def plot_areas_society_progress(ax: plt.axis, time_array: List,
society_snapshot: Dict,
society_progress: Dict):
previous_status = None
ax.set_xlabel('time [days]')
ax.set_ylabel('population percentage')
for st in Status:
society_progress[st.name].append(society_snapshot[st.name])
if previous_status:
lower_limit = society_progress[previous_status.name]
else:
lower_limit = [0]
ax.fill_between(x=time_array,
y1=lower_limit,
y2=society_progress[st.name],
color=st.value,
label=st.name,
alpha=0.25)
ax.text(x=time_array[-1],
y=1 / 2 * (lower_limit[-1] + society_snapshot[st.name]),
s=r"{0:.2f}".format(society_snapshot[st.name] -
lower_limit[-1]),
size=10,
color=st.value)
previous_status = st
def plot_percentiles(
ax: plt.axis, df: pd.DataFrame, percentiles: Tuple[float, float],
alpha: float) -> None:
assert 0 <= alpha <= 1
assert len(percentiles) == 2 and \
0 <= percentiles[0] <= 1 and \
0 <= percentiles[1] <= 1, "percentiles must be between 0 and 1"
pct_low = df.quantile(percentiles[0], axis=1)
pct_high = df.quantile(percentiles[1], axis=1)
ax.fill_between(df.index, pct_low, pct_high, alpha=alpha)
def _plot_summary_on_axis(
self,
ax: plt.axis,
label_y_axis: bool,
use_title: bool,
):
"""used to plot summary on multi-axis figure, or in standalone figure"""
# axis
if use_title:
ax.set_title('Average', fontsize=configs.Figs.title_font_size)
y_axis_label = self.y_axis_label
else:
y_axis_label = f'Average {self.y_axis_label}'
ax.spines['right'].set_visible(False)
ax.spines['top'].set_visible(False)
ax.spines['top'].set_visible(False)
ax.set_ylim(self.y_lims)
# x-axis
ax.set_xticks([self.last_step])
ax.set_xticklabels([shorten_tick_label(self.last_step)],
fontsize=configs.Figs.tick_font_size)
ax.set_xlabel(self.x_axis_label, fontsize=configs.Figs.ax_font_size)
# y axis
if label_y_axis:
ax.set_ylabel(y_axis_label, fontsize=configs.Figs.ax_font_size)
ax.set_yticks(self.y_ticks)
ax.set_yticklabels(self.y_ticks,
fontsize=configs.Figs.tick_font_size)
else:
ax.set_ylabel('', fontsize=configs.Figs.ax_font_size)
ax.set_yticks([])
ax.set_yticklabels([], fontsize=configs.Figs.tick_font_size)
# collect curves for each replication across all paradigms
gn2rep2curves_by_pd = defaultdict(dict)
for pd in self.pds:
for gn, rep2curve in pd.group_name2rep2curve.items():
for rep, curve in rep2curve.items():
# this curve is performance collapsed across template and for a unique rep and paradigm
gn2rep2curves_by_pd[gn].setdefault(rep, []).append(curve)
# plot
for gn, rep2curves_by_pd in gn2rep2curves_by_pd.items():
# average across paradigms
rep2curve_avg_across_pds = {
rep: np.array(curves_by_pd).mean(axis=0)
for rep, curves_by_pd in rep2curves_by_pd.items()
}
curves = np.array([
rep2curve_avg_across_pds[rep]
for rep in rep2curve_avg_across_pds
]) # one for each rep
color = f'C{self.pds[0].group_names.index(gn)}'
x = np.arange(0, self.last_step + self.step_size, self.step_size)
# plot averages for BabyBERTa
y = np.array(curves).mean(axis=0)
ax.plot(x, y, linewidth=self.line_width, color=color)
# plot average for RoBERTa-base
y_roberta_base = np.repeat(
np.mean(list(self.paradigm2roberta_base_accuracy.values())),
len(x))
ax.plot(x,
y_roberta_base,
linewidth=self.line_width,
**self.ax_kwargs_roberta_base)
# plot average for frequency baseline
y_baseline = np.repeat(
np.mean(list(self.paradigm2baseline_accuracy.values())),
len(x))
ax.plot(x,
y_baseline,
linewidth=self.line_width,
**self.ax_kwargs_baseline)
# plot the margin of error (shaded region)
n = len(curves)
h = sem(curves, axis=0) * t.ppf(
(1 + self.confidence) / 2, n - 1) # margin of error
ax.fill_between(x, y + h, y - h, alpha=0.2, color=color)
# printout
if use_title: # to prevent printing summary twice
print(f'{gn} avg acc at step {self.last_step} = {y[-1]:.3f}')
if use_title:
y_roberta_base = np.mean(
list(self.paradigm2roberta_base_accuracy.values()))
print(
f'roberta-base Liu2019 avg acc at step {self.last_step} = {y_roberta_base:.3f}'
)