matrixprofile / stumpy / mulltiple time-series handling / pandas UDF per group (no aggregation to scalar

foo.py

sure:

%pylab inline
import stumpy

import pandas as pd
import numpy as np

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 = 1
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.head()
m=30
mp_T1 = stumpy.stump(df_single_device['metrik_0'], m)

mp_T1 = stumpy.stump(df_single_device['metrik_0'], m)

is the example to apply the UDF to all the values at once (but this is not the desired result).
I certainly could iterate over all the results - as outlined beforehand. But I would want to vectorize this iterating procedure.