Update Fitbit HR feature name
Meng Li
parent
d3241c79f1
commit
10384204a1
|
|
@ -18,26 +18,26 @@ def statsFeatures(heartrate_data, features, features_type, heartrate_features):
|
|||
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)
|
||||
if "intradaysum" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_intradaysum" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].sum()
|
||||
if "intradaymax" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_intradaymax" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].max()
|
||||
if "intradaymin" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_intradaymin" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].min()
|
||||
if "intradayavg" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_intradayavg" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].mean()
|
||||
if "intradaymedian" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_intradaymedian" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].median()
|
||||
if "intradaymode" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_intradaymode" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].agg(lambda x: pd.Series.mode(x)[0])
|
||||
if "intradaystd" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_intradaystd" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].std()
|
||||
if "intradaydiffmaxmode" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_intradaydiffmaxmode" + 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 "intradaydiffminmode" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_intradaydiffminmode" + 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 "intradayentropy" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_intradayentropy" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].agg(entropy)
|
||||
|
||||
return heartrate_features
|
||||
|
||||
|
|
@ -54,8 +54,8 @@ def extractHRFeaturesFromIntradayData(heartrate_intraday_data, features, day_seg
|
|||
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)):
|
||||
heartrate_zone = heartrate_intraday_data[heartrate_intraday_data["heartrate_zone"] == feature_name[9:-4]]
|
||||
for feature_name in list(set(["intradayminutesonoutofrangezone", "intradayminutesonfatburnzone", "intradayminutesoncardiozone", "intradayminutesonpeakzone"]) & set(features)):
|
||||
heartrate_zone = heartrate_intraday_data[heartrate_intraday_data["heartrate_zone"] == feature_name[17:-4]]
|
||||
heartrate_intraday_features["heartrate_rapids_" + feature_name] = heartrate_zone.groupby(["local_segment"])["device_id"].count() / num_rows_per_minute
|
||||
heartrate_intraday_features.fillna(value={"heartrate_rapids_" + feature_name: 0}, inplace=True)
|
||||
heartrate_intraday_features.reset_index(inplace=True)
|
||||
|
|
@ -67,9 +67,9 @@ def rapids_features(sensor_data_files, day_segment, provider, filter_data_by_seg
|
|||
|
||||
heartrate_intraday_data = pd.read_csv(sensor_data_files["sensor_data"])
|
||||
|
||||
requested_intraday_features = provider["FEATURES"]
|
||||
requested_intraday_features = ["intraday" + x for x in provider["FEATURES"]]
|
||||
# name of the features this function can compute
|
||||
base_intraday_features_names = ["maxhr", "minhr", "avghr", "medianhr", "modehr", "stdhr", "diffmaxmodehr", "diffminmodehr", "entropyhr", "minutesonoutofrangezone", "minutesonfatburnzone", "minutesoncardiozone", "minutesonpeakzone"]
|
||||
base_intraday_features_names = ["intradaymaxhr", "intradayminhr", "intradayavghr", "intradaymedianhr", "intradaymodehr", "intradaystdhr", "intradaydiffmaxmodehr", "intradaydiffminmodehr", "intradayentropyhr", "intradayminutesonoutofrangezone", "intradayminutesonfatburnzone", "intradayminutesoncardiozone", "intradayminutesonpeakzone"]
|
||||
# the subset of requested features this function can compute
|
||||
intraday_features_to_compute = list(set(requested_intraday_features) & set(base_intraday_features_names))
|
||||
|
||||
|
|
|
|||
|
|
@ -18,26 +18,26 @@ def statsFeatures(heartrate_data, features, features_type, heartrate_features):
|
|||
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)
|
||||
if "summarysum" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_summarysum" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].sum()
|
||||
if "summarymax" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_summarymax" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].max()
|
||||
if "summarymin" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_summarymin" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].min()
|
||||
if "summaryavg" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_summaryavg" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].mean()
|
||||
if "summarymedian" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_summarymedian" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].median()
|
||||
if "summarymode" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_summarymode" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].agg(lambda x: pd.Series.mode(x)[0])
|
||||
if "summarystd" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_summarystd" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].std()
|
||||
if "summarydiffmaxmode" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_summarydiffmaxmode" + 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 "summarydiffminmode" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_summarydiffminmode" + 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 "summaryentropy" + features_type in features:
|
||||
heartrate_features["heartrate_rapids_summaryentropy" + features_type] = heartrate_data[["local_segment", col_name]].groupby(["local_segment"])[col_name].agg(entropy)
|
||||
|
||||
return heartrate_features
|
||||
|
||||
|
|
@ -63,9 +63,9 @@ def rapids_features(sensor_data_files, day_segment, provider, filter_data_by_seg
|
|||
|
||||
heartrate_summary_data = pd.read_csv(sensor_data_files["sensor_data"])
|
||||
|
||||
requested_summary_features = provider["FEATURES"]
|
||||
requested_summary_features = ["summary" + x for x in provider["FEATURES"]]
|
||||
# name of the features this function can compute
|
||||
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_summary_features_names = ["summarymaxrestinghr", "summaryminrestinghr", "summaryavgrestinghr", "summarymedianrestinghr", "summarymoderestinghr", "summarystdrestinghr", "summarydiffmaxmoderestinghr", "summarydiffminmoderestinghr", "summaryentropyrestinghr", "summarysumcaloriesoutofrange", "summarymaxcaloriesoutofrange", "summarymincaloriesoutofrange", "summaryavgcaloriesoutofrange", "summarymediancaloriesoutofrange", "summarystdcaloriesoutofrange", "summaryentropycaloriesoutofrange", "summarysumcaloriesfatburn", "summarymaxcaloriesfatburn", "summarymincaloriesfatburn", "summaryavgcaloriesfatburn", "summarymediancaloriesfatburn", "summarystdcaloriesfatburn", "summaryentropycaloriesfatburn", "summarysumcaloriescardio", "summarymaxcaloriescardio", "summarymincaloriescardio", "summaryavgcaloriescardio", "summarymediancaloriescardio", "summarystdcaloriescardio", "summaryentropycaloriescardio", "summarysumcaloriespeak", "summarymaxcaloriespeak", "summarymincaloriespeak", "summaryavgcaloriespeak", "summarymediancaloriespeak", "summarystdcaloriespeak", "summaryentropycaloriespeak"]
|
||||
# the subset of requested features this function can compute
|
||||
summary_features_to_compute = list(set(requested_summary_features) & set(base_summary_features_names))
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue