Accept nested feature configuration.

To do this, pass a dict as parameters to SensorFeatures class, rather than actually reading the object from yaml file.

exploration/ex_ml_pipeline.py

@@ -158,7 +158,11 @@ from machine_learning import pipeline
 
 # %%
 with open("../machine_learning/config/minimal_features.yaml", "r") as file:
-    sensor_features = yaml.full_load(file)
+    sensor_features_params = yaml.safe_load(file)
+
+# %%
+sensor_features = pipeline.SensorFeatures(**sensor_features_params)
+sensor_features.data_types
 
 # %%
 sensor_features.get_sensor_data("proximity")
@@ -174,3 +178,5 @@ sensor_features.calculate_features()
 
 # %%
 sensor_features.get_features("proximity", "all")
+
+# %%

machine_learning/config/minimal_features.yaml

@@ -1,5 +1,5 @@
---- !SensorFeatures
 grouping_variable: date_lj
-data_types: [proximity]
+features:
-feature_names: all
+  proximity:
+    all
 participants_usernames: [nokia_0000003]

machine_learning/pipeline.py

@@ -1,7 +1,7 @@
 import datetime
+from collections.abc import Collection
 
 import pandas as pd
-import yaml
 from sklearn.model_selection import cross_val_score
 
 import participants.query_db
@@ -9,21 +9,16 @@ from features import communication, esm, helper, proximity
 from machine_learning import QUESTIONNAIRE_IDS, QUESTIONNAIRE_IDS_RENAME
 
 
-class SensorFeatures(yaml.YAMLObject):
+class SensorFeatures:
-    yaml_tag = u"!SensorFeatures"
-
     def __init__(
         self,
-        grouping_variable,
+        grouping_variable: str,
-        data_types,
+        features: dict,
-        feature_names=None,
+        participants_usernames: Collection = None,
-        participants_usernames=None,
     ):
-        self.data_types = data_types
         self.grouping_variable = grouping_variable
 
-        if feature_names is None:
+        self.data_types = features.keys()
-            self.feature_names = []
 
         if participants_usernames is None:
             participants_usernames = participants.query_db.get_usernames(