df-merger

# DataFrame Merger for Construction Data

## Overview
Construction projects combine data from BIM, schedules, costs, and sensors. This skill merges DataFrames from disparate sources with intelligent key matching and schema reconciliation.

## Python Implementation

```python
import pandas as pd
import numpy as np
from typing import Dict, Any, List, Optional, Tuple
from dataclasses import dataclass
from enum import Enum
from difflib import SequenceMatcher


class MergeStrategy(Enum):
    """DataFrame merge strategies."""
    INNER = "inner"       # Only matching rows
    LEFT = "left"         # All left, matching right
    RIGHT = "right"       # Matching left, all right
    OUTER = "outer"       # All rows from both
    CROSS = "cross"       # Cartesian product


@dataclass
class MergeResult:
    """Result of merge operation."""
    merged_df: pd.DataFrame
    matched_rows: int
    left_only: int
    right_only: int
    merge_quality: float  # 0-1 score


class ConstructionDFMerger:
    """Merge DataFrames from construction sources."""

    # Common construction column name mappings
    COLUMN_MAPPINGS = {
        'element_id': ['elementid', 'elem_id', 'id', 'guid', 'globalid'],
        'type_name': ['typename', 'type', 'element_type', 'category'],
        'level': ['level', 'floor', 'storey', 'building_storey'],
        'material': ['material', 'mat', 'material_name'],
        'volume': ['volume', 'vol', 'volume_m3', 'qty_volume'],
        'area': ['area', 'surface_area', 'qty_area', 'area_m2'],
        'cost': ['cost', 'price', 'total_cost', 'amount'],
        'task_id': ['task_id', 'activity_id', 'wbs', 'activity'],
        'start_date': ['start', 'start_date', 'planned_start', 'begin'],
        'end_date': ['end', 'end_date', 'planned_finish', 'finish']
    }

    def __init__(self):
        self.column_cache: Dict[str, str] = {}

    def find_common_key(self, df1: pd.DataFrame,
                        df2:...