def plot(self, experiment, **kwargs):
"""Plot a bar chart"""
if not experiment:
raise util.CytoflowViewError("No experiment specified")
if not self.variable:
raise util.CytoflowViewError("variable not set")
if self.variable not in experiment.conditions:
raise util.CytoflowViewError("variable {0} not in the experiment"
.format(self.variable))
if not (experiment.conditions[self.variable] == "float" or
experiment.conditions[self.variable] == "int"):
raise util.CytoflowViewError("variable {0} isn't numeric"
.format(self.variable))
if not self.xchannel:
raise util.CytoflowViewError("X channel isn't set.")
if self.xchannel not in experiment.data:
raise util.CytoflowViewError("X channel {0} isn't in the experiment"
.format(self.xchannel))
if not self.xfunction:
raise util.CytoflowViewError("X summary function isn't set")
if not self.ychannel:
raise util.CytoflowViewError("Y channel isn't set.")
if self.ychannel not in experiment.data:
raise util.CytoflowViewError("Y channel {0} isn't in the experiment"
.format(self.ychannel))
if not self.yfunction:
raise util.CytoflowViewError("Y summary function isn't set")
if self.xfacet and self.xfacet not in experiment.conditions:
raise util.CytoflowViewError("X facet {0} not in the experiment")
if self.yfacet and self.yfacet not in experiment.conditions:
raise util.CytoflowViewError("Y facet {0} not in the experiment")
if self.huefacet and self.huefacet not in experiment.metadata:
raise util.CytoflowViewError("Hue facet {0} not in the experiment")
if self.x_error_bars and self.x_error_bars != 'data' \
and self.x_error_bars not in experiment.conditions:
raise util.CytoflowViewError("x_error_bars must be either 'data' or "
"a condition in the experiment")
if self.x_error_bars and not self.x_error_function:
raise util.CytoflowViewError("didn't set an x error function")
if self.y_error_bars and self.y_error_bars != 'data' \
and self.y_error_bars not in experiment.conditions:
raise util.CytoflowViewError("y_error_bars must be either 'data' or "
"a condition in the experiment")
if self.y_error_bars and not self.y_error_function:
raise util.CytoflowViewError("didn't set an error function")
kwargs.setdefault('antialiased', True)
if self.subset:
try:
data = experiment.query(self.subset).data.reset_index()
except:
raise util.CytoflowViewError("Subset string '{0}' isn't valid"
.format(self.subset))
if len(data.index) == 0:
raise util.CytoflowViewError("Subset string '{0}' returned no events"
.format(self.subset))
else:
data = experiment.data
group_vars = [self.variable]
if self.xfacet: group_vars.append(self.xfacet)
if self.yfacet: group_vars.append(self.yfacet)
if self.huefacet: group_vars.append(self.huefacet)
g = data.groupby(by = group_vars)
plot_data = pd.DataFrame(
{self.xchannel : g[self.xchannel].aggregate(self.xfunction),
self.ychannel : g[self.ychannel].aggregate(self.yfunction)}) \
.reset_index()
# compute the x error statistic
if self.x_error_bars:
if self.x_error_bars == 'data':
# compute the error statistic on the same subsets as the summary
# statistic
error_stat = g[self.xchannel].aggregate(self.x_error_function).reset_index()
else:
# subdivide the data set further by the error_bars condition
err_vars = list(group_vars)
err_vars.append(self.x_error_bars)
# apply the summary statistic to each subgroup
data_g = data.groupby(by = err_vars)
data_stat = data_g[self.xchannel].aggregate(self.xfunction).reset_index()
# apply the error function to the summary statistics
err_g = data_stat.groupby(by = group_vars)
error_stat = err_g[self.xchannel].aggregate(self.x_error_function).reset_index()
x_err_name = util.random_string(6)
plot_data[x_err_name] = error_stat[self.xchannel]
# compute the y error statistic
if self.y_error_bars:
if self.y_error_bars == 'data':
# compute the error statistic on the same subsets as the summary
# statistic
error_stat = g[self.ychannel].aggregate(self.y_error_function).reset_index()
else:
# subdivide the data set further by the error_bars condition
err_vars = list(group_vars)
err_vars.append(self.y_error_bars)
# apply the summary statistic to each subgroup
data_g = data.groupby(by = err_vars)
data_stat = data_g[self.ychannel].aggregate(self.yfunction).reset_index()
# apply the error function to the summary statistics
err_g = data_stat.groupby(by = group_vars)
error_stat = err_g[self.ychannel].aggregate(self.y_error_function).reset_index()
y_err_name = util.random_string(6)
plot_data[y_err_name] = error_stat[self.ychannel]
grid = sns.FacetGrid(plot_data,
size = 6,
aspect = 1.5,
col = (self.xfacet if self.xfacet else None),
row = (self.yfacet if self.yfacet else None),
hue = (self.huefacet if self.huefacet else None),
col_order = (np.sort(data[self.xfacet].unique()) if self.xfacet else None),
row_order = (np.sort(data[self.yfacet].unique()) if self.yfacet else None),
hue_order = (np.sort(data[self.huefacet].unique()) if self.huefacet else None),
legend_out = False,
sharex = False,
sharey = False)
xscale = util.scale_factory(self.xscale, experiment, self.xchannel)
yscale = util.scale_factory(self.yscale, experiment, self.ychannel)
for ax in grid.axes.flatten():
ax.set_xscale(self.xscale, **xscale.mpl_params)
ax.set_yscale(self.yscale, **yscale.mpl_params)
# plot the error bars first so the axis labels don't get overwritten
if self.x_error_bars:
grid.map(_x_error_bars, self.xchannel, x_err_name, self.ychannel)
if self.y_error_bars:
grid.map(_y_error_bars, self.xchannel, self.ychannel, y_err_name)
grid.map(plt.plot, self.xchannel, self.ychannel, **kwargs)
# if we have a hue facet and a lot of hues, make a color bar instead
# of a super-long legend.
if self.huefacet:
current_palette = mpl.rcParams['axes.color_cycle']
if len(grid.hue_names) > len(current_palette):
plot_ax = plt.gca()
cmap = mpl.colors.ListedColormap(sns.color_palette("husl",
n_colors = len(grid.hue_names)))
cax, _ = mpl.colorbar.make_axes(plt.gca())
norm = mpl.colors.Normalize(vmin = np.min(grid.hue_names),
vmax = np.max(grid.hue_names),
clip = False)
mpl.colorbar.ColorbarBase(cax,
cmap = cmap,
norm = norm,
label = self.huefacet)
plt.sca(plot_ax)
else:
grid.add_legend(title = self.huefacet)
def plot(self, experiment, plot_name=None, **kwargs):
"""Plot a bar chart"""
if not experiment:
raise util.CytoflowViewError("No experiment specified")
if not self.variable:
raise util.CytoflowViewError("variable not set")
if self.variable not in experiment.conditions:
raise util.CytoflowViewError(
"variable {0} not in the experiment".format(self.variable))
if not self.xstatistic:
raise util.CytoflowViewError("X statistic not set")
if self.xstatistic not in experiment.statistics:
raise util.CytoflowViewError(
"Can't find X statistic {} in experiment".format(
self.ystatistic))
else:
xstat = experiment.statistics[self.xstatistic]
if not self.ystatistic:
raise util.CytoflowViewError("Y statistic not set")
if self.ystatistic not in experiment.statistics:
raise util.CytoflowViewError(
"Can't find Y statistic {} in experiment".format(
self.ystatistic))
else:
ystat = experiment.statistics[self.ystatistic]
if not xstat.index.equals(ystat.index):
raise util.CytoflowViewError(
"X statistic and Y statistic must have "
"the same indices: {}".format(xstat.index.names))
if self.x_error_statistic[0]:
if self.x_error_statistic not in experiment.statistics:
raise util.CytoflowViewError(
"X error statistic not in experiment")
else:
x_error_stat = experiment.statistics[self.x_error_statistic]
if not x_error_stat.index.equals(xstat.index):
raise util.CytoflowViewError(
"X error statistic doesn't have the "
"same indices as the X statistic")
else:
x_error_stat = None
if self.y_error_statistic[0]:
if self.y_error_statistic not in experiment.statistics:
raise util.CytoflowViewError(
"Y error statistic not in experiment")
else:
y_error_stat = experiment.statistics[self.y_error_statistic]
if not y_error_stat.index.equals(ystat.index):
raise util.CytoflowViewError(
"Y error statistic doesn't have the "
"same indices as the Y statistic")
else:
y_error_stat = None
col_wrap = kwargs.pop('col_wrap', None)
if col_wrap and self.yfacet:
raise util.CytoflowViewError(
"Can't set yfacet and col_wrap at the same time.")
data = pd.DataFrame(index=xstat.index)
xname = util.random_string(6)
data[xname] = xstat
yname = util.random_string(6)
data[yname] = ystat
if x_error_stat is not None:
#x_error_data = x_error_stat.reset_index()
x_error_name = util.random_string(6)
data[x_error_name] = x_error_stat
if y_error_stat is not None:
y_error_name = util.random_string(6)
data[y_error_name] = y_error_stat
if y_error_stat is not None:
y_error_data = y_error_stat.reset_index()
y_error_name = util.random_string()
data[y_error_name] = y_error_data[y_error_stat.name]
if self.subset:
try:
# TODO - either sanitize column names, or check to see that
# all conditions are valid Python variables
data = data.query(self.subset)
except:
raise util.CytoflowViewError(
"Subset string '{0}' isn't valid".format(self.subset))
if len(data) == 0:
raise util.CytoflowViewError(
"Subset string '{0}' returned no values".format(
self.subset))
names = list(data.index.names)
for name in names:
unique_values = data.index.get_level_values(name).unique()
if len(unique_values) == 1:
warn("Only one value for level {}; dropping it.".format(name),
util.CytoflowViewWarning)
try:
data.index = data.index.droplevel(name)
except AttributeError:
raise util.CytoflowViewError("Must have more than one "
"value to plot.")
names = list(data.index.names)
if not self.variable in experiment.conditions:
raise util.CytoflowViewError(
"Variable {} not in experiment".format(self.variable))
if not self.variable in data.index.names:
raise util.CytoflowViewError(
"Variable {} not in statistic; must be one of {}".format(
self.variable, data.index.names))
if self.xfacet and self.xfacet not in experiment.conditions:
raise util.CytoflowViewError(
"X facet {} not in the experiment".format(self.xfacet))
if self.xfacet and self.xfacet not in data.index.names:
raise util.CytoflowViewError(
"X facet {} not in statistics; must be one of {}".format(
self.xfacet, data.index.names))
if self.yfacet and self.yfacet not in experiment.conditions:
raise util.CytoflowViewError(
"Y facet {} not in the experiment".format(self.yfacet))
if self.yfacet and self.yfacet not in data.index.names:
raise util.CytoflowViewError(
"Y facet {} not in statistics; must be one of {}".format(
self.yfacet, data.index.names))
if self.huefacet and self.huefacet not in experiment.metadata:
raise util.CytoflowViewError(
"Hue facet {} not in the experiment".format(self.huefacet))
if self.huefacet and self.huefacet not in data.index.names:
raise util.CytoflowViewError(
"Hue facet {} not in statistics; must be one of {}".format(
self.huefacet, data.index.names))
col_wrap = kwargs.pop('col_wrap', None)
if col_wrap and self.yfacet:
raise util.CytoflowViewError(
"Can't set yfacet and col_wrap at the same time.")
if col_wrap and not self.xfacet:
raise util.CytoflowViewError("Must set xfacet to use col_wrap.")
facets = filter(
lambda x: x,
[self.variable, self.xfacet, self.yfacet, self.huefacet])
if len(facets) != len(set(facets)):
raise util.CytoflowViewError("Can't reuse facets")
unused_names = list(set(names) - set(facets))
if plot_name is not None and not unused_names:
raise util.CytoflowViewError("You specified a plot name, but all "
"the facets are already used")
data.reset_index(inplace=True)
if unused_names:
groupby = data.groupby(unused_names)
if plot_name is None:
raise util.CytoflowViewError(
"You must use facets {} in either the "
"plot variables or the plot name. "
"Possible plot names: {}".format(unused_names,
groupby.groups.keys()))
if plot_name not in set(groupby.groups.keys()):
raise util.CytoflowViewError(
"Plot {} not from plot_enum; must "
"be one of {}".format(plot_name, groupby.groups.keys()))
data = groupby.get_group(plot_name)
if self.x_error_statistic is not None:
xscale = util.scale_factory(self.xscale,
experiment,
statistic=self.xstatistic)
else:
xscale = util.scale_factory(self.xscale,
experiment,
statistic=self.x_error_statistic)
if self.y_error_statistic is not None:
yscale = util.scale_factory(self.yscale,
experiment,
statistic=self.ystatistic)
else:
yscale = util.scale_factory(self.yscale,
experiment,
statistic=self.y_error_statistic)
xlim = kwargs.pop("xlim", None)
if xlim is None:
xlim = (xscale.clip(data[xname].min() * 0.9),
xscale.clip(data[xname].max() * 1.1))
if x_error_stat is not None:
try:
xlim = (xscale.clip(
min([x[0] for x in x_error_stat]) * 0.9),
xscale.clip(
max([x[1] for x in x_error_stat]) * 1.1))
except IndexError:
xlim = (xscale.clip(x_error_stat.min() * 0.9),
xscale.clip(x_error_stat.max() * 1.1))
ylim = kwargs.pop("ylim", None)
if ylim is None:
ylim = (yscale.clip(data[yname].min() * 0.9),
yscale.clip(data[yname].max() * 1.1))
if y_error_stat is not None:
try:
ylim = (yscale.clip(
min([x[0] for x in y_error_stat]) * 0.9),
yscale.clip(
max([x[1] for x in y_error_stat]) * 1.1))
except IndexError:
ylim = (yscale.clip(y_error_stat.min() * 0.9),
yscale.clip(y_error_stat.max() * 1.1))
kwargs.setdefault('antialiased', True)
cols = col_wrap if col_wrap else \
len(data[self.xfacet].unique()) if self.xfacet else 1
sharex = kwargs.pop('sharex', True)
sharey = kwargs.pop('sharey', True)
grid = sns.FacetGrid(data,
size=(6 / cols),
aspect=1.5,
col=(self.xfacet if self.xfacet else None),
row=(self.yfacet if self.yfacet else None),
hue=(self.huefacet if self.huefacet else None),
col_order=(np.sort(data[self.xfacet].unique())
if self.xfacet else None),
row_order=(np.sort(data[self.yfacet].unique())
if self.yfacet else None),
hue_order=(np.sort(data[self.huefacet].unique())
if self.huefacet else None),
col_wrap=col_wrap,
legend_out=False,
sharex=sharex,
sharey=sharey,
xlim=xlim,
ylim=ylim)
for ax in grid.axes.flatten():
ax.set_xscale(self.xscale, **xscale.mpl_params)
ax.set_yscale(self.yscale, **yscale.mpl_params)
# plot the error bars first so the axis labels don't get overwritten
if x_error_stat:
grid.map(_x_error_bars, xname, yname, x_error_name)
if y_error_stat:
grid.map(_y_error_bars, xname, yname, y_error_name)
grid.map(plt.plot, xname, yname, **kwargs)
# if we have an xfacet, make sure the y scale is the same for each
fig = plt.gcf()
fig_y_min = float("inf")
fig_y_max = float("-inf")
for ax in fig.get_axes():
ax_y_min, ax_y_max = ax.get_ylim()
if ax_y_min < fig_y_min:
fig_y_min = ax_y_min
if ax_y_max > fig_y_max:
fig_y_max = ax_y_max
for ax in fig.get_axes():
ax.set_ylim(fig_y_min, fig_y_max)
# if we have a yfacet, make sure the x scale is the same for each
fig = plt.gcf()
fig_x_min = float("inf")
fig_x_max = float("-inf")
for ax in fig.get_axes():
ax_x_min, ax_x_max = ax.get_xlim()
if ax_x_min < fig_x_min:
fig_x_min = ax_x_min
if ax_x_max > fig_x_max:
fig_x_max = ax_x_max
# if we have a hue facet and a lot of hues, make a color bar instead
# of a super-long legend.
if self.huefacet:
current_palette = mpl.rcParams['axes.color_cycle']
if util.is_numeric(experiment.data[self.huefacet]) and \
len(grid.hue_names) > len(current_palette):
plot_ax = plt.gca()
cmap = mpl.colors.ListedColormap(
sns.color_palette("husl", n_colors=len(grid.hue_names)))
cax, _ = mpl.colorbar.make_axes(plt.gca())
hue_scale = util.scale_factory(self.huescale,
experiment,
condition=self.huefacet)
mpl.colorbar.ColorbarBase(cax,
cmap=cmap,
norm=hue_scale.color_norm(),
label=self.huefacet)
plt.sca(plot_ax)
else:
grid.add_legend(title=self.huefacet)
plt.xlabel(self.xstatistic)
plt.ylabel(self.ystatistic)
if unused_names and plot_name is not None:
plt.title("{0} = {1}".format(unused_names, plot_name))
def plot(self, experiment, plot_name=None, **kwargs):
"""Plot a bar chart"""
if not experiment:
raise util.CytoflowViewError("No experiment specified")
if self.statistic not in experiment.statistics:
raise util.CytoflowViewError(
"Can't find the statistic {} in the experiment".format(
self.statistic))
else:
stat = experiment.statistics[self.statistic]
if self.error_statistic[0]:
if self.error_statistic not in experiment.statistics:
raise util.CytoflowViewError(
"Can't find the error statistic in the experiment")
else:
error_stat = experiment.statistics[self.error_statistic]
else:
error_stat = None
if error_stat is not None:
if not stat.index.equals(error_stat.index):
raise util.CytoflowViewError(
"Data statistic and error statistic "
" don't have the same index.")
data = pd.DataFrame(index=stat.index)
data[stat.name] = stat
if error_stat is not None:
error_name = util.random_string(6)
data[error_name] = error_stat
else:
error_name = None
if self.subset:
try:
data = data.query(self.subset)
except:
raise util.CytoflowViewError(
"Subset string '{0}' isn't valid".format(self.subset))
if len(data) == 0:
raise util.CytoflowViewError(
"Subset string '{0}' returned no values".format(
self.subset))
names = list(data.index.names)
for name in names:
unique_values = data.index.get_level_values(name).unique()
if len(unique_values) == 1:
warn("Only one value for level {}; dropping it.".format(name),
util.CytoflowViewWarning)
try:
data.index = data.index.droplevel(name)
except AttributeError:
raise util.CytoflowViewError("Must have more than one "
"value to plot.")
names = list(data.index.names)
if not self.variable:
raise util.CytoflowViewError("variable not specified")
if not self.variable in names:
raise util.CytoflowViewError("Variable {} isn't in the statistic; "
"must be one of {}".format(
self.variable, names))
if self.xfacet and self.xfacet not in experiment.conditions:
raise util.CytoflowViewError(
"X facet {0} isn't in the experiment".format(self.xfacet))
if self.xfacet and self.xfacet not in names:
raise util.CytoflowViewError(
"X facet {} is not a statistic index; "
"must be one of {}".format(self.xfacet, names))
if self.yfacet and self.yfacet not in experiment.conditions:
raise util.CytoflowViewError(
"Y facet {0} isn't in the experiment".format(self.yfacet))
if self.yfacet and self.yfacet not in names:
raise util.CytoflowViewError(
"Y facet {} is not a statistic index; "
"must be one of {}".format(self.yfacet, names))
if self.huefacet and self.huefacet not in experiment.conditions:
raise util.CytoflowViewError(
"Hue facet {0} isn't in the experiment".format(self.huefacet))
if self.huefacet and self.huefacet not in names:
raise util.CytoflowViewError(
"Hue facet {} is not a statistic index; "
"must be one of {}".format(self.huefacet, names))
col_wrap = kwargs.pop('col_wrap', None)
if col_wrap and self.yfacet:
raise util.CytoflowViewError(
"Can't set yfacet and col_wrap at the same time.")
if col_wrap and not self.xfacet:
raise util.CytoflowViewError("Must set xfacet to use col_wrap.")
facets = filter(
lambda x: x,
[self.variable, self.xfacet, self.yfacet, self.huefacet])
if len(facets) != len(set(facets)):
raise util.CytoflowViewError("Can't reuse facets")
unused_names = list(set(names) - set(facets))
if plot_name is not None and not unused_names:
raise util.CytoflowViewError("You specified a plot name, but all "
"the facets are already used")
data.reset_index(inplace=True)
if unused_names:
groupby = data.groupby(unused_names)
if plot_name is None:
raise util.CytoflowViewError(
"You must use facets {} in either the "
"plot variables or the plot name. "
"Possible plot names: {}".format(unused_names,
groupby.groups.keys()))
if plot_name not in set(groupby.groups.keys()):
raise util.CytoflowViewError(
"Plot {} not from plot_enum; must "
"be one of {}".format(plot_name, groupby.groups.keys()))
data = groupby.get_group(plot_name)
sharex = kwargs.pop('sharex', True)
sharey = kwargs.pop('sharey', True)
cols = col_wrap if col_wrap else \
len(data[self.xfacet].unique()) if self.xfacet else 1
g = sns.FacetGrid(data,
size=(6 / cols),
aspect=1.5,
col=(self.xfacet if self.xfacet else None),
row=(self.yfacet if self.yfacet else None),
col_order=(np.sort(data[self.xfacet].unique())
if self.xfacet else None),
row_order=(np.sort(data[self.yfacet].unique())
if self.yfacet else None),
col_wrap=col_wrap,
legend_out=False,
sharex=sharex,
sharey=sharey)
scale = util.scale_factory(self.scale,
experiment,
statistic=self.statistic)
# because the bottom of a bar chart is "0", masking out bad
# values on a log scale doesn't work. we must clip instead.
if self.scale == "log":
scale.mode = "clip"
# set the scale for each set of axes; can't just call plt.xscale()
for ax in g.axes.flatten():
if self.orientation == 'horizontal':
ax.set_xscale(self.scale, **scale.mpl_params)
else:
ax.set_yscale(self.scale, **scale.mpl_params)
map_args = [self.variable, stat.name]
if self.huefacet:
map_args.append(self.huefacet)
if error_stat is not None:
map_args.append(error_name)
g.map(_barplot,
*map_args,
view=self,
stat_name=stat.name,
error_name=error_name,
**kwargs)
if sharex:
# if are sharing axes make sure the x scale is the same for each
fig = plt.gcf()
fig_x_min = float("inf")
fig_x_max = float("-inf")
for ax in fig.get_axes():
ax_x_min, ax_x_max = ax.get_xlim()
if ax_x_min < fig_x_min:
fig_x_min = ax_x_min
if ax_x_max > fig_x_max:
fig_x_max = ax_x_max
for ax in fig.get_axes():
ax.set_xlim(fig_x_min, fig_x_max)
if sharey:
# if we are sharing y axes, make sure the y scale is the same for each
fig = plt.gcf()
fig_y_min = float("inf")
fig_y_max = float("-inf")
for ax in fig.get_axes():
ax_y_min, ax_y_max = ax.get_ylim()
if ax_y_min < fig_y_min:
fig_y_min = ax_y_min
if ax_y_max > fig_y_max:
fig_y_max = ax_y_max
for ax in fig.get_axes():
ax.set_ylim(fig_y_min, fig_y_max)
if self.huefacet:
labels = np.sort(data[self.huefacet].unique())
labels = [str(x) for x in labels]
g.add_legend(title=self.huefacet, label_order=labels)
if self.orientation == 'horizontal':
plt.sca(fig.get_axes()[0])
plt.xlabel(self.statistic)
else:
plt.sca(fig.get_axes()[0])
plt.ylabel(self.statistic)
if unused_names and plot_name is not None:
plt.title("{0} = {1}".format(unused_names, plot_name))
def enum_plots(self, experiment):
"""
Returns an iterator over the possible plots that this View can
produce. The values returned can be passed to "plot".
"""
# TODO - all this is copied from below. can we abstract it out somehow?
if not experiment:
raise util.CytoflowViewError("No experiment specified")
if not self.variable:
raise util.CytoflowViewError("variable not set")
if self.variable not in experiment.conditions:
raise util.CytoflowViewError(
"variable {0} not in the experiment".format(self.variable))
if not self.xstatistic:
raise util.CytoflowViewError("X statistic not set")
if self.xstatistic not in experiment.statistics:
raise util.CytoflowViewError(
"Can't find X statistic {} in experiment".format(
self.ystatistic))
else:
xstat = experiment.statistics[self.xstatistic]
if not self.ystatistic:
raise util.CytoflowViewError("Y statistic not set")
if self.ystatistic not in experiment.statistics:
raise util.CytoflowViewError(
"Can't find Y statistic {} in experiment".format(
self.ystatistic))
else:
ystat = experiment.statistics[self.ystatistic]
if not xstat.index.equals(ystat.index):
raise util.CytoflowViewError(
"X statistic and Y statistic must have "
"the same indices: {}".format(xstat.index.names))
if self.x_error_statistic[0]:
if self.x_error_statistic not in experiment.statistics:
raise util.CytoflowViewError(
"X error statistic not in experiment")
else:
x_error_stat = experiment.statistics[self.x_error_statistic]
if not x_error_stat.index.equals(xstat.index):
raise util.CytoflowViewError(
"X error statistic doesn't have the "
"same indices as the X statistic")
else:
x_error_stat = None
if self.y_error_statistic[0]:
if self.y_error_statistic not in experiment.statistics:
raise util.CytoflowViewError(
"Y error statistic not in experiment")
else:
y_error_stat = experiment.statistics[self.y_error_statistic]
if not y_error_stat.index.equals(ystat.index):
raise util.CytoflowViewError(
"Y error statistic doesn't have the "
"same indices as the Y statistic")
else:
y_error_stat = None
data = pd.DataFrame(index=xstat.index)
xname = util.random_string(6)
data[xname] = xstat
yname = util.random_string(6)
data[yname] = ystat
if x_error_stat is not None:
#x_error_data = x_error_stat.reset_index()
x_error_name = util.random_string(6)
data[x_error_name] = x_error_stat
if y_error_stat is not None:
y_error_name = util.random_string(6)
data[y_error_name] = y_error_stat
if y_error_stat is not None:
y_error_data = y_error_stat.reset_index()
y_error_name = util.random_string()
data[y_error_name] = y_error_data[y_error_stat.name]
if self.subset:
try:
# TODO - either sanitize column names, or check to see that
# all conditions are valid Python variables
data = data.query(self.subset)
except:
raise util.CytoflowViewError(
"Subset string '{0}' isn't valid".format(self.subset))
if len(data) == 0:
raise util.CytoflowViewError(
"Subset string '{0}' returned no values".format(
self.subset))
names = list(data.index.names)
for name in names:
unique_values = data.index.get_level_values(name).unique()
if len(unique_values) == 1:
warn("Only one value for level {}; dropping it.".format(name),
util.CytoflowViewWarning)
try:
data.index = data.index.droplevel(name)
except AttributeError:
raise util.CytoflowViewError("Must have more than one "
"value to plot.")
names = list(data.index.names)
if not self.variable in experiment.conditions:
raise util.CytoflowViewError(
"Variable {} not in experiment".format(self.variable))
if not self.variable in data.index.names:
raise util.CytoflowViewError(
"Variable {} not in statistic; must be one of {}".format(
self.variable, data.index.names))
if self.xfacet and self.xfacet not in experiment.conditions:
raise util.CytoflowViewError(
"X facet {} not in the experiment".format(self.xfacet))
if self.xfacet and self.xfacet not in data.index.names:
raise util.CytoflowViewError(
"X facet {} not in statistics; must be one of {}".format(
self.xfacet, data.index.names))
if self.yfacet and self.yfacet not in experiment.conditions:
raise util.CytoflowViewError(
"Y facet {} not in the experiment".format(self.yfacet))
if self.yfacet and self.yfacet not in data.index.names:
raise util.CytoflowViewError(
"Y facet {} not in statistics; must be one of {}".format(
self.yfacet, data.index.names))
if self.huefacet and self.huefacet not in experiment.metadata:
raise util.CytoflowViewError(
"Hue facet {} not in the experiment".format(self.huefacet))
if self.huefacet and self.huefacet not in data.index.names:
raise util.CytoflowViewError(
"Hue facet {} not in statistics; must be one of {}".format(
self.huefacet, data.index.names))
facets = filter(
lambda x: x,
[self.variable, self.xfacet, self.yfacet, self.huefacet])
if len(facets) != len(set(facets)):
raise util.CytoflowViewError("Can't reuse facets")
by = list(set(names) - set(facets))
class plot_enum(object):
def __init__(self, experiment, by):
self._iter = None
self._returned = False
if by:
self._iter = experiment.data.groupby(by).__iter__()
def __iter__(self):
return self
def next(self):
if self._iter:
return self._iter.next()[0]
else:
if self._returned:
raise StopIteration
else:
self._returned = True
return None
return plot_enum(experiment, by)
def enum_plots(self, experiment):
"""
Returns an iterator over the possible plots that this View can
produce. The values returned can be passed to "plot".
"""
# TODO - all this is copied from below. can we abstract it out somehow?
if not experiment:
raise util.CytoflowViewError("No experiment specified")
if self.statistic not in experiment.statistics:
raise util.CytoflowViewError(
"Can't find the statistic {} in the experiment".format(
self.statistic))
else:
stat = experiment.statistics[self.statistic]
if self.error_statistic[0]:
if self.error_statistic not in experiment.statistics:
raise util.CytoflowViewError(
"Can't find the error statistic in the experiment")
else:
error_stat = experiment.statistics[self.error_statistic]
else:
error_stat = None
if error_stat is not None:
if not stat.index.equals(error_stat.index):
raise util.CytoflowViewError(
"Data statistic and error statistic "
" don't have the same index.")
data = pd.DataFrame(index=stat.index)
data[stat.name] = stat
if error_stat is not None:
error_name = util.random_string(6)
data[error_name] = error_stat
else:
error_name = None
if self.subset:
try:
data = data.query(self.subset)
except:
raise util.CytoflowViewError(
"Subset string '{0}' isn't valid".format(self.subset))
if len(data) == 0:
raise util.CytoflowViewError(
"Subset string '{0}' returned no values".format(
self.subset))
names = list(data.index.names)
for name in names:
unique_values = data.index.get_level_values(name).unique()
if len(unique_values) == 1:
warn("Only one value for level {}; dropping it.".format(name),
util.CytoflowViewWarning)
try:
data.index = data.index.droplevel(name)
except AttributeError:
raise util.CytoflowViewError("Must have more than one "
"value to plot.")
names = list(data.index.names)
if not self.variable:
raise util.CytoflowViewError("variable not specified")
if not self.variable in data.index.names:
raise util.CytoflowViewError("Variable {} isn't in the statistic; "
"must be one of {}".format(
self.variable, data.index.names))
if self.xfacet and self.xfacet not in experiment.conditions:
raise util.CytoflowViewError(
"X facet {0} isn't in the experiment".format(self.xfacet))
if self.xfacet and self.xfacet not in data.index.names:
raise util.CytoflowViewError(
"X facet {} is not a statistic index; "
"must be one of {}".format(self.xfacet, data.index.names))
if self.yfacet and self.yfacet not in experiment.conditions:
raise util.CytoflowViewError(
"Y facet {0} isn't in the experiment".format(self.yfacet))
if self.yfacet and self.yfacet not in data.index.names:
raise util.CytoflowViewError(
"Y facet {} is not a statistic index; "
"must be one of {}".format(self.yfacet, data.index.names))
if self.huefacet and self.huefacet not in experiment.conditions:
raise util.CytoflowViewError(
"Hue facet {0} isn't in the experiment".format(self.huefacet))
if self.huefacet and self.huefacet not in data.index.names:
raise util.CytoflowViewError(
"Hue facet {} is not a statistic index; "
"must be one of {}".format(self.huefacet, data.index.names))
facets = filter(
lambda x: x,
[self.variable, self.xfacet, self.yfacet, self.huefacet])
if len(facets) != len(set(facets)):
raise util.CytoflowViewError("Can't reuse facets")
by = list(set(names) - set(facets))
class plot_enum(object):
def __init__(self, experiment, by):
self._iter = None
self._returned = False
if by:
self._iter = experiment.data.groupby(by).__iter__()
def __iter__(self):
return self
def next(self):
if self._iter:
return self._iter.next()[0]
else:
if self._returned:
raise StopIteration
else:
self._returned = True
return None
return plot_enum(experiment, by)