stress_at_work_analysis/machine_learning/pipeline.py

import datetime

import pandas as pd

import participants.query_db
from features import esm, helper, proximity
from machine_learning import QUESTIONNAIRE_IDS, QUESTIONNAIRE_IDS_RENAME


class MachineLearningPipeline:
    def __init__(self, labels_questionnaire, data_types, participants_usernames=None):
        if participants_usernames is None:
            participants_usernames = participants.query_db.get_usernames(
                collection_start=datetime.date.fromisoformat("2020-08-01")
            )
        self.participants_usernames = participants_usernames
        self.labels_questionnaire = labels_questionnaire
        self.data_types = data_types

        self.df_esm = pd.DataFrame()
        self.df_esm_preprocessed = pd.DataFrame()
        self.df_esm_interest = pd.DataFrame()
        self.df_esm_clean = pd.DataFrame()

        self.df_proximity = pd.DataFrame()

        self.df_full_data_daily_means = pd.DataFrame()
        self.df_esm_daily_means = pd.DataFrame()
        self.df_proximity_daily_counts = pd.DataFrame()

    def get_labels(self):
        self.df_esm = esm.get_esm_data(self.participants_usernames)
        self.df_esm_preprocessed = esm.preprocess_esm(self.df_esm)
        if self.labels_questionnaire == "PANAS":
            self.df_esm_interest = self.df_esm_preprocessed[
                (
                    self.df_esm_preprocessed["questionnaire_id"]
                    == QUESTIONNAIRE_IDS.get("PANAS").get("PA")
                )
                | (
                    self.df_esm_preprocessed["questionnaire_id"]
                    == QUESTIONNAIRE_IDS.get("PANAS").get("NA")
                )
            ]
        self.df_esm_clean = esm.clean_up_esm(self.df_esm_interest)

    def get_sensor_data(self):
        if "proximity" in self.data_types:
            self.df_proximity = proximity.get_proximity_data(
                self.participants_usernames
            )
            self.df_proximity = helper.get_date_from_timestamp(self.df_proximity)
            self.df_proximity = proximity.recode_proximity(self.df_proximity)

    def aggregate_daily(self):
        self.df_esm_daily_means = (
            self.df_esm_clean.groupby(["participant_id", "date_lj", "questionnaire_id"])
            .esm_user_answer_numeric.agg("mean")
            .reset_index()
            .rename(columns={"esm_user_answer_numeric": "esm_numeric_mean"})
        )
        self.df_esm_daily_means = (
            self.df_esm_daily_means.pivot(
                index=["participant_id", "date_lj"],
                columns="questionnaire_id",
                values="esm_numeric_mean",
            )
            .reset_index(col_level=1)
            .rename(columns=QUESTIONNAIRE_IDS_RENAME)
            .set_index(["participant_id", "date_lj"])
        )
        self.df_full_data_daily_means = self.df_esm_daily_means.copy()
        if "proximity" in self.data_types:
            self.df_proximity_daily_counts = proximity.count_proximity(
                self.df_proximity, ["participant_id", "date_lj"]
            )
            self.df_full_data_daily_means = self.df_full_data_daily_means.join(
                self.df_proximity_daily_counts
            )