Do not compute all features and discard not needed features later on (takes too long)

rpeaks2hrv.py

@@ -13,36 +13,6 @@ class FeatureDomain(Enum):
     NON_LINEAR = 'non_lin'
 
 
-FEATURE_COLS = {
-    FeatureDomain.TIME.value: [
-        'HRV_MeanNN', 'HRV_SDNN', 'HRV_SDANN1', 'HRV_SDNNI1', 
-        'HRV_SDANN2', 'HRV_SDNNI2', 'HRV_SDANN5', 'HRV_SDNNI5', 
-        'HRV_RMSSD', 'HRV_SDSD', 'HRV_CVNN', 'HRV_CVSD', 'HRV_MedianNN', 
-        'HRV_MadNN', 'HRV_MCVNN', 'HRV_IQRNN', 'HRV_SDRMSSD', 'HRV_Prc20NN', 'HRV_Prc80NN', 
-        'HRV_pNN50', 'HRV_pNN20', 'HRV_MinNN', 'HRV_MaxNN', 'HRV_HTI', 'HRV_TINN'],
-    FeatureDomain.FREQUENCY.value: [
-        'HRV_ULF', 'HRV_VLF', 'HRV_LF', 'HRV_HF', 'HRV_VHF', 'HRV_TP',
-       'HRV_LFHF', 'HRV_LFn', 'HRV_HFn', 'HRV_LnHF'
-       ],
-    FeatureDomain.NON_LINEAR.value: [
-        'HRV_SD1', 'HRV_SD2', 'HRV_SD1SD2', 'HRV_S', 'HRV_CSI', 'HRV_CVI',
-       'HRV_CSI_Modified', 'HRV_PIP', 'HRV_IALS', 'HRV_PSS', 'HRV_PAS',
-       'HRV_GI', 'HRV_SI', 'HRV_AI', 'HRV_PI', 'HRV_C1d', 'HRV_C1a',
-       'HRV_SD1d', 'HRV_SD1a', 'HRV_C2d', 'HRV_C2a', 'HRV_SD2d', 'HRV_SD2a',
-       'HRV_Cd', 'HRV_Ca', 'HRV_SDNNd', 'HRV_SDNNa', 'HRV_DFA_alpha1',
-       'HRV_MFDFA_alpha1_Width', 'HRV_MFDFA_alpha1_Peak',
-       'HRV_MFDFA_alpha1_Mean', 'HRV_MFDFA_alpha1_Max',
-       'HRV_MFDFA_alpha1_Delta', 'HRV_MFDFA_alpha1_Asymmetry',
-       'HRV_MFDFA_alpha1_Fluctuation', 'HRV_MFDFA_alpha1_Increment',
-       'HRV_DFA_alpha2', 'HRV_MFDFA_alpha2_Width', 'HRV_MFDFA_alpha2_Peak',
-       'HRV_MFDFA_alpha2_Mean', 'HRV_MFDFA_alpha2_Max',
-       'HRV_MFDFA_alpha2_Delta', 'HRV_MFDFA_alpha2_Asymmetry',
-       'HRV_MFDFA_alpha2_Fluctuation', 'HRV_MFDFA_alpha2_Increment',
-       'HRV_ApEn', 'HRV_SampEn', 'HRV_ShanEn', 'HRV_FuzzyEn', 'HRV_MSEn',
-       'HRV_CMSEn', 'HRV_RCMSEn', 'HRV_CD', 'HRV_HFD', 'HRV_KFD', 'HRV_LZC'
-       ]
-}
-
 
 class RPeak2HRV():
 
@@ -165,15 +135,23 @@ class RPeak2HRV():
             return data_for_pipeline
 
     def _calculate_features(self, data, feature_domains, sampling_rate):
-        # Calculate all possible features, then only keep needed
-        hrv_features = []
         for feature in feature_domains:
-            try:
-                hrv_features.extend(FEATURE_COLS[feature])
-            except KeyError:
-                raise KeyError(f"{feature} is not a supported feature domain. feature_domains may only include 'time', 'freq' and 'non_lin'.")
-        result = nk.hrv(self._convert_format(data), sampling_rate)
-        return result[hrv_features]
+            if (feature not in [item.value for item in FeatureDomain]):
+                raise KeyError(f"'{feature}' is not a supported feature domain. feature_domains may only include 'time', 'freq' and 'non_lin'.")
+        data = self._convert_format(data)
+        if FeatureDomain.TIME.value in feature_domains and FeatureDomain.FREQUENCY.value in feature_domains and FeatureDomain.NON_LINEAR.value in feature_domains:
+            return nk.hrv(data, sampling_rate)
+        else:
+            result = pd.DataFrame()
+            if FeatureDomain.TIME.value in feature_domains:
+                result = nk.hrv_time(data, sampling_rate)
+            if FeatureDomain.FREQUENCY.value in feature_domains:
+                frequency_values = nk.hrv_frequency(data, sampling_rate)
+                result = pd.concat([result, frequency_values], axis=1)
+            if FeatureDomain.NON_LINEAR.value in feature_domains:
+                nonlinear_values = nk.hrv_nonlinear(data, sampling_rate)
+                result = pd.concat([result, nonlinear_values], axis=1)
+        return result