155 lines
3.1 KiB
Python
155 lines
3.1 KiB
Python
import marimo
|
|
|
|
__generated_with = "0.19.2"
|
|
app = marimo.App(width="medium")
|
|
|
|
with app.setup:
|
|
import marimo as mo
|
|
import polars as pl
|
|
from pathlib import Path
|
|
|
|
from validation import check_progress, duration_validation, check_straight_liners
|
|
from utils import JPMCSurvey, combine_exclusive_columns, calculate_weighted_ranking_scores
|
|
import utils
|
|
|
|
from speaking_styles import SPEAKING_STYLES
|
|
|
|
|
|
@app.cell
|
|
def _():
|
|
|
|
file_browser = mo.ui.file_browser(
|
|
initial_path="./data/exports", multiple=False, restrict_navigation=True, filetypes=[".csv"], label="Select 'Labels' File"
|
|
)
|
|
file_browser
|
|
|
|
return (file_browser,)
|
|
|
|
|
|
@app.cell
|
|
def _(file_browser):
|
|
mo.stop(file_browser.path(index=0) is None, mo.md("**⚠️ Please select a `_Labels.csv` file above to proceed**"))
|
|
RESULTS_FILE = Path(file_browser.path(index=0))
|
|
QSF_FILE = 'data/exports/OneDrive_2026-01-21/Soft Launch Data/JPMC_Chase_Brand_Personality_Quant_Round_1.qsf'
|
|
return QSF_FILE, RESULTS_FILE
|
|
|
|
|
|
@app.cell
|
|
def _(QSF_FILE, RESULTS_FILE):
|
|
S = JPMCSurvey(RESULTS_FILE, QSF_FILE)
|
|
try:
|
|
data_all = S.load_data()
|
|
except NotImplementedError as e:
|
|
mo.stop(True, mo.md(f"**⚠️ {str(e)}**"))
|
|
return S, data_all
|
|
|
|
|
|
@app.cell(hide_code=True)
|
|
def _():
|
|
mo.md(r"""
|
|
---
|
|
# Load Data
|
|
|
|
**Dataset:** `{Path(RESULTS_FILE).name}`
|
|
|
|
**Responses**: `{data_all.collect().shape[0]}`
|
|
""")
|
|
return
|
|
|
|
|
|
@app.cell
|
|
def _(S, data_all):
|
|
sl_ss_max_score = 5
|
|
sl_v1_10_max_score = 10
|
|
|
|
_ss_all = S.get_ss_green_blue(data_all)[0].join(S.get_ss_orange_red(data_all)[0], on='_recordId')
|
|
_sl_ss_c, sl_ss_df = check_straight_liners(_ss_all, max_score=sl_ss_max_score)
|
|
|
|
_sl_v1_10_c, sl_v1_10_df = check_straight_liners(
|
|
S.get_voice_scale_1_10(data_all)[0],
|
|
max_score=sl_v1_10_max_score
|
|
)
|
|
|
|
|
|
mo.md(f"""
|
|
# Data Validation
|
|
|
|
{check_progress(data_all)}
|
|
|
|
|
|
|
|
{duration_validation(data_all)}
|
|
|
|
|
|
## Speaking Style - Straight Liners
|
|
{_sl_ss_c}
|
|
|
|
|
|
## Voice Score Scale 1-10 - Straight Liners
|
|
{_sl_v1_10_c}
|
|
""")
|
|
return
|
|
|
|
|
|
@app.cell
|
|
def _(data_all):
|
|
# # Drop any Voice Scale 1-10 responses with straight-lining, using sl_v1_10_df _responseId values
|
|
# records_to_drop = sl_v1_10_df.select('Record ID').to_series().to_list()
|
|
|
|
# data_validated = data_all.filter(~pl.col('_recordId').is_in(records_to_drop))
|
|
|
|
# mo.md(f"""
|
|
# Dropped `{len(records_to_drop)}` responses with straight-lining in Voice Scale 1-10 evaluation.
|
|
# """)
|
|
data_validated = data_all
|
|
return (data_validated,)
|
|
|
|
|
|
@app.cell(hide_code=True)
|
|
def _():
|
|
|
|
|
|
return
|
|
|
|
|
|
@app.cell
|
|
def _(data_validated):
|
|
data = data_validated
|
|
|
|
data.collect()
|
|
return
|
|
|
|
|
|
@app.cell(hide_code=True)
|
|
def _():
|
|
mo.md(r"""
|
|
---
|
|
|
|
# Introduction (Respondent Demographics)
|
|
""")
|
|
return
|
|
|
|
|
|
@app.cell(hide_code=True)
|
|
def _():
|
|
mo.md(r"""
|
|
---
|
|
|
|
# Brand Character Results
|
|
""")
|
|
return
|
|
|
|
|
|
@app.cell(hide_code=True)
|
|
def _():
|
|
mo.md(r"""
|
|
---
|
|
|
|
# Spoken Voice Results
|
|
""")
|
|
return
|
|
|
|
|
|
if __name__ == "__main__":
|
|
app.run()
|