def plot_2d(self,
x: str,
y: str = 'all',
plot_type: str = 'line',
figsize: Tuple[float, float] = (15, 8),
marker: str = 'X',
marker_size: int = 50,
marker_color: str = 'r',
xlim: Tuple[float, float] = None,
hspace: float = None) -> None:
"""Creates a 2D plot of the optimization output for plotting 1 parameter and costs.
Args:
x: Name of the parameter to plot on the x axis, corresponding to the same name in the generator.
y: Can be one of:
"cost"
The name of another cost variable corresponding to the output from the cost function
"all", which creates a subplot for cost plus all other costs
plot_type: line or scatter (default line)
figsize: Figure size
marker: Adds a marker to each point in x, y to show the actual data used for interpolation. You can set this to None to turn markers off.
hspace: Vertical space between subplots
"""
if len(self.experiments) == 0: return
if not has_display(): return
# Get rid of nans since matplotlib does not like them
experiments = [experiment for experiment in self.experiments if experiment.valid()]
if xlim:
experiments = [experiment for experiment in experiments if experiment.suggestion[x] >= xlim[0] and experiment.suggestion[x] <= xlim[1]]
xvalues = [experiment.suggestion[x] for experiment in experiments]
yvalues = []
if y == 'all':
yvalues.append(('cost', np.array([experiment.cost for experiment in experiments])))
other_cost_keys = experiments[0].other_costs.keys()
for key in other_cost_keys:
yvalues.append((key, np.array([experiment.other_costs[key] for experiment in experiments])))
elif y == 'cost':
yvalues.append(('cost', np.array([experiment.cost for experiment in experiments])))
else:
yvalues.append((y, np.array([experiment.other_costs[y] for experiment in experiments])))
xarray = np.array(xvalues)
x_sort_indices = np.argsort(xarray)
xarray = xarray[x_sort_indices]
subplots = []
for tup in yvalues:
name = tup[0]
yarray = tup[1]
yarray = yarray[x_sort_indices]
disp = LinePlotAttributes(marker=marker, marker_size=marker_size, marker_color=marker_color)
subplots.append(
Subplot(data_list=[XYData(name, xarray, yarray, display_attributes=disp)], xlabel=x, ylabel=name, xlim=xlim))
plot = Plot(subplots, figsize=figsize, title='Optimizer 1D Test')
plot.draw()
def draw(self, check_data_size: bool = True) -> Optional[Tuple[mpl.figure.Figure, mpl.axes.Axes]]:
'''Draw the subplots.
Args:
check_data_size: If set to True, will not plot if there are > 100K points to avoid locking up your computer for a long time.
Default True
'''
if not has_display():
print('no display found, cannot plot')
return None
plot_timestamps = self._get_plot_timestamps()
if check_data_size and plot_timestamps is not None and len(plot_timestamps) > 100000:
raise Exception(f'trying to plot large data set with {len(plot_timestamps)} points, reduce date range or turn check_data_size flag off')
date_formatter = None
if plot_timestamps is not None:
date_formatter = get_date_formatter(plot_timestamps, self.date_format)
height_ratios = [subplot.height_ratio for subplot in self.subplot_list]
fig = plt.figure(figsize=self.figsize)
gs = gridspec.GridSpec(len(self.subplot_list), 1, height_ratios=height_ratios, hspace=self.hspace)
axes = []
for i, subplot in enumerate(self.subplot_list):
if subplot.is_3d:
ax = plt.subplot(gs[i], projection='3d')
else:
ax = plt.subplot(gs[i])
axes.append(ax)
time_axes = [axes[i] for i, s in enumerate(self.subplot_list) if s.time_plot]
if len(time_axes):
time_axes[0].get_shared_x_axes().join(*time_axes)
for i, subplot in enumerate(self.subplot_list):
subplot._draw(axes[i], plot_timestamps, date_formatter)
if self.title: axes[0].set_title(self.title)
# We may have added new axes in candlestick plot so get list of axes again
ax_list = fig.axes
for ax in ax_list:
if self.show_grid: ax.grid(linestyle='dotted')
for ax in ax_list:
if ax not in axes: time_axes.append(ax)
for ax in time_axes:
if self.show_date_gaps and plot_timestamps is not None: _draw_date_gap_lines(ax, plot_timestamps)
for ax in ax_list:
ax.relim()
ax.autoscale_view()
return fig, ax_list
def time_distribution(self,
frequency: str = '15 minutes',
display: bool = True,
plot: bool = True,
figsize: Optional[Tuple[int, int]] = None) -> pd.DataFrame:
'''
Return a dataframe with the time distribution of the bars
Args:
frequency: The width of each bin (default "15 minutes"). You can use hours or days as well.
display: Whether to display the data in addition to returning it.
plot: Whether to plot the data in addition to returning it.
figsize: If plot is set, optional figure size for the plot (default (20,8))
'''
group_col = None
n = int(frequency.split(' ')[0])
freq = frequency.split(' ')[1]
df = self.df().reset_index()
if freq == 'minutes' or freq == 'mins' or freq == 'min':
group_col = [df.date.dt.hour, df.date.dt.minute // n * n]
names = ['hour', 'minute']
elif freq == 'hours' or freq == 'hrs' or freq == 'hr':
group_col = [df.date.dt.weekday_name, df.date.dt.hour // n * n]
names = ['weekday', 'hour']
elif freq == 'weekdays' or freq == 'days' or freq == 'day':
group_col = df.date.dt.weekday_name // n * n
names = ['weekday']
else:
raise Exception(f'unknown time freq: {freq}')
count = df.groupby(group_col)['c'].count()
tdf = pd.DataFrame({'close_count': count, 'count_pct': count / df.c.count()})[['close_count', 'count_pct']]
if 'v' in df.columns:
vsum = df.groupby(group_col)['v'].sum()
vdf = pd.DataFrame({'volume': vsum, 'volume_pct': vsum / df.v.sum()})[['volume', 'volume_pct']]
tdf = pd.concat([vdf, tdf], axis=1)
tdf.index.names = names
if display:
dsp.display(tdf)
if plot:
if not figsize: figsize = (20, 8)
cols = ['close_count', 'volume'] if 'v' in df.columns else ['close_count']
if not has_display():
print('no display found, cannot plot time distribution')
return tdf
tdf[cols].plot(figsize=figsize, kind='bar', subplots=True, title='Time Distribution')
return tdf
def plot_3d(self,
x,
y,
z='all',
plot_type='surface',
figsize=(15, 15),
interpolation='linear',
cmap='viridis',
marker='X',
marker_size=50,
marker_color='r',
xlim=None,
ylim=None,
hspace=None):
"""Creates a 3D plot of the optimization output for plotting 2 parameters and costs.
Args:
x: Name of the parameter to plot on the x axis, corresponding to the same name in the generator.
y: Name of the parameter to plot on the y axis, corresponding to the same name in the generator.
z: Can be one of:
"cost"
The name of another cost variable corresponding to the output from the cost function
"all", which creates a subplot for cost plus all other costs
plot_type: surface or contour (default surface)
figsize: Figure size
interpolation: Can be ‘linear’, ‘nearest’ or ‘cubic’ for plotting z points between the ones passed in. See scipy.interpolate.griddata for details
cmap: Colormap to use (default viridis). See matplotlib colormap for details
marker: Adds a marker to each point in x, y, z to show the actual data used for interpolation. You can set this to None to turn markers off.
hspace: Vertical space between subplots
"""
if len(self.experiments) == 0:
print('No experiments found')
return
if not has_display(): return
# Get rid of nans since matplotlib does not like them
experiments = [
experiment for experiment in self.experiments
if experiment.valid()
]
if not len(experiments):
print('No valid experiments found')
return
if xlim:
experiments = [
experiment for experiment in experiments
if experiment.suggestion[x] >= xlim[0]
and experiment.suggestion[x] <= xlim[1]
]
if ylim:
experiments = [
experiment for experiment in experiments
if experiment.suggestion[y] >= ylim[0]
and experiment.suggestion[y] <= ylim[1]
]
xvalues = [experiment.suggestion[x] for experiment in experiments]
yvalues = [experiment.suggestion[y] for experiment in experiments]
zvalues = []
if z == 'all':
zvalues.append(
('cost',
np.array([experiment.cost for experiment in experiments])))
if len(experiments[0].other_costs):
other_cost_keys = experiments[0].other_costs.keys()
for key in other_cost_keys:
zvalues.append((key,
np.array([
experiment.other_costs[key]
for experiment in experiments
])))
elif z == 'cost':
zvalues.append(
('cost',
np.array([experiment.cost for experiment in experiments])))
else:
zvalues.append((z,
np.array([
experiment.other_costs[zname]
for experiment in experiments
])))
subplots = []
for tup in zvalues:
name = tup[0]
zarray = tup[1]
if plot_type == 'contour':
zlabel = None
title = name
else:
zlabel = name
title = None
subplots.append(
Subplot(data_list=[
XYZData(name,
xvalues,
yvalues,
zarray,
plot_type=plot_type,
marker=marker,
marker_size=marker_size,
marker_color=marker_color,
interpolation=interpolation,
cmap=cmap)
],
title=title,
xlabel=x,
ylabel=y,
zlabel=zlabel,
xlim=xlim,
ylim=ylim))
plot = Plot(subplots,
figsize=figsize,
title='Optimizer 2D Test',
hspace=hspace)
plot.draw()
