def averages_by_period_table(data,
variable,
freq='M',
normalize: bool = False,
age_group_size=10,
gradient_axis=1):
d = data[variable].drop(columns='unknown')
d = ic.aggregate_age_groups(d, age_group_size)
d = ic.average_by_period(d, freq=freq)
if normalize:
d = d.div(d.sum(axis=1), axis=0)
fmt = '{:.1%}'
else:
fmt = '{:.0f}'
label = 'casi' if variable == 'cases' else 'decessi'
if freq == 'M':
index_name = 'Mese'
freq_label = 'mese per mese'
else:
index_name = 'Data di fine periodo'
freq_label = f'periodi di {freq} giorni'
caption = f'Numero medio di {label} giornalieri ({freq_label})'
d.columns = d.columns.rename('Età')
d.index = d.index.rename(index_name)
return (d.style.format(fmt).background_gradient(
axis=gradient_axis).set_caption(caption))
def double_area_chart_of_running_averages(
data: pd.DataFrame,
variable: str = "cases",
*,
strings: Translation,
window: int = 14,
age_group_size: int = 20,
period: Optional[Period] = None,
**figure_args,
):
check_variable(variable)
check_age_group_size(age_group_size)
period_slice = slice(*period) if period else slice(data.index[0], None)
r = resample_if_needed(data[variable].drop(columns="unknown"), "D")
d = r[period_slice]
d = d.diff(window).iloc[window:]
d = ic.aggregate_age_groups(d, cuts=age_group_size, fmt_last="{}+")
if window > 1:
d = d / window
figure_args.setdefault("figsize", DOUBLE_CHART_FIGSIZE)
fig, ax = plt.subplots(2, 1, **figure_args)
area_chart(d, ax=ax[0], lang=strings.lang)
area_chart(d, ax=ax[1], normalize=True, lang=strings.lang)
ax[0].set_title(
strings.get(f"running_average_{variable}_title", count=window))
return fig
def double_area_chart_of_cumulative_counts(
data: pd.DataFrame,
variable: str = "cases",
*,
age_group_size: int = 20,
period: Optional[Period] = None,
strings: Translation,
**figure_args,
) -> plt.Figure:
"""
Not a very interesting chart.
Args:
data:
DataFrame having 'cases' and/or 'deaths' as first-level columns
(e.g. ``ic.get()``)
variable:
age_group_size:
period:
strings:
lang:
Returns:
"""
check_variable(variable)
check_age_group_size(age_group_size)
period_slice: slice = slice(
*period) if period else slice(data.index[0], None)
# resample for a smoother graph
d = resample_if_needed(data[variable], "D", hour=18, method="pchip")
d = ic.aggregate_age_groups(
d[period_slice].drop(columns="unknown"),
cuts=age_group_size,
fmt_last="{}+",
)
figure_args.setdefault("figsize", DOUBLE_CHART_FIGSIZE)
fig, ax = plt.subplots(2, 1, **figure_args)
title = strings[f"title.{variable}"]
ax[0].set_title(title)
area_chart(d, ax=ax[0], lang=strings.lang)
area_chart(d, normalize=True, ax=ax[1], lang=strings.lang)
def __init__(
self,
counts: pd.DataFrame,
variable: str = "cases",
*,
strings: Translation = NullTranslation(),
normalize: bool = True,
age_group_size: int = 10,
window: int = 14,
population_distribution: pd.Series = None,
ax: plt.Axes = None,
resample_kwargs: Dict[str, Any] = {},
):
"""
Shows the age distribution of cases/deaths at a given date.
Usable either to draw a static chart or to generate an animation.
Args:
counts:
variable:
normalize:
age_group_size:
window:
population_distribution:
ax:
lang:
"""
self.ax = ax = ax or plt.gca()
s = strings
data = counts[variable].drop(columns="unknown")
data = ic.running_average(data, window=window, **resample_kwargs)
data = ic.aggregate_age_groups(data, cuts=age_group_size)
if normalize:
data = data.divide(data.sum(axis=1), axis=0)
ax.yaxis.set_major_formatter(
mpl.ticker.PercentFormatter(xmax=1.0, decimals=0))
self.data = data
if normalize and population_distribution is not None:
population = ic.aggregate_age_groups(population_distribution,
cuts=age_group_size)
sns.barplot(
ax=ax,
label=s["istat_population_data_label"],
x=population.index,
y=population,
facecolor='#a1c9f4',
hatch="/",
edgecolor="white",
)
age_groups = data.columns
label = s[f"{variable}_label"]
self.bars = ax.bar(
x=age_groups,
height=[0] * len(age_groups),
label=label,
facecolor='#4878d0',
alpha=0.7,
)
self.labels, self.update_labels = add_labels_to_bars(
self.bars,
fmt='{:.0%}' if normalize else '{:n}',
fontsize=10,
ax=ax,
color='white',
bbox=dict(
boxstyle=mpl.patches.BoxStyle("Round", pad=0.3),
color='black',
alpha=.35,
),
)
ymax = 1.05 * data.max().max()
ax.set_ylim(0, ymax)
ax.set_xticklabels(age_groups)
ax.set_xlabel(s["age"])
ax.set_ylabel("")
ax.grid(False, which='both', axis='x')
if normalize:
title = s.get(f"running_{variable}_age_distribution", count=window)
else:
title = s.get(f"running_average_{variable}_title", count=window)
ax.set_title(title, fontsize=14)
if normalize and population_distribution is not None:
ax.yaxis.set_major_formatter(
mpl.ticker.PercentFormatter(xmax=1.0, decimals=0))
ax.legend()
self.date_text = ax.text(
0.5,
0.93,
"",
ha="center",
va="center",
transform=ax.transAxes,
color=(1, 1, 1, 0.9),
bbox=dict(
boxstyle=mpl.patches.BoxStyle("Round", pad=0.4),
color=(0, 0, 0, 0.30),
),
fontsize=14,
fontweight="semibold",
)
self.artists = [self.date_text, *self.bars, *self.labels]
def average_by_period_bar_chart(
counts: pd.DataFrame,
variable: str,
*,
strings: Translation,
freq: Union[str, int] = 7,
normalize: bool = False,
age_group_size: int = 20,
stacked: bool = True,
ylim: float = None,
ax: Optional[plt.Axes] = None,
figsize: Tuple[float, float] = (12, 7),
) -> plt.Axes:
if ax is None:
_, ax = plt.subplots(figsize=figsize)
# Data preparation
d = counts[variable].drop(columns='unknown')
d = ic.aggregate_age_groups(d, age_group_size)
d = ic.count_by_period(d, freq=freq)
if normalize:
d = d.div(d.sum(axis=1), axis=0)
# Plot
ax = d.plot.bar(stacked=stacked, cmap=DEFAULT_CMAP, ax=ax, width=.85)
legend(ax=ax, title=strings['age'])
# Axes setup
if freq == 'M':
xlabel = strings['month']
date_fmt = '%B'
xtick_rotation = 0
else:
xlabel = strings['period_end_date']
date_fmt = '%d %b'
xtick_rotation = 45
ax.set_xticklabels(d.index.strftime(date_fmt), rotation=xtick_rotation)
ax.set_xlabel(xlabel)
if normalize:
if stacked:
ax.set_ylim([0, 1.0])
ax.yaxis.set_major_formatter(
mpl.ticker.PercentFormatter(xmax=1.0, decimals=0))
else:
ax.yaxis.set_major_formatter(mpl.ticker.StrMethodFormatter('{x:n}'))
if ylim:
ax.set_ylim(0, ylim * ax.get_ylim()[1])
# Title
base_title = strings[f'{variable}_age_distribution'
if normalize else f'average_daily_{variable}']
if freq == 'M':
period_label = strings['month_by_month']
elif freq in {'W', 'W-SUN'}:
period_label = strings['week_by_week']
elif isinstance(freq, int):
period_label = strings.get('by_periods_of_n_days', count=freq)
title = f"{base_title} {period_label}"
ax.set_title(title)
return ax