def plot_model(df, model_type, n_components, title='', plot_CIs=True, repetitions=20, save_file_to='model.pdf',
maxiter=5000, maxfun=5000, method='nm', period=24):
rows, cols = hlp.get_factors(1)
fig = plt.figure(figsize=(8 * cols, 8 * rows))
gs = gridspec.GridSpec(rows, cols)
results, df_result, _ = dproc.fit_to_model(df, n_components, model_type, period, maxiter, maxfun, method, 0)
# plot
ax = fig.add_subplot(gs[0])
if plot_CIs:
CIs = subplot_confidence_intervals(df, n_components, model_type, ax, repetitions=repetitions, maxiter=maxiter,
maxfun=maxfun, period=period, method=method)
subplot_model(df['X'], df['Y'], df_result['X_test'], df_result['Y_test'], ax, color='blue', title=title,
fit_label='fitted curve')
ax_list = fig.axes
for ax in ax_list:
ax.legend(loc='upper left', fontsize='large')
fig.tight_layout()
plt.show()
# save
try:
hlp.make_results_dir()
fig.savefig(r'results\/' + save_file_to)
except:
print("Can not save plot.")
if plot_CIs:
return CIs
def plot_raw_data(df, title, hour_intervals, save_file_to='raw.pdf'):
rows, cols = hlp.get_factors(1)
fig = plt.figure(figsize=(8 * cols, 8 * rows))
gs = gridspec.GridSpec(rows, cols)
var = df[['Y']].to_numpy().var()
mean = df[['Y']].to_numpy().mean()
print(title, " Var: ", var, " Mean: ", mean)
ax = fig.add_subplot(gs[0])
ax.scatter(df.date.head(500), df.Y.head(500), c='blue', s=1)
date_form = md.DateFormatter("%d-%m %H:00")
ax.xaxis.set_major_formatter(date_form)
ax.xaxis.set_major_locator(mdates.HourLocator(interval=hour_intervals))
plt.xticks(rotation=45)
plt.xlabel('Day [d-m h:min]')
plt.ylabel('Count')
plt.title(title)
fig.tight_layout()
plt.show()
# save
try:
hlp.make_results_dir()
fig.savefig(r'results\/' + save_file_to)
except:
print("Can not save plot.")
def plot_confidence_intervals(df, model_type, n_components, title='', repetitions=20, maxiter=5000, maxfun=5000,
period=24, method='nm', save_file_to='CIs.pdf'):
rows, cols = hlp.get_factors(1)
fig = plt.figure(figsize=(8 * cols, 8 * rows))
gs = gridspec.GridSpec(rows, cols)
ax = fig.add_subplot(gs[0])
Y = df['Y']
results, df_result, X_fit_test = dproc.fit_to_model(df, n_components, model_type, period, maxiter, maxfun, method,
0)
# CI
res2 = copy.deepcopy(results)
params = res2.params
CIs = dproc.calculate_confidence_intervals(df, n_components, model_type, repetitions, maxiter, maxfun, method,
period)
N2 = round(10 * (0.7 ** n_components) + 4)
P = np.zeros((len(params), N2))
i = 0
for index, CI in CIs.iterrows():
P[i, :] = np.linspace(CI[0], CI[1], N2)
i = i + 1
param_samples = hlp.lazy_cartesian_product(P)
size = param_samples.max_size
N = round(df.shape[0] - df.shape[0] / 3)
for i in range(0, N):
j = random.randint(0, size)
p = param_samples.entry_at(j)
res2.initialize(results.model, p)
if model_type == 'zero_nb' or model_type == "zero_poisson":
Y_test_CI = res2.predict(X_fit_test, exog_infl=X_fit_test)
else:
Y_test_CI = res2.predict(X_fit_test)
if i == 0:
ax.plot(df_result['X_test'], Y_test_CI, color='tomato', alpha=0.05, linewidth=0.1,
label='confidence intervals')
else:
ax.plot(df_result['X_test'], Y_test_CI, color='tomato', alpha=0.05, linewidth=0.1)
subplot_model(df['X'], Y, df_result['X_test'], df_result['Y_test'], ax, title=title, plot_model=False)
ax_list = fig.axes
for ax in ax_list:
ax.legend(loc='upper left', fontsize='large')
fig.tight_layout()
plt.show()
# save
try:
hlp.make_results_dir()
fig.savefig(r'results\/' + save_file_to)
except:
print("Can not save plot.")
return CIs
def fit_to_models(df, models_type=models_type, n_components=n_components, maxiter=5000, maxfun=5000, disp=0,
method='nm', plot_models=True, period=24, ax_lim=2500,save_file_to='models.pdf'):
df_results = pd.DataFrame()
if plot_models:
rows, cols = hlp.get_factors(len(models_type))
fig = plt.figure(figsize=(8 * cols, 8 * rows))
gs = gridspec.GridSpec(rows, cols)
i = 0
for model_type in models_type:
c = 0
if plot_models:
ax = fig.add_subplot(gs[i])
if model_type == "zero_nb":
ax.set_ylim(0,ax_lim)
for n_component in n_components:
_, df_result, _ = fit_to_model(df, n_component, model_type, period, maxiter, maxfun, method, disp)
# plot
if plot_models:
title = hlp.get_model_name(model_type)
if c == 0:
plot.subplot_model(df['X'], df['Y'], df_result['X_test'], df_result['Y_test'], ax, color=colors[c],
title=title, fit_label='N=' + str(n_component))
else:
plot.subplot_model(df['X'], df['Y'], df_result['X_test'], df_result['Y_test'], ax, color=colors[c],
title=title, fit_label='N=' + str(n_component), plot_measurements=False)
c = c + 1
df_results = df_results.append(df_result, ignore_index=True)
i = i + 1
# show plots
if plot_models:
ax_list = fig.axes
for ax in ax_list:
ax.legend(loc='upper left', fontsize='medium')
fig.tight_layout()
plt.show()
# save
try:
hlp.make_results_dir()
fig.savefig(r'results\/' + save_file_to)
except:
print("Can not save plot.")
return df_results