Update HR main.py
Meng Li
parent
daa88b8d25
commit
93055dacee
|
|
@ -266,7 +266,7 @@ FITBIT_HEARTRATE:
|
|||
RAPIDS:
|
||||
COMPUTE: False
|
||||
FEATURES:
|
||||
SUMMARY: ["restinghr"] # calories features' accuracy depend on the accuracy of the participants fitbit profile (e.g. height, weight) use these with care: ["caloriesoutofrange", "caloriesfatburn", "caloriescardio", "caloriespeak"]
|
||||
SUMMARY: ["maxrestinghr", "minrestinghr", "avgrestinghr", "medianrestinghr", "moderestinghr", "stdrestinghr", "diffmaxmoderestinghr", "diffminmoderestinghr", "entropyrestinghr"] # calories features' accuracy depend on the accuracy of the participants fitbit profile (e.g. height, weight) use these with care: ["sumcaloriesoutofrange", "maxcaloriesoutofrange", "mincaloriesoutofrange", "avgcaloriesoutofrange", "mediancaloriesoutofrange", "stdcaloriesoutofrange", "entropycaloriesoutofrange", "sumcaloriesfatburn", "maxcaloriesfatburn", "mincaloriesfatburn", "avgcaloriesfatburn", "mediancaloriesfatburn", "stdcaloriesfatburn", "entropycaloriesfatburn", "sumcaloriescardio", "maxcaloriescardio", "mincaloriescardio", "avgcaloriescardio", "mediancaloriescardio", "stdcaloriescardio", "entropycaloriescardio", "sumcaloriespeak", "maxcaloriespeak", "mincaloriespeak", "avgcaloriespeak", "mediancaloriespeak", "stdcaloriespeak", "entropycaloriespeak"]
|
||||
INTRADAY: ["maxhr", "minhr", "avghr", "medianhr", "modehr", "stdhr", "diffmaxmodehr", "diffminmodehr", "entropyhr", "minutesonoutofrangezone", "minutesonfatburnzone", "minutesoncardiozone", "minutesonpeakzone"]
|
||||
SRC_FOLDER: "rapids" # inside src/features/fitbit_heartrate
|
||||
SRC_LANGUAGE: "python"
|
||||
|
|
|
|||
|
|
@ -1,20 +1,59 @@
|
|||
import pandas as pd
|
||||
from scipy.stats import entropy
|
||||
|
||||
def statsFeatures(heartrate_data, features, features_type, heartrate_features):
|
||||
|
||||
if features_type == "hr":
|
||||
col_name = "heartrate"
|
||||
elif features_type == "restinghr":
|
||||
col_name = "heartrate_daily_restinghr"
|
||||
elif features_type == "caloriesoutofrange":
|
||||
col_name = "heartrate_daily_caloriesoutofrange"
|
||||
elif features_type == "caloriesfatburn":
|
||||
col_name = "heartrate_daily_caloriesfatburn"
|
||||
elif features_type == "caloriescardio":
|
||||
col_name = "heartrate_daily_caloriescardio"
|
||||
elif features_type == "caloriespeak":
|
||||
col_name = "heartrate_daily_caloriespeak"
|
||||
else:
|
||||
raise ValueError("features_type can only be one of ['hr', 'restinghr', 'caloriesoutofrange', 'caloriesfatburn', 'caloriescardio', 'caloriespeak'].")
|
||||
|
||||
if "sum" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_sum" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].sum()
|
||||
if "max" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_max" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].max()
|
||||
if "min" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_min" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].min()
|
||||
if "avg" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_avg" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].mean()
|
||||
if "median" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_median" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].median()
|
||||
if "mode" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_mode" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].agg(lambda x: pd.Series.mode(x)[0])
|
||||
if "std" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_std" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].std()
|
||||
if "diffmaxmode" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_diffmaxmode" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].max() - heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].agg(lambda x: pd.Series.mode(x)[0])
|
||||
if "diffminmode" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_diffminmode" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].agg(lambda x: pd.Series.mode(x)[0]) - heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].min()
|
||||
if "entropy" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_entropy" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].agg(entropy)
|
||||
|
||||
return heartrate_features
|
||||
|
||||
def extractHRFeaturesFromSummaryData(heartrate_summary_data, summary_features):
|
||||
heartrate_summary_data.set_index("local_segment", inplace=True)
|
||||
heartrate_summary_features = pd.DataFrame()
|
||||
if "restinghr" in summary_features:
|
||||
heartrate_summary_features["heartrate_rapids_restinghr"] = heartrate_summary_data["heartrate_daily_restinghr"]
|
||||
|
||||
# get stats of resting heartrate
|
||||
heartrate_summary_features = statsFeatures(heartrate_summary_data, summary_features, "restinghr", heartrate_summary_features)
|
||||
|
||||
# get stats of calories features
|
||||
# calories features might be inaccurate: they depend on users' fitbit profile (weight, height, etc.)
|
||||
if "caloriesoutofrange" in summary_features:
|
||||
heartrate_summary_features["heartrate_rapids_caloriesoutofrange"] = heartrate_summary_data["heartrate_daily_caloriesoutofrange"]
|
||||
if "caloriesfatburn" in summary_features:
|
||||
heartrate_summary_features["heartrate_rapids_caloriesfatburn"] = heartrate_summary_data["heartrate_daily_caloriesfatburn"]
|
||||
if "caloriescardio" in summary_features:
|
||||
heartrate_summary_features["heartrate_rapids_caloriescardio"] = heartrate_summary_data["heartrate_daily_caloriescardio"]
|
||||
if "caloriespeak" in summary_features:
|
||||
heartrate_summary_features["heartrate_rapids_caloriespeak"] = heartrate_summary_data["heartrate_daily_caloriespeak"]
|
||||
heartrate_summary_features = statsFeatures(heartrate_summary_data, summary_features, "caloriesoutofrange", heartrate_summary_features)
|
||||
heartrate_summary_features = statsFeatures(heartrate_summary_data, summary_features, "caloriesfatburn", heartrate_summary_features)
|
||||
heartrate_summary_features = statsFeatures(heartrate_summary_data, summary_features, "caloriescardio", heartrate_summary_features)
|
||||
heartrate_summary_features = statsFeatures(heartrate_summary_data, summary_features, "caloriespeak", heartrate_summary_features)
|
||||
|
||||
heartrate_summary_features.reset_index(inplace=True)
|
||||
|
||||
return heartrate_summary_features
|
||||
|
|
@ -29,24 +68,7 @@ def extractHRFeaturesFromIntradayData(heartrate_intraday_data, features, day_seg
|
|||
heartrate_intraday_features = pd.DataFrame()
|
||||
|
||||
# get stats of heartrate
|
||||
if "maxhr" in features:
|
||||
heartrate_intraday_features["heartrate_rapids_maxhr"] = heartrate_intraday_data[["local_segment", "heartrate"]].groupby(["local_segment"])["heartrate"].max()
|
||||
if "minhr" in features:
|
||||
heartrate_intraday_features["heartrate_rapids_minhr"] = heartrate_intraday_data[["local_segment", "heartrate"]].groupby(["local_segment"])["heartrate"].min()
|
||||
if "avghr" in features:
|
||||
heartrate_intraday_features["heartrate_rapids_avghr"] = heartrate_intraday_data[["local_segment", "heartrate"]].groupby(["local_segment"])["heartrate"].mean()
|
||||
if "medianhr" in features:
|
||||
heartrate_intraday_features["heartrate_rapids_medianhr"] = heartrate_intraday_data[["local_segment", "heartrate"]].groupby(["local_segment"])["heartrate"].median()
|
||||
if "modehr" in features:
|
||||
heartrate_intraday_features["heartrate_rapids_modehr"] = heartrate_intraday_data[["local_segment", "heartrate"]].groupby(["local_segment"])["heartrate"].agg(lambda x: pd.Series.mode(x)[0])
|
||||
if "stdhr" in features:
|
||||
heartrate_intraday_features["heartrate_rapids_stdhr"] = heartrate_intraday_data[["local_segment", "heartrate"]].groupby(["local_segment"])["heartrate"].std()
|
||||
if "diffmaxmodehr" in features:
|
||||
heartrate_intraday_features["heartrate_rapids_diffmaxmodehr"] = heartrate_intraday_data[["local_segment", "heartrate"]].groupby(["local_segment"])["heartrate"].max() - heartrate_intraday_data[["local_segment", "heartrate"]].groupby(["local_segment"])["heartrate"].agg(lambda x: pd.Series.mode(x)[0])
|
||||
if "diffminmodehr" in features:
|
||||
heartrate_intraday_features["heartrate_rapids_diffminmodehr"] = heartrate_intraday_data[["local_segment", "heartrate"]].groupby(["local_segment"])["heartrate"].agg(lambda x: pd.Series.mode(x)[0]) - heartrate_intraday_data[["local_segment", "heartrate"]].groupby(["local_segment"])["heartrate"].min()
|
||||
if "entropyhr" in features:
|
||||
heartrate_intraday_features["heartrate_rapids_entropyhr"] = heartrate_intraday_data[["local_segment", "heartrate"]].groupby(["local_segment"])["heartrate"].agg(entropy)
|
||||
heartrate_intraday_features = statsFeatures(heartrate_intraday_data, features, "hr", heartrate_intraday_features)
|
||||
|
||||
# get number of minutes in each heart rate zone
|
||||
for feature_name in list(set(["minutesonoutofrangezone", "minutesonfatburnzone", "minutesoncardiozone", "minutesonpeakzone"]) & set(features)):
|
||||
|
|
@ -66,29 +88,32 @@ def rapids_features(sensor_data_files, day_segment, provider, filter_data_by_seg
|
|||
requested_summary_features = provider["FEATURES"]["SUMMARY"]
|
||||
requested_intraday_features = provider["FEATURES"]["INTRADAY"]
|
||||
# name of the features this function can compute
|
||||
base_summary_features_names = ["restinghr", "caloriesoutofrange", "caloriesfatburn", "caloriescardio", "caloriespeak"]
|
||||
base_summary_features_names = ["maxrestinghr", "minrestinghr", "avgrestinghr", "medianrestinghr", "moderestinghr", "stdrestinghr", "diffmaxmoderestinghr", "diffminmoderestinghr", "entropyrestinghr", "sumcaloriesoutofrange", "maxcaloriesoutofrange", "mincaloriesoutofrange", "avgcaloriesoutofrange", "mediancaloriesoutofrange", "stdcaloriesoutofrange", "entropycaloriesoutofrange", "sumcaloriesfatburn", "maxcaloriesfatburn", "mincaloriesfatburn", "avgcaloriesfatburn", "mediancaloriesfatburn", "stdcaloriesfatburn", "entropycaloriesfatburn", "sumcaloriescardio", "maxcaloriescardio", "mincaloriescardio", "avgcaloriescardio", "mediancaloriescardio", "stdcaloriescardio", "entropycaloriescardio", "sumcaloriespeak", "maxcaloriespeak", "mincaloriespeak", "avgcaloriespeak", "mediancaloriespeak", "stdcaloriespeak", "entropycaloriespeak"]
|
||||
base_intraday_features_names = ["maxhr", "minhr", "avghr", "medianhr", "modehr", "stdhr", "diffmaxmodehr", "diffminmodehr", "entropyhr", "minutesonoutofrangezone", "minutesonfatburnzone", "minutesoncardiozone", "minutesonpeakzone"]
|
||||
# the subset of requested features this function can compute
|
||||
summary_features_to_compute = list(set(requested_summary_features) & set(base_summary_features_names))
|
||||
intraday_features_to_compute = list(set(requested_intraday_features) & set(base_intraday_features_names))
|
||||
|
||||
# extract features from summary data
|
||||
heartrate_summary_features = pd.DataFrame(columns=["local_segment"] + ["heartrate_rapids_" + x for x in summary_features_to_compute])
|
||||
if not heartrate_summary_data.empty:
|
||||
heartrate_summary_data = filter_data_by_segment(heartrate_summary_data, day_segment)
|
||||
|
||||
if not heartrate_summary_data.empty:
|
||||
# only keep the segments start at 00:00:00 and end at 23:59:59
|
||||
datetime_start_regex = "[0-9]{4}[\\-|\\/][0-9]{2}[\\-|\\/][0-9]{2} 00:00:00"
|
||||
datetime_end_regex = "[0-9]{4}[\\-|\\/][0-9]{2}[\\-|\\/][0-9]{2} 23:59:59"
|
||||
|
||||
segment_regex = "{}#{},{}".format(day_segment, datetime_start_regex, datetime_end_regex)
|
||||
heartrate_summary_data = heartrate_summary_data[heartrate_summary_data["local_segment"].str.match(segment_regex)]
|
||||
|
||||
if not heartrate_summary_data.empty:
|
||||
heartrate_summary_features = extractHRFeaturesFromSummaryData(heartrate_summary_data, summary_features_to_compute)
|
||||
|
||||
# extract features from intraday data
|
||||
heartrate_intraday_features = extractHRFeaturesFromIntradayData(heartrate_intraday_data, intraday_features_to_compute, day_segment, filter_data_by_segment)
|
||||
if not heartrate_summary_data.empty and day_segment == "daily" and summary_features_to_compute != []:
|
||||
# filter by segment and skipping any non-daily segment
|
||||
heartrate_summary_data = filter_data_by_segment(heartrate_summary_data, "daily")
|
||||
|
||||
datetime_start_regex = "[0-9]{4}[\\-|\\/][0-9]{2}[\\-|\\/][0-9]{2} 00:00:00"
|
||||
datetime_end_regex = "[0-9]{4}[\\-|\\/][0-9]{2}[\\-|\\/][0-9]{2} 23:59:59"
|
||||
|
||||
segment_regex = "daily#{},{}".format(datetime_start_regex, datetime_end_regex)
|
||||
heartrate_summary_data = heartrate_summary_data[heartrate_summary_data["local_segment"].str.match(segment_regex)]
|
||||
|
||||
# extract daily features from summary data
|
||||
heartrate_summary_features = extractHRFeaturesFromSummaryData(heartrate_summary_data, summary_features_to_compute)
|
||||
|
||||
# merge summary features and intraday features
|
||||
heartrate_features = heartrate_intraday_features.merge(heartrate_summary_features, on=["local_segment"], how="outer")
|
||||
else:
|
||||
heartrate_features = heartrate_intraday_features
|
||||
|
||||
# merge summary features and intraday features
|
||||
heartrate_features = heartrate_intraday_features.merge(heartrate_summary_features, on=["local_segment"], how="outer")
|
||||
|
||||
return heartrate_features
|
||||
|
|
|
|||
Loading…
Reference in New Issue