def plot_forces_violinplots(experiment):
ensemble = experiment.observations.kinematics
ensembleF = ensemble.loc[
(ensemble['position_x'] > 0.25) & (ensemble['position_x'] < 0.95),
['totalF_x', 'totalF_y', 'totalF_z',
'randomF_x', 'randomF_y', 'randomF_z',
'upwindF_x',
'wallRepulsiveF_x', 'wallRepulsiveF_y', 'wallRepulsiveF_z',
'stimF_x', 'stimF_y', 'stimF_z']] #== Nans
# plot Forces
# f, axes = plt.subplots(2, 2, figsize=(9, 9), sharex=True, sharey=True)
## forcefig = plt.figure(5, figsize=(9, 8))
## gs2 = gridspec.GridSpec(2, 2)
## Faxs = [fig.add_subplot(ss) for ss in gs2]
forcefig = plt.figure()
# Faxs1 = forcefig.add_subplot(211)
# Faxs2 = forcefig.add_subplot(212)
sns.violinplot(ensembleF, lw=3, alpha=0.7, palette="Set2")
# tF = sns.jointplot('totalF_x', 'totalF_y', ensemble, kind="hex", size=10)
plt.suptitle("Force distributions")
# plt.xticks(range(4,((len(alignments.keys())+1)*4),4), [i[1] for i in medians_sgc], rotation=90, fontsize = 4)
plt.tick_params(axis='x', pad=4)
plt.xticks(rotation=40)
# remove_border()
plt.tight_layout(pad=1.8)
plt.ylabel("Force magnitude distribution (newtons)")
fileappend, path, agent = get_agent_info(experiment.agent)
plt.savefig(os.path.join(path, "Force Distributions" + fileappend + FIG_FORMAT))
plt.show()
def _update_plot(self, axis, view):
if self.plot_type == 'regplot':
sns.regplot(x=view.x,
y=view.y,
data=view.data,
ax=axis,
**self.style)
elif self.plot_type == 'boxplot':
self.style.pop('return_type', None)
self.style.pop('figsize', None)
sns.boxplot(view.data[view.y],
view.data[view.x],
ax=axis,
**self.style)
elif self.plot_type == 'violinplot':
sns.violinplot(view.data[view.y],
view.data[view.x],
ax=axis,
**self.style)
elif self.plot_type == 'interact':
sns.interactplot(view.x,
view.x2,
view.y,
data=view.data,
ax=axis,
**self.style)
elif self.plot_type == 'corrplot':
sns.corrplot(view.data, ax=axis, **self.style)
elif self.plot_type == 'lmplot':
sns.lmplot(x=view.x,
y=view.y,
data=view.data,
ax=axis,
**self.style)
elif self.plot_type in ['pairplot', 'pairgrid', 'facetgrid']:
map_opts = [(k, self.style.pop(k)) for k in self.style.keys()
if 'map' in k]
if self.plot_type == 'pairplot':
g = sns.pairplot(view.data, **self.style)
elif self.plot_type == 'pairgrid':
g = sns.PairGrid(view.data, **self.style)
elif self.plot_type == 'facetgrid':
g = sns.FacetGrid(view.data, **self.style)
for opt, args in map_opts:
plot_fn = getattr(sns, args[0]) if hasattr(
sns, args[0]) else getattr(plt, args[0])
getattr(g, opt)(plot_fn, *args[1:])
plt.close(self.handles['fig'])
self.handles['fig'] = plt.gcf()
else:
super(SNSFramePlot, self)._update_plot(axis, view)
def _update_plot(self, axis, view):
style = self._process_style(self.style[self.cyclic_index])
if self.plot_type == 'factorplot':
opts = dict(style, **({'hue': view.x2} if view.x2 else {}))
sns.factorplot(x=view.x, y=view.y, data=view.data, **opts)
elif self.plot_type == 'regplot':
sns.regplot(x=view.x, y=view.y, data=view.data, ax=axis, **style)
elif self.plot_type == 'boxplot':
style.pop('return_type', None)
style.pop('figsize', None)
sns.boxplot(view.data[view.y], view.data[view.x], ax=axis, **style)
elif self.plot_type == 'violinplot':
if view.x:
sns.violinplot(view.data[view.y],
view.data[view.x],
ax=axis,
**style)
else:
sns.violinplot(view.data, ax=axis, **style)
elif self.plot_type == 'interact':
sns.interactplot(view.x,
view.x2,
view.y,
data=view.data,
ax=axis,
**style)
elif self.plot_type == 'corrplot':
sns.corrplot(view.data, ax=axis, **style)
elif self.plot_type == 'lmplot':
sns.lmplot(x=view.x, y=view.y, data=view.data, ax=axis, **style)
elif self.plot_type in ['pairplot', 'pairgrid', 'facetgrid']:
style_keys = list(style.keys())
map_opts = [(k, style.pop(k)) for k in style_keys if 'map' in k]
if self.plot_type == 'pairplot':
g = sns.pairplot(view.data, **style)
elif self.plot_type == 'pairgrid':
g = sns.PairGrid(view.data, **style)
elif self.plot_type == 'facetgrid':
g = sns.FacetGrid(view.data, **style)
for opt, args in map_opts:
plot_fn = getattr(sns, args[0]) if hasattr(
sns, args[0]) else getattr(plt, args[0])
getattr(g, opt)(plot_fn, *args[1:])
plt.close(self.handles['fig'])
self.handles['fig'] = plt.gcf()
else:
super(SNSFramePlot, self)._update_plot(axis, view)
def _update_plot(self, axis, view):
style = self._process_style(self.style[self.cyclic_index])
if self.plot_type == 'factorplot':
opts = dict(style, **({'hue': view.x2} if view.x2 else {}))
sns.factorplot(x=view.x, y=view.y, data=view.data, **opts)
elif self.plot_type == 'regplot':
sns.regplot(x=view.x, y=view.y, data=view.data,
ax=axis, **style)
elif self.plot_type == 'boxplot':
style.pop('return_type', None)
style.pop('figsize', None)
sns.boxplot(view.data[view.y], view.data[view.x], ax=axis,
**style)
elif self.plot_type == 'violinplot':
if view.x:
sns.violinplot(view.data[view.y], view.data[view.x], ax=axis,
**style)
else:
sns.violinplot(view.data, ax=axis, **style)
elif self.plot_type == 'interact':
sns.interactplot(view.x, view.x2, view.y,
data=view.data, ax=axis, **style)
elif self.plot_type == 'corrplot':
sns.corrplot(view.data, ax=axis, **style)
elif self.plot_type == 'lmplot':
sns.lmplot(x=view.x, y=view.y, data=view.data,
ax=axis, **style)
elif self.plot_type in ['pairplot', 'pairgrid', 'facetgrid']:
style_keys = list(style.keys())
map_opts = [(k, style.pop(k)) for k in style_keys if 'map' in k]
if self.plot_type == 'pairplot':
g = sns.pairplot(view.data, **style)
elif self.plot_type == 'pairgrid':
g = sns.PairGrid(view.data, **style)
elif self.plot_type == 'facetgrid':
g = sns.FacetGrid(view.data, **style)
for opt, args in map_opts:
plot_fn = getattr(sns, args[0]) if hasattr(sns, args[0]) else getattr(plt, args[0])
getattr(g, opt)(plot_fn, *args[1:])
if self._close_figures:
plt.close(self.handles['fig'])
self.handles['fig'] = plt.gcf()
else:
super(SNSFramePlot, self)._update_plot(axis, view)
def violinplot(self, x=None, y=None, hue=None, data=None, *args, **kwargs):
"""
Draw a violin plot to show distributions with respect to categories
Parameters
----------
x : the name of a variable in data that provides labels for categories
y : a list of names of variables in data that needs to visualize \
distribution
hue : the name of a variable in data that provides labels for \
sub-categories in each big category
data : pandas dataframe
**kwargs : other arguments in seaborn.violinplot
order, hue_order : lists of strings, optional
bw : {'scott', 'silverman', float}, optional
cut : float, optional
scale : {'area', 'count', 'width'}, optional
scale_hue : bool, optional
gridsize : int, optional
width : float, optional
inner : {'box', 'quartile', 'point', 'stick', None}, optional
split : bool, optional
dodge : bool, optional
orient : 'v' | 'h', optional
linewidth : float, optional
color : matplotlib color, optional
palette : palette name, list, or dict, optional
saturation : float, optional
Returns
-------
figure : matplotlib figure with multiple axes
References
----------
Seaborn violinplot further documentation
https://seaborn.pydata.org/generated/seaborn.violinplot.html
"""
# check data
if not isinstance(data, (pd.DataFrame)):
raise ValueError('data must be pandas dataframe')
# check x and hue
if x is not None:
if x not in data.columns.values:
raise ValueError('{} is NOT in data'.format(x))
if hue is not None:
if hue not in data.columns.values:
raise ValueError('{} is NOT in data'.format(hue))
# handle single string
if not isinstance(y, (list, tuple, np.ndarray, pd.Index)):
y = [y]
# create fig and axes
nrows = len(y)
plt.close()
fig, axes = plt.subplots(nrows=nrows,
ncols=1,
sharex=self.sharex,
figsize=(self.size[0], nrows * self.size[1]))
# HACK: handle Axes indexing when only one ax in fig
if nrows == 1:
axes = [axes]
# iterate thru x
for i, col in enumerate(y):
# check if col in data
if col not in data.columns.values:
raise ValueError('{} is NOT in data'.format(col))
a = data[col]
not_nan = np.ones(a.shape[0], dtype=np.bool)
if np.logical_not(np.isfinite(a)).any():
logger.warning('RUNTIME WARNING: {} column has inf or nan '
''.format(col))
a = a.replace([-np.inf, np.inf], np.nan)
# filter
not_nan = np.logical_not(a.isnull())
# plot
sns.violinplot(x=x,
y=col,
hue=hue,
data=data[not_nan],
ax=axes[i],
*args,
**kwargs)
if x is not None:
axes[i].set_title(
label='Violin Distribution of {} With Respect To {} '
''.format(col, x),
fontsize=self.title_fontsize)
axes[i].set_xlabel(xlabel=x, fontsize=self.label_fontsize)
axes[i].set_ylabel(ylabel=col, fontsize=self.label_fontsize)
else: # x is None
axes[i].set_title(
label='Violin Distribution of {}'.format(col),
fontsize=self.title_fontsize)
axes[i].set_xlabel(xlabel=col, fontsize=self.label_fontsize)
axes[i].set_ylabel(ylabel='value',
fontsize=self.label_fontsize)
axes[i].tick_params(axis='both',
which='maj',
labelsize=self.tick_fontsize)
axes[i].legend(loc='lower right')
fig.subplots_adjust(wspace=0.5,
hspace=0.3,
left=0.125,
right=0.9,
top=0.9,
bottom=0.1)
fig.tight_layout()
plt.show()
return axes
# Box plot survived x age
fig.add_subplot(3, 3, 7)
#sns.swarmplot(x="Survived", y="Age", hue="Sex", alpha=.7, data=df)
sns.distplot(df[df.Survived == 0]['Age'].dropna(),
bins=20,
kde_kws={"lw": 2},
hist_kws={"alpha": .4},
label='0')
sns.distplot(df[df.Survived == 1]['Age'].dropna(),
bins=20,
kde_kws={"lw": 2},
hist_kws={"alpha": .4},
label='1')
plt.legend()
fig.add_subplot(3, 3, 8)
sns.violinplot(x="Survived", y="Age", data=df, alpha=.7)
# fare and Survived
fig.add_subplot(3, 3, 9)
sns.violinplot(x="Survived", y="Fare", alpha=.7, data=df, saturation=.7)
plt.show()
# In[425]:
cm = df.drop(['PassengerId'], axis=1).corr()
mask = np.zeros_like(cm, dtype=np.bool)
mask[np.triu_indices_from(mask)] = True
plt.figure(figsize=(16, 8))
hm = sns.heatmap(cm,
mask=mask,
matching_df['y_pred'],
bins=np.arange(0, .9, .2)
)
bins = matching_df['y_pred_bin'].unique()
# (matching_df
# .loc[lambda df: df['GoodCustomer'] == 1]
# .loc[lambda df: df['y_pred_bin'] == bins[0]]
# )
max_cost = matching_df['total_cost'].max()
plt.rc("font", size=20)
for y_true in [-1, +1]:
plt.figure(figsize=(4, 4))
ax = sns.violinplot(x='y_pred_bin', y='total_cost', hue='Gender',
data=matching_df.loc[lambda df: df['GoodCustomer'] == y_true].sort_values('Gender'),
linewidth = 0.5, cut=0, background='white',
scale = 'width', color="gold", inner = 'quartile')
# , inner = 'quartile', color = "gold", scale = 'width'
ax.set_xticklabels(["10%", "30%", "50%", "70%"])#, rotation='vertical')
ax.spines['right'].set_visible(False)
ax.spines['top'].set_visible(False)
ax.set_ylim((0, max_cost))
# plt.title('Total Cost By Gender')
plt.ylabel('Cost of Recourse')
plt.xlabel('Predicted Risk' )
# plt.legend(bbox_to_anchor=(0.1, .03, .65, .14), ncol=2, mode="expand", borderaxespad=0.)
# plt.legend(fontsize=14, ncol=2, mode='expand',bbox_to_anchor=(.18, .51, .875, .51), )
if y_true == -1:
'Age-downsampled': "Sample Pop.",
'Full Dataset': "Target Pop.",
}
plt.rc("font", size=20)
for y_true in [0, 1]:
for training_run in ['Downsampled', 'Full Dataset']:
plt.figure(figsize=(4, 4))
ax = sns.violinplot(
x='age_cut',
y='total_cost',
data=(combined_data_df.
loc[lambda df: df['Training Run'] == training_run].
loc[lambda df: df['y_true'] == y_true]),
linewidth=0.5,
cut=0,
scale='width',
color="gold",
inner='quartile')
plt.ylim((0, max_total_cost))
plt.ylabel("Cost of Recourse")
plt.xlabel("Age")
ax.set_ylim((0, 1))
ax.set_xticks(np.arange(0, 14, 2) - 1, )
ax.set_xticklabels(np.arange(20, 90, 10))
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
for l in ax.lines:
