def test_stats_activities(self):
from pyadlml.dataset.stats.activities import activities_dist, activities_count, \
activities_transitions, activity_durations
for len_acts, num_acts, df_activity_attr, lst_activity_attr in zip(self.len_activities, self.num_activities, \
self.df_activity_attrs, self.lst_activity_attrs):
df = getattr(self.data, df_activity_attr)
lst = getattr(self.data, lst_activity_attr)
act_count = activities_count(df, lst)
assert len(act_count) == len(lst)
act_count = activities_count(df)
assert len(act_count) == num_acts
act_trans = activities_transitions(df, lst)
assert len(act_trans) == len(lst)
assert act_trans.values.sum() == len(df) - 1
act_trans = activities_transitions(df)
assert len(act_trans) == num_acts
act_durs = activity_durations(df, lst)
assert len(act_durs) == len(lst)
act_durs = activity_durations(df)
assert len(act_durs) == num_acts
act_dist = activities_dist(df, lst, n=100)
assert len(act_dist.columns) == len(lst)
assert len(act_dist) == 100
act_dist = activities_dist(df, n=100)
assert len(act_dist.columns) == num_acts
assert len(act_dist) == 100
def test_stats_activities(self):
from pyadlml.dataset.stats.activities import activities_dist, activities_count, \
activities_transitions, activity_durations
df = self.data.df_activities_admin
lst = self.data.lst_activities
act_count = activities_count(df, lst)
assert len(act_count) == len(lst)
act_count = activities_count(df)
assert len(act_count) == 2
act_trans = activities_transitions(df, lst)
assert len(act_trans) == len(lst)
assert act_trans.values.sum() == len(df) - 1
act_trans = activities_transitions(df)
assert len(act_trans) == 2
act_durs = activity_durations(df, lst)
assert len(act_durs) == len(lst)
act_durs = activity_durations(df)
assert len(act_durs) == 2
act_dist = activities_dist(df, lst, n=100)
assert len(act_dist.columns) == len(lst)
assert len(act_dist) == 100
act_dist = activities_dist(df, n=100)
assert len(act_dist.columns) == 2
assert len(act_dist) == 100
def hist_counts(df_act, y_scale='norm'):
"""
plots the activities durations against each other
"""
assert y_scale in ['norm', 'log']
col_label = 'occurence'
title = 'activity occurrences'
df = activities_count(df_act.copy())
df.reset_index(level=0, inplace=True)
if y_scale == 'log':
df[col_label] = np.log(df[col_label])
labels = {col_label: 'log count'}
else:
labels = {col_label: 'count'}
df = df.sort_values(by=['occurence'], axis=0)
fig = px.bar(df,
title=title,
y='activity',
x=col_label,
orientation='h',
labels=labels,
height=400)
return fig
def hist_counts(df_act, y_scale=None, idle=False, figsize=(9, 3)):
""" plots the activities durations against each other
"""
assert y_scale in [None, 'log']
df_act = df_act.copy()
col_label = 'occurence'
title = 'Activity occurrences'
xlabel = 'counts'
if idle:
df_act = add_idle(df_act)
df = activities_count(df_act)
df.reset_index(level=0, inplace=True)
df = df.sort_values(by=['occurence'], axis=0)
# plot
fig, ax = plt.subplots(figsize=figsize)
plt.title(title)
plt.xlabel(xlabel)
ax.barh(df['activity'], df['occurence'])
if y_scale == 'log':
ax.set_xscale('log')
return fig
def hist_counts(df_acts=None,
lst_acts=None,
df_ac=None,
y_scale="linear",
idle=False,
figsize=None,
color=None,
file_path=None):
"""
Plot a bar chart displaying how often activities are occurring.
Parameters
----------
df_acts : pd.DataFrame, optional
recorded activities from a dataset. Fore more information refer to the
:ref:`user guide<activity_dataframe>`.
lst_acts : lst of str, optional
A list of activities that are included in the statistic. The list can be a
subset of the recorded activities or contain activities that are not recorded.
idle : bool, default: False
Determines whether gaps between activities should be assigned
the activity *idle* or be ignored.
y_scale : {"log", "linear"}, default: linear
The axis scale type to apply.
figsize : (float, float), default: None
width, height in inches. If not provided, the figsize is inferred by automatically.
color : str, optional
sets the color of the plot. When not set, the primary theming color is used.
Learn more about theming in the :ref:`user guide <theming>`
file_path : str, optional
If set, saves the plot under the given file path and return *None* instead
of returning the figure.
Examples
--------
>>> from pyadlml.plot import plot_activity_bar_count
>>> plot_activity_bar_count(data.df_activities, idle=True);
.. image:: ../_static/images/plots/act_bar_cnt.png
:height: 300px
:width: 500 px
:scale: 90 %
:alt: alternate text
:align: center
Returns
-------
res : fig or None
Either a figure if file_path is not specified or nothing
"""
assert not (df_acts is None and df_ac is None)
assert y_scale in [None, 'log']
title = 'Activity occurrences'
col_label = 'occurrence'
xlabel = 'counts'
color = (get_primary_color() if color is None else color)
# create statistics if the don't exists
if df_ac is None:
df_acts = df_acts.copy()
if idle:
df_acts = add_idle(df_acts)
df = activities_count(df_acts, lst_acts=lst_acts)
else:
df = df_ac
# prepare dataframe for plotting
df.reset_index(level=0, inplace=True)
df = df.sort_values(by=[col_label], axis=0)
# define plot modalities
num_act = len(df)
figsize = (_num_bars_2_figsize(num_act) if figsize is None else figsize)
# create plot
fig, ax = plt.subplots(figsize=figsize)
plt.title(title)
plt.xlabel(xlabel)
ax.barh(df['activity'], df[col_label], color=color)
if y_scale == 'log':
ax.set_xscale('log')
# save or return fig
if file_path is not None:
savefig(fig, file_path)
return
else:
return fig