JPMC-quant/01_ingest_qualtrics_export.py

import marimo

__generated_with = "0.19.2"
app = marimo.App(width="medium")


@app.cell
def _():
    import marimo as mo
    import polars as pl
    from pathlib import Path

    from utils import JPMCSurvey
    from plots import plot_average_scores_with_counts, plot_top3_ranking_distribution
    return (
        JPMCSurvey,
        mo,
        plot_average_scores_with_counts,
        plot_top3_ranking_distribution,
    )


@app.cell
def _():
    RESULTS_FILE = 'data/exports/OneDrive_2026-01-21/Soft Launch Data/JPMC_Chase Brand Personality_Quant Round 1_January 21, 2026_Soft Launch_Labels.csv'
    QSF_FILE = 'data/exports/OneDrive_2026-01-21/Soft Launch Data/JPMC_Chase_Brand_Personality_Quant_Round_1.qsf'
    # RESULTS_FILE = 'data/exports/OneDrive_1_1-16-2026/JPMC_Chase Brand Personality_Quant Round 1_TestData_Labels.csv'
    return QSF_FILE, RESULTS_FILE


@app.cell
def _(JPMCSurvey, QSF_FILE, RESULTS_FILE):
    survey = JPMCSurvey(RESULTS_FILE, QSF_FILE)
    survey.qid_descr_map
    return (survey,)


@app.cell
def _(survey):
    data = survey.load_data()
    df = data.collect()


    df.select([q for q in df.columns if 'QID98' in q])

    return (data,)


@app.cell
def _(mo):
    mo.md(r"""
    # Data Cleanup

    - Remove incomplete responses (progress < 100)
    - Flag outliers based on duration (add column)
    - Flag responses that give the same rating for everything (indicates lack of engagement)
    """)
    return


@app.cell
def _(mo):
    mo.md(r"""
    # Answers Decoding

    Pipeline to decode the ranking of voices. Currently saved as QID's, they need to be remapped back to their actual values so that the analysis can be performed. ie:

    `GQIK26_G0_x8_RANK` -> Refers to question `Top 3 Traits_0_8_RANK - What are the important traits for the Chase AI virtual assistant?` and thus the #8 option
    """)
    return


@app.cell(hide_code=True)
def _(mo):
    mo.md(r"""
    ## TODO:

    Create a python function for each of the questions. ie `def QID63()`. Each function should return a Polars query, that can be added to an existing query.

    Ideas:
    - Map column name to include the Voice number (VID) (ie the questions that only have 1 voice). The VID is in this case often included in the question description
    - `QID_x_GROUP` Contains the rankings of the values, stored in order. The following columns (ie `QID26_G0_x1_RANK`) are redundant and not necessary for us. The function should drop the unnecessary columns  to clean up
    <!-- - Translate the RANK values back to the actual VID, and create an aggregate column that contains a list of the VIDs in order. ie: [V34, V56, V81].
      - Use the first line of the question description (see `qid_descr_map`) to get the `"DataExportTag"`, which is a property that can be found in the `.qsf` file to inspect the choice number and it's corresponding VID
      - "`VOICE SEL. 8-3_0_5_RANK`" refers to `"DataExportTag": "VOICE SEL. 8-3"`, `Group 0` (not important for this), `Choice 5`, and the value in the cell refers to the Rank assigned to that voice
      - QSF file example to retrieve the VID: `"SurveyElements" -> (Find item where "Payload"["DataExportTag"] == "VOICE SEL. 8-3") -> "Payload" -> "Choices" -> "5" -> "Display" -> (Extract 'Voice <xx>' from the HTML)` -->
    """)
    return


@app.cell
def _(survey):
    cfg = survey._get_qsf_question_by_QID('QID36')['Payload']
    cfg
    return


@app.cell
def _(data, survey):
    survey.get_demographics(data)[0].collect()
    return


@app.cell
def _(data, survey):
    survey.get_top_8_traits(data)[0].collect()
    return


@app.cell
def _(data, survey):
    survey.get_top_3_traits(data)[0].collect()
    return


@app.cell
def _(data, survey):
    survey.get_character_ranking(data)[0].collect()
    return


@app.cell
def _(data, survey):
    survey.get_18_8_3(data)[0].collect()
    return


@app.cell
def _(mo):
    mo.md(r"""
    # Voice Scales 1-10
    """)
    return


@app.cell
def _(data, survey):
    vscales = survey.get_voice_scale_1_10(data)[0].collect()
    vscales
    return (vscales,)


@app.cell
def _(plot_average_scores_with_counts, vscales):
    plot_average_scores_with_counts(vscales, x_label='Voice', width=1000)
    return


@app.cell
def _(mo):
    mo.md(r"""
    # SS Green Blue
    """)
    return


@app.cell
def _(data, survey):
    _lf, _choice_map = survey.get_ss_green_blue(data)
    print(_lf.collect().head())
    return


@app.cell
def _(mo):
    mo.md(r"""
    # Top 3 Voices
    """)
    return


@app.cell
def _(data, survey):
    top3_voices = survey.get_top_3_voices(data)[0].collect()
    top3_voices
    return (top3_voices,)


@app.cell
def _(top3_voices):

    print(top3_voices.head())
    return


@app.cell
def _(plot_top3_ranking_distribution, top3_voices):
    plot_top3_ranking_distribution(top3_voices, x_label='Voice', width=1000)
    return


@app.cell
def _(mo):
    mo.md(r"""
    # SS Orange / Red
    """)
    return


@app.cell
def _(data, survey):
    _lf, choice_map = survey.get_ss_orange_red(data)
    _d = _lf.collect()
    _d
    return


if __name__ == "__main__":
    app.run()