Example #1
0
def experiment_loop_comparative(
    base_dat: str,
    cmip_dat: str,
    variable: str,
    spatial_window: int,
    subsample: Optional[int] = None,
    trial: int = 1,
    regrid_filename: Optional[str] = None,
) -> Dict:
    """Performs one experimental loop for calculating the IT measures
    for the models"""
    # 1.1) get base model
    base_dat = get_base_model(base_dat, variable)

    # 1.2) get cmip5 model
    cmip_dat = get_cmip5_model(cmip_dat, variable)

    # 2) regrid data w. reference grid and
    reference_ds = get_reference_dataset("noresm1_m")
    base_dat = regrid_data(reference_ds,
                           base_dat,
                           filename=regrid_filename + ".nc")
    cmip_dat = regrid_data(reference_ds,
                           cmip_dat,
                           filename=regrid_filename + ".nc")

    # 3) find overlapping times
    base_dat, cmip_dat = get_time_overlap(base_dat, cmip_dat)

    # 4) get density cubes
    base_df = get_spatial_cubes(base_dat, spatial_window)
    cmip_df = get_spatial_cubes(cmip_dat, spatial_window)

    # 5) normalize data
    base_df = normalize_data(base_df)
    cmip_df = normalize_data(cmip_df)

    # 6) Resample/ Subsample data
    base_df = resample(base_df, n_samples=subsample, random_state=trial)
    cmip_df = resample(cmip_df, n_samples=subsample, random_state=trial)

    # 7.1) Mutual Information
    mutual_info, time_mi = run_rbig_models(base_df,
                                           cmip_df,
                                           measure="mi",
                                           verbose=None)

    # 7.2 - Pearson, Spearman, KendelTau
    pearson = stats.pearsonr(base_df.ravel(), cmip_df.ravel())[0]
    spearman = stats.spearmanr(base_df.ravel(), cmip_df.ravel())[0]
    kendelltau = stats.kendalltau(base_df.ravel(), cmip_df.ravel())[0]

    results = {
        "mi": mutual_info,
        "time_mi": time_mi,
        "pearson": pearson,
        "spearman": spearman,
        "kendelltau": kendelltau,
    }
    return results
Example #2
0
def experiment_loop_individual(
    base: str,
    cmip: str,
    variable: str,
    spatial_window: int,
    subsample: Optional[int] = None,
    trial: int = 1,
    batch_size: Optional[int] = None,
    regrid_filename: Optional[str] = None,
) -> Dict:
    """Performs one experimental loop for calculating the IT measures
    for the models"""
    # 1.1) get base model
    base_dat = get_base_model(base, variable)

    # 1.2) get cmip5 model
    cmip_dat = get_cmip5_model(cmip, variable)

    # 2) regrid data w. reference grid and
    reference_ds = get_reference_dataset("ipsl_cm5a_lr")
    base_dat = regrid_data(reference_ds,
                           base_dat,
                           filename=regrid_filename + ".nc")
    cmip_dat = regrid_data(reference_ds,
                           cmip_dat,
                           filename=regrid_filename + ".nc")

    # 3) find overlapping times
    base_dat, cmip_dat = get_time_overlap(base_dat, cmip_dat)

    # 4) get density cubes
    base_df = get_spatial_cubes(base_dat, spatial_window)
    cmip_df = get_spatial_cubes(cmip_dat, spatial_window)

    # 5) normalize data
    base_df = normalize_data(base_df)
    cmip_df = normalize_data(cmip_df)

    # 6) Resample/ Subsample data
    base_df = resample(base_df, n_samples=subsample, random_state=trial)
    cmip_df = resample(cmip_df, n_samples=subsample, random_state=trial)

    # 7.1 - Entropy
    tc_base, h_base, h_time_base = run_rbig_models(base_df,
                                                   measure="h",
                                                   verbose=None)
    # 7.1 - Total Correlation
    tc_cmip, h_cmip, h_time_cmip = run_rbig_models(cmip_df,
                                                   measure="h",
                                                   verbose=None)

    results = {
        "h_base": h_base,
        "tc_base": tc_base,
        "h_cmip": h_cmip,
        "tc_cmip": tc_cmip,
        "t_base": h_time_base,
        "t_cmip": h_time_cmip,
    }
    return results
Example #3
0
def get_features_loop(base: str, cmip: str, variable: str,
                      regrid_name: str) -> Dict:
    """Performs one experimental loop for calculating the IT measures
    for the models"""
    # 1.1) get base model
    # print(base)
    base_dat = get_base_model(base, variable)

    # 1.2) get cmip5 model
    cmip_dat = get_cmip5_model(cmip, variable, model="rcp")

    # 2) regrid data

    # 2) regrid data w. reference grid and
    reference_ds = get_reference_dataset("noresm1_m")
    base_dat = regrid_data(reference_ds,
                           base_dat,
                           filename=regrid_name + ".nc")
    cmip_dat = regrid_data(reference_ds,
                           cmip_dat,
                           filename=regrid_name + ".nc")

    # 3) find overlapping times
    base_dat, cmip_dat = get_time_overlap(base_dat, cmip_dat)

    return base_dat, cmip_dat
Example #4
0
def experiment_loop_comparative(
    base: str,
    cmip: str,
    variable: str,
    spatial_window: int,
    subsample: Optional[int] = None,
    batch_size: Optional[int] = None,
) -> Dict:
    """Performs one experimental loop for calculating the IT measures
    for the models"""
    # 1.1) get base model
    base_dat = get_base_model(base, variable)

    # 1.2) get cmip5 model
    cmip_dat = get_cmip5_model(cmip, variable)

    # 2) regrid data
    base_dat, cmip_dat = regrid_2_lower_res(base_dat, cmip_dat)

    # 3) find overlapping times
    base_dat, cmip_dat = get_time_overlap(base_dat, cmip_dat)

    # 4) get density cubes
    base_df = get_spatial_cubes(base_dat, spatial_window)
    cmip_df = get_spatial_cubes(cmip_dat, spatial_window)

    # 5) normalize data
    base_df = normalize_data(base_df)
    cmip_df = normalize_data(cmip_df)

    # 7.1) Mutual Information
    print("Mutual Information")
    mutual_info, time_mi = run_rbig_models(
        base_df[:subsample],
        cmip_df[:subsample],
        measure="mi",
        verbose=1,
        batch_size=batch_size,
    )

    # 7.2 - Pearson, Spearman, KendelTau
    print("Pearson")
    pearson = stats.pearsonr(base_df[:subsample].ravel(),
                             cmip_df[:subsample].ravel())[0]
    print("Spearman")
    spearman = stats.spearmanr(base_df[:subsample].ravel(),
                               cmip_df[:subsample].ravel())[0]
    print("KendelTau")
    kendelltau = stats.kendalltau(base_df[:subsample].ravel(),
                                  cmip_df[:subsample].ravel())[0]

    results = {
        "mi": mutual_info,
        "time_mi": time_mi,
        "pearson": pearson,
        "spearman": spearman,
        "kendelltau": kendelltau,
    }
    return results
Example #5
0
def experiment_loop_individual(
    base: str,
    cmip: str,
    variable: str,
    spatial_window: int,
    subsample: Optional[int] = None,
    batch_size: Optional[int] = None,
) -> Dict:
    """Performs one experimental loop for calculating the IT measures
    for the models"""
    # 1.1) get base model
    base_dat = get_base_model(base, variable)

    # 1.2) get cmip5 model
    cmip_dat = get_cmip5_model(cmip, variable)

    # 2) regrid data
    base_dat, cmip_dat = regrid_2_lower_res(base_dat, cmip_dat)

    # 3) find overlapping times
    base_dat, cmip_dat = get_time_overlap(base_dat, cmip_dat)

    # 4) get density cubes
    base_df = get_spatial_cubes(base_dat, spatial_window)
    cmip_df = get_spatial_cubes(cmip_dat, spatial_window)

    # 5) normalize data
    base_df = normalize_data(base_df)
    cmip_df = normalize_data(cmip_df)

    # 7.1) Total Correlation
    print("TOTAL CORRELATION")
    print("Base Model")
    tc_base, time_base = run_rbig_models(base_df[:subsample],
                                         measure="t",
                                         verbose=1,
                                         batch_size=batch_size)
    print("CMIP Model")
    tc_cmip, time_cmip = run_rbig_models(cmip_df[:subsample],
                                         measure="t",
                                         verbose=1,
                                         batch_size=batch_size)

    # 7.2 - ENTROPY
    print("ENTROPY")
    print("Base Model")
    h_base, time_base = run_rbig_models(base_df[:subsample],
                                        measure="h",
                                        verbose=1,
                                        batch_size=batch_size)
    print("CMIP Model")
    h_cmip, time_cmip = run_rbig_models(cmip_df[:subsample],
                                        measure="h",
                                        verbose=1,
                                        batch_size=batch_size)

    results = {
        "h_base": h_base,
        "tc_base": tc_base,
        "h_cmip": h_cmip,
        "tc_cmip": tc_cmip,
        "t_base": time_base,
        "t_cmip": time_cmip,
    }
    return results