def plot_heated_stacked_area(df: pd.DataFrame,
lines: str,
heat: str,
backtest: str = None,
reset_y_lim: bool = False,
figsize: Tuple[int, int] = (16, 9),
color_map: str = 'afmhot',
ax: Axis = None,
upper_lower_missing_scale: float = 0.05) -> Axis:
color_function = plt.get_cmap(color_map)
x = df.index
y = df[lines].values
c = df[heat].values
b = df[backtest].values if backtest is not None else None
# assert enough data
assert len(y.shape) > 1 and len(
c.shape) > 1, "lines and heat need to be 2 dimensions!"
# make sure we have one more line as heats
if c.shape[1] == y.shape[1] + 1:
lower = np.full((c.shape[0], 1),
y.min() * (1 - upper_lower_missing_scale))
upper = np.full((c.shape[0], 1),
y.max() * (1 + upper_lower_missing_scale))
y = np.hstack([lower, y, upper])
# check for matching columns
assert y.shape[1] - 1 == c.shape[
1], f'unexpeced shapes: {y.shape[1] - 1} != {c.shape[1]}'
_, ax = plt.subplots(figsize=figsize) if ax is None else (None, ax)
ax.plot(x, y, color='k', alpha=0.0)
for ci in range(c.shape[1]):
for xi in range(len(x)):
ax.fill_between(x[xi - 1:xi + 1],
y[xi - 1:xi + 1, ci],
y[xi - 1:xi + 1, ci + 1],
facecolors=color_function(c[xi - 1:xi + 1, ci]))
if ci > 0:
# todo annotate all first last and only convert date if it is actually a date
ax.annotate(f'{y[-1, ci]:.2f}',
xy=(mdates.date2num(x[-1]), y[-1, ci]),
xytext=(4, -4),
textcoords='offset pixels')
# reset limits
ax.autoscale(tight=True)
if reset_y_lim:
ax.set_ylim(bottom=y[:, 1].min(), top=y[:, -1].max())
# backtest
if backtest:
ax.plot(x, b)
return ax
def file_vs_value_plot(
a_x: Axis, field_name: str, row: pd.DataFrame, range_columns: List[str], fontsize: float, pad: float
) -> None:
"""Create a dot plot with one point per file"""
assert field_name in ["rt_peak", "peak_height"]
a_x.tick_params(direction="in", length=1, pad=pad, width=0.1, labelsize=fontsize)
num_files = len(range_columns)
a_x.scatter(range(num_files), row[:num_files], s=0.2)
if field_name == "rt_peak":
a_x.axhline(y=row["atlas RT peak"], color="r", linestyle="-", linewidth=0.2)
range_columns += ["atlas RT peak"]
a_x.set_ylim(np.nanmin(row.loc[range_columns]) - 0.12, np.nanmax(row.loc[range_columns]) + 0.12)
else:
a_x.set_yscale("log")
a_x.set_ylim(bottom=1e4, top=1e10)
a_x.set_xlim(-0.5, num_files + 0.5)
a_x.xaxis.set_major_locator(mticker.FixedLocator(np.arange(0, num_files, 1.0)))
_ = [s.set_linewidth(0.1) for s in a_x.spines.values()]
# truncate name so it fits above a single subplot
a_x.set_title(row.name[:33], pad=pad, fontsize=fontsize)
a_x.set_xlabel("Files", labelpad=pad, fontsize=fontsize)
ylabel = "Actual RTs" if field_name == "rt_peak" else "Peak Height"
a_x.set_ylabel(ylabel, labelpad=pad, fontsize=fontsize)