import pandas as pd

import features.esm

QUESTIONNAIRE_ID_SAM = {
    "event_stress": 87,
    "event_threat": 88,
    "event_challenge": 89,
    "event_time": 90,
    "event_duration": 91,
    "event_work_related": 92,
    "period_stress": 93,
}
QUESTIONNAIRE_ID_SAM_LOW = min(QUESTIONNAIRE_ID_SAM.values())
QUESTIONNAIRE_ID_SAM_HIGH = max(QUESTIONNAIRE_ID_SAM.values())

GROUP_QUESTIONNAIRES_BY = [
    "participant_id",
    "device_id",
    "esm_session",
    "questionnaire_id",
]
# Each questionnaire occurs only once within each esm_session on the same device within the same participant.


def extract_stressful_events(df_esm: pd.DataFrame) -> pd.DataFrame:
    # 0. Select only questions from Stress Appraisal Measure.
    df_esm_preprocessed = features.esm.preprocess_esm(df_esm)
    df_esm_sam = df_esm_preprocessed[
        (df_esm_preprocessed["questionnaire_id"] >= QUESTIONNAIRE_ID_SAM_LOW)
        & (df_esm_preprocessed["questionnaire_id"] <= QUESTIONNAIRE_ID_SAM_HIGH)
    ]

    df_esm_sam_clean = features.esm.clean_up_esm(df_esm_sam)
    # 1.
    df_esm_event_threat_challenge_mean_wide = calculate_threat_challenge_means(
        df_esm_sam_clean
    )
    # 2.
    df_esm_event_stress = detect_stressful_event(df_esm_sam_clean)

    # Join to the previously calculated features related to the events.
    df_esm_events = df_esm_event_threat_challenge_mean_wide.join(
        df_esm_event_stress[
            GROUP_QUESTIONNAIRES_BY + ["event_present", "event_stressfulness"]
        ].set_index(GROUP_QUESTIONNAIRES_BY)
    )

    # 3.
    df_esm_event_time = convert_event_time(df_esm_sam_clean)

    df_esm_events = df_esm_events.join(
        df_esm_event_time[GROUP_QUESTIONNAIRES_BY.append("event_time")].set_index(
            GROUP_QUESTIONNAIRES_BY
        )
    )

    # 4.
    df_esm_event_duration = extract_event_duration(df_esm_sam_clean)

    df_esm_events = df_esm_events.join(
        df_esm_event_duration[
            GROUP_QUESTIONNAIRES_BY + ["event_duration", "event_duration_info"]
        ].set_index(GROUP_QUESTIONNAIRES_BY)
    )

    return df_esm_events


def calculate_threat_challenge_means(df_esm_sam_clean: pd.DataFrame) -> pd.DataFrame:
    # Select only threat and challenge assessments for events
    df_esm_event_threat_challenge = df_esm_sam_clean[
        (
            df_esm_sam_clean["questionnaire_id"]
            == QUESTIONNAIRE_ID_SAM.get("event_threat")
        )
        | (
            df_esm_sam_clean["questionnaire_id"]
            == QUESTIONNAIRE_ID_SAM.get("event_challenge")
        )
    ]
    # Calculate mean of threat and challenge subscales for each ESM session.
    df_esm_event_threat_challenge_mean = (
        df_esm_event_threat_challenge.groupby(GROUP_QUESTIONNAIRES_BY)
        .esm_user_answer_numeric.agg("mean")
        .reset_index()
        .rename(columns={"esm_user_answer_numeric": "esm_numeric_mean"})
    )
    # Rename questionnaire ID to indicate their names.
    df_esm_event_threat_challenge_mean[
        "event_subscale"
    ] = df_esm_event_threat_challenge_mean.questionnaire_id.astype(
        "category"
    ).cat.rename_categories(
        {
            QUESTIONNAIRE_ID_SAM.get("event_threat"): "threat_mean",
            QUESTIONNAIRE_ID_SAM.get("event_challenge"): "challenge_mean",
        }
    )
    # Pivot a table so that each ESM session is represented by one row with threat and challenge means as two columns.
    df_esm_event_threat_challenge_mean_wide = pd.pivot(
        df_esm_event_threat_challenge_mean,
        index=GROUP_QUESTIONNAIRES_BY,
        columns=["event_subscale"],
        values=["esm_numeric_mean"],
    )
    return df_esm_event_threat_challenge_mean_wide


def detect_stressful_event(df_esm_sam_clean: pd.DataFrame) -> pd.DataFrame:
    df_esm_event_stress = df_esm_sam_clean[
        df_esm_sam_clean["questionnaire_id"] == QUESTIONNAIRE_ID_SAM.get("event_stress")
    ]
    df_esm_event_stress = df_esm_event_stress.assign(
        event_present=lambda x: x.esm_user_answer_numeric > 0,
        event_stressfulness=lambda x: x.esm_user_answer_numeric,
    )
    return df_esm_event_stress


def convert_event_time(df_esm_sam_clean: pd.DataFrame) -> pd.DataFrame:
    df_esm_event_time = df_esm_sam_clean[
        df_esm_sam_clean["questionnaire_id"] == QUESTIONNAIRE_ID_SAM.get("event_time")
    ].assign(
        event_time=lambda x: pd.to_datetime(
            x.esm_user_answer, errors="coerce", infer_datetime_format=True, exact=True
        )
    )
    return df_esm_event_time


def extract_event_duration(df_esm_sam_clean: pd.DataFrame) -> pd.DataFrame:
    df_esm_event_duration = df_esm_sam_clean[
        df_esm_sam_clean["questionnaire_id"]
        == QUESTIONNAIRE_ID_SAM.get("event_duration")
    ].assign(
        event_duration=lambda x: pd.to_datetime(
            x.esm_user_answer.str.slice(start=0, stop=-6), errors="coerce"
        ).dt.time
    )
    # TODO Explore the values recorded in event_duration and possibly fix mistakes.
    # For example, participants reported setting 23:50:00 instead of 00:50:00.

    # For the events that no duration was found (i.e. event_duration = NaT),
    # we can determine whether:
    #   - this event is still going on ("1 - It is still going on")
    #   - the participant couldn't remember it's duration ("0 - I do not remember")
    # Generally, these answers were converted to esm_user_answer_numeric in clean_up_esm,
    # but only the numeric types of questions and answers.
    # Since this was of "datetime" type, convert these specific answers here again.
    df_esm_event_duration[
        df_esm_event_duration.event_duration.isna()
    ] = df_esm_event_duration[df_esm_event_duration.event_duration.isna()].assign(
        event_duration_info=lambda x: x.esm_user_answer.str.slice(stop=1).astype(
            int
        )
    )

    return df_esm_event_duration


# TODO: How many questions about the stressfulness of the period were asked and how does this relate to events?