in src/lookoutequipment/evaluation.py [0:0]
def plot_histograms(self, nb_cols=3, max_plots=12):
"""
Once the histograms are computed, we can plot the top N by decreasing
ranking distance. By default, this will plot the histograms for the top
12 signals, with 3 plots per line.
Parameters:
nb_cols (integer):
Number of plots to assemble on a given row (default: 3)
max_plots (integer):
Number of signal to consider (default: 12)
Returns:
tuple: tuple containing:
* A ``matplotlib.pyplot.figure`` where the plots are drawn
* A ``list of matplotlib.pyplot.Axis`` with each plot drawn here
"""
# Prepare the figure:
nb_rows = len(self.df_list.keys()) // nb_cols + 1
plt.style.use('Solarize_Light2')
prop_cycle = plt.rcParams['axes.prop_cycle']
colors = prop_cycle.by_key()['color']
fig = plt.figure(figsize=(16, int(nb_rows * 3)))
gs = gridspec.GridSpec(nb_rows, nb_cols, hspace=0.5, wspace=0.25)
axes = []
for i in range(max_plots):
axes.append(fig.add_subplot(gs[i]))
# Loops through each signal by decreasing distance order:
i = 0
for tag, current_rank in tqdm(
self.rank.items(),
total=max_plots,
desc='Preparing histograms'
):
# We stop after reaching the number of plots we are interested in:
if i > max_plots - 1:
break
try:
# Get the anomaly and the normal values from the current signal:
current_signal_values = self.df_list[tag][tag]
current_signal_evaluation = self.df_list[tag].loc[self.ts_label_evaluation, tag]
current_signal_training = self.df_list[tag].loc[self.ts_normal_training, tag]
# Compute the bin width and bin edges to match the
# number of bins we want to have on each histogram:
bin_width =(np.max(current_signal_values) - np.min(current_signal_values))/self.num_bins
bins = np.arange(
np.min(current_signal_values),
np.max(current_signal_values) + bin_width,
bin_width
)
# Add both histograms in the same plot:
axes[i].hist(current_signal_training,
density=True,
alpha=0.5,
color=colors[1],
bins=bins,
edgecolor='#FFFFFF')
axes[i].hist(current_signal_evaluation,
alpha=0.5,
density=True,
color=colors[5],
bins=bins,
edgecolor='#FFFFFF')
except Exception as e:
print(e)
axes[i] = plt.subplot(gs[i])
# Removes all the decoration to leave only the histograms:
axes[i].grid(False)
axes[i].get_yaxis().set_visible(False)
axes[i].get_xaxis().set_visible(False)
# Title will be the tag name followed by the score:
title = tag
title += f' (score: {current_rank:.02f})'
axes[i].set_title(title, fontsize=10)
i+= 1
return fig, axes