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
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