Add vibrations entityset (#18)

* add vibrations entityset

* add example vibrations

* fix lint

* modify entityset function

* entityset

* fix sphinx

* add lxml_html_clean to fix nsphinx issue

---------

Co-authored-by: Sara Pido <sarapid@dai-desk34.lids.mit.edu>
Co-authored-by: SaraPido <sara.pido@mail.polimi.it>
Co-authored-by: Raymond Pan <rpan@dai-desk34.lids.mit.edu>

Author: 4 people

docs/conf.py

@@ -80,7 +80,7 @@
 #
 # This is also used if you do content translation via gettext catalogs.
 # Usually you set "language" from the command line for these cases.
-language = None
+language = 'en'
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.

notebooks/data/vibrations.csv

@@ -0,0 +1,5 @@
+COD_ELEMENT,signal_id,timestamp,xvalues,yvalues
+0,S1,2022-01-02 13:21:01,"[2022-01-02 13:21:01, 2022-01-02 13:41:01, 2022-01-02 14:01:01]","[0.5, 0.4, 0.2]"
+0,S2,2022-03-08 11:00:00,"[2022-03-08 11:00:00, 2022-03-08 11:10:00, 2022-03-08 11:20:00]","[10, 10, 9]"
+1,S1,2022-01-02 13:21:01,"[2022-01-02 13:21:01, 2022-01-02 13:41:01, 2022-01-02 14:01:01]","[0.9, 0.95, 0.8]"
+1,S2,2022-03-08 11:00:00,"[2022-03-08 11:00:00, 2022-03-08 11:10:00, 2022-03-08 11:20:00]","[15, 11, 9]"

setup.py

@@ -48,6 +48,7 @@
 
     # docs
     'docutils>=0.12,<0.18',
+    'lxml_html_clean>=0.2.2',
     'm2r2>=0.2.5,<0.3',
     'nbsphinx>=0.5.0,<0.7',
     'Sphinx>=3,<3.3',

zephyr_ml/entityset.py

@@ -1,3 +1,5 @@
+from itertools import chain
+
 import featuretools as ft
 
 from zephyr_ml.metadata import get_mapped_kwargs
@@ -73,10 +75,47 @@ def create_scada_entityset(dfs, new_kwargs_mapping=None):
     return es
 
 
+def create_vibrations_entityset(dfs, new_kwargs_mapping=None):
+    '''Generate an entityset for Vibrations data datasets
+
+    Args:
+        data_paths (dict): Dictionary mapping entity names ('alarms', 'notifications',
+            'stoppages', 'work_orders', 'vibrations', 'turbines') to the pandas
+            dataframe for that entity. Optionally 'pidata' and 'scada' can be included.
+    '''
+    entities = ['vibrations']
+
+    pidata_kwargs, scada_kwargs = {}, {}
+    if 'pidata' in dfs:
+        pidata_kwargs = get_mapped_kwargs('pidata', new_kwargs_mapping)
+        entities.append('pidata')
+    if 'scada' in dfs:
+        pidata_kwargs = get_mapped_kwargs('scada', new_kwargs_mapping)
+        entities.append('scada')
+
+    entity_kwargs = {
+        **pidata_kwargs,
+        **scada_kwargs,
+        **get_mapped_kwargs('vibrations', new_kwargs_mapping),
+    }
+    _validate_data(dfs, entities, entity_kwargs)
+
+    es = _create_entityset(dfs, 'vibrations', entity_kwargs)
+    es.id = 'Vibrations data'
+
+    return es
+
+
 def _validate_data(dfs, es_type, es_kwargs):
     '''Validate data by checking for required columns in each entity
     '''
-    entities = set(['alarms', 'stoppages', 'work_orders', 'notifications', 'turbines', es_type])
+    if not isinstance(es_type, list):
+        es_type = [es_type]
+
+    entities = set(chain(
+        ['alarms', 'stoppages', 'work_orders', 'notifications', 'turbines', *es_type]
+    ))
+
     if set(dfs.keys()) != entities:
         missing = entities.difference(set(dfs.keys()))
         extra = set(dfs.keys()).difference(entities)

zephyr_ml/metadata.py

@@ -126,6 +126,58 @@
             'TIMESTAMP': 'datetime',
             'COD_ELEMENT': 'categorical'
         }
+    },
+    'vibrations': {
+        'index': '_index',
+        'make_index': True,
+        'time_index': 'timestamp',
+        'logical_types': {
+            'COD_ELEMENT': 'categorical',
+            'turbine_id': 'categorical',
+            'signal_id': 'categorical',
+            'timestamp': 'datetime',
+            'sensorName': 'categorical',
+            'sensorType': 'categorical',
+            'sensorSerial': 'integer_nullable',
+            'siteName': 'categorical',
+            'turbineName': 'categorical',
+            'turbineSerial': 'integer_nullable',
+            'configurationName': 'natural_language',
+            'softwareVersion': 'categorical',
+            'rpm': 'double',
+            'rpmStatus': 'natural_language',
+            'duration': 'natural_language',
+            'condition': 'categorical',
+            'maskTime': 'datetime',
+            'Mask Status': 'natural_language',
+            'System Serial': 'categorical',
+            'WPS-ActivePower-Average': 'double',
+            'WPS-ActivePower-Minimum': 'double',
+            'WPS-ActivePower-Maximum': 'double',
+            'WPS-ActivePower-Deviation': 'double',
+            'WPS-ActivePower-StartTime': 'datetime',
+            'WPS-ActivePower-StopTime': 'datetime',
+            'WPS-ActivePower-Counts': 'natural_language',
+            'Measured RPM': 'double',
+            'WPS-ActivePower': 'double',
+            'WPS-Gearoiltemperature': 'double',
+            'WPS-GeneratorRPM': 'double',
+            'WPS-PitchReference': 'double',
+            'WPS-RotorRPM': 'double',
+            'WPS-Windspeed': 'double',
+            'WPS-YawAngle': 'double',
+            'overload warning': 'categorical',
+            'bias warning': 'categorical',
+            'bias voltage': 'double',
+            'xValueOffset': 'double',
+            'xValueDelta': 'double',
+            'xValueUnit': 'categorical',
+            'yValueUnit': 'categorical',
+            'TotalCount-RPM0': 'double',
+            'TotalCount-RPM1': 'double',
+            'TotalCount-RPM2': 'double',
+            'TotalCount-RPM3': 'double'
+        }
     }
 }