rapids/src/features/google_activity_recognition.py

63 lines
3.1 KiB
Python
Raw Normal View History

import pandas as pd
import numpy as np
import scipy.stats as stats
2019-11-28 00:06:31 +01:00
from features_utils import splitOvernightEpisodes, splitMultiSegmentEpisodes
2019-11-18 20:22:08 +01:00
day_segment = snakemake.params["segment"]
metrics = snakemake.params["metrics"]
2019-11-18 20:22:08 +01:00
#Read csv into a pandas dataframe
2019-11-28 00:06:31 +01:00
data = pd.read_csv(snakemake.input['gar_events'],parse_dates=['local_date_time'])
ar_deltas = pd.read_csv(snakemake.input['gar_deltas'],parse_dates=["local_start_date_time", "local_end_date_time", "local_start_date", "local_end_date"])
columns = list("ar_" + str(day_segment) + "_" + column for column in metrics)
2019-11-28 00:06:31 +01:00
2019-11-12 20:48:19 +01:00
if data.empty:
2019-11-18 20:22:08 +01:00
finalDataset = pd.DataFrame(columns = columns)
2019-11-12 20:48:19 +01:00
else:
finalDataset = pd.DataFrame()
2019-11-28 00:06:31 +01:00
ar_deltas = splitOvernightEpisodes(ar_deltas, [],['activity'])
if day_segment != "daily":
ar_deltas = splitMultiSegmentEpisodes(ar_deltas, day_segment, [])
2019-11-12 20:48:19 +01:00
data.local_date_time = pd.to_datetime(data.local_date_time)
resampledData = data.set_index(data.local_date_time)
resampledData.drop(columns=['local_date_time'],inplace=True)
2019-11-18 20:22:08 +01:00
if(day_segment!='daily'):
resampledData = resampledData.loc[resampledData['local_day_segment'] == str(day_segment)]
2019-11-12 20:48:19 +01:00
if resampledData.empty:
finalDataset = pd.DataFrame(columns = columns)
else:
#Finding the count of samples of the day
if("count" in metrics):
finalDataset["ar_" + str(day_segment) + "_count"] = resampledData['activity_type'].resample('D').count()
#Finding most common activity of the day
if("mostcommonactivity" in metrics):
finalDataset["ar_" + str(day_segment) + "_mostcommonactivity"] = resampledData['activity_type'].resample('D').apply(lambda x:stats.mode(x)[0])
#finding different number of activities during a day
if("countuniqueactivities" in metrics):
finalDataset["ar_" + str(day_segment) + "_countuniqueactivities"] = resampledData['activity_type'].resample('D').nunique()
#finding Number of times activity changed
if("activitychangecount" in metrics):
resampledData['activity_type_shift'] = resampledData['activity_type'].shift().fillna(resampledData['activity_type'].head(1))
resampledData['different_activity'] = np.where(resampledData['activity_type']!=resampledData['activity_type_shift'],1,0)
finalDataset["ar_" + str(day_segment) + "_activitychangecount"] = resampledData['different_activity'].resample('D').sum()
deltas_metrics = {'sumstationary':['still','tilting'],
'summobile':['on_foot','running','on_bicycle'],
'sumvehicle':['in_vehicle']}
for column, activity_labels in deltas_metrics.items():
if column in metrics:
finalDataset["ar_" + str(day_segment) + "_"+str(column)] = (ar_deltas[ar_deltas['activity'].isin(pd.Series(activity_labels))]
.groupby(['local_start_date'])['time_diff']
.agg({"ar_" + str(day_segment) + "_" + str(column) :'sum'}))
2019-11-28 00:06:31 +01:00
2019-11-18 20:22:08 +01:00
finalDataset.index.names = ['local_date']
finalDataset.to_csv(snakemake.output[0])