def _get_parallel_coordinate_plot(
study: Study,
params: Optional[List[str]] = None,
target: Optional[Callable[[FrozenTrial], float]] = None,
target_name: str = "Objective Value",
) -> "Axes":
if target is None:
def _target(t: FrozenTrial) -> float:
return cast(float, t.value)
target = _target
reversescale = study.direction == StudyDirection.MINIMIZE
else:
reversescale = True
# Set up the graph style.
fig, ax = plt.subplots()
cmap = plt.get_cmap("Blues_r" if reversescale else "Blues")
ax.set_title("Parallel Coordinate Plot")
ax.spines["top"].set_visible(False)
ax.spines["bottom"].set_visible(False)
# Prepare data for plotting.
trials = [
trial for trial in study.trials if trial.state == TrialState.COMPLETE
]
if len(trials) == 0:
_logger.warning("Your study does not have any completed trials.")
return ax
all_params = {p_name for t in trials for p_name in t.params.keys()}
if params is not None:
for input_p_name in params:
if input_p_name not in all_params:
raise ValueError(
"Parameter {} does not exist in your study.".format(
input_p_name))
all_params = set(params)
sorted_params = sorted(all_params)
skipped_trial_numbers = _get_skipped_trial_numbers(trials, sorted_params)
obj_org = [
target(t) for t in trials if t.number not in skipped_trial_numbers
]
if len(obj_org) == 0:
_logger.warning(
"Your study has only completed trials with missing parameters.")
return ax
obj_min = min(obj_org)
obj_max = max(obj_org)
obj_w = obj_max - obj_min
dims_obj_base = [[o] for o in obj_org]
cat_param_names = []
cat_param_values = []
cat_param_ticks = []
param_values = []
var_names = [target_name]
numeric_cat_params_indices: List[int] = []
for param_index, p_name in enumerate(sorted_params):
values = [
t.params[p_name] for t in trials
if t.number not in skipped_trial_numbers
]
if _is_categorical(trials, p_name):
vocab = defaultdict(
lambda: len(vocab)) # type: DefaultDict[str, int]
if _is_numerical(trials, p_name):
_ = [vocab[v] for v in sorted(values)]
numeric_cat_params_indices.append(param_index)
values = [vocab[v] for v in values]
cat_param_names.append(p_name)
vocab_item_sorted = sorted(vocab.items(), key=lambda x: x[1])
cat_param_values.append([v[0] for v in vocab_item_sorted])
cat_param_ticks.append([v[1] for v in vocab_item_sorted])
if _is_log_scale(trials, p_name):
values_for_lc = [np.log10(v) for v in values]
else:
values_for_lc = values
p_min = min(values_for_lc)
p_max = max(values_for_lc)
p_w = p_max - p_min
if p_w == 0.0:
center = obj_w / 2 + obj_min
for i in range(len(values)):
dims_obj_base[i].append(center)
else:
for i, v in enumerate(values_for_lc):
dims_obj_base[i].append((v - p_min) / p_w * obj_w + obj_min)
var_names.append(
p_name if len(p_name) < 20 else "{}...".format(p_name[:17]))
param_values.append(values)
if numeric_cat_params_indices:
# np.lexsort consumes the sort keys the order from back to front.
# So the values of parameters have to be reversed the order.
sorted_idx = np.lexsort([
param_values[index] for index in numeric_cat_params_indices
][::-1])
# Since the values are mapped to other categories by the index,
# the index will be swapped according to the sorted index of numeric params.
param_values = [list(np.array(v)[sorted_idx]) for v in param_values]
# Draw multiple line plots and axes.
# Ref: https://stackoverflow.com/a/50029441
ax.set_xlim(0, len(sorted_params))
ax.set_ylim(obj_min, obj_max)
xs = [range(len(sorted_params) + 1) for _ in range(len(dims_obj_base))]
segments = [np.column_stack([x, y]) for x, y in zip(xs, dims_obj_base)]
lc = LineCollection(segments, cmap=cmap)
lc.set_array(np.asarray(obj_org))
axcb = fig.colorbar(lc, pad=0.1)
axcb.set_label(target_name)
plt.xticks(range(len(sorted_params) + 1), var_names, rotation=330)
for i, p_name in enumerate(sorted_params):
ax2 = ax.twinx()
ax2.set_ylim(min(param_values[i]), max(param_values[i]))
if _is_log_scale(trials, p_name):
ax2.set_yscale("log")
ax2.spines["top"].set_visible(False)
ax2.spines["bottom"].set_visible(False)
ax2.xaxis.set_visible(False)
ax2.plot([1] * len(param_values[i]), param_values[i], visible=False)
ax2.spines["right"].set_position(
("axes", (i + 1) / len(sorted_params)))
if p_name in cat_param_names:
idx = cat_param_names.index(p_name)
tick_pos = cat_param_ticks[idx]
tick_labels = cat_param_values[idx]
ax2.set_yticks(tick_pos)
ax2.set_yticklabels(tick_labels)
ax.add_collection(lc)
return ax
def _get_parallel_coordinate_plot(
study: Study,
params: Optional[List[str]] = None,
target: Optional[Callable[[FrozenTrial], float]] = None,
target_name: str = "Objective Value",
) -> "go.Figure":
layout = go.Layout(title="Parallel Coordinate Plot")
reverse_scale = _is_reverse_scale(study, target)
trials = _filter_nonfinite(
study.get_trials(deepcopy=False, states=(TrialState.COMPLETE,)), target=target
)
if len(trials) == 0:
_logger.warning("Your study does not have any completed trials.")
return go.Figure(data=[], layout=layout)
all_params = {p_name for t in trials for p_name in t.params.keys()}
if params is not None:
for input_p_name in params:
if input_p_name not in all_params:
raise ValueError("Parameter {} does not exist in your study.".format(input_p_name))
all_params = set(params)
sorted_params = sorted(all_params)
if target is None:
def _target(t: FrozenTrial) -> float:
return cast(float, t.value)
target = _target
skipped_trial_ids = _get_skipped_trial_numbers(trials, sorted_params)
objectives = tuple([target(t) for t in trials if t.number not in skipped_trial_ids])
if len(objectives) == 0:
_logger.warning("Your study has only completed trials with missing parameters.")
return go.Figure(data=[], layout=layout)
dims: List[Dict[str, Any]] = [
{
"label": target_name,
"values": objectives,
"range": (min(objectives), max(objectives)),
}
]
numeric_cat_params_indices: List[int] = []
for dim_index, p_name in enumerate(sorted_params, start=1):
values = []
for t in trials:
if t.number in skipped_trial_ids:
continue
if p_name in t.params:
values.append(t.params[p_name])
if _is_log_scale(trials, p_name):
values = [math.log10(v) for v in values]
min_value = min(values)
max_value = max(values)
tickvals = list(range(math.ceil(min_value), math.ceil(max_value)))
if min_value not in tickvals:
tickvals = [min_value] + tickvals
if max_value not in tickvals:
tickvals = tickvals + [max_value]
dim = {
"label": p_name if len(p_name) < 20 else "{}...".format(p_name[:17]),
"values": tuple(values),
"range": (min_value, max_value),
"tickvals": tickvals,
"ticktext": ["{:.3g}".format(math.pow(10, x)) for x in tickvals],
}
elif _is_categorical(trials, p_name):
vocab: DefaultDict[str, int] = defaultdict(lambda: len(vocab))
if _is_numerical(trials, p_name):
_ = [vocab[v] for v in sorted(values)]
values = [vocab[v] for v in values]
ticktext = list(sorted(vocab.keys()))
numeric_cat_params_indices.append(dim_index)
else:
values = [vocab[v] for v in values]
ticktext = list(sorted(vocab.keys(), key=lambda x: vocab[x]))
dim = {
"label": p_name if len(p_name) < 20 else "{}...".format(p_name[:17]),
"values": tuple(values),
"range": (min(values), max(values)),
"tickvals": list(range(len(vocab))),
"ticktext": ticktext,
}
else:
dim = {
"label": p_name if len(p_name) < 20 else "{}...".format(p_name[:17]),
"values": tuple(values),
"range": (min(values), max(values)),
}
dims.append(dim)
if numeric_cat_params_indices:
# np.lexsort consumes the sort keys the order from back to front.
# So the values of parameters have to be reversed the order.
idx = np.lexsort([dims[index]["values"] for index in numeric_cat_params_indices][::-1])
for dim in dims:
# Since the values are mapped to other categories by the index,
# the index will be swapped according to the sorted index of numeric params.
dim.update({"values": tuple(np.array(dim["values"])[idx])})
traces = [
go.Parcoords(
dimensions=dims,
labelangle=30,
labelside="bottom",
line={
"color": dims[0]["values"],
"colorscale": COLOR_SCALE,
"colorbar": {"title": target_name},
"showscale": True,
"reversescale": reverse_scale,
},
)
]
figure = go.Figure(data=traces, layout=layout)
return figure
def _get_parallel_coordinate_info(
study: Study,
params: Optional[List[str]] = None,
target: Optional[Callable[[FrozenTrial], float]] = None,
target_name: str = "Objective Value",
) -> _ParallelCoordinateInfo:
reverse_scale = _is_reverse_scale(study, target)
trials = _filter_nonfinite(study.get_trials(
deepcopy=False, states=(TrialState.COMPLETE, )),
target=target)
all_params = {p_name for t in trials for p_name in t.params.keys()}
if params is not None:
for input_p_name in params:
if input_p_name not in all_params:
raise ValueError(
"Parameter {} does not exist in your study.".format(
input_p_name))
all_params = set(params)
sorted_params = sorted(all_params)
if target is None:
def _target(t: FrozenTrial) -> float:
return cast(float, t.value)
target = _target
skipped_trial_numbers = _get_skipped_trial_numbers(trials, sorted_params)
objectives = tuple(
[target(t) for t in trials if t.number not in skipped_trial_numbers])
# The value of (0, 0) is a dummy range. It is ignored when we plot.
objective_range = (min(objectives),
max(objectives)) if len(objectives) > 0 else (0, 0)
dim_objective = _DimensionInfo(
label=target_name,
values=objectives,
range=objective_range,
is_log=False,
is_cat=False,
tickvals=[],
ticktext=[],
)
if len(trials) == 0:
_logger.warning("Your study does not have any completed trials.")
return _ParallelCoordinateInfo(
dim_objective=dim_objective,
dims_params=[],
reverse_scale=reverse_scale,
target_name=target_name,
)
if len(objectives) == 0:
_logger.warning(
"Your study has only completed trials with missing parameters.")
return _ParallelCoordinateInfo(
dim_objective=dim_objective,
dims_params=[],
reverse_scale=reverse_scale,
target_name=target_name,
)
numeric_cat_params_indices: List[int] = []
dims = []
for dim_index, p_name in enumerate(sorted_params, start=1):
values = []
for t in trials:
if t.number in skipped_trial_numbers:
continue
if p_name in t.params:
values.append(t.params[p_name])
if _is_log_scale(trials, p_name):
values = [math.log10(v) for v in values]
min_value = min(values)
max_value = max(values)
tickvals = list(range(math.ceil(min_value), math.ceil(max_value)))
if min_value not in tickvals:
tickvals = [min_value] + tickvals
if max_value not in tickvals:
tickvals = tickvals + [max_value]
dim = _DimensionInfo(
label=_truncate_label(p_name),
values=tuple(values),
range=(min_value, max_value),
is_log=True,
is_cat=False,
tickvals=tickvals,
ticktext=["{:.3g}".format(math.pow(10, x)) for x in tickvals],
)
elif _is_categorical(trials, p_name):
vocab: DefaultDict[str, int] = defaultdict(lambda: len(vocab))
if _is_numerical(trials, p_name):
_ = [vocab[v] for v in sorted(values)]
values = [vocab[v] for v in values]
ticktext = list(sorted(vocab.keys()))
numeric_cat_params_indices.append(dim_index)
else:
values = [vocab[v] for v in values]
ticktext = list(sorted(vocab.keys(), key=lambda x: vocab[x]))
dim = _DimensionInfo(
label=_truncate_label(p_name),
values=tuple(values),
range=(min(values), max(values)),
is_log=False,
is_cat=True,
tickvals=list(range(len(vocab))),
ticktext=ticktext,
)
else:
dim = _DimensionInfo(
label=_truncate_label(p_name),
values=tuple(values),
range=(min(values), max(values)),
is_log=False,
is_cat=False,
tickvals=[],
ticktext=[],
)
dims.append(dim)
if numeric_cat_params_indices:
dims.insert(0, dim_objective)
# np.lexsort consumes the sort keys the order from back to front.
# So the values of parameters have to be reversed the order.
idx = np.lexsort(
[dims[index].values for index in numeric_cat_params_indices][::-1])
updated_dims = []
for dim in dims:
# Since the values are mapped to other categories by the index,
# the index will be swapped according to the sorted index of numeric params.
updated_dims.append(
_DimensionInfo(
label=dim.label,
values=tuple(np.array(dim.values)[idx]),
range=dim.range,
is_log=dim.is_log,
is_cat=dim.is_cat,
tickvals=dim.tickvals,
ticktext=dim.ticktext,
))
dim_objective = updated_dims[0]
dims = updated_dims[1:]
return _ParallelCoordinateInfo(
dim_objective=dim_objective,
dims_params=dims,
reverse_scale=reverse_scale,
target_name=target_name,
)