How to highlight line segments of a plot in matplotlib/seaborn?
I have multiple time-series and multiple labels. Whenever there is a label available I would want to highlight a time-series in i.e. red.
existing plot
I have a line chart where I can highlight certain elements of a plot such as:
for cohort_id in sorted(df.cohort_id.unique()):
print(cohort_id)
figsize = (25, 9)
fig, ax = plt.subplots(figsize=figsize)
ax = sns.lineplot(x='hour', y='metrik_0', data=df[df.cohort_id == cohort_id], ax=ax)
ax.xaxis.set_major_locator(aut_locator)
ax.xaxis.set_major_formatter(aut_formatter)
plt.title(f'cohort_id: {cohort_id}', fontsize=45)
plt.xlabel('')
plt.ylabel('metrik_0', fontsize=35)
for index, row in marker_labels.iterrows():
start = row.start
end = row.end
marker_type = row.marker_type
if marker_type == 'b':
ax.axvspan(start, end, color='gray', alpha=0.2)
else:
ax.axvspan(start, end, color='orange', alpha=0.5)
plt.show()
This plot can be converted into a cycleplot highlighting certain periodicities like:
for cohort_id in sorted(df.cohort_id.unique()):
print(cohort_id)
figsize = (25, 9)
fig, ax = plt.subplots(figsize=figsize)
a1 = sns.lineplot(x=df['hour'].dt.hour, y='metrik_0', hue='device_id', units='dt', style='dt', estimator=None, data=df[(df.cohort_id == cohort_id)], ax=ax)
handles, labels = a1.get_legend_handles_labels()
a1.legend(handles=handles[1:], labels=labels[1:], loc='center', bbox_to_anchor=(0.5, -0.25), ncol=6, fontsize=20)
plt.title(f'cohort_id: {cohort_id}', fontsize=35)
plt.xlabel('hour of the day', fontsize=35)
plt.ylabel('metrik_0', fontsize=35)
plt.show()
But now the labels can not be displayed anymore.
question
How can I re-add the labels to the cycle plot? Any method would be fine. But so far I thought it would be best to highlight the matched time intervals in red
data generation
To generate some example Data:
%pylab inline
import pandas as pd
import numpy as np
import seaborn as sns; sns.set()
import matplotlib.dates as mdates
aut_locator = mdates.AutoDateLocator(minticks=3, maxticks=7)
aut_formatter = mdates.ConciseDateFormatter(aut_locator)
import random
random_seed = 47
np.random.seed(random_seed)
random.seed(random_seed)
def generate_df_for_device(n_observations, n_metrics, device_id, geo_id, topology_id, cohort_id):
df = pd.DataFrame(np.random.randn(n_observations,n_metrics), index=pd.date_range('2020', freq='H', periods=n_observations))
df.columns = [f'metrik_{c}' for c in df.columns]
df['geospatial_id'] = geo_id
df['topology_id'] = topology_id
df['cohort_id'] = cohort_id
df['device_id'] = device_id
return df
def generate_multi_device(n_observations, n_metrics, n_devices, cohort_levels, topo_levels):
results = []
for i in range(1, n_devices +1):
#print(i)
r = random.randrange(1, n_devices)
cohort = random.randrange(1, cohort_levels)
topo = random.randrange(1, topo_levels)
df_single_dvice = generate_df_for_device(n_observations, n_metrics, i, r, topo, cohort)
results.append(df_single_dvice)
#print(r)
return pd.concat(results)
# hourly data, 1 week of data
n_observations = 7 * 24
n_metrics = 3
n_devices = 20
cohort_levels = 3
topo_levels = 5
df = generate_multi_device(n_observations, n_metrics, n_devices, cohort_levels, topo_levels)
df = df.sort_index()
df = df.reset_index().rename(columns={'index':'hour'})
df['dt'] = df.hour.dt.date
and labels:
marker_labels = pd.DataFrame({'cohort_id':[1,1, 1], 'marker_type':['a', 'b', 'a'], 'start':['2020-01-2', '2020-01-04 05', '2020-01-06'], 'end':[np.nan, '2020-01-05 16', np.nan]})
marker_labels['start'] = pd.to_datetime(marker_labels['start'])
marker_labels['end'] = pd.to_datetime(marker_labels['end'])
marker_labels.loc[marker_labels['end'].isnull(), 'end'] = marker_labels.start + pd.Timedelta(days=1) - pd.Timedelta(seconds=1)
marker_labels
A detailed Jupyter notebook with example data and current plotting code can be found here: https://github.com/geoHeil/plotting_tricks
edit
Assuming we perform a LEFT join for the labels of the time segments:
merged_res = (df.reset_index()
.merge(marker_labels, on='cohort_id', how='left')
.query('start <= hour <= end')
.set_index('index')
.reindex(df.index)
)
merged_res = merged_res.combine_first(df)
merged_res.marker_type = merged_res.marker_type.fillna('no_labels_reported')
with plotting code of:
for cohort_id in sorted(merged_res.cohort_id.unique()):
print(cohort_id)
figsize = (25, 9)
fig, ax = plt.subplots(figsize=figsize)
a1 = sns.lineplot(x=merged_res['hour'].dt.hour, y='metrik_0', hue='marker_type', units='dt', style='dt', estimator=None, data=merged_res[(merged_res.cohort_id == cohort_id)], ax=ax)
handles, labels = a1.get_legend_handles_labels()
a1.legend(handles=handles[1:], labels=labels[1:], loc='center', bbox_to_anchor=(0.5, -0.25), ncol=6, fontsize=20)
plt.title(f'cohort_id: {cohort_id}', fontsize=35)
plt.xlabel('hour of the day', fontsize=35)
plt.ylabel('metrik_0', fontsize=35)
plt.show()
results in:
However:
- this is still rather chaotic
- individual time-series of the devices are aggregated/averaged in the visualization
The best thing so far seems to be hvplot:
merged_res['hour_time'] = merged_res['hour'].dt.hour
merged_res.device_id = merged_res.device_id.astype(str)
for cohort_id in sorted(merged_res.cohort_id.unique()):
print(cohort_id)
current_plot = merged_res[merged_res.cohort_id == cohort_id].set_index(['hour_time'])[['metrik_0', 'marker_type', 'device_id', 'dt']].hvplot(by=['marker_type'],
hover_cols=['dt', 'device_id'], width=width, height=height).opts(active_tools=['box_zoom'])
display(current_plot)
resulting in:
As I am still not fully satisfied - I will leave it open (unanswered) to see if someone comes up with a better solution.
In particular, I do not like that this displays lines - probably points would be better. I.e. as something is changing from no label to having a label the timeseries is not drawn continously (=changing color) but in fact jumping (=a new different line is created. So using points would also only be a workaround (but probably better than having the jumping lines.