stress_at_work_analysis/features/esm.py

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 esm 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)
    )
    df_esm_json = pd.json_normalize(df_esm["esm_json"]).drop(
        columns=["esm_trigger"]
    )  # The esm_trigger column is already present in the main df.
    return df_esm.join(df_esm_json)