Merge ambient sensors into one file.

Explore barometer sensor data for one phone.

exploration/expl_ambient.py

@@ -6,7 +6,7 @@
 #       extension: .py
 #       format_name: percent
 #       format_version: '1.3'
-#       jupytext_version: 1.11.4
+#       jupytext_version: 1.12.0
 #   kernelspec:
 #     display_name: straw2analysis
 #     language: python
@@ -32,18 +32,18 @@ import participants.query_db
 TZ_LJ = timezone("Europe/Ljubljana")
 
 # %%
-from features.light import *
+from features.ambient import *
 
 # %% [markdown]
-# # Basic characteristics
+# # Light
 
 # %%
-df_light_nokia = get_light_data(["nokia_0000003"])
+df_light_nokia = get_ambient_data(["nokia_0000003"], "light")
 print(df_light_nokia)
 
 # %%
 participants_inactive_usernames = participants.query_db.get_usernames()
-df_light_inactive = get_light_data(participants_inactive_usernames)
+df_light_inactive = get_ambient_data(participants_inactive_usernames, "light")
 
 # %%
 df_light_inactive.accuracy.value_counts()
@@ -166,3 +166,31 @@ sns.displot(data=df_light_participants, x="std_rel", binwidth=0.005)
 # Relative variability is homogeneous.
 #
 # This means that light data needs to be standardized. Min/max standardization would probably fit best.
+
+# %% [markdown]
+# # Barometer
+
+# %% [markdown]
+# ## Barometer sensor
+
+# %%
+df_barometer_sensor_samsung = get_ambient_data(["samsung_0000002"], "barometer_sensor")
+df_barometer_sensor_samsung.shape
+
+# %% [markdown]
+# Even though we have many values for this sensor, they are all repeated as seen below.
+
+# %%
+barometer_sensor_cols = df_barometer_sensor_samsung.columns.to_list()
+barometer_sensor_cols.remove("id")
+barometer_sensor_cols.remove("_id")
+barometer_sensor_cols.remove("timestamp")
+barometer_sensor_cols.remove("device_id")
+print(df_barometer_sensor_samsung.drop_duplicates(subset=barometer_sensor_cols))
+
+# %%
+## Barometer data
+
+# %%
+df_barometer_sensor_samsung = get_ambient_data(["samsung_0000002"], "barometer")
+print(df_barometer_sensor_samsung)

features/ambient.py

@@ -0,0 +1,62 @@
+from collections.abc import Collection
+
+import pandas as pd
+
+from config.models import Barometer, BarometerSensor, LightSensor, Participant, Temperature, TemperatureSensor
+from setup import db_engine, session
+
+
+def get_ambient_data(usernames: Collection, sensor=None) -> pd.DataFrame:
+    """
+    Read the data from any of the ambient sensor tables and return it in a dataframe.
+
+    Parameters
+    ----------
+    usernames: Collection
+        A list of usernames to put into the WHERE condition.
+    sensor: str
+        One of: barometer, barometer_sensor, light, temperature, temperature_sensor.
+        Here, the _sensor tables describe the phone sensors, such as their range, dela, resolution, vendor etc.,
+        whereas barometer, light, and temperature describe the measured characteristics of the environment.
+
+    Returns
+    -------
+    df_ambient: pd.DataFrame
+        A dataframe of ambient sensor data.
+    """
+    if sensor == "barometer":
+        query_ambient = (
+            session.query(Barometer, Participant.username)
+            .filter(Participant.id == Barometer.participant_id)
+        )
+    elif sensor == "barometer_sensor":
+        query_ambient = (
+            session.query(BarometerSensor, Participant.username)
+                .filter(Participant.id == BarometerSensor.participant_id)
+        )
+    elif sensor == "light":
+        query_ambient = (
+            session.query(LightSensor, Participant.username)
+            .filter(Participant.id == LightSensor.participant_id)
+        )
+    # Note that LightSensor and its light_sensor table are incorrectly named.
+    # In this table, we actually find light data, i.e. double_light_lux, the ambient luminance in lux,
+    # and NOT light sensor data (its range, dela, resolution, vendor etc.) as the name suggests.
+    # We do not have light sensor data saved in the database.
+    elif sensor == "temperature":
+        query_ambient = (
+            session.query(Temperature, Participant.username)
+            .filter(Participant.id == Temperature.participant_id)
+        )
+    elif sensor == "temperature_sensor":
+        query_ambient = (
+            session.query(TemperatureSensor, Participant.username)
+            .filter(Participant.id == TemperatureSensor.participant_id)
+        )
+    else:
+        raise KeyError("Specify one of the ambient sensors: barometer, barometer_sensor, light, temperature, or temperature_sensor.")
+
+    query_ambient = query_ambient.filter(Participant.username.in_(usernames))
+    with db_engine.connect() as connection:
+        df_ambient = pd.read_sql(query_ambient.statement, connection)
+    return df_ambient

features/light.py

@@ -1,30 +0,0 @@
-from collections.abc import Collection
-
-import pandas as pd
-
-from config.models import LightSensor, Participant
-from setup import db_engine, session
-
-
-def get_light_data(usernames: Collection) -> pd.DataFrame:
-    """
-    Read the data from the light sensor table and return it in a dataframe.
-
-    Parameters
-    ----------
-    usernames: Collection
-        A list of usernames to put into the WHERE condition.
-
-    Returns
-    -------
-    df_light: pd.DataFrame
-        A dataframe of light data.
-    """
-    query_light = (
-        session.query(LightSensor, Participant.username)
-        .filter(Participant.id == LightSensor.participant_id)
-        .filter(Participant.username.in_(usernames))
-    )
-    with db_engine.connect() as connection:
-        df_light = pd.read_sql(query_light.statement, connection)
-    return df_light