File size: 16,300 Bytes
c2a61b6 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 | """
Data Preprocessing Module
Handles normalization, missing value interpolation, outlier detection,
and data validation for climate data. All preprocessing is designed
to be deterministic and reproducible.
Design Decisions:
- Statistics computed once on training data, applied to all splits
- Missing values handled by spatial/temporal interpolation
- Outliers are flagged, not removed (climate extremes are real)
- All transformations are invertible for output interpretation
Why Z-Score Normalization?
- Neural networks train better with zero-mean, unit-variance inputs
- Gradient flow is more stable across layers
- Prevents any single variable from dominating
Time Complexity: O(n) for n data points
Space Complexity: O(n) for data + O(1) for statistics
"""
import numpy as np
from pathlib import Path
from typing import Any, Dict, Optional, Tuple
from scipy.ndimage import binary_dilation
from scipy.interpolate import griddata
import warnings
class Preprocessor:
"""
Climate data preprocessor with normalization and quality assurance.
Designed to be fitted once on training data and applied to all splits.
Statistics are persistable for inference on new data.
Attributes:
config: Configuration dictionary
statistics: Dict of per-variable normalization statistics
is_fitted: Whether the preprocessor has been fitted
"""
def __init__(self, config: Dict[str, Any]):
"""
Initialize the preprocessor.
Args:
config: Configuration dictionary with preprocessing settings
"""
self.config = config
# Extract settings
preproc_config = config.get("preprocessing", {})
self.normalize = preproc_config.get("normalize", True)
self.normalize_method = preproc_config.get("normalize_method", "zscore")
self.handle_missing = preproc_config.get("handle_missing", "interpolate")
self.outlier_method = preproc_config.get("outlier_method", "zscore")
self.outlier_threshold = preproc_config.get("outlier_threshold", 3.0)
self.clip_outliers = preproc_config.get("clip_outliers", False)
# Per-variable statistics (computed during fit)
self.statistics: Dict[str, Dict[str, float]] = {}
self.is_fitted = False
# Variables that require log-transformation (skewed distributions)
self.log_vars = {"tp", "precip", "total_precipitation", "precipitation"}
def _is_log_var(self, variable: str) -> bool:
"""Check if variable requires log transformation."""
return variable.lower() in self.log_vars
def fit(self, data: np.ndarray, variable: str) -> 'Preprocessor':
"""
Compute normalization statistics from training data.
Only call this on training data to avoid data leakage.
Args:
data: Array of shape (time, lat, lon)
variable: Variable name for statistics storage
Returns:
self for method chaining
"""
# Handle missing values first
clean_data = self._handle_missing_values(data)
# Apply log transform if needed
if self._is_log_var(variable):
# log1p(x) = log(x + 1) handles zeros gracefully
# ensure non-negative
clean_data = np.log1p(np.maximum(clean_data, 0))
# Compute statistics (ignoring NaN if any remain)
if self.normalize_method == "zscore":
mean = float(np.nanmean(clean_data))
std = float(np.nanstd(clean_data))
# Prevent division by zero
if std < 1e-8:
std = 1.0
warnings.warn(f"Variable {variable} has near-zero std, using 1.0")
self.statistics[variable] = {
"mean": mean,
"std": std,
"min": float(np.nanmin(clean_data)),
"max": float(np.nanmax(clean_data)),
}
elif self.normalize_method == "minmax":
min_val = float(np.nanmin(clean_data))
max_val = float(np.nanmax(clean_data))
# Prevent division by zero
if max_val - min_val < 1e-8:
max_val = min_val + 1.0
warnings.warn(f"Variable {variable} has near-zero range")
self.statistics[variable] = {
"min": min_val,
"max": max_val,
"mean": float(np.nanmean(clean_data)),
"std": float(np.nanstd(clean_data)),
}
self.is_fitted = True
return self
def transform(
self,
data: np.ndarray,
variable: str
) -> Tuple[np.ndarray, np.ndarray]:
"""
Apply preprocessing transformations.
Steps:
1. Handle missing values
2. Detect outliers
3. Apply normalization
Args:
data: Array of shape (time, lat, lon)
variable: Variable name for looking up statistics
Returns:
Tuple of (transformed_data, outlier_mask)
"""
if not self.is_fitted:
raise RuntimeError("Preprocessor must be fitted before transform")
if variable not in self.statistics:
raise KeyError(f"No statistics for variable '{variable}'. Fit first.")
# Step 1: Handle missing values
processed = self._handle_missing_values(data.copy())
# Apply log transform if needed (before outlier/norm)
if self._is_log_var(variable):
processed = np.log1p(np.maximum(processed, 0))
# Step 2: Detect outliers
outlier_mask = self._detect_outliers(processed, variable)
# Optionally clip outliers
if self.clip_outliers:
processed = self._clip_outliers(processed, variable)
# Step 3: Normalize
if self.normalize:
processed = self._normalize(processed, variable)
return processed.astype(np.float32), outlier_mask
def fit_transform(
self,
data: np.ndarray,
variable: str
) -> Tuple[np.ndarray, np.ndarray]:
"""
Fit and transform in one step (for training data).
Args:
data: Array of shape (time, lat, lon)
variable: Variable name
Returns:
Tuple of (transformed_data, outlier_mask)
"""
self.fit(data, variable)
return self.transform(data, variable)
def inverse_transform(self, data: np.ndarray, variable: str) -> np.ndarray:
"""
Reverse the normalization transformation.
Used to convert model outputs back to physical units.
Args:
data: Normalized data array
variable: Variable name
Returns:
Data in original physical units
"""
if not self.is_fitted:
raise RuntimeError("Preprocessor must be fitted first")
stats = self.statistics[variable]
# 1. Denormalize
if self.normalize_method == "zscore":
denorm = data * stats["std"] + stats["mean"]
elif self.normalize_method == "minmax":
denorm = data * (stats["max"] - stats["min"]) + stats["min"]
else:
denorm = data
# 2. Inverse log (expm1) if needed
if self._is_log_var(variable):
denorm = np.expm1(denorm)
# Clip negative values that might result from numerical noise
denorm = np.maximum(denorm, 0)
return denorm
def _handle_missing_values(self, data: np.ndarray) -> np.ndarray:
"""
Handle missing values in climate data.
Strategies:
- interpolate: Spatial/temporal interpolation
- mask: Keep NaN and let training handle it
- drop: Not recommended, raises warning
Args:
data: Input array (may contain NaN)
Returns:
Array with missing values handled
"""
# Identify missing values
missing_mask = np.isnan(data) | np.isinf(data)
if not missing_mask.any():
return data
n_missing = missing_mask.sum()
total = data.size
missing_pct = 100 * n_missing / total
if missing_pct > 10:
warnings.warn(
f"High missing data percentage: {missing_pct:.1f}%. "
"Consider data quality review."
)
if self.handle_missing == "mask":
# Keep NaN - training will use masked loss
return data
elif self.handle_missing == "drop":
warnings.warn("'drop' strategy removes data. Use 'interpolate' instead.")
return data
elif self.handle_missing == "interpolate":
return self._interpolate_missing(data, missing_mask)
return data
def _interpolate_missing(
self,
data: np.ndarray,
missing_mask: np.ndarray
) -> np.ndarray:
"""
Interpolate missing values using spatial then temporal interpolation.
Strategy:
1. Try spatial interpolation within each timestep
2. Fall back to temporal interpolation for remaining gaps
3. Use mean for any remaining values
Args:
data: Data array with missing values
missing_mask: Boolean mask of missing locations
Returns:
Interpolated data array
"""
result = data.copy()
# Process each timestep
for t in range(data.shape[0]):
frame = result[t]
mask = missing_mask[t]
if not mask.any():
continue
# Get coordinates of valid and missing points
valid_points = np.argwhere(~mask)
missing_points = np.argwhere(mask)
if len(valid_points) < 4:
# Not enough valid points for interpolation
# Use previous/next timestep if available
if t > 0:
result[t][mask] = result[t-1][mask]
elif t < data.shape[0] - 1:
result[t][mask] = data[t+1][mask]
continue
# Spatial interpolation
valid_values = frame[~mask]
try:
interpolated = griddata(
valid_points,
valid_values,
missing_points,
method='linear',
fill_value=np.nanmean(valid_values)
)
# Fill in interpolated values
for i, point in enumerate(missing_points):
result[t, point[0], point[1]] = interpolated[i]
except Exception:
# Fall back to mean fill
result[t][mask] = np.nanmean(frame)
# Any remaining NaN gets filled with global mean
remaining_nan = np.isnan(result)
if remaining_nan.any():
result[remaining_nan] = np.nanmean(result)
return result
def _detect_outliers(
self,
data: np.ndarray,
variable: str
) -> np.ndarray:
"""
Detect outliers using configured method.
Note: Outliers are flagged but not removed by default.
Climate extremes (heat waves, heavy rain) are real events.
Args:
data: Data array
variable: Variable name
Returns:
Boolean mask where True indicates outlier
"""
if self.outlier_method == "none":
return np.zeros_like(data, dtype=bool)
stats = self.statistics[variable]
if self.outlier_method == "zscore":
z_scores = np.abs((data - stats["mean"]) / stats["std"])
return z_scores > self.outlier_threshold
elif self.outlier_method == "iqr":
# Compute quartiles from stored statistics
# This is an approximation using normal distribution assumption
q1 = stats["mean"] - 0.675 * stats["std"]
q3 = stats["mean"] + 0.675 * stats["std"]
iqr = q3 - q1
lower = q1 - self.outlier_threshold * iqr
upper = q3 + self.outlier_threshold * iqr
return (data < lower) | (data > upper)
return np.zeros_like(data, dtype=bool)
def _clip_outliers(self, data: np.ndarray, variable: str) -> np.ndarray:
"""
Clip outliers to threshold boundaries.
Args:
data: Data array
variable: Variable name
Returns:
Clipped data array
"""
stats = self.statistics[variable]
if self.outlier_method == "zscore":
lower = stats["mean"] - self.outlier_threshold * stats["std"]
upper = stats["mean"] + self.outlier_threshold * stats["std"]
else:
lower = stats["min"]
upper = stats["max"]
return np.clip(data, lower, upper)
def _normalize(self, data: np.ndarray, variable: str) -> np.ndarray:
"""
Apply normalization transformation.
Args:
data: Data array
variable: Variable name
Returns:
Normalized data array
"""
stats = self.statistics[variable]
if self.normalize_method == "zscore":
return (data - stats["mean"]) / stats["std"]
elif self.normalize_method == "minmax":
return (data - stats["min"]) / (stats["max"] - stats["min"])
return data
def save_statistics(self, path: str) -> None:
"""
Save fitted statistics to disk for later use.
Args:
path: Path to save statistics (JSON-like format via NumPy)
"""
save_path = Path(path)
save_path.parent.mkdir(parents=True, exist_ok=True)
np.savez(
save_path,
statistics=np.array([self.statistics], dtype=object),
normalize_method=self.normalize_method,
outlier_method=self.outlier_method,
outlier_threshold=self.outlier_threshold,
)
def load_statistics(self, path: str) -> None:
"""
Load previously saved statistics.
Args:
path: Path to statistics file
"""
loaded = np.load(path, allow_pickle=True)
self.statistics = loaded["statistics"].item()
self.normalize_method = str(loaded["normalize_method"])
self.outlier_method = str(loaded["outlier_method"])
self.outlier_threshold = float(loaded["outlier_threshold"])
self.is_fitted = True
def get_report(self) -> Dict[str, Any]:
"""
Generate a preprocessing report.
Returns:
Dictionary with preprocessing summary
"""
return {
"normalize_method": self.normalize_method,
"outlier_method": self.outlier_method,
"outlier_threshold": self.outlier_threshold,
"handle_missing": self.handle_missing,
"variables": list(self.statistics.keys()),
"statistics": self.statistics,
"is_fitted": self.is_fitted,
}
|