def _add_scipy_dist_CI(x,y,color,columns,ncells,alpha,dist,theta_star,label=None):
ax = plt.gca()
xvar, yvar, loc = _get_variables(ax,columns)
X,Y = _get_XYgrid(x,y,ncells)
data_slice = []
if isinstance(dist, stats._multivariate.multivariate_normal_frozen):
for var in theta_star.index:
if var == xvar:
data_slice.append(X)
elif var == yvar:
data_slice.append(Y)
elif var not in [xvar,yvar]:
data_slice.append(np.array([[theta_star[var]]*ncells]*ncells))
data_slice = np.dstack(tuple(data_slice))
elif isinstance(dist, stats.kde.gaussian_kde):
for var in theta_star.index:
if var == xvar:
data_slice.append(X.ravel())
elif var == yvar:
data_slice.append(Y.ravel())
elif var not in [xvar,yvar]:
data_slice.append(np.array([theta_star[var]]*ncells*ncells))
data_slice = np.array(data_slice)
else:
return
Z = dist.pdf(data_slice)
Z = Z.reshape((ncells, ncells))
ax.contour(X,Y,Z, levels=[alpha], colors=color)
def _add_obj_contour(x,y,color,columns,data,theta_star,label=None):
ax = plt.gca()
xvar, yvar, loc = _get_variables(ax,columns)
try:
X, Y, Z = _get_data_slice(xvar,yvar,columns,data,theta_star)
triang = matplotlib.tri.Triangulation(X, Y)
cmap = plt.cm.get_cmap('Greys')
plt.tricontourf(triang,Z,cmap=cmap)
except:
print('Objective contour plot for', xvar, yvar,'slice failed')
def _add_rectangle_CI(x,y,color,columns,lower_bound,upper_bound,label=None):
ax = plt.gca()
xvar, yvar, loc = _get_variables(ax,columns)
xmin = lower_bound[xvar]
ymin = lower_bound[yvar]
xmax = upper_bound[xvar]
ymax = upper_bound[yvar]
ax.plot([xmin, xmax], [ymin, ymin], color=color)
ax.plot([xmax, xmax], [ymin, ymax], color=color)
ax.plot([xmax, xmin], [ymax, ymax], color=color)
ax.plot([xmin, xmin], [ymax, ymin], color=color)
def grouped_violinplot(data1, data2, normalize=False, group_names=['data1', 'data2'],
filename=None):
"""
Plot a grouped violinplot to compare two datasets
The datasets can be normalized by the median and standard deviation of data1.
Parameters
----------
data1: DataFrame
Data set, columns = variable names
data2: DataFrame
Data set, columns = variable names
normalize : bool, optional
Normalize both datasets by the median and standard deviation of data1
group_names : list, optional
Names used in the legend
filename: string, optional
Filename used to save the figure
"""
assert isinstance(data1, pd.DataFrame)
assert isinstance(data2, pd.DataFrame)
assert isinstance(normalize, bool)
assert isinstance(group_names, list)
assert isinstance(filename, (type(None), str))
data = _get_grouped_data(data1, data2, normalize, group_names)
plt.figure()
sns.violinplot(data=data, hue='set', y='value', x='columns',
order=data1.columns, split=True)
plt.gca().legend().set_title('')
plt.gca().set_xlabel('')
plt.gca().set_ylabel('')
if filename is None:
plt.show()
else:
plt.savefig(filename)
plt.close()
def _add_scatter(x,y,color,columns,theta_star,label=None):
ax = plt.gca()
xvar, yvar, loc = _get_variables(ax, columns)
ax.scatter(theta_star[xvar], theta_star[yvar], c=color, s=35)
