bidder_name: str,
                    code_column: str = 'item_code',
                    quantity_column: str = 'quantity',
                    rate_column: str = 'unit_rate',
                    total_column: str = 'total_price') -> BidAnalysis:
        """Analyze single bid against benchmarks."""

        line_items = []

        for _, row in bid_data.iterrows():
            code = row[code_column]
            qty = float(row[quantity_column])
            bid_rate = float(row[rate_column])
            bid_total = float(row.get(total_column, bid_rate * qty))

            benchmark_rate = self.get_benchmark_rate(code)
            if benchmark_rate is None:
                benchmark_rate = bid_rate  # No comparison possible

            benchmark_total = benchmark_rate * qty
            variance_pct = ((bid_rate - benchmark_rate) / benchmark_rate * 100) if benchmark_rate > 0 else 0

            line_items.append(BidLineItem(
                item_code=code,
                description=str(row.get('description', '')),
                quantity=qty,
                unit=str(row.get('unit', '')),
                unit_rate=bid_rate,
                total_price=bid_total,
                benchmark_rate=benchmark_rate,
                benchmark_total=benchmark_total,
                variance_pct=round(variance_pct, 1),
                price_flag=self._get_price_flag(variance_pct)
            ))

        # Totals
        bid_total = sum(item.total_price for item in line_items)
        benchmark_total = sum(item.benchmark_total for item in line_items)
        total_variance = ((bid_total - benchmark_total) / benchmark_total * 100) if benchmark_total > 0 else 0

        # Flagged items
        flagged = [item for item in line_items if item.price_flag != PriceFlag.NORMAL]

        # Determine status
        if len([f for f in flagged if f.price_flag in [PriceFlag.VERY_LOW, PriceFlag.VERY_HIGH]]) > len(line_items) * 0.1:
            status = BidStatus.UNDER_REVIEW