def boxplot(x, y, data=None, legend=None, marker='o',
alpha=.5, points=True, cumprob=False, yscale='linear',
cmap='default', figsize=(12, 6), orderby=None, table=True,
fig=None, axes=None, cgrid=None, violin=False, **kwargs):
"""
Boxplot function
:param x: str or ndarray
:param y: str or ndarray
:param data: pd.Dataframe, source of data
:param legend: str or ndarray color code by this column
:param marker: str, default marker to use in plots
:param alpha: float, alpha for plots
:param points: bool, display or not display points
:param cumprob: bool, display cumprob plot?
:param yscale: str, default = linear, can be log or symlog too
:param cmap: str, matplotlib colormap
:param figsize: tuple(int,int), figure size
:param orderby: str, order x axis by this param
:param datatable: bool, show or not show datatable is available
:param fig: matplotlib figure, if you want to re-use the figure, pass in one already created
:param axes: matplotlib axes, if this is specified, the boxplot will be created on that axes,
and other axes will not be created.
:param kwargs:
:return: matplotlib figure
"""
# if no dataframe is supplied, create one
if data is None:
(x, y, _, legend, _, _), data = components.create_df(x, y, legend)
df = data.copy()
df = df.reset_index()
df[x] = df[x].astype('str')
df[y] = df[y].astype('float').dropna()
# TODO: this doesn't really work right
if orderby:
temp = df.sort(x)
t = temp.groupby(x)[orderby]
map_of_x = col.OrderedDict()
for mg in sorted(t.groups):
g = t.get_group(mg).reset_index()
map_of_x[mg] = g[orderby][0]
list_to_order = sorted([value for value in map_of_x.values()])
order = []
x_to_loc = {}
for k, v in map_of_x.items():
idx = list_to_order.index(v)
x_to_loc[k] = idx
order.append(idx)
min_, max_ = np.min(df[y]), np.max(df[y])
# if an axis is supplied, we will not create another one
# if a figure is supplied, we will reuse the figure
if fig and not axes:
fig = fig
canvas = mbb.FigureCanvasAgg(fig)
axm, axc, axl, axt = components.get_axes(fig)
elif axes:
axm = axes
else:
fig = mpl.figure.Figure(figsize=figsize, tight_layout=True)
canvas = mbb.FigureCanvasAgg(fig)
axm, axc, axl, axt = components.create_axes(cumprob, legend, table, fig=fig)
if violin:
array = []
for arr in sorted(set(df[x])):
array.append(df[df[x] == arr][y])
axm.violinplot(array, showmedians=True)
else:
if orderby:
df.boxplot(column=y, by=x, ax=axm, showfliers=False,
positions=order, fontsize=8, **kwargs)
else:
df.boxplot(column=y, by=x, ax=axm, showfliers=False, fontsize=8, **kwargs)
# We need to identify all of the unique entries in the groupby column
unique_groups = set(df[x])
nonan_grps = []
for group in unique_groups:
if 'nan' not in group:
nonan_grps.append(group)
if legend:
# colormap is supposed to be the goto function to get all colormaps
# should return a colorgrid that maps each point to a set of colors
# if cgrid is already supplied, we will re-use that color grid
if cgrid is None:
cgrid = common.colors.colormap(df[legend], kind='discrete', cmap=cmap)
legend_color = {}
for i, key in df[legend].iteritems():
legend_color[key] = cgrid[i]
if not axes: # skip over creation of legend if axes is provided
axl = components.legend(sorted(list(legend_color.items())), axl)
axl.set_title(legend, loc='left')
# add all the point level data
groups = sorted(nonan_grps)
for j, val in enumerate(groups):
ys = df[y][df[x] == val]
if orderby:
pos = x_to_loc[val]
xs = np.random.normal(pos, 0.05, size=len(ys))
else:
# create the jitters for the points
xs = np.random.normal(j + 1, 0.05, size=len(ys))
if points:
# if cgrid is None, that is the standard way of creating the plot
# cgrid is typically supplied by the jp.grid function
if legend or cgrid is not None:
cs = cgrid[df[x] == val]
axm.scatter(xs, ys.values, color=cs, marker=marker, alpha=alpha,
linewidths=1, **kwargs)
else:
axm.scatter(xs, ys.values, marker=marker, alpha=alpha,
linewidths=1, **kwargs)
# skip creating the cumprob plot if the axes was supplied
if cumprob and not axes:
if legend:
cs = cgrid[df[x] == val]
axc = components.cumprob(ys, axc, color=cs, alpha=alpha, swapxy=True)
else:
axc = components.cumprob(ys, axc, alpha=alpha, swapxy=True)
# various formating
axm.set_ylim(min_, max_)
axm.set_yscale(yscale)
axm.set_ylabel(y)
for label in axm.get_xticklabels():
label.set_rotation(90)
if cumprob and not axes:
axc.set_ylim(min_, max_)
axc.set_yscale(yscale)
axc.set_yticklabels([], visible=False)
for label in axc.get_xticklabels():
label.set_rotation(90)
if table and not axes:
components.datatable(y, data, axt, by=x)
axm.set_title('')
if axes:
return axm
fig.suptitle('')
return canvas.figure
def cumprob(x, data=None, legend=None, figsize=(12, 6),
xscale='linear', yscale='linear', cmap='default', alpha=0.5,
marker='.', table=True, fig=None, axes=None, cgrid=None, **kwargs):
"""
:param x: str or ndarray
:param data: is x is a str, this is a pd.Dataframe
:param legend: str or ndarray,
:param figsize: default is 9,6; sets the figure size
:param xscale: default is linear, set the scale type [linear, log, symlog]
:param yscale: default is linear, set the scale type [linear, log, symlog]
:param cmap: colormap to use for plotting
:param alpha: default is 0.5
:param marker: set matplotlib marker
:param table: bool, default is True, prints the datatable summary to the graph
:param kwargs: passed to matplotlib hist function
:param fig: matplotlib figure if you want to reuse the figure.
:return: matplotlib figure
"""
# if no dataframe is supplied, create one
if data is None:
(x, _, _, legend, _, _), data = components.create_df(x, None, legend)
df = data.copy()
df = df.reset_index()
df[x] = df[x].astype('float').dropna()
min_, max_ = np.min(df[x]), np.max(df[x])
if fig:
fig = fig
canvas = mbb.FigureCanvasAgg(fig)
axm, axc, axl, axt = components.get_axes(fig)
elif axes:
axm = axes
else:
fig = mpl.figure.Figure(figsize=figsize, tight_layout=True)
canvas = mbb.FigureCanvasAgg(fig)
axm, axc, axl, axt = components.create_axes(None, legend, table, fig=fig)
if table and not axes:
axt = components.datatable(x, data, axt, by=legend)
if legend:
# colormap is supposed to be the goto function to get all colormaps
# should return a colorgrid that maps each point to a set of colors
if cgrid is None:
cgrid = common.colors.colormap(df[legend], kind='discrete', cmap=cmap)
legend_color = {}
for i, key in df[legend].iteritems():
legend_color[key] = cgrid[i]
if not axes:
axl = components.legend(sorted(list(legend_color.items())), axl)
axl.set_title(legend,loc='left')
for group in sorted(set(df[legend])):
axm = components.cumprob(df[df[legend] == group][x],
axm,
color=legend_color[group],
marker=marker,
alpha=alpha)
else:
axm = components.cumprob(df[x], axm, marker=marker, alpha=alpha)
# various formating
for label in axm.get_xticklabels():
label.set_rotation(90)
axm.set_xlim(min_, max_)
axm.set_xscale(xscale)
axm.set_yscale(yscale)
axm.set_xlabel(x)
if axes:
return axm
return canvas.figure
def cumprob(x,
data=None,
legend=None,
figsize=(12, 6),
xscale='linear',
yscale='linear',
cmap='default',
alpha=0.5,
marker='.',
table=True,
fig=None,
axes=None,
cgrid=None,
**kwargs):
"""
:param x: str or ndarray
:param data: is x is a str, this is a pd.Dataframe
:param legend: str or ndarray,
:param figsize: default is 9,6; sets the figure size
:param xscale: default is linear, set the scale type [linear, log, symlog]
:param yscale: default is linear, set the scale type [linear, log, symlog]
:param cmap: colormap to use for plotting
:param alpha: default is 0.5
:param marker: set matplotlib marker
:param table: bool, default is True, prints the datatable summary to the graph
:param kwargs: passed to matplotlib hist function
:param fig: matplotlib figure if you want to reuse the figure.
:return: matplotlib figure
"""
# if no dataframe is supplied, create one
if data is None:
(x, _, _, legend, _, _), data = components.create_df(x, None, legend)
df = data.copy()
df = df.reset_index()
df[x] = df[x].astype('float').dropna()
min_, max_ = np.min(df[x]), np.max(df[x])
if fig:
fig = fig
canvas = mbb.FigureCanvasAgg(fig)
axm, axc, axl, axt = components.get_axes(fig)
elif axes:
axm = axes
else:
fig = mpl.figure.Figure(figsize=figsize, tight_layout=True)
canvas = mbb.FigureCanvasAgg(fig)
axm, axc, axl, axt = components.create_axes(None,
legend,
table,
fig=fig)
if table and not axes:
axt = components.datatable(x, data, axt, by=legend)
if legend:
# colormap is supposed to be the goto function to get all colormaps
# should return a colorgrid that maps each point to a set of colors
if cgrid is None:
cgrid = common.colors.colormap(df[legend],
kind='discrete',
cmap=cmap)
legend_color = {}
for i, key in df[legend].iteritems():
legend_color[key] = cgrid[i]
if not axes:
axl = components.legend(sorted(list(legend_color.items())), axl)
axl.set_title(legend, loc='left')
for group in sorted(set(df[legend])):
axm = components.cumprob(df[df[legend] == group][x],
axm,
color=legend_color[group],
marker=marker,
alpha=alpha)
else:
axm = components.cumprob(df[x], axm, marker=marker, alpha=alpha)
# various formating
for label in axm.get_xticklabels():
label.set_rotation(90)
axm.set_xlim(min_, max_)
axm.set_xscale(xscale)
axm.set_yscale(yscale)
axm.set_xlabel(x)
if axes:
return axm
return canvas.figure
def boxplot(x,
y,
data=None,
legend=None,
marker='o',
alpha=.5,
points=True,
cumprob=False,
yscale='linear',
cmap='default',
figsize=(12, 6),
orderby=None,
table=True,
fig=None,
axes=None,
cgrid=None,
violin=False,
**kwargs):
"""
Boxplot function
:param x: str or ndarray
:param y: str or ndarray
:param data: pd.Dataframe, source of data
:param legend: str or ndarray color code by this column
:param marker: str, default marker to use in plots
:param alpha: float, alpha for plots
:param points: bool, display or not display points
:param cumprob: bool, display cumprob plot?
:param yscale: str, default = linear, can be log or symlog too
:param cmap: str, matplotlib colormap
:param figsize: tuple(int,int), figure size
:param orderby: str, order x axis by this param
:param datatable: bool, show or not show datatable is available
:param fig: matplotlib figure, if you want to re-use the figure, pass in one already created
:param axes: matplotlib axes, if this is specified, the boxplot will be created on that axes,
and other axes will not be created.
:param kwargs:
:return: matplotlib figure
"""
# if no dataframe is supplied, create one
if data is None:
(x, y, _, legend, _, _), data = components.create_df(x, y, legend)
df = data.copy()
df = df.reset_index()
df[x] = df[x].astype('str')
df[y] = df[y].astype('float').dropna()
# TODO: this doesn't really work right
if orderby:
temp = df.sort(x)
t = temp.groupby(x)[orderby]
map_of_x = col.OrderedDict()
for mg in sorted(t.groups):
g = t.get_group(mg).reset_index()
map_of_x[mg] = g[orderby][0]
list_to_order = sorted([value for value in map_of_x.values()])
order = []
x_to_loc = {}
for k, v in map_of_x.items():
idx = list_to_order.index(v)
x_to_loc[k] = idx
order.append(idx)
min_, max_ = np.min(df[y]), np.max(df[y])
# if an axis is supplied, we will not create another one
# if a figure is supplied, we will reuse the figure
if fig and not axes:
fig = fig
canvas = mbb.FigureCanvasAgg(fig)
axm, axc, axl, axt = components.get_axes(fig)
elif axes:
axm = axes
else:
fig = mpl.figure.Figure(figsize=figsize, tight_layout=True)
canvas = mbb.FigureCanvasAgg(fig)
axm, axc, axl, axt = components.create_axes(cumprob,
legend,
table,
fig=fig)
if violin:
array = []
for arr in sorted(set(df[x])):
array.append(df[df[x] == arr][y])
axm.violinplot(array, showmedians=True)
else:
if orderby:
df.boxplot(column=y,
by=x,
ax=axm,
showfliers=False,
positions=order,
fontsize=8,
**kwargs)
else:
df.boxplot(column=y,
by=x,
ax=axm,
showfliers=False,
fontsize=8,
**kwargs)
# We need to identify all of the unique entries in the groupby column
unique_groups = set(df[x])
nonan_grps = []
for group in unique_groups:
if 'nan' not in group:
nonan_grps.append(group)
if legend:
# colormap is supposed to be the goto function to get all colormaps
# should return a colorgrid that maps each point to a set of colors
# if cgrid is already supplied, we will re-use that color grid
if cgrid is None:
cgrid = common.colors.colormap(df[legend],
kind='discrete',
cmap=cmap)
legend_color = {}
for i, key in df[legend].iteritems():
legend_color[key] = cgrid[i]
if not axes: # skip over creation of legend if axes is provided
axl = components.legend(sorted(list(legend_color.items())), axl)
axl.set_title(legend, loc='left')
# add all the point level data
groups = sorted(nonan_grps)
for j, val in enumerate(groups):
ys = df[y][df[x] == val]
if orderby:
pos = x_to_loc[val]
xs = np.random.normal(pos, 0.05, size=len(ys))
else:
# create the jitters for the points
xs = np.random.normal(j + 1, 0.05, size=len(ys))
if points:
# if cgrid is None, that is the standard way of creating the plot
# cgrid is typically supplied by the jp.grid function
if legend or cgrid is not None:
cs = cgrid[df[x] == val]
axm.scatter(xs,
ys.values,
color=cs,
marker=marker,
alpha=alpha,
linewidths=1,
**kwargs)
else:
axm.scatter(xs,
ys.values,
marker=marker,
alpha=alpha,
linewidths=1,
**kwargs)
# skip creating the cumprob plot if the axes was supplied
if cumprob and not axes:
if legend:
cs = cgrid[df[x] == val]
axc = components.cumprob(ys,
axc,
color=cs,
alpha=alpha,
swapxy=True)
else:
axc = components.cumprob(ys, axc, alpha=alpha, swapxy=True)
# various formating
axm.set_ylim(min_, max_)
axm.set_yscale(yscale)
axm.set_ylabel(y)
for label in axm.get_xticklabels():
label.set_rotation(90)
if cumprob and not axes:
axc.set_ylim(min_, max_)
axc.set_yscale(yscale)
axc.set_yticklabels([], visible=False)
for label in axc.get_xticklabels():
label.set_rotation(90)
if table and not axes:
components.datatable(y, data, axt, by=x)
axm.set_title('')
if axes:
return axm
fig.suptitle('')
return canvas.figure
def scatter(x, y, data=None, legend=None, marker='o', alpha=.5,
xscale='linear', yscale='linear', cmap='default', figsize=(12, 6),
fit=None, fitparams=None, table=True, fig=None, axes=None, cgrid=None,
**kwargs):
"""
Scatter plots with regression lines
:param x: str or ndarray
:param y: str or ndarray
:param data: pandas.Dataframe
:param legend: str or ndarray, color/fit by this column
:param marker: matplotlib marker style
:param alpha: float, matplotlib alpha
:param xscale: default == linear, any of matplotlib scale types
:param yscale: default == linear, any of matplotlib scale types
:param cmap: any of matplotlib cmaps
:param figsize: default == (9,6);
:param fit: [linear, quadratic, smooth, interpolate]
:param fitparams: params to pass to fitting function
:param table: show the regression table
:param kwargs:
:return: fig, (axes)
"""
# if no dataframe is supplied, create one
if data is None:
(x, y, _, legend, _, _), data = components.create_df(x, y, legend)
if not fitparams:
fitparams = {}
df = data.copy()
df = df[[i for i in (x, y, legend) if i]]
# many of the fitting routines don't work with nan or non-sorted data.
df = df.dropna()
df.sort_values(x)
df = df.reset_index()
# fit axis is for the regression equations
makefitaxis = False
if fit == 'linear' or fit == 'quadratic':
makefitaxis = True
if fig:
fig = fig
canvas = mbb.FigureCanvasAgg(fig)
axm, axc, axl, axt = components.get_axes(fig)
elif axes:
axm = axes
else:
fig = mpl.figure.Figure(figsize=figsize, tight_layout=True)
canvas = mbb.FigureCanvasAgg(fig)
axm, axc, axl, axt = components.create_axes(False, legend, table and makefitaxis, fig=fig)
if legend:
# colormap is supposed to be the goto function to get all colormaps
# should return a colorgrid that maps each point to a set of colors
if cgrid is None:
cgrid = common.colors.colormap(df[legend],
kind='discrete', cmap=cmap)
legend_color = {}
for i, key in df[legend].iteritems():
legend_color[key] = cgrid[i]
# if the axis is supplied, we do not want to create a legend axis
if not axes:
components.legend(sorted(list(legend_color.items())), axl)
axl.set_title(legend, loc='left')
text = ''
for l in sorted(set(df[legend])):
t = df[df[legend] == l]
axm.scatter(x=t[x], y=t[y], c=legend_color[l],
marker=marker, alpha=alpha, **kwargs)
if fit:
xs, ys, fn = _get_fit(x, y, t, fit, fitparams)
axm.plot(xs, ys, c=legend_color[l])
if makefitaxis and table:
text += '${}: {}$\n'.format(str(l).strip(), fn)
if makefitaxis and table and not axes:
components.regressiontable(text, axt, fig)
axt.axis('off')
else:
axm.scatter(x=df[x], y=df[y],
marker=marker, alpha=alpha, **kwargs)
if fit:
xs, ys, fn = _get_fit(x, y, df, fit, fitparams)
axm.plot(xs, ys)
if makefitaxis and table:
components.regressiontable('{}'.format(fn), axt, fig)
axm.set_xlim(np.min(df[x]), np.max(df[x]))
axm.set_ylim(np.min(df[y]), np.max(df[y]))
axm.set_yscale(yscale)
axm.set_xscale(xscale)
axm.set_xlabel(x)
axm.set_ylabel(y)
if axes:
return axm
return canvas.figure
def contour(x,
y,
z,
data=None,
marker=None,
alpha=.5,
xscale='linear',
yscale='linear',
cmap=None,
ncontours=100,
gridsize=100,
colorbar=True,
labels=False,
figsize=(12, 6),
filled=True,
fig=None,
axes=None,
cgrid=None,
axislabels=True,
axisticks=True,
**kwargs):
"""
Create a contour plot from x, y, ans z values
"""
# if no dataframe is supplied, create one
if data is None:
(x, y, z, _), data = components.create_df(x, y, z, _)
df = data.copy()
df = df[[i for i in (x, y, z) if i]]
df = df.dropna()
df = df.reset_index()
if fig and not axes:
fig = fig
canvas = mbb.FigureCanvasAgg(fig)
axm, axc, axl, axt = components.get_axes_1(fig)
elif axes:
axm = axes
else:
fig = mpl.figure.Figure(figsize=figsize, tight_layout=True)
canvas = mbb.FigureCanvasAgg(fig)
axm, _, _, _ = components.create_axes(False, False, False, fig=fig)
xi = np.linspace(np.min(df[x]), np.max(df[x]), gridsize)
yi = np.linspace(np.min(df[y]), np.max(df[y]), gridsize)
try:
zi = mpl.mlab.griddata(df[x], df[y], df[z], xi, yi, interp='linear')
except ValueError:
return
if filled:
cf = axm.contourf(xi, yi, zi, ncontours, cmap=cmap, **kwargs)
else:
cf = axm.contour(xi, yi, zi, ncontours, cmap=cmap, **kwargs)
if not axisticks:
axm.get_xaxis().set_visible(False)
axm.get_yaxis().set_visible(False)
if marker:
axm.scatter(df[x], df[y], marker=marker, color='k')
if colorbar and not axes:
fig.colorbar(cf)
if labels:
axm.clabel(cf)
axm.set_xlim(np.min(df[x]), np.max(df[x]))
axm.set_ylim(np.min(df[y]), np.max(df[y]))
axm.set_yscale(yscale)
axm.set_xscale(xscale)
if axislabels:
axm.set_xlabel(x)
axm.set_ylabel(y)
if axes:
return axm
else:
return canvas.figure
