stress_at_work_analysis/exploration/expl_esm_labels.py

# -*- coding: utf-8 -*-
# ---
# jupyter:
#   jupytext:
#     formats: ipynb,py:percent
#     text_representation:
#       extension: .py
#       format_name: percent
#       format_version: '1.3'
#       jupytext_version: 1.11.2
#   kernelspec:
#     display_name: straw2analysis
#     language: python
#     name: straw2analysis
# ---

# %%
import os
import sys

import seaborn as sns

nb_dir = os.path.split(os.getcwd())[0]
if nb_dir not in sys.path:
    sys.path.append(nb_dir)
import participants.query_db
from features.esm import *
from features.esm_JCQ import *

# %%
participants_inactive_usernames = participants.query_db.get_usernames(
    collection_start=datetime.date.fromisoformat("2020-08-01")
)
df_esm_inactive = get_esm_data(participants_inactive_usernames)

# %%
df_esm_preprocessed = preprocess_esm(df_esm_inactive)

# %% [markdown]
# # PANAS

# %%
df_esm_PANAS = df_esm_preprocessed[
    (df_esm_preprocessed["questionnaire_id"] == 8)
    | (df_esm_preprocessed["questionnaire_id"] == 9)
]
df_esm_PANAS_clean = clean_up_esm(df_esm_PANAS)

# %% [markdown]
# Group by participants, date, and subscale and calculate daily means.

# %%
df_esm_PANAS_daily_means = (
    df_esm_PANAS_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"})
)

# %% [markdown]
# Next, calculate mean, median, and standard deviation across all days for each participant.

# %%
df_esm_PANAS_summary_participant = (
    df_esm_PANAS_daily_means.groupby(["participant_id", "questionnaire_id"])
    .agg(["mean", "median", "std"])
    .reset_index(col_level=1)
)
df_esm_PANAS_summary_participant.columns = df_esm_PANAS_summary_participant.columns.get_level_values(
    1
)
df_esm_PANAS_summary_participant[
    "PANAS_subscale"
] = df_esm_PANAS_daily_means.questionnaire_id.astype("category").cat.rename_categories(
    {8.0: "PA", 9.0: "NA"}
)

# %%
sns.displot(
    data=df_esm_PANAS_summary_participant, x="mean", hue="PANAS_subscale", binwidth=0.2
)

# %%
sns.displot(
    data=df_esm_PANAS_summary_participant,
    x="median",
    hue="PANAS_subscale",
    binwidth=0.2,
)

# %%
sns.displot(
    data=df_esm_PANAS_summary_participant, x="std", hue="PANAS_subscale", binwidth=0.05
)

# %%
df_esm_PANAS_summary_participant[df_esm_PANAS_summary_participant["std"] < 0.1]

# %% [markdown]
# # Stress appraisal measure

# %%
df_esm_SAM = df_esm_preprocessed[
    (df_esm_preprocessed["questionnaire_id"] >= 87)
    & (df_esm_preprocessed["questionnaire_id"] <= 93)
]
df_esm_SAM_clean = clean_up_esm(df_esm_SAM)

# %% [markdown]
# ## Stressful events

# %%
df_esm_SAM_event = df_esm_SAM_clean[df_esm_SAM_clean["questionnaire_id"] == 87].assign(
    stressful_event=lambda x: (x.esm_user_answer_numeric > 0)
)

# %%
df_esm_SAM_daily_events = (
    df_esm_SAM_event.groupby(["participant_id", "date_lj"])
    .stressful_event.agg("mean")
    .reset_index()
    .rename(columns={"stressful_event": "SAM_event_ratio"})
)

# %% [markdown]
# Calculate the daily mean of YES (1) or NO (0) answers to the question about a stressful events. This is then the daily ratio of EMA sessions that included a stressful event.

# %%
df_esm_SAM_event_summary_participant = (
    df_esm_SAM_daily_events.groupby(["participant_id"])
    .agg(["mean", "median", "std"])
    .reset_index(col_level=1)
)
df_esm_SAM_event_summary_participant.columns = df_esm_SAM_event_summary_participant.columns.get_level_values(
    1
)

# %%
sns.displot(data=df_esm_SAM_event_summary_participant, x="mean", binwidth=0.1)

# %%
sns.displot(data=df_esm_SAM_event_summary_participant, x="std", binwidth=0.05)

# %% [markdown]
# ### Threat and challenge

# %% [markdown]
# * Example of threat: "Did this event make you feel anxious?"
# * Example of challenge: "How eager are you to tackle this event?"
# * Possible answers: 0 - Not at all, 1 - Slightly, 2 - Moderately, 3 - Considerably, 4 - Extremely

# %%
df_esm_SAM_daily = (
    df_esm_SAM_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"})
)

# %%
df_esm_SAM_daily_threat_challenge = df_esm_SAM_daily[
    (df_esm_SAM_daily["questionnaire_id"] == 88)
    | (df_esm_SAM_daily["questionnaire_id"] == 89)
]

# %%
df_esm_SAM_summary_participant = (
    df_esm_SAM_daily.groupby(["participant_id", "questionnaire_id"])
    .agg(["mean", "median", "std"])
    .reset_index(col_level=1)
)
df_esm_SAM_summary_participant.columns = df_esm_SAM_summary_participant.columns.get_level_values(
    1
)

# %%
df_esm_SAM_threat_challenge_summary_participant = df_esm_SAM_summary_participant[
    (df_esm_SAM_summary_participant["questionnaire_id"] == 88)
    | (df_esm_SAM_summary_participant["questionnaire_id"] == 89)
]
df_esm_SAM_threat_challenge_summary_participant[
    "event_subscale"
] = df_esm_SAM_threat_challenge_summary_participant.questionnaire_id.astype(
    "category"
).cat.rename_categories(
    {88: "threat", 89: "challenge"}
)

# %%
sns.displot(
    data=df_esm_SAM_threat_challenge_summary_participant,
    x="mean",
    hue="event_subscale",
    binwidth=0.2,
)

# %%
sns.displot(
    data=df_esm_SAM_threat_challenge_summary_participant,
    x="std",
    hue="event_subscale",
    binwidth=0.1,
)

# %% [markdown]
# ## Stressfulness of period

# %%
df_esm_SAM_period_summary_participant = df_esm_SAM_summary_participant[
    df_esm_SAM_summary_participant["questionnaire_id"] == 93
]

# %%
sns.displot(data=df_esm_SAM_period_summary_participant, x="mean", binwidth=0.2)

# %%
sns.displot(data=df_esm_SAM_period_summary_participant, x="std", binwidth=0.1)

# %% [markdown]
# # Job demand and control

# %%
df_esm_JCQ_demand_control = df_esm_preprocessed[
    (df_esm_preprocessed["questionnaire_id"] >= 10)
    & (df_esm_preprocessed["questionnaire_id"] <= 11)
]
df_esm_JCQ_demand_control_clean = clean_up_esm(df_esm_JCQ_demand_control)

# %%
df_esm_JCQ_demand_control_reversed = reverse_jcq_demand_control_scoring(
    df_esm_JCQ_demand_control_clean
)

# %%
df_esm_JCQ_daily = (
    df_esm_JCQ_demand_control_reversed.groupby(
        ["participant_id", "date_lj", "questionnaire_id"]
    )
    .esm_user_score.agg("mean")
    .reset_index()
    .rename(columns={"esm_user_score": "esm_score_mean"})
)
df_esm_JCQ_summary_participant = (
    df_esm_JCQ_daily.groupby(["participant_id", "questionnaire_id"])
    .agg(["mean", "median", "std"])
    .reset_index(col_level=1)
)
df_esm_JCQ_summary_participant.columns = df_esm_JCQ_summary_participant.columns.get_level_values(
    1
)
df_esm_JCQ_summary_participant[
    "JCQ_subscale"
] = df_esm_JCQ_summary_participant.questionnaire_id.astype(
    "category"
).cat.rename_categories(
    {10: "job demand", 11: "job control"}
)

# %%
sns.displot(
    data=df_esm_JCQ_summary_participant, x="mean", hue="JCQ_subscale", binwidth=0.1,
)

# %%
sns.displot(
    data=df_esm_JCQ_summary_participant, x="std", hue="JCQ_subscale", binwidth=0.05,
)