def test_pearson_recursive():
x = np.random.rand(100)
y = np.random.rand(100)
r, p = met.pearsonr(x, y)
r_rec, _ = met.pearsonr_recursive(x, y)
nptest.assert_almost_equal(r, r_rec)
args = []
for xi, yi in zip(x, y):
r_rec, args = met.pearsonr_recursive(np.array([xi]),
np.array([yi]), *args)
nptest.assert_almost_equal(r, r_rec)
def test_pearson_recursive():
x = np.random.rand(100)
y = np.random.rand(100)
r, p = met.pearsonr(x, y)
r_rec, _ = met.pearsonr_recursive(x, y)
nptest.assert_almost_equal(r, r_rec)
args = []
for xi, yi in zip(x, y):
r_rec, args = met.pearsonr_recursive(np.array([xi]), np.array([yi]),
*args)
nptest.assert_almost_equal(r, r_rec)
def calc_metrics(self, data, gpi_info):
"""
calculates the desired statistics
Parameters
----------
data : pandas.DataFrame
with 2 columns, the first column is the reference dataset
named 'ref'
the second column the dataset to compare against named 'other'
gpi_info : tuple
of (gpi, lon, lat)
Notes
-----
Kendall tau is calculation is optional at the moment
because the scipy implementation is very slow which is problematic for
global comparisons
"""
dataset = copy.deepcopy(self.result_template)
dataset["n_obs"][0] = len(data)
dataset["gpi"][0] = gpi_info[0]
dataset["lon"][0] = gpi_info[1]
dataset["lat"][0] = gpi_info[2]
if len(data) < 10:
return dataset
x, y = data["ref"].values, data[self.other_name].values
R, p_R = metrics.pearsonr(x, y)
rho, p_rho = metrics.spearmanr(x, y)
RMSD = metrics.rmsd(x, y)
BIAS = metrics.bias(x, y)
dataset["R"][0], dataset["p_R"][0] = R, p_R
dataset["rho"][0], dataset["p_rho"][0] = rho, p_rho
dataset["RMSD"][0] = RMSD
dataset["BIAS"][0] = BIAS
if self.calc_tau:
tau, p_tau = metrics.kendalltau(x, y)
dataset["tau"][0], dataset["p_tau"][0] = tau, p_tau
return dataset
def calc_metrics(self, data, gpi_info):
"""
calculates the desired statistics
Parameters
----------
data : pandas.DataFrame
with 2 columns, the first column is the reference dataset
named 'ref'
the second column the dataset to compare against named 'other'
gpi_info : tuple
of (gpi, lon, lat)
Notes
-----
Kendall tau is calculation is optional at the moment
because the scipy implementation is very slow which is problematic for
global comparisons
"""
dataset = copy.deepcopy(self.result_template)
dataset['n_obs'][0] = len(data)
dataset['gpi'][0] = gpi_info[0]
dataset['lon'][0] = gpi_info[1]
dataset['lat'][0] = gpi_info[2]
if len(data) < 10:
return dataset
x, y = data['ref'].values, data[self.other_name].values
R, p_R = metrics.pearsonr(x, y)
rho, p_rho = metrics.spearmanr(x, y)
RMSD = metrics.rmsd(x, y)
BIAS = metrics.bias(x, y)
dataset['R'][0], dataset['p_R'][0] = R, p_R
dataset['rho'][0], dataset['p_rho'][0] = rho, p_rho
dataset['RMSD'][0] = RMSD
dataset['BIAS'][0] = BIAS
if self.calc_tau:
tau, p_tau = metrics.kendalltau(x, y)
dataset['tau'][0], dataset['p_tau'][0] = tau, p_tau
return dataset
def calc_metrics(self, data, gpi_info):
"""
calculates the desired statistics
Parameters
----------
data : pandas.DataFrame
with 2 columns, the first column is the reference dataset
named 'ref'
the second column the dataset to compare against named 'other'
gpi_info : tuple
of (gpi, lon, lat)
Notes
-----
Kendall tau is not calculated at the moment
because the scipy implementation is very slow which is problematic for
global comparisons
"""
dataset = copy.deepcopy(self.result_template)
dataset['n_obs'][0] = len(data)
dataset['gpi'][0] = gpi_info[0]
dataset['lon'][0] = gpi_info[1]
dataset['lat'][0] = gpi_info[2]
if len(data) < 10:
return dataset
x, y = data['ref'].values, data['other'].values
R, p_R = metrics.pearsonr(x, y)
rho, p_rho = metrics.spearmanr(x, y)
# tau, p_tau = metrics.kendalltau(x, y)
RMSD = metrics.rmsd(x, y)
BIAS = metrics.bias(x, y)
dataset['R'][0], dataset['p_R'][0] = R, p_R
dataset['rho'][0], dataset['p_rho'][0] = rho, p_rho
# dataset['tau'][0], dataset['p_tau'][0] = tau, p_tau
dataset['RMSD'][0] = RMSD
dataset['BIAS'][0] = BIAS
return dataset
def calc_metrics(self, data, gpi_info):
"""
calculates the desired statistics
Parameters
----------
data : pandas.DataFrame
with 2 columns, the first column is the reference dataset
named 'ref'
the second column the dataset to compare against named 'other'
gpi_info : tuple
Grid point info (i.e. gpi, lon, lat)
"""
dataset = copy.deepcopy(self.result_template)
dataset['gpi'][0] = gpi_info[0]
dataset['lon'][0] = gpi_info[1]
dataset['lat'][0] = gpi_info[2]
for season in self.seasons:
if season != 'ALL':
subset = self.month_to_season[data.index.month] == season
else:
subset = np.ones(len(data), dtype=bool)
if subset.sum() < 10:
continue
x = data['ref'].values[subset]
y = data[self.other_name].values[subset]
R, p_R = metrics.pearsonr(x, y)
rho, p_rho = metrics.spearmanr(x, y)
dataset['{:}_n_obs'.format(season)][0] = subset.sum()
dataset['{:}_R'.format(season)][0] = R
dataset['{:}_p_R'.format(season)][0] = p_R
dataset['{:}_rho'.format(season)][0] = rho
dataset['{:}_p_rho'.format(season)][0] = p_rho
return dataset
def calc_metrics(self, data, gpi_info):
"""
calculates the desired statistics
Parameters
----------
data : pandas.DataFrame
with 2 columns, the first column is the reference dataset
named 'ref'
the second column the dataset to compare against named 'other'
gpi_info : tuple
Grid point info (i.e. gpi, lon, lat)
"""
dataset = copy.deepcopy(self.result_template)
dataset['gpi'][0] = gpi_info[0]
dataset['lon'][0] = gpi_info[1]
dataset['lat'][0] = gpi_info[2]
for season in self.seasons:
if season != 'ALL':
subset = self.month_to_season[data.index.month] == season
else:
subset = np.ones(len(data), dtype=bool)
if subset.sum() < 10:
continue
x = data['ref'].values[subset]
y = data[self.other_name].values[subset]
R, p_R = metrics.pearsonr(x, y)
rho, p_rho = metrics.spearmanr(x, y)
dataset['{:}_n_obs'.format(season)][0] = subset.sum()
dataset['{:}_R'.format(season)][0] = R
dataset['{:}_p_R'.format(season)][0] = p_R
dataset['{:}_rho'.format(season)][0] = rho
dataset['{:}_p_rho'.format(season)][0] = p_rho
return dataset
scaled_data.plot(secondary_y=[label_ascat])
plt.show()
plt.scatter(matched_data[scaled_ascat_label].values,matched_data[label_insitu].values)
plt.xlabel(scaled_ascat_label)
plt.ylabel(label_insitu)
plt.show()
#calculate correlation coefficients, RMSD, bias, Nash Sutcliffe
x, y = matched_data[scaled_ascat_label].values, matched_data[label_insitu].values
print "ISMN time series:",ISMN_time_series
print "compared to"
print ascat_time_series
print "Results:"
print "Pearson's (R,p_value)", metrics.pearsonr(x, y)
print "Spearman's (rho,p_value)", metrics.spearmanr(x, y)
print "Kendalls's (tau,p_value)", metrics.kendalltau(x, y)
print "RMSD", metrics.rmsd(x, y)
print "Bias", metrics.bias(x, y)
print "Nash Sutcliffe", metrics.nash_sutcliffe(x, y)
i += 1
#only show the first 2 stations, otherwise this program would run a long time
#and produce a lot of plots
if i >= 2:
break
scaled_data.plot(secondary_y=[label_ascat])
plt.show()
plt.scatter(matched_data[scaled_ascat_label].values,
matched_data[label_insitu].values)
plt.xlabel(scaled_ascat_label)
plt.ylabel(label_insitu)
plt.show()
#calculate correlation coefficients, RMSD, bias, Nash Sutcliffe
x, y = matched_data[scaled_ascat_label].values, matched_data[
label_insitu].values
print "ISMN time series:", ISMN_time_series
print "compared to"
print ascat_time_series
print "Results:"
print "Pearson's (R,p_value)", metrics.pearsonr(x, y)
print "Spearman's (rho,p_value)", metrics.spearmanr(x, y)
print "Kendalls's (tau,p_value)", metrics.kendalltau(x, y)
print "RMSD", metrics.rmsd(x, y)
print "Bias", metrics.bias(x, y)
print "Nash Sutcliffe", metrics.nash_sutcliffe(x, y)
i += 1
#only show the first 2 stations, otherwise this program would run a long time
#and produce a lot of plots
if i >= 2:
break
def _calc_validation_metrics(self):
"""
Calculate vertical metrics between candidate and reference using pytesmo.
Currently implemented:
bias, mad, rmsd, nrmsd,
Returns
-------
df_validation_metrics: pd.DataFrame
Data Frame that contains the metrics between the candidate and reference
for the 2 groups
"""
df_validation_metrics = pd.DataFrame()
for group_no, subset_data in enumerate([self.set0, self.set1, self.setfull]):
if group_no in [0,1]:
group = 'group%i' % group_no
else:
group = 'FRAME'
if 'bias' in self.metrics:
if any([subset_data[col].empty for col in [self.candidate_name, self.reference_name]]):
bias = np.nan
else:
bias =metrics.bias(subset_data[self.reference_name].values,
subset_data[self.candidate_name].values)
df_validation_metrics.at['bias', '%s' % group] = bias
if 'mad' in self.metrics:
if any([subset_data[col].empty for col in [self.candidate_name, self.reference_name]]):
mad = np.nan
else:
mad =metrics.mad(subset_data[self.reference_name].values,
subset_data[self.candidate_name].values)
df_validation_metrics.at['mad', '%s' % group] = mad
if 'rmsd' in self.metrics:
if any([subset_data[col].empty for col in [self.candidate_name, self.reference_name]]):
rmsd = np.nan
else:
rmsd =metrics.rmsd(subset_data[self.reference_name].values,
subset_data[self.candidate_name].values)
df_validation_metrics.at['rmsd', '%s' % group] = rmsd
if 'nrmsd' in self.metrics:
if any([subset_data[col].empty for col in [self.candidate_name, self.reference_name]]):
nrmsd = np.nan
else:
nrmsd =metrics.nrmsd(subset_data[self.reference_name].values,
subset_data[self.candidate_name].values)
df_validation_metrics.at['nrmsd', '%s' % group] = nrmsd
if 'PearsonR' in self.metrics:
if any([subset_data[col].empty for col in [self.candidate_name, self.reference_name]]):
pr, pp = np.nan, np.nan
else:
with warnings.catch_warnings(): # supress scipy warnings
warnings.filterwarnings('ignore')
pr, pp =metrics.pearsonr(subset_data[self.reference_name].values,
subset_data[self.candidate_name].values)
df_validation_metrics.at['PearsonR', '%s' % group] = pr
df_validation_metrics.at['Pp', '%s' % group] = pp
if 'SpearmanR' in self.metrics:
if any([subset_data[col].empty for col in [self.candidate_name, self.reference_name]]):
sr, sp = np.nan, np.nan
else:
with warnings.catch_warnings(): # supress scipy warnings
warnings.filterwarnings('ignore')
sr, sp = metrics.spearmanr(subset_data[self.reference_name].values,
subset_data[self.candidate_name].values)
df_validation_metrics.at['SpearmanR', '%s' % group] = sr
df_validation_metrics.at['Sp', '%s' % group] = sp
return df_validation_metrics
