Qumo/JPMC-quant
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

missing data analysis

Browse Source
This commit is contained in:
Luigi Maiorano
2026-02-10 14:24:26 +01:00
parent 14e28cf368
commit 9dfab75925
5 changed files with 1477 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
XX_quant_report.script.py
View File

@@ -16,8 +16,8 @@ from speaking_styles import SPEAKING_STYLES
# %% Fixed Variables
# RESULTS_FILE = 'data/exports/2-4-26/JPMC_Chase Brand Personality_Quant Round 1_February 4, 2026_Labels.csv'
RESULTS_FILE = 'data/exports/debug/JPMC_Chase Brand Personality_Quant Round 1_February 2, 2026_Labels.csv'
RESULTS_FILE = 'data/exports/2-4-26/JPMC_Chase Brand Personality_Quant Round 1_February 4, 2026_Labels.csv'
# RESULTS_FILE = 'data/exports/debug/JPMC_Chase Brand Personality_Quant Round 1_February 2, 2026_Labels.csv'
QSF_FILE = 'data/exports/OneDrive_2026-01-21/Soft Launch Data/JPMC_Chase_Brand_Personality_Quant_Round_1.qsf'
@@ -51,6 +51,7 @@ def parse_cli_args():
parser.add_argument('--figures-dir', type=str, default=f'figures/{Path(RESULTS_FILE).parts[2]}', help='Override the default figures directory')
parser.add_argument('--best-character', type=str, default="the_coach", help='Slug of the best chosen character (default: "the_coach")')
parser.add_argument('--sl-threshold', type=int, default=None, help='Exclude respondents who straight-lined >= N question groups (e.g. 3 removes anyone with 3+ straight-lined groups)')
parser.add_argument('--voice-ranking-filter', type=str, default=None, choices=['only-missing', 'exclude-missing'], help='Filter by voice ranking completeness: "only-missing" keeps only respondents missing QID98 ranking data, "exclude-missing" removes them')
# Only parse if running as script (not in Jupyter/interactive)
try:
@@ -58,7 +59,7 @@ def parse_cli_args():
get_ipython() # noqa: F821 # type: ignore
# Return namespace with all filters set to None
no_filters = {f: None for f in FILTER_CONFIG}
return argparse.Namespace(**no_filters, filter_name=None, figures_dir=f'figures/statistical_significance/{Path(RESULTS_FILE).parts[2]}', best_character="the_coach", sl_threshold=None)
return argparse.Namespace(**no_filters, filter_name=None, figures_dir=f'figures/statistical_significance/{Path(RESULTS_FILE).parts[2]}', best_character="the_coach", sl_threshold=None, voice_ranking_filter=None)
except NameError:
args = parser.parse_args()
# Parse JSON strings to lists
@@ -174,6 +175,26 @@ if cli_args.sl_threshold is not None:
else:
print(" No straight-liners detected — no respondents removed.")
# %% Apply voice-ranking completeness filter (if specified)
# Keeps only / excludes respondents who are missing the explicit voice
# ranking question (QID98) despite completing the top-3 selection (QID36).
if cli_args.voice_ranking_filter is not None:
S.voice_ranking_filter = cli_args.voice_ranking_filter # Store on Survey so filter slug/description include it
_vr_missing = S.get_top_3_voices_missing_ranking(_d)
_vr_missing_ids = _vr_missing.select('_recordId')
_n_before = _d.select(pl.len()).collect().item()
if cli_args.voice_ranking_filter == 'only-missing':
print(f"Voice ranking filter: keeping ONLY respondents missing QID98 ranking data...")
_d = _d.collect().join(_vr_missing_ids, on='_recordId', how='inner').lazy()
elif cli_args.voice_ranking_filter == 'exclude-missing':
print(f"Voice ranking filter: EXCLUDING respondents missing QID98 ranking data...")
_d = _d.collect().join(_vr_missing_ids, on='_recordId', how='anti').lazy()
S.data_filtered = _d
_n_after = _d.select(pl.len()).collect().item()
print(f" {_n_before} → {_n_after} respondents ({_vr_missing_ids.height} missing ranking data)")
# Save to logical variable name for further analysis
data = _d
data.collect()