def boxplot_duration(df_act, y_scale='norm', idle=False, figsize=(10, 8)):
"""
plot a boxplot of activity durations (mean) max min
"""
assert y_scale in ['norm', 'log']
if idle:
df_act = add_idle(df_act)
df = activities_duration_dist(df_act)
# select data for each device
activities = df['activity'].unique()
df['seconds'] = df['minutes'] * 60
dat = []
for activity in activities:
df_activity = df[df['activity'] == activity]
#tmp = np.log(df_device['td'].dt.total_seconds())
dat.append(df_activity['seconds'])
# plot boxsplot
fig, ax = plt.subplots(figsize=figsize)
ax.boxplot(dat, vert=False)
ax.set_title('Activity durations')
ax.set_yticklabels(activities, ha='right')
ax.set_xlabel('log seconds')
ax.set_xscale('log')
# create secondary axis with
# 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_sec))
return fig
def hist_cum_duration(df_act, y_scale=None, idle=False, figsize=(9, 3)):
""" plots the cummulated activities durations in a histogram for each activity
"""
assert y_scale in [None, 'log']
title = 'Cummulative activity durations'
if y_scale == 'log':
xlabel = 'log seconds'
else:
xlabel = 'seconds'
if idle:
df_act = add_idle(df_act)
act_dur = activities_durations(df_act)
df = act_dur[['minutes']]
df.reset_index(level=0, inplace=True)
df = df.sort_values(by=['minutes'], axis=0)
# TODO change in activities duration to return time in seconds
df['seconds'] = df['minutes'] * 60
# plot
fig, ax = plt.subplots(figsize=figsize)
plt.title(title)
plt.xlabel(xlabel)
ax.barh(df['activity'], df['seconds'])
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_sec))
return fig
def heatmap_transitions(df_act, z_scale=None, figsize=(8, 6), idle=False):
""" """
assert z_scale in [None,
'log'], 'z-scale has to be either of type None or log'
title = 'Activity transitions'
z_label = 'count'
df_act = add_idle(df_act) if idle else df_act
# get the list of cross tabulations per t_window
df = activities_transitions(df_act)
act_lst = list(df.columns)
x_labels = act_lst
y_labels = act_lst
values = df.values
log = True if z_scale == 'log' else False
valfmt = '{x:.0f}'
# begin plotting
fig, ax = plt.subplots(figsize=figsize)
im, cbar = heatmap_square(values,
y_labels,
x_labels,
log=log,
ax=ax,
cbarlabel=z_label)
texts = annotate_heatmap(im,
textcolors=("white", "black"),
log=log,
valfmt=valfmt)
ax.set_title(title)
return fig
def heatmap_contingency_overlaps(df_dev,
df_act,
figsize=(18, 12),
z_scale='log',
idle=False):
"""
"""
cbarlabel = 'second overlap'
title = 'Cross correlation activites'
if idle:
df_act = add_idle(df_act.copy())
df_con = contingency_table_interval_overlaps(df_act, df_dev)
tmp = df_con.reset_index()
tmp['index'] = tmp['device'] + ' ' + tmp['val'].astype(str)
tmp = tmp.set_index('index')
tmp = tmp.drop(['device', 'val'], axis=1)
# convert time to seconds
tmp = tmp.astype(int) / 1000000000
vals = tmp.values.T
acts = tmp.columns
devs = list(tmp.index)
#if z_scale == 'log':
# format_func = lambda x, p: func_formatter_sec(np.exp(x), p)
#else:
format_func = lambda x, p: func_formatter_sec(x, p)
valfmt = matplotlib.ticker.FuncFormatter(format_func)
heatmap_contingency(vals,
acts,
devs,
cbarlabel,
title,
valfmt,
figsize,
z_scale=z_scale)
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 ridge_line(df_acts=None,
lst_acts=None,
df_act_dist=None,
idle=False,
n=1000,
ylim_upper=None,
color=None,
figsize=None,
file_path=None):
"""
Plots the activity density distribution over one day.
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.
df_act_dist : pd.DataFrame, optional
A precomputed activity density distribution. If the *df_trans* parameter is given, parameters
*df_acts* and *lst_acts* are ignored. The transition table can be computed
in :ref:`stats <stats_acts_trans>`.
n : int, default=1000
The number of monte-carlo samples to draw.
ylim_upper: float, optional
The offset from the top of the plot to the first ridge_line. Set this if
the automatically determined value is not satisfying.
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>`
idle : bool, default: False
Determines whether gaps between activities should be assigned
the activity *idle* or be ignored.
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_ridgeline
>>> plot_activity_ridgeline(data.df_activities)
.. image:: ../_static/images/plots/act_ridge_line.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_act_dist is None)
title = 'Activity distribution over one day'
xlabel = 'day'
color = (get_primary_color() if color is None else color)
if df_act_dist is None:
if idle:
df_acts = add_idle(df_acts)
df = activities_dist(df_acts.copy(), lst_acts=lst_acts, n=n)
if df.empty:
raise ValueError(
"no activity was recorded and no activity list was given.")
else:
df = df_act_dist
def date_2_second(date):
""" maps time onto seconds of a day
Parameters
----------
date : np.datetime64
all the dates are on the day 1990-01-01
Returns
-------
"""
if pd.isnull(date):
return -1
val = (date - np.datetime64('1990-01-01')) / np.timedelta64(1, 's')
total_seconds = 60 * 60 * 24
assert val <= total_seconds and val >= 0
return int(val)
df = df.apply(np.vectorize(date_2_second))
# sort every columns values ascending
for col in df.columns:
df[col] = df[col].sort_values()
grouped = [(col, df[col].values) for col in df.columns]
acts, data = zip(*grouped)
num_act = len(list(acts))
# infer visual properties
figsize = (_num_items_2_ridge_figsize(num_act)
if figsize is None else figsize)
ylim_upper = (_num_items_2_ridge_ylimit(num_act)
if ylim_upper is None else ylim_upper)
# plot the ridgeline
fig, ax = plt.subplots(figsize=figsize)
ridgeline(data,
labels=acts,
overlap=.85,
fill=color,
n_points=100,
dist_scale=0.13)
plt.title(title)
plt.gca().spines['left'].set_visible(False)
plt.gca().spines['right'].set_visible(False)
plt.gca().spines['top'].set_visible(False)
plt.ylim((0, ylim_upper))
plt.xlabel(xlabel)
# set xaxis labels
def func(x, p):
#x = x + 0.5
#if x == 0.0 or str(x)[-1:] == '5':
# return ''
#else:
if True:
if np.ceil(x / k) < 10:
return '0{}:00'.format(int(x / k) + 1)
else:
return '{}:00'.format(int(x / k) + 1)
a = 0
b = 60 * 60 * 24
k = (b - a) / 24
plt.xlim((a, b))
tcks_pos = np.arange(0, 23) * k + (-0.5 + k)
x_locator = ticker.FixedLocator(tcks_pos)
ax.xaxis.set_major_formatter(ticker.FuncFormatter(func))
ax.xaxis.set_major_locator(x_locator)
fig.autofmt_xdate(rotation=45)
plt.grid(zorder=0)
if file_path is not None:
savefig(fig, file_path)
return
else:
return fig
def heatmap_transitions(df_acts=None,
lst_acts=None,
df_trans=None,
z_scale="linear",
figsize=None,
idle=False,
numbers=True,
grid=True,
cmap=None,
file_path=None):
"""
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.
df_trans : pd.DataFrame
A precomputed transition table. If the *df_trans* parameter is given, parameters
*df_acts* and *lst_acts* are ignored. The transition table can be computed
in :ref:`stats <stats_acts_trans>`.
figsize : (float, float), default: None
width, height in inches. If not provided, the figsize is inferred by automatically.
z_scale : {"log", "linear"}, default: None
The axis scale type to apply.
numbers : bool, default: True
Whether to display numbers inside the heatmaps fields or not.
idle : bool, default: False
Determines whether gaps between activities should be assigned
the activity *idle* or be ignored.
cmap : str or Colormap, optional
The Colormap instance or registered colormap name used to map scalar
data to colors. This parameter is ignored for RGB(A) data.
Defaults 'viridis'.
grid : bool, default: True
determines whether to display a white grid, seperating the fields or not.
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_hm_transitions
>>> plot_activity_hm_transitions(data.df_activities)
.. image:: ../_static/images/plots/act_hm_trans.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 z_scale in [None,
'log'], 'z-scale has to be either of type None or log'
assert not (df_acts is None and df_trans is None)
title = 'Activity transitions'
z_label = 'count'
if df_trans is None:
df_acts = add_idle(df_acts) if idle else df_acts
df = activities_transitions(df_acts, lst_acts=lst_acts)
else:
df = df_trans
# get the list of cross tabulations per t_window
act_lst = list(df.columns)
num_act = len(act_lst)
figsize = (_num_items_2_heatmap_square_figsize(num_act)
if figsize is None else figsize)
cmap = (get_sequential_color() if cmap is None else cmap)
x_labels = act_lst
y_labels = act_lst
values = df.values
log = True if z_scale == 'log' else False
valfmt = '{x:.0f}'
# begin plotting
fig, ax = plt.subplots(figsize=figsize)
im, cbar = heatmap_square(values,
y_labels,
x_labels,
log=log,
cmap=cmap,
ax=ax,
cbarlabel=z_label,
grid=grid)
if numbers:
texts = annotate_heatmap(im,
textcolors=("white", "black"),
log=log,
valfmt=valfmt)
ax.set_title(title)
if file_path is not None:
savefig(fig, file_path)
return
else:
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
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
def boxplot_duration(df_acts,
lst_acts=None,
y_scale=None,
idle=False,
figsize=None,
file_path=None):
"""
Plot a boxplot for activity durations.
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.
figsize : (float, float), default: None
width, height in inches. If not provided, the figsize is inferred by automatically.
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.
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_devices_bp_duration
>>> plot_devices_bp_duration(data.df_activities)
.. image:: ../_static/images/plots/act_bp.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']
title = 'Activity durations'
xlabel = 'seconds'
if idle:
df_acts = add_idle(df_acts)
df = activities_duration_dist(df_acts, lst_acts=lst_acts)
# select data for each device
activities = df['activity'].unique()
df['seconds'] = df['minutes'] * 60
num_act = len(activities)
figsize = (_num_bars_2_figsize(num_act) if figsize is None else figsize)
dat = []
for activity in activities:
df_activity = df[df['activity'] == activity]
#tmp = np.log(df_device['td'].dt.total_seconds())
dat.append(df_activity['seconds'])
# plot boxsplot
fig, ax = plt.subplots(figsize=figsize)
ax.boxplot(dat, vert=False)
ax.set_title(title)
ax.set_yticklabels(activities, ha='right')
ax.set_xlabel(xlabel)
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
def ridge_line(df_act,
t_range='day',
idle=False,
n=1000,
dist_scale=0.05,
ylim_upper=1.1,
figsize=(10, 8)):
"""
Parameters
----------
ylim_upper: float
height that determines how many ridgelines are displayed. Adjust value to fit all
the ridgelines into the plot
dist_scale: float
the scale of the distributions of a ridgeline.
"""
if idle:
df_act = add_idle(df_act)
def date_2_second(date):
""" maps time onto seconds of a day
Parameters
----------
date : np.datetime64
all the dates are on the day 1990-01-01
Returns
-------
"""
val = (date - np.datetime64('1990-01-01')) / np.timedelta64(1, 's')
total_seconds = 60 * 60 * 24
assert val <= total_seconds and val >= 0
return int(val)
title = 'Activity distribution over one day'
df = activities_dist(df_act.copy(), t_range, n)
df = df.apply(np.vectorize(date_2_second))
# sort every columns values ascending
for col in df.columns:
df[col] = df[col].sort_values()
grouped = [(col, df[col].values) for col in df.columns]
fig, ax = plt.subplots(figsize=figsize)
acts, data = zip(*grouped)
ridgeline(data,
labels=acts,
overlap=.85,
fill='tab:blue',
n_points=1000,
dist_scale=dist_scale)
plt.title(title)
plt.gca().spines['left'].set_visible(False)
plt.gca().spines['right'].set_visible(False)
plt.gca().spines['top'].set_visible(False)
plt.ylim((0, 1.1))
plt.xlabel('day')
# set xaxis labels
def func(x, p):
#x = x + 0.5
#if x == 0.0 or str(x)[-1:] == '5':
# return ''
#else:
if True:
if int(x / k) < 10:
return '0{}:00'.format(int(x / k) + 1)
else:
return '{}:00'.format(int(x / k) + 1)
a = 0
b = 60 * 60 * 24
k = (b - a) / 24
plt.xlim((a, b))
tcks_pos = np.arange(0, 23) * k + (-0.5 + k)
x_locator = ticker.FixedLocator(tcks_pos)
ax.xaxis.set_major_formatter(ticker.FuncFormatter(func))
ax.xaxis.set_major_locator(x_locator)
fig.autofmt_xdate(rotation=45)
plt.grid(zorder=0)
plt.show()
def heatmap_contingency_overlaps(df_devs=None, df_acts=None, df_con_tab=None, figsize=None, \
z_scale='log', idle=False, numbers=True, file_path=None):
"""
Plots a heatmap the device on and off intervals are measured against
the activities
Parameters
----------
df_devs : pd.DataFrame, optional
recorded devices from a dataset. For more information refer to
:ref:`user guide<device_dataframe>`. If the parameter *df_devs* is not set,
the parameter *df_con_tab* has to be set.
df_acts : pd.DataFrame, optional
recorded activities from a dataset. Fore more information refer to the
:ref:`user guide<activity_dataframe>`. If the parameter *df_acts* is not set,
the parameter *df_con_tab* has to be set.
df_con_tab : pd.DataFrame, optional
A precomputed contingency table. If the *df_con_tab* parameter is given, parameters
*df_acts* and *df_devs* are ignored. The contingency table can be computed
in :ref:`stats <stats_dna_con_dur>`.
figsize : (float, float), optional
width, height in inches. If not provided, the figsize is inferred by automatically.
z_scale : {"log", "linear"}, default: 'log'
The axis scale type to apply.
numbers : bool, default: True
Whether to display numbers inside the heatmaps fields or not.
idle : bool, default: False
Determines whether gaps between activities should be assigned
the activity *idle* or be ignored.
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_hm_contingency_duration
>>> plot_hm_contingency_duration(data.df_devices, data.df_activities)
.. image:: ../_static/images/plots/cont_hm_duration.png
:height: 300px
:width: 800 px
:scale: 90 %
:alt: alternate text
:align: center
Returns
-------
fig : Figure or None
If the parameter file_path is specified, the method return None rather than a matplotlib figure.
"""
assert (df_devs is not None
and df_acts is not None) or df_con_tab is not None
title = 'Mutual time: activities vs. devices'
cbarlabel = 'mutual time in seconds'
if df_con_tab is None:
if idle:
df_acts = add_idle(df_acts.copy())
df_con = contingency_duration(df_devs, df_acts)
else:
df_con = df_con_tab
# convert time (ns) to seconds
df_con = df_con.astype(int) / 1000000000
# rename labels
df_con = df_con.reset_index(drop=False)
df_con['index'] = df_con['index'].apply(lambda x: x
if "Off" in x else "On")
df_con = df_con.set_index('index')
# set values
vals = df_con.values.T
acts = df_con.columns.values
devs = list(df_con.index)
valfmt = matplotlib.ticker.FuncFormatter(
lambda x, p: func_formatter_seconds2time(x, p))
heatmap_contingency(acts,
devs,
vals,
title,
cbarlabel,
valfmt=valfmt,
figsize=figsize,
z_scale=z_scale,
numbers=numbers)
