def test_mse():
"""
Test for mse
"""
# example 1
x = np.arange(10)
y = np.arange(10) + 2
mse_pred = 4.
mse_bias_pred = 2. ** 2
mse_obs, _, mse_bias, _ = met.mse(x, y)
nptest.assert_equal(mse_obs, mse_pred)
nptest.assert_equal(mse_bias, mse_bias_pred)
# example 2, with outlier
x = np.arange(10)
y = np.arange(10) + 2
y[-1] = 51.
mse_pred = 180.
mse_bias_pred = 36.
mse_obs, _, mse_bias, _ = met.mse(x, y)
nptest.assert_almost_equal(mse_obs, mse_pred, 6)
nptest.assert_almost_equal(mse_bias, mse_bias_pred, 6)
def test_mse():
"""
Test for mse
"""
# example 1
x = np.arange(10)
y = np.arange(10) + 2
mse_pred = 4.
mse_bias_pred = 2.**2
mse_obs, _, mse_bias, _ = met.mse(x, y)
nptest.assert_equal(mse_obs, mse_pred)
nptest.assert_equal(mse_bias, mse_bias_pred)
# example 2, with outlier
x = np.arange(10)
y = np.arange(10) + 2
y[-1] = 51.
mse_pred = 180.
mse_bias_pred = 36.
mse_obs, _, mse_bias, _ = met.mse(x, y)
nptest.assert_almost_equal(mse_obs, mse_pred, 6)
nptest.assert_almost_equal(mse_bias, mse_bias_pred, 6)
def calc_metrics(self, data, gpi_info):
dataset = super(BasicMetricsPlusMSE, self).calc_metrics(data, gpi_info)
if len(data) < self.min_obs:
return dataset
x, y = data['ref'].values, data[self.other_name].values
mse, mse_corr, mse_bias, mse_var = metrics.mse(x, y)
dataset['mse'][0] = mse
dataset['mse_corr'][0] = mse_corr
dataset['mse_bias'][0] = mse_bias
dataset['mse_var'][0] = mse_var
return dataset
def calc_metrics(self, data, gpi_info):
dataset = super(BasicMetricsPlusMSE, self).calc_metrics(data, gpi_info)
if len(data) < 10:
return dataset
x, y = data["ref"].values, data[self.other_name].values
mse, mse_corr, mse_bias, mse_var = metrics.mse(x, y)
dataset["mse"][0] = mse
dataset["mse_corr"][0] = mse_corr
dataset["mse_bias"][0] = mse_bias
dataset["mse_var"][0] = mse_var
return dataset
def test_rmsd_mse():
"""
Test for rmsd and mse
"""
# example 1
x = np.random.randn(1000)
y = np.random.randn(1000)
rmsd_pred = met.rmsd(x, y)
mse_pred, _, _, _ = met.mse(x, y)
nptest.assert_almost_equal(rmsd_pred ** 2, mse_pred, 6)
def test_rmsd_mse():
"""
Test for rmsd and mse
"""
# example 1
x = np.random.randn(1000)
y = np.random.randn(1000)
rmsd_pred = met.rmsd(x, y)
mse_pred, _, _, _ = met.mse(x, y)
nptest.assert_almost_equal(rmsd_pred**2, mse_pred, 6)
def test_mse(arange_testdata):
"""
Test for mse
"""
with pytest.deprecated_call():
# example 1
x, y = arange_testdata
mse_pred = 4.
mse_bias_pred = 2.**2
mse_obs, _, mse_bias, _ = met.mse(x, y)
nptest.assert_equal(mse_obs, mse_pred)
nptest.assert_equal(mse_bias, mse_bias_pred)
# example 2, with outlier
y[-1] = 51.
mse_pred = 180.
mse_bias_pred = 36.
mse_obs, _, mse_bias, _ = met.mse(x, y)
nptest.assert_almost_equal(mse_obs, mse_pred, 6)
nptest.assert_almost_equal(mse_bias, mse_bias_pred, 6)
def compare_data(ismn_data, validation_data, scaling='linreg', anomaly=None):
"""
Compare data from an ISMN station to the defined validation datasets.
Parameters
----------
ismn_data: pandas.Dataframe
Data from the ISMN used as a reference
validation_data: dict
Dictionary of pandas.DataFrames, One for each dataset to
compare against
scaling: string, optional
Scaling method to use.
anomaly: string
If set then the validation is done for anomalies.
"""
insitu_label = 'soil moisture'
if anomaly != None:
if anomaly == 'climatology':
ascat_clim = anomaly_calc.calc_climatology(
ascat_masked[ascat_label])
insitu_clim = anomaly_calc.calc_climatology(
ismn_data['soil moisture'])
ascat_anom = anomaly_calc.calc_anomaly(ascat_masked[ascat_label],
climatology=ascat_clim)
ascat_masked[ascat_label] = ascat_anom.values
insitu_anom = anomaly_calc.calc_anomaly(ISMN_data['insitu'],
climatology=insitu_clim)
ISMN_data['insitu'] = insitu_anom.values
if anomaly == 'average':
ascat_anom = anomaly_calc.calc_anomaly(ascat_masked[ascat_label])
ascat_masked[ascat_label] = ascat_anom.values
insitu_anom = anomaly_calc.calc_anomaly(ISMN_data['insitu'])
ISMN_data['insitu'] = insitu_anom.values
ascat_masked = ascat_masked.dropna()
ISMN_data = ISMN_data.dropna()
for dname in validation_data:
vdata = validation_data[dname]
vdata_label = 'cci_sm'
matched_data = temp_match.matching(ismn_data, vdata, window=1)
if scaling != 'noscale' and scaling != 'porosity':
scaled_data = scale.add_scaled(matched_data,
label_in=vdata_label,
label_scale=insitu_label,
method=scaling)
scaled_label = vdata_label + '_scaled_' + scaling
scaled_data = scaled_data[[insitu_label, scaled_label]]
elif scaling == 'noscale':
scaled_data = matched_data[[insitu_label, vdata_label]]
scaled_label = vdata_label
# scaled_data.rename(columns={'insitu': ISMN_ts_name}, inplace=True)
labels, values = scaled_data.to_dygraph_format()
ascat_insitu = {'labels': labels, 'data': values}
x, y = scaled_data[insitu_label].values, scaled_data[scaled_label].values
kendall, p_kendall = sc_stats.kendalltau(x.tolist(), y.tolist())
spearman, p_spearman = sc_stats.spearmanr(x, y)
pearson, p_pearson = sc_stats.pearsonr(x, y)
rmsd = metrics.rmsd(x, y)
bias = metrics.bias(y, x)
mse, mse_corr, mse_bias, mse_var = metrics.mse(x, y)
statistics = {
'kendall': {
'v': '%.2f' % kendall,
'p': '%.4f' % p_kendall
},
'spearman': {
'v': '%.2f' % spearman,
'p': '%.4f' % p_spearman
},
'pearson': {
'v': '%.2f' % pearson,
'p': '%.4f' % p_pearson
},
'bias': '%.4f' % bias,
'rmsd': {
'rmsd': '%.4f' % np.sqrt(mse),
'rmsd_corr': '%.4f' % np.sqrt(mse_corr),
'rmsd_bias': '%.4f' % np.sqrt(mse_bias),
'rmsd_var': '%.4f' % np.sqrt(mse_var)
},
'mse': {
'mse': '%.4f' % mse,
'mse_corr': '%.4f' % mse_corr,
'mse_bias': '%.4f' % mse_bias,
'mse_var': '%.4f' % mse_var
}
}
scaling_options = {
'noscale': 'No scaling',
'porosity': 'Scale using porosity',
'linreg': 'Linear Regression',
'mean_std': 'Mean - standard deviation',
'min_max': 'Minimum,maximum',
'lin_cdf_match': 'Piecewise <br> linear CDF matching',
'cdf_match': 'CDF matching'
}
settings = {
'scaling': scaling_options[scaling],
# 'snow_depth': mask['snow_depth'],
# 'surface_temp': mask['st_l1'],
# 'air_temp': mask['air_temp']
}
era_data = {'labels': [], 'data': []}
output_data = {
'validation_data': ascat_insitu,
'masking_data': era_data,
'statistics': statistics,
'settings': settings
}
return output_data, 1
