Timon
fabbf3214d
- Updated `detect_mosaic_mode` function to check for grid-size subdirectories in addition to tile-named files. - Added comprehensive tests for DOY reset logic in `test_doy_logic.py`. - Implemented feature extraction tests in `test_feature_extraction.py`. - Created tests for growing window method in `test_growing_window_only.py`. - Developed a complete model inference test in `test_model_inference.py`. - Added a debug script for testing two-step refinement logic in `test_script22_debug.py`.
74 lines
2.5 KiB
Python
74 lines
2.5 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Quick test: Verify feature extraction works
|
|
"""
|
|
|
|
import sys
|
|
import pandas as pd
|
|
import numpy as np
|
|
from pathlib import Path
|
|
|
|
sys.path.insert(0, str(Path(__file__).parent))
|
|
|
|
from harvest_date_pred_utils import extract_features, load_model_and_config
|
|
|
|
project_name = "angata"
|
|
base_storage = Path("../laravel_app/storage/app") / project_name / "Data"
|
|
CI_DATA_FILE = base_storage / "extracted_ci" / "ci_data_for_python" / "ci_data_for_python.csv"
|
|
|
|
print("="*80)
|
|
print("DEBUG: Feature Extraction Test")
|
|
print("="*80)
|
|
|
|
# Load model config
|
|
print("\n[1] Loading model config...")
|
|
model, config, scalers = load_model_and_config(Path("."))
|
|
print(f" Config features: {config['features']}")
|
|
print(f" Number of features: {len(config['features'])}")
|
|
|
|
# Load CI data
|
|
print("\n[2] Loading CI data...")
|
|
ci_data = pd.read_csv(CI_DATA_FILE, dtype={'field': str})
|
|
ci_data['Date'] = pd.to_datetime(ci_data['Date'])
|
|
print(f" Columns: {ci_data.columns.tolist()}")
|
|
print(f" Total rows: {len(ci_data)}")
|
|
|
|
# Test on a single field
|
|
test_field = "1"
|
|
field_data = ci_data[ci_data['field'] == test_field].sort_values('Date').reset_index(drop=True)
|
|
print(f"\n[3] Testing on field {test_field}...")
|
|
print(f" Data points: {len(field_data)}")
|
|
print(f" Date range: {field_data['Date'].min().date()} to {field_data['Date'].max().date()}")
|
|
print(f" Columns in field data: {field_data.columns.tolist()}")
|
|
print(f" Sample values:")
|
|
print(field_data[['Date', 'value']].head())
|
|
|
|
# Test feature extraction on first 50 days
|
|
print(f"\n[4] Extracting features for first 50 days...")
|
|
try:
|
|
subset = field_data.iloc[:50].copy()
|
|
features = extract_features(subset, config['features'], ci_column='value')
|
|
print(f" ✓ Success!")
|
|
print(f" Feature shape: {features.shape}")
|
|
print(f" Expected shape: (50, {len(config['features'])})")
|
|
print(f" Feature values sample (first 5 days):")
|
|
for i in range(min(5, features.shape[0])):
|
|
print(f" Day {i}: {features[i]}")
|
|
except Exception as e:
|
|
print(f" ✗ Error: {e}")
|
|
import traceback
|
|
traceback.print_exc()
|
|
|
|
print("\n[5] Testing on growing windows...")
|
|
try:
|
|
for window_size in [10, 20, 30, 50]:
|
|
window_data = field_data.iloc[:window_size].copy()
|
|
features = extract_features(window_data, config['features'], ci_column='value')
|
|
print(f" Window size {window_size}: shape={features.shape}, min={features.min():.4f}, max={features.max():.4f}")
|
|
except Exception as e:
|
|
print(f" ✗ Error: {e}")
|
|
import traceback
|
|
traceback.print_exc()
|
|
|
|
print("\n✓ Feature extraction test complete")
|