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_cum_duration(df_act, y_scale='both'):
"""
plots the cummulated activities durations in a histogram for each activity
"""
assert y_scale in ['norm', 'log', 'both']
title = 'Activity cummulative durations'
act_dur = activity_durations(df_act.copy())
df = act_dur[['minutes']]
df.reset_index(level=0, inplace=True)
if y_scale in ['norm', 'log']:
if y_scale == 'log':
df['minutes'] = np.log(df['minutes'])
labels = {'minutes': 'log minutes'}
else:
labels = {'minutes': 'minutes'}
df = df.sort_values(by=['minutes'], axis=0)
fig = px.bar(
df,
y='activity',
x='minutes',
title=title,
labels=labels,
height=400,
#hover_data=['fraction'] TODO add the fraction by hovering
)
else:
df = df.sort_values(by=['minutes'], axis=0)
col_label = 'minutes'
col_label_log = 'log minutes'
col_activity = 'activity'
df[col_label_log] = np.log(df[col_label])
fig = go.Figure()
fig.add_trace(go.Bar(x=df[col_label], y=df[col_activity], \
orientation='h', name='duration'))
fig.add_trace(go.Bar(x=df[col_label_log], y=df[col_activity], \
orientation='h', name='log duration', \
visible=False))
# Add dropdown
fig.update_layout(title=title,
xaxis_title="duration",
yaxis_title='activities',
updatemenus=[
dict(buttons=list([
dict(label="no scaling",
method="update",
args=[{
"visible": [True, False]
}, {
"title": title,
"xaxis_title": 'asdf'
}]),
dict(label="log scaled",
method="update",
args=[{
"visible": [False, True]
}, {
"title": title,
"xaxis_title": 'asdf'
}])
]),
active=0,
direction="up",
showactive=True,
x=1.0,
xanchor="right",
y=-0.2,
yanchor="bottom"),
])
return fig
def hist_cum_duration(df_acts=None,
lst_acts=None,
df_dur=None,
y_scale=None,
idle=False,
figsize=None,
color=None,
file_path=None):
"""
Plots the cumulative duration for each activity in a bar plot.
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.
y_scale : {"log", "linear"}, default: None
The axis scale type to apply.
idle : bool, default: False
Determines whether gaps between activities should be assigned
the activity *idle* or be ignored.
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.plots import plot_activity_bar_duration
>>> plot_activity_bar_duration(data.df_activities)
.. image:: ../_static/images/plots/act_bar_dur.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 y_scale in [None, 'log']
assert not (df_acts is None and df_dur is None)
title = 'Cummulative activity durations'
xlabel = 'seconds'
freq = 'seconds'
color = (get_primary_color() if color is None else color)
if df_dur is None:
if idle:
df_acts = add_idle(df_acts.copy())
df = activity_durations(df_acts, lst_acts=lst_acts, time_unit=freq)
else:
df = df_dur
df = df.sort_values(by=[freq], axis=0)
num_act = len(df)
figsize = (_num_bars_2_figsize(num_act) if figsize is None else figsize)
# plot
fig, ax = plt.subplots(figsize=figsize)
plt.title(title)
plt.xlabel(xlabel)
ax.barh(df['activity'], df['seconds'], color=color)
if y_scale == 'log':
ax.set_xscale('log')
# create secondary axis with time format 1s, 1m, 1d
ax_top = ax.secondary_xaxis('top', functions=(lambda x: x, lambda x: x))
ax_top.set_xlabel('time')
ax_top.xaxis.set_major_formatter(
ticker.FuncFormatter(func_formatter_seconds2time))
if file_path is not None:
savefig(fig, file_path)
return
else:
return fig