def plot_cdf(self, x: ndarray, *, show_ecdf: bool = False, **kwargs):
cdf_value = self.cdf_estimate(x=x)
if show_ecdf:
if not isinstance(self.univariate_data, ndarray):
raise Exception(
"Should specify 'univariate_data' to include the empirical cdf plot"
)
else:
protect = kwargs.pop('label') if 'label' in kwargs else None
ax = self.plot_ecdf(x=x,
color='r',
linestyle='--',
linewidth=1.0,
label='Empirical cdf',
**kwargs)
kwargs.setdefault('label', protect)
else:
ax = None
return series(x,
cdf_value,
ax=ax,
y_label='Cumulative probability',
color='k',
linestyle='-',
linewidth=0.5,
**kwargs)
def plot_pdf(self,
x: ndarray,
pdf_value=None,
show_hist: bool = False,
ax=None,
*args,
**kwargs):
pdf_value = pdf_value if pdf_value is not None else self.pdf_estimate(
x=x)
if show_hist:
if not isinstance(self.univariate_data, ndarray):
raise Exception(
"Should specify 'univariate_data' to include the histogram plot"
)
else:
protect = kwargs.pop('label') if 'label' in kwargs else None
bins = kwargs.pop('bins') if 'bins' in kwargs else None
ax = self.plot_hist(ax,
density=True,
color='darkorange',
label='histogram',
bins=bins,
*args,
**kwargs)
kwargs.setdefault('label', protect)
color = kwargs.pop('color') if 'color' in kwargs else 'k'
linestyle = kwargs.pop('linestyle') if 'linestyle' in kwargs else '-'
return series(x,
pdf_value,
ax=ax,
y_label='Probability density',
color=color,
linestyle=linestyle,
linewidth=1,
*args,
**kwargs)
def plot_one_model_uncertainty_and_save_csv(model_name,
y_linestyle: str,
*,
save_csv_name: str = None):
if model_name == 'two_dim_mc':
model_results = two_dim_mc_results
elif model_name == 'cvine_gmcm':
model_results = cvine_gmcm_results
elif model_name == 'empirical':
model_results = empirical_results
else:
raise
y1 = model_results['pout_by_what_model_5'][time_mask_pure] / 3000
y2 = model_results['pout_by_what_model_95'][time_mask_pure] / 3000
y_mean = model_results['pout_by_what_model_mean'][
time_mask_pure] / 3000
ax = series_uncertainty_plot(
xx,
y1=test_data['test_pout_actual_5'][time_mask_pure] / 3000,
y2=test_data['test_pout_actual_95'][time_mask_pure] / 3000,
facecolor='g',
edgecolor='g',
hatch='/' * 6,
linestyle='-',
linewidth=1,
alpha=0.2)
ax = series_uncertainty_plot(xx,
y1=y1,
y2=y2,
ax=ax,
facecolor='b',
edgecolor='b',
hatch='\\' * 6,
linestyle='-',
linewidth=1,
alpha=0.2)
ax = series(x=xx,
y=test_data.get('test_pout_actual')[time_mask_pure] /
3000,
ax=ax,
linestyle='-',
color=[0, 1, 0])
ax = series(xx,
y_mean,
ax=ax,
linestyle=y_linestyle,
color='b',
save_file_=cvine_gmcm_path + model_name,
x_label='Time stamp (x-th day in the season)',
y_label='Power output (p.u.)',
x_lim=(xx[0] - 0.01, xx[-1] + 0.01),
y_lim=(-0.01, 1.01))
if save_csv_name is not None:
f = open(cvine_gmcm_path + save_csv_name + '.csv',
'w',
encoding='utf-8')
csv_writer = csv.writer(f)
header = [
'actual_Pout_mean', 'actual_Pout_5_percentile',
'actual_Pout_95_percentile'
]
header_extend = [
'_model_mean', '_model_5_percentile',
'_model_95_percentile'
]
header_extend = [model_name + x for x in header_extend]
header.extend(header_extend)
csv_writer.writerow(header)
rows = np.stack(
(test_data['test_pout_actual'][time_mask_pure] / 3000,
test_data['test_pout_actual_5'][time_mask_pure] / 3000,
test_data['test_pout_actual_95'][time_mask_pure] / 3000,
y_mean, y1, y2),
axis=1)
csv_writer.writerows(rows.tolist())
def find_extreme_wind_speed_for_rated_power_sasa(rated_power=3000,
bin_step=0.5):
# histogram
measurements = load_old_wind_farm_corrected()
measurements.iloc[:, -1] /= 3000
measurements.iloc[:, -1] /= 0.98
# 画10-min的
bivariate = Bivariate(measurements['Wind speed'].values,
measurements.iloc[:, -1].values,
bin_step=bin_step)
key = bivariate.find_mob_key_according_to_mob_or_mob_fitting_like_dict(
23, bivariate.mob)['accurate_bin_key']
_5_percentile_in_mob = bivariate.cal_mob_statistic_eg_quantile(
np.array([0.05]))
_5_percentile_in_mob *= 0.99
_95_percentile_in_mob = bivariate.cal_mob_statistic_eg_quantile(
np.array([0.95]))
# ax = vlines(_5_percentile_in_mob[key, 1], color='k', linestyles=':',
# label='5$^\mathrm{th}$ percentile')
# ax = vlines(_95_percentile_in_mob[key, 1], color='r', linestyles='-',
# label='95$^\mathrm{th}$ percentile',
# ax=ax)
# hist(bivariate.mob[key]['dependent_var_in_this_bin'],
# x_label='Power output (p.u.) in wind speed bin = [22.75, 23.25) (m/s)',
# y_label='Probability density',
# x_lim=(0, 1.03),
# y_lim=(0, 26),
# bins=np.arange(0, 1.025, 0.0125) + 0.0125 / 2,
# normed=True,
# ax=ax,
# label='WF data',
# legend_loc='upper left')
tt = 1
# resample
# ws, pout = measurements['Wind speed'].values, measurements.iloc[:, -1].values
# ws = ws.reshape(-1, 6)
# pout = pout.reshape(-1, 6)
# ws = np.nanmean(ws, axis=1)
# pout = np.nanmean(pout, axis=1)
# scatter(ws, pout)
# bivariate = Bivariate(ws, pout, bin_step=bin_step)
# 基于所有的原始数据，画风速-power的scatter
ax = scatter(
measurements['Wind speed'].values,
measurements.iloc[:, -1],
x_lim=(0, 28.5),
y_lim=(-0.0125, 1.05),
c=(0.6, 0.6, 0.6),
# label='WF wind speed - power output data',
alpha=0.2,
figure_size=(5, 5 * 0.618 + 0.22))
# 画5/95
ax = series(
bivariate.array_of_bin_boundary[:, 1],
_5_percentile_in_mob[:, -1],
linestyle=':',
color='k',
label='5$^\mathrm{th}$ percentile power curve',
ax=ax,
linewidth=2.5,
)
ax = vlines(bivariate.mob[28]['this_bin_boundary'][1],
ax=ax,
color='cyan',
linewidth=2.5)
ax = vlines(bivariate.mob[45]['this_bin_boundary'][1],
ax=ax,
color='g',
linestyles='-.',
linewidth=2.5)
ax = series(
bivariate.array_of_bin_boundary[:, 1],
_95_percentile_in_mob[:, -1],
ax=ax,
color='r',
x_label='Wind Speed (m/s)',
y_label='Power Output (p.u.)',
x_lim=(0, 28.5),
y_lim=(-0.0125, 1.05),
label='95$^\mathrm{th}$ percentile power curve',
legend_loc='upper left',
linewidth=2.5,
)
ax.legend(bbox_to_anchor=(-0.12, 1.02, 1.12, .102),
loc=3,
ncol=2,
mode="expand",
borderaxespad=0.)
ax.annotate("14.5 m/s",
xy=(14.5, -0.0125),
xytext=(10.5, 0.2),
arrowprops=dict(arrowstyle="->"))
ax.annotate("23 m/s",
xy=(23, -0.0125),
xytext=(19, 0.2),
arrowprops=dict(arrowstyle="->"))
tt = 1
def plot_pdf_like_ndarray(self, *args, **kwargs):
return series(self.pdf_like_ndarray[:, 1], self.pdf_like_ndarray[:, 0],
*args, **kwargs)
def plot_ecdf(self, x: ndarray = None, **kwargs):
return series(x, self.ecdf(x), **kwargs)