Add a method to transform ESM data and the test.

config/environment.yml

@@ -14,6 +14,7 @@ dependencies:
   - pandas
   - psycopg2
   - python-dotenv
+  - pytz
   - seaborn
   - sqlalchemy
   - tabulate

features/esm.py

@@ -0,0 +1,46 @@
+import datetime
+from collections.abc import Collection
+
+import pandas as pd
+from pytz import timezone
+
+from config.models import ESM, Participant
+from setup import db_engine, session
+
+TZ_LJ = timezone("Europe/Ljubljana")
+
+
+def get_esm_data(usernames: Collection) -> pd.DataFrame:
+    """
+    Read the data from the esm table and return it in a dataframe.
+
+    Parameters
+    ----------
+    usernames: Collection
+        A list of usernames to put into the WHERE condition.
+
+    Returns
+    -------
+    df_esm: pd.DataFrame
+        A dataframe of call data.
+    """
+    query_esm = (
+        session.query(ESM, Participant.username)
+        .filter(Participant.id == ESM.participant_id)
+        .filter(Participant.username.in_(usernames))
+    )
+    with db_engine.connect() as connection:
+        df_esm = pd.read_sql(query_esm.statement, connection)
+    return df_esm
+
+
+def preprocess_esm(df_esm: pd.DataFrame) -> pd.DataFrame:
+    df_esm["datetime_lj"] = df_esm["double_esm_user_answer_timestamp"].apply(
+        lambda x: datetime.datetime.fromtimestamp(x / 1000.0, tz=TZ_LJ)
+    )
+    #TODO: Deal with ESM_JSON
+    #(esm_json_b = purrr::map(esm_json, jsonlite::fromJSON),
+                  # questionnaire_id = map_int(esm_json_b, "questionnaire_id", .default=NA),
+                  # esm_type = map_int(esm_json_b, "esm_type", .default=NA),
+                  # esm_question = map_chr(esm_json_b, "esm_instructions", .default=NA))
+    return df_esm

test/test_esm.py

@@ -0,0 +1,20 @@
+import unittest
+
+import numpy as np
+import pandas as pd
+from numpy.random import default_rng
+from pandas.testing import assert_series_equal
+
+from features.esm import preprocess_esm
+
+
+class EsmFeatures(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        cls.esm = pd.DataFrame(
+            {"double_esm_user_answer_timestamp": [1622127860000, 1622129860000]}
+        )
+
+    def test_preprocess_esm(self):
+        self.esm_processed = preprocess_esm(self.esm)
+        print(self.esm_processed)