stress_at_work_analysis/test/test_esm.py

import unittest

from pandas.testing import assert_series_equal
from pyprojroot import here

from features.esm import *
from features.esm_JCQ import *


class EsmFeatures(unittest.TestCase):
    @classmethod
    def setUpClass(cls) -> None:
        cls.esm = pd.read_csv(here("data/example_esm.csv"), sep=";")
        cls.esm["esm_json"] = cls.esm["esm_json"].apply(eval)
        cls.esm_processed = preprocess_esm(cls.esm)
        cls.esm_clean = clean_up_esm(cls.esm_processed)

    def test_preprocess_esm(self):
        self.esm_processed = preprocess_esm(self.esm)
        # Check for columns which should have been extracted from esm_json.
        self.assertIn("question_id", self.esm_processed)
        self.assertIn("questionnaire_id", self.esm_processed)
        self.assertIn("esm_instructions", self.esm_processed)
        self.assertIn("esm_type", self.esm_processed)
        self.assertIn("time", self.esm_processed)
        # Check for explicitly added column.
        self.assertIn("datetime_lj", self.esm_processed)
        # All of these keys are referenced in other functions, so they are expected to be present in preprocessed ESM.
        # Since all of these are added in a single function, it should be OK to have many assert statements in one test.

    def test_classify_sessions_by_completion(self):
        self.esm_classified_sessions = classify_sessions_by_completion(
            self.esm_processed
        )
        self.assertFalse(self.esm_classified_sessions["session_response"].isna().any())
        # Test that all sessions were indeed classified.

    def test_classify_sessions_by_completion_time(self):
        self.esm_classified = classify_sessions_by_completion_time(self.esm_processed)
        session_of_interest = (
            self.esm_processed.query(
                "(device_id == '049df3f8-8541-4cf5-af2b-83f6b3f0cf4b') & (esm_session == 1)"
            )
            .sort_values("_id")
            .reset_index()
        )
        session_of_interest_reclassified = self.esm_classified.query(
            "(device_id == '049df3f8-8541-4cf5-af2b-83f6b3f0cf4b') & (esm_session == 1)"
        ).reset_index()
        self.assertEqual(session_of_interest.loc[0, "time"], "morning")
        self.assertEqual(session_of_interest_reclassified.loc[0, "time"], "daytime")
        # Check that the first (morning) session is reclassified as a daytime session.

    def test_clean_up_esm(self):
        self.assertNotIn("esm_user_answer_numeric", self.esm_processed)
        self.assertIn("esm_user_answer_numeric", self.esm_clean)

    def test_reverse_jcq_demand_control_scoring(self):
        esm_reversed = reverse_jcq_demand_control_scoring(self.esm_clean)

        self.assertEqual(
            0,
            int(
                self.esm_clean.loc[
                    self.esm_clean["question_id"] == 73, "esm_user_answer_numeric"
                ]
            ),
        )
        self.assertEqual(
            1,
            int(esm_reversed.loc[esm_reversed["question_id"] == 73, "esm_user_score"]),
        )
        # An example of a regular item: the score gets incremented by 1, to shift to 1-4 scoring.

        self.assertEqual(
            0,
            int(
                self.esm_clean.loc[
                    self.esm_clean["question_id"] == 79, "esm_user_answer_numeric"
                ]
            ),
        )
        self.assertEqual(
            4,
            int(esm_reversed.loc[esm_reversed["question_id"] == 79, "esm_user_score"]),
        )
        # An example of a reversed item.