Quickstart

git clone https://github.com/CFARS/TACT.git
cd TACT

pip install -r requirements.txt

timestamp,ref_ws,ref_ti,rsd_ws,rsd_ti
2024-01-01 00:00:00,5.2,0.12,5.1,0.15
2024-01-01 00:10:00,6.1,0.14,6.0,0.16
...

{
    "input_data_column_mapping": {
        "reference": {
            "wind_speed": "ref_ws",
            "turbulence_intensity": "ref_ti",
            "standard_deviation": "ref_sd"
        },
        "rsd": {
            "primary": {
                "wind_speed": "rsd_ws",
                "turbulence_intensity": "rsd_ti",
                "standard_deviation": "rsd_sd"
            }
        }
    }
}

from tact import TACT
from tact.utils.load_data import load_data
from tact.utils.setup_processors import setup_processors
from tact.utils.process_statistics import process_statistics
from tact.utils.save_results import save_results
from tact.validation import validate_dnv_rp0661
from tact.visualization import plot_dnv_validation

def main():
    # Configuration
    config = {
        "data_path": "data.csv",              # Your input data file
        "config_path": "config.json",         # Your column mapping file
        "output_dir": "output",              # Where to save results
        "method": "ss-sf",                   # Using SS-SF method
        "parameters": {"split": True}         # Split data into training/testing sets
    }

    # Initialize TACT
    tact = TACT()

    # Load and process data
    data = load_data(config["data_path"])

    # Setup data processors
    binning_processor, ti_data_processor, stats_processor = setup_processors(config["config_path"])

    # Process data through pipeline
    data = binning_processor.process(data)    # Bin wind speed data
    data = ti_data_processor.process(data)    # Calculate TI metrics

    # Perform SS-SF adjustment
    results = tact.adjust(
        data=data,
        method=config["method"],
        parameters={**config["parameters"], "config_path": config["config_path"]}
    )

    # Validate against DNV RP-0661
    validation = validate_dnv_rp0661(
        adjusted_data=results["adjusted_data"],
        reference_col="ref_ti",
        adjusted_col="adjTI_RSD_TI",
        wind_speed_col="ref_ws",
        bin_col="bins",
        criteria_type="LV"
    )

    # Print validation results
    print(f"MRBE: {validation['overall']['MRBE_%'].iloc[0]:.2f}%")
    print(f"RRMSE: {validation['overall']['RRMSE_%'].iloc[0]:.2f}%")
    print(f"Passed: {validation['overall']['pass'].iloc[0]}")

    # Generate validation plots
    plot_dnv_validation(
        validation_results=validation,
        adjusted_data=results["adjusted_data"],
        reference_col="ref_ti",
        adjusted_col="adjTI_RSD_TI",
        unadjusted_col="rsd_ti",
        wind_speed_col="ref_ws",
        bin_col="bins",
        method_name="SS-SF",
        output_dir=f"{config['output_dir']}/plots"
    )

    # Calculate statistics
    means = process_statistics(results["adjusted_data"], stats_processor)

    # Save all results
    save_results(
        means=means,
        adjusted_data=results["adjusted_data"],
        reg_results=results["reg_results"],
        method=config["method"],
        output_dir=config["output_dir"]
    )

    print(f"\nResults saved to {config['output_dir']}/")

if __name__ == "__main__":
    main()

output/
├── ss-sf_adjusted_data.csv       # Full dataset with adjusted values
├── ss-sf_reg_results.csv         # Regression model statistics
├── ss-sf_all_stats.csv           # Summary statistics
└── plots/
    ├── ss-sf_mrbe_by_bin.png    # MRBE per wind speed bin
    ├── ss-sf_rrmse_by_bin.png   # RRMSE per wind speed bin
    ├── ss-sf_ti_scatter.png      # Adjusted vs reference scatter plot
    └── ss-sf_ti_comparison.png   # Before/after comparison by bin