Spaces:
Running
Running
File size: 8,113 Bytes
b953016 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 |
from typing import Dict, List, Any, Optional
import pandas as pd
import numpy as np
from pathlib import Path
import json
class EnhancedExcelProcessor:
def __init__(self):
"""Initialize the enhanced Excel processor"""
self.sheet_summaries = {}
self.relationships = {}
self.sheet_metadata = {}
def process_excel(self, file_path: Path) -> str:
"""
Process Excel file with enhanced multi-sheet handling
Args:
file_path (Path): Path to Excel file
Returns:
str: Structured text representation of Excel content
"""
# Read all sheets
excel_file = pd.ExcelFile(file_path)
sheets_data = {}
for sheet_name in excel_file.sheet_names:
df = pd.read_excel(excel_file, sheet_name=sheet_name)
sheets_data[sheet_name] = df
# Generate sheet summary
self.sheet_summaries[sheet_name] = self._generate_sheet_summary(df)
# Extract sheet metadata
self.sheet_metadata[sheet_name] = {
'columns': list(df.columns),
'rows': len(df),
'numeric_columns': df.select_dtypes(include=[np.number]).columns.tolist(),
'date_columns': df.select_dtypes(include=['datetime64']).columns.tolist(),
'categorical_columns': df.select_dtypes(include=['object']).columns.tolist()
}
# Detect relationships between sheets
self.relationships = self._detect_relationships(sheets_data)
# Generate structured text representation
return self._generate_structured_text(sheets_data)
def _generate_sheet_summary(self, df: pd.DataFrame) -> Dict:
"""Generate statistical summary for a sheet"""
summary = {
'total_rows': len(df),
'total_columns': len(df.columns),
'column_types': {},
'numeric_summaries': {},
'categorical_summaries': {},
'null_counts': df.isnull().sum().to_dict()
}
# Process numeric columns
numeric_cols = df.select_dtypes(include=[np.number]).columns
for col in numeric_cols:
summary['numeric_summaries'][col] = {
'mean': float(df[col].mean()),
'median': float(df[col].median()),
'std': float(df[col].std()),
'min': float(df[col].min()),
'max': float(df[col].max())
}
summary['column_types'][col] = 'numeric'
# Process categorical columns
categorical_cols = df.select_dtypes(include=['object']).columns
for col in categorical_cols:
value_counts = df[col].value_counts()
summary['categorical_summaries'][col] = {
'unique_values': int(len(value_counts)),
'top_values': value_counts.head(5).to_dict()
}
summary['column_types'][col] = 'categorical'
return summary
def _detect_relationships(self, sheets_data: Dict[str, pd.DataFrame]) -> Dict:
"""Detect potential relationships between sheets"""
relationships = {}
sheet_names = list(sheets_data.keys())
for i, sheet1 in enumerate(sheet_names):
for sheet2 in sheet_names[i+1:]:
common_cols = set(sheets_data[sheet1].columns) & set(sheets_data[sheet2].columns)
if common_cols:
relationships[f"{sheet1}__{sheet2}"] = {
'common_columns': list(common_cols),
'type': 'potential_join'
}
# Check for foreign key relationships
for col1 in sheets_data[sheet1].columns:
for col2 in sheets_data[sheet2].columns:
if (col1.lower().endswith('_id') or col2.lower().endswith('_id')):
unique_vals1 = set(sheets_data[sheet1][col1].dropna())
unique_vals2 = set(sheets_data[sheet2][col2].dropna())
if unique_vals1 & unique_vals2:
relationships[f"{sheet1}__{sheet2}__{col1}__{col2}"] = {
'type': 'foreign_key',
'columns': [col1, col2]
}
return relationships
def _generate_structured_text(self, sheets_data: Dict[str, pd.DataFrame]) -> str:
"""Generate structured text representation of Excel content"""
output_parts = []
# Overall summary
output_parts.append(f"Excel File Overview:")
output_parts.append(f"Total Sheets: {len(sheets_data)}")
output_parts.append("")
# Sheet details
for sheet_name, df in sheets_data.items():
output_parts.append(f"Sheet: {sheet_name}")
output_parts.append("=" * (len(sheet_name) + 7))
metadata = self.sheet_metadata[sheet_name]
summary = self.sheet_summaries[sheet_name]
# Basic info
output_parts.append(f"Rows: {metadata['rows']}")
output_parts.append(f"Columns: {', '.join(metadata['columns'])}")
output_parts.append("")
# Column summaries
if metadata['numeric_columns']:
output_parts.append("Numeric Columns Summary:")
for col in metadata['numeric_columns']:
stats = summary['numeric_summaries'][col]
output_parts.append(f" {col}:")
output_parts.append(f" Range: {stats['min']} to {stats['max']}")
output_parts.append(f" Average: {stats['mean']:.2f}")
output_parts.append("")
if metadata['categorical_columns']:
output_parts.append("Categorical Columns Summary:")
for col in metadata['categorical_columns']:
cats = summary['categorical_summaries'][col]
output_parts.append(f" {col}:")
output_parts.append(f" Unique Values: {cats['unique_values']}")
if cats['top_values']:
output_parts.append(" Top Values: " +
", ".join(f"{k} ({v})" for k, v in
list(cats['top_values'].items())[:3]))
output_parts.append("")
# Sample data
output_parts.append("Sample Data:")
output_parts.append(df.head(3).to_string())
output_parts.append("\n")
# Relationships
if self.relationships:
output_parts.append("Sheet Relationships:")
for rel_key, rel_info in self.relationships.items():
if rel_info['type'] == 'potential_join':
sheets = rel_key.split('__')
output_parts.append(f"- {sheets[0]} and {sheets[1]} share columns: " +
f"{', '.join(rel_info['common_columns'])}")
elif rel_info['type'] == 'foreign_key':
parts = rel_key.split('__')
output_parts.append(f"- Potential foreign key relationship between " +
f"{parts[0]}.{parts[2]} and {parts[1]}.{parts[3]}")
return "\n".join(output_parts)
def get_sheet_summary(self, sheet_name: str) -> Optional[Dict]:
"""Get summary for a specific sheet"""
return self.sheet_summaries.get(sheet_name)
def get_relationships(self) -> Dict:
"""Get detected relationships between sheets"""
return self.relationships
def get_metadata(self) -> Dict:
"""Get complete metadata for all sheets"""
return self.sheet_metadata |