Spaces:
Sleeping
Sleeping
File size: 9,303 Bytes
48909ac |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 |
"""
Data processing module for the Business Intelligence Dashboard.
This module handles data loading, cleaning, filtering, and profiling
using the Strategy Pattern for different data operations.
"""
from abc import ABC, abstractmethod
from typing import Dict, List, Optional, Tuple, Any
import pandas as pd
import numpy as np
from utils import detect_column_types, validate_dataframe, get_missing_value_summary
from constants import MIN_NUMERICAL_COLUMNS_FOR_CORRELATION
class DataLoadStrategy(ABC):
"""Abstract base class for data loading strategies."""
@abstractmethod
def load(self, file_path: str) -> pd.DataFrame:
"""
Load data from file.
Args:
file_path: Path to the data file
Returns:
Loaded DataFrame
"""
pass
class CSVLoadStrategy(DataLoadStrategy):
"""Strategy for loading CSV files."""
def load(self, file_path: str) -> pd.DataFrame:
"""Load CSV file."""
return pd.read_csv(file_path)
class ExcelLoadStrategy(DataLoadStrategy):
"""Strategy for loading Excel files."""
def load(self, file_path: str) -> pd.DataFrame:
"""Load Excel file."""
return pd.read_excel(file_path)
class DataLoader:
"""Context class for data loading using Strategy Pattern."""
def __init__(self):
"""Initialize with default strategies."""
self._strategies = {
'.csv': CSVLoadStrategy(),
'.xlsx': ExcelLoadStrategy(),
'.xls': ExcelLoadStrategy()
}
def load_data(self, file_path: str) -> Tuple[pd.DataFrame, Optional[str]]:
"""
Load data file using appropriate strategy.
Args:
file_path: Path to the data file
Returns:
Tuple of (DataFrame, error_message)
"""
try:
import os
_, ext = os.path.splitext(file_path.lower())
if ext not in self._strategies:
return None, f"Unsupported file format: {ext}"
strategy = self._strategies[ext]
df = strategy.load(file_path)
# Validate loaded data
is_valid, error = validate_dataframe(df)
if not is_valid:
return None, error
return df, None
except Exception as e:
return None, f"Error loading file: {str(e)}"
class FilterStrategy(ABC):
"""Abstract base class for filtering strategies."""
@abstractmethod
def apply_filter(
self,
df: pd.DataFrame,
column: str,
filter_value: Any
) -> pd.DataFrame:
"""
Apply filter to DataFrame.
Args:
df: Input DataFrame
column: Column to filter on
filter_value: Filter value/range
Returns:
Filtered DataFrame
"""
pass
class NumericalFilterStrategy(FilterStrategy):
"""Strategy for filtering numerical columns."""
def apply_filter(
self,
df: pd.DataFrame,
column: str,
filter_value: Tuple[float, float]
) -> pd.DataFrame:
"""Apply range filter to numerical column."""
min_val, max_val = filter_value
return df[(df[column] >= min_val) & (df[column] <= max_val)]
class CategoricalFilterStrategy(FilterStrategy):
"""Strategy for filtering categorical columns."""
def apply_filter(
self,
df: pd.DataFrame,
column: str,
filter_value: List[str]
) -> pd.DataFrame:
"""Apply multi-select filter to categorical column."""
if not filter_value:
return df
return df[df[column].isin(filter_value)]
class DateFilterStrategy(FilterStrategy):
"""Strategy for filtering date columns."""
def apply_filter(
self,
df: pd.DataFrame,
column: str,
filter_value: Tuple[str, str]
) -> pd.DataFrame:
"""Apply date range filter."""
start_date, end_date = filter_value
if start_date and end_date:
df[column] = pd.to_datetime(df[column], errors='coerce')
return df[(df[column] >= start_date) & (df[column] <= end_date)]
return df
class DataFilter:
"""Context class for data filtering using Strategy Pattern."""
def __init__(self):
"""Initialize with filter strategies."""
self._strategies = {
'numerical': NumericalFilterStrategy(),
'categorical': CategoricalFilterStrategy(),
'date': DateFilterStrategy()
}
def apply_filters(
self,
df: pd.DataFrame,
filters: Dict[str, Any]
) -> pd.DataFrame:
"""
Apply multiple filters to DataFrame.
Args:
df: Input DataFrame
filters: Dictionary of {column: filter_value}
Returns:
Filtered DataFrame
"""
filtered_df = df.copy()
numerical, categorical, date_columns = detect_column_types(df)
for column, filter_value in filters.items():
if filter_value is None:
continue
if column in numerical:
strategy = self._strategies['numerical']
elif column in categorical:
strategy = self._strategies['categorical']
elif column in date_columns:
strategy = self._strategies['date']
else:
continue
try:
filtered_df = strategy.apply_filter(filtered_df, column, filter_value)
except Exception as e:
print(f"Error applying filter to {column}: {e}")
continue
return filtered_df
class DataProfiler:
"""Class for generating data profiling and statistics."""
@staticmethod
def get_basic_info(df: pd.DataFrame) -> Dict[str, Any]:
"""
Get basic dataset information.
Args:
df: Input DataFrame
Returns:
Dictionary with basic info
"""
return {
'shape': df.shape,
'columns': list(df.columns),
'dtypes': df.dtypes.to_dict(),
'memory_usage': df.memory_usage(deep=True).sum()
}
@staticmethod
def get_numerical_stats(df: pd.DataFrame) -> pd.DataFrame:
"""
Get statistics for numerical columns.
Args:
df: Input DataFrame
Returns:
DataFrame with numerical statistics, with column names as a column
"""
numerical, _, _ = detect_column_types(df)
if not numerical:
return pd.DataFrame()
stats = df[numerical].describe()
stats.loc['median'] = df[numerical].median()
stats.loc['std'] = df[numerical].std()
# Transpose so column names become rows (index)
stats_transposed = stats.T
# Reset index to make column names a regular column for display
stats_transposed = stats_transposed.reset_index()
stats_transposed.rename(columns={'index': 'Column'}, inplace=True)
# Reorder columns for better readability (Column first, then statistics)
column_order = ['Column', 'count', 'mean', 'std', 'min', '25%', '50%', '75%', 'max', 'median']
# Only include columns that exist
available_columns = [col for col in column_order if col in stats_transposed.columns]
stats_transposed = stats_transposed[available_columns]
return stats_transposed
@staticmethod
def get_categorical_stats(df: pd.DataFrame) -> pd.DataFrame:
"""
Get statistics for categorical columns.
Args:
df: Input DataFrame
Returns:
DataFrame with categorical statistics
"""
_, categorical, _ = detect_column_types(df)
if not categorical:
return pd.DataFrame()
stats = []
for col in categorical:
unique_count = df[col].nunique()
mode_value = df[col].mode().iloc[0] if not df[col].mode().empty else None
mode_count = df[col].value_counts().iloc[0] if not df[col].empty else 0
stats.append({
'Column': col,
'Unique_Values': unique_count,
'Mode': mode_value,
'Mode_Count': mode_count,
'Total_Count': len(df)
})
return pd.DataFrame(stats)
@staticmethod
def get_correlation_matrix(df: pd.DataFrame) -> pd.DataFrame:
"""
Get correlation matrix for numerical columns.
Args:
df: Input DataFrame
Returns:
Correlation matrix DataFrame
"""
numerical, _, _ = detect_column_types(df)
if len(numerical) < MIN_NUMERICAL_COLUMNS_FOR_CORRELATION:
return pd.DataFrame()
return df[numerical].corr()
|