Qumo/JPMC-quant
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
8dd41dfc9630b57d637d33d432b5e029a25920eb
JPMC-quant/03_quant_report.script.py

632 lines
16 KiB
Python
Raw Blame History

__generated_with = "0.19.7"
# %%
import marimo as mo
import polars as pl
from pathlib import Path
import argparse
import json
from validation import check_progress, duration_validation, check_straight_liners
from utils import QualtricsSurvey, combine_exclusive_columns, calculate_weighted_ranking_scores
import utils
from speaking_styles import SPEAKING_STYLES
# %%
# CLI argument parsing for batch automation
# When run as script: python 03_quant_report.script.py --age '["18 to 21 years"]' --consumer '["Starter"]'
# When run in Jupyter: args will use defaults (all filters = None = all options selected)
def parse_cli_args():
parser = argparse.ArgumentParser(description='Generate quant report with optional filters')
parser.add_argument('--age', type=str, default=None, help='JSON list of age groups')
parser.add_argument('--gender', type=str, default=None, help='JSON list of genders')
parser.add_argument('--ethnicity', type=str, default=None, help='JSON list of ethnicities')
parser.add_argument('--income', type=str, default=None, help='JSON list of income groups')
parser.add_argument('--consumer', type=str, default=None, help='JSON list of consumer segments')
# Only parse if running as script (not in Jupyter/interactive)
try:
# Check if running in Jupyter by looking for ipykernel
get_ipython() # noqa: F821
return argparse.Namespace(age=None, gender=None, ethnicity=None, income=None, consumer=None)
except NameError:
args = parser.parse_args()
# Parse JSON strings to lists
args.age = json.loads(args.age) if args.age else None
args.gender = json.loads(args.gender) if args.gender else None
args.ethnicity = json.loads(args.ethnicity) if args.ethnicity else None
args.income = json.loads(args.income) if args.income else None
args.consumer = json.loads(args.consumer) if args.consumer else None
return args
cli_args = parse_cli_args()
# %%
# file_browser = mo.ui.file_browser(
# initial_path="./data/exports", multiple=False, restrict_navigation=True, filetypes=[".csv"], label="Select 'Labels' File"
# )
# 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))
RESULTS_FILE = 'data/exports/2-2-26/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'
# %%
S = QualtricsSurvey(RESULTS_FILE, QSF_FILE)
try:
data_all = S.load_data()
except NotImplementedError as e:
mo.stop(True, mo.md(f"**⚠️ {str(e)}**"))
# %%
BEST_CHOSEN_CHARACTER = "the_coach"
# # %%
# filter_form = mo.md('''
# {age}
# {gender}
# {ethnicity}
# {income}
# {consumer}
# '''
# ).batch(
# age=mo.ui.multiselect(options=S.options_age, value=S.options_age, label="Select Age Group(s):"),
# gender=mo.ui.multiselect(options=S.options_gender, value=S.options_gender, label="Select Gender(s):"),
# ethnicity=mo.ui.multiselect(options=S.options_ethnicity, value=S.options_ethnicity, label="Select Ethnicities:"),
# income=mo.ui.multiselect(options=S.options_income, value=S.options_income, label="Select Income Group(s):"),
# consumer=mo.ui.multiselect(options=S.options_consumer, value=S.options_consumer, label="Select Consumer Groups:")
# ).form()
# mo.md(f'''
# ---
# # Data Filter
# {filter_form}
# ''')
# %%
# mo.stop(filter_form.value is None, mo.md("**Please submit filter above to proceed**"))
# CLI args: None means "all options selected" (use S.options_* defaults)
_filter_age = cli_args.age if cli_args.age is not None else S.options_age
_filter_gender = cli_args.gender if cli_args.gender is not None else S.options_gender
_filter_ethnicity = cli_args.ethnicity if cli_args.ethnicity is not None else S.options_ethnicity
_filter_income = cli_args.income if cli_args.income is not None else S.options_income
_filter_consumer = cli_args.consumer if cli_args.consumer is not None else S.options_consumer
_d = S.filter_data(data_all, age=_filter_age, gender=_filter_gender, income=_filter_income, ethnicity=_filter_ethnicity, consumer=_filter_consumer)
# Stop execution and prevent other cells from running if no data is selected
# mo.stop(len(_d.collect()) == 0, mo.md("**No Data available for current filter combination**"))
data = _d
# data = data_validated
data.collect()
# %%
# %%
# Check if all business owners are missing a 'Consumer type' in demographics
# assert all([a is None for a in data_all.filter(pl.col('QID4') == 'Yes').collect()['Consumer'].unique()]) , "Not all business owners are missing 'Consumer type' in demographics."
# %%
mo.md(r"""
# Demographic Distributions
""")
# %%
demo_plot_cols = [
'Age',
'Gender',
# 'Race/Ethnicity',
'Bussiness_Owner',
'Consumer'
]
# %%
_content = """
"""
for c in demo_plot_cols:
_fig = S.plot_demographic_distribution(
data=S.get_demographics(data)[0],
column=c,
title=f"{c.replace('Bussiness', 'Business').replace('_', ' ')} Distribution of Survey Respondents"
)
_content += f"""{mo.ui.altair_chart(_fig)}\n\n"""
mo.md(_content)
# %%
mo.md(r"""
---
# Brand Character Results
""")
# %%
mo.md(r"""
## Best performing: Original vs Refined frankenstein
""")
# %%
char_refine_rank = S.get_character_refine(data)[0]
# print(char_rank.collect().head())
print(char_refine_rank.collect().head())
# %%
mo.md(r"""
## Character ranking points
""")
# %%
mo.md(r"""
## Character ranking 1-2-3
""")
# %%
char_rank = S.get_character_ranking(data)[0]
# %%
char_rank_weighted = calculate_weighted_ranking_scores(char_rank)
S.plot_weighted_ranking_score(char_rank_weighted, title="Most Popular Character - Weighted Popularity Score<br>(1st=3pts, 2nd=2pts, 3rd=1pt)", x_label='Voice')
# %%
S.plot_top3_ranking_distribution(char_rank, x_label='Character Personality', title='Character Personality: Rankings Top 3')
# %%
mo.md(r"""
### Statistical Significance Character Ranking
""")
# %%
_pairwise_df, _meta = S.compute_ranking_significance(char_rank)
# print(_pairwise_df.columns)
mo.md(f"""
{mo.ui.altair_chart(S.plot_significance_heatmap(_pairwise_df, metadata=_meta))}
{mo.ui.altair_chart(S.plot_significance_summary(_pairwise_df, metadata=_meta))}
""")
# %%
mo.md(r"""
## Character Ranking: times 1st place
""")
# %%
S.plot_most_ranked_1(char_rank, title="Most Popular Character<br>(Number of Times Ranked 1st)", x_label='Character Personality')
# %%
mo.md(r"""
## Prominent predefined personality traits wordcloud
""")
# %%
top8_traits = S.get_top_8_traits(data)[0]
S.plot_traits_wordcloud(
data=top8_traits,
column='Top_8_Traits',
title="Most Prominent Personality Traits",
)
# %%
mo.md(r"""
## Trait frequency per brand character
""")
# %%
char_df = S.get_character_refine(data)[0]
# %%
from theme import ColorPalette
# Assuming you already have char_df (your data from get_character_refine or similar)
characters = ['Bank Teller', 'Familiar Friend', 'The Coach', 'Personal Assistant']
character_colors = {
'Bank Teller': (ColorPalette.CHARACTER_BANK_TELLER, ColorPalette.CHARACTER_BANK_TELLER_HIGHLIGHT),
'Familiar Friend': (ColorPalette.CHARACTER_FAMILIAR_FRIEND, ColorPalette.CHARACTER_FAMILIAR_FRIEND_HIGHLIGHT),
'The Coach': (ColorPalette.CHARACTER_COACH, ColorPalette.CHARACTER_COACH_HIGHLIGHT),
'Personal Assistant': (ColorPalette.CHARACTER_PERSONAL_ASSISTANT, ColorPalette.CHARACTER_PERSONAL_ASSISTANT_HIGHLIGHT),
}
# Build consistent sort order (by total frequency across all characters)
all_trait_counts = {}
for char in characters:
freq_df, _ = S.transform_character_trait_frequency(char_df, char)
for row in freq_df.iter_rows(named=True):
all_trait_counts[row['trait']] = all_trait_counts.get(row['trait'], 0) + row['count']
consistent_sort_order = sorted(all_trait_counts.keys(), key=lambda x: -all_trait_counts[x])
_content = """"""
# Generate 4 plots (one per character)
for char in characters:
freq_df, _ = S.transform_character_trait_frequency(char_df, char)
main_color, highlight_color = character_colors[char]
chart = S.plot_single_character_trait_frequency(
data=freq_df,
character_name=char,
bar_color=main_color,
highlight_color=highlight_color,
trait_sort_order=consistent_sort_order,
)
_content += f"""
{mo.ui.altair_chart(chart)}
"""
mo.md(_content)
# %%
mo.md(r"""
## Statistical significance best characters
zie chat
> voorbeeld: als de nr 1 en 2 niet significant verschillen maar wel van de nr 3 bijvoorbeeld is dat ook top. Beetje meedenkend over hoe ik het kan presenteren weetje wat ik bedoel?:)
>
""")
# %%
# %%
# %%
mo.md(r"""
---
# Spoken Voice Results
""")
# %%
COLOR_GENDER = True
# %%
mo.md(r"""
## Top 8 Most Chosen out of 18
""")
# %%
v_18_8_3 = S.get_18_8_3(data)[0]
# %%
S.plot_voice_selection_counts(v_18_8_3, title="Top 8 Voice Selection from 18 Voices", x_label='Voice', color_gender=COLOR_GENDER)
# %%
mo.md(r"""
## Top 3 most chosen out of 8
""")
# %%
S.plot_top3_selection_counts(v_18_8_3, title="Top 3 Voice Selection Counts from 8 Voices", x_label='Voice', color_gender=COLOR_GENDER)
# %%
mo.md(r"""
## Voice Ranking Weighted Score
""")
# %%
top3_voices = S.get_top_3_voices(data)[0]
top3_voices_weighted = calculate_weighted_ranking_scores(top3_voices)
# %%
S.plot_weighted_ranking_score(top3_voices_weighted, title="Most Popular Voice - Weighted Popularity Score<br>(1st = 3pts, 2nd = 2pts, 3rd = 1pt)", color_gender=COLOR_GENDER)
# %%
mo.md(r"""
## Which voice is ranked best in the ranking question for top 3?
(not best 3 out of 8 question)
""")
# %%
S.plot_ranking_distribution(top3_voices, x_label='Voice', title="Distribution of Top 3 Voice Rankings (1st, 2nd, 3rd)", color_gender=COLOR_GENDER)
# %%
mo.md(r"""
### Statistical significance for voice ranking
""")
# %%
# print(top3_voices.collect().head())
# %%
# _pairwise_df, _metadata = S.compute_ranking_significance(
# top3_voices,alpha=0.05,correction="none")
# # View significant pairs
# # print(pairwise_df.filter(pl.col('significant') == True))
# # Create heatmap visualization
# _heatmap = S.plot_significance_heatmap(
# _pairwise_df,
# metadata=_metadata,
# title="Weighted Voice Ranking Significance<br>(Pairwise Comparisons)"
# )
# # Create summary bar chart
# _summary = S.plot_significance_summary(
# _pairwise_df,
# metadata=_metadata
# )
# mo.md(f"""
# {mo.ui.altair_chart(_heatmap)}
# {mo.ui.altair_chart(_summary)}
# """)
# %%
## Voice Ranked 1st the most
# %%
S.plot_most_ranked_1(top3_voices, title="Most Popular Voice<br>(Number of Times Ranked 1st)", x_label='Voice', color_gender=COLOR_GENDER)
# %%
mo.md(r"""
## Voice Scale 1-10
""")
# %%
# Get your voice scale data (from notebook)
voice_1_10, _ = S.get_voice_scale_1_10(data)
S.plot_average_scores_with_counts(voice_1_10, x_label='Voice', domain=[1,10], title="Voice General Impression (Scale 1-10)", color_gender=COLOR_GENDER)
# %%
mo.md(r"""
### Statistical Significance (Scale 1-10)
""")
# %%
# Compute pairwise significance tests
pairwise_df, metadata = S.compute_pairwise_significance(
voice_1_10,
test_type="mannwhitney", # or "ttest", "chi2", "auto"
alpha=0.05,
correction="bonferroni" # or "holm", "none"
)
# View significant pairs
# print(pairwise_df.filter(pl.col('significant') == True))
# Create heatmap visualization
_heatmap = S.plot_significance_heatmap(
pairwise_df,
metadata=metadata,
title="Voice Rating Significance<br>(Pairwise Comparisons)"
)
# Create summary bar chart
_summary = S.plot_significance_summary(
pairwise_df,
metadata=metadata
)
mo.md(f"""
{mo.ui.altair_chart(_heatmap)}
{mo.ui.altair_chart(_summary)}
""")
# %%
# %%
mo.md(r"""
## Ranking points for Voice per Chosen Brand Character
**missing mapping**
""")
# %%
mo.md(r"""
## Correlation Speaking Styles
""")
# %%
ss_or, choice_map_or = S.get_ss_orange_red(data)
ss_gb, choice_map_gb = S.get_ss_green_blue(data)
# Combine the data
ss_all = ss_or.join(ss_gb, on='_recordId')
_d = ss_all.collect()
choice_map = {**choice_map_or, **choice_map_gb}
# print(_d.head())
# print(choice_map)
ss_long = utils.process_speaking_style_data(ss_all, choice_map)
df_style = utils.process_speaking_style_data(ss_all, choice_map)
vscales = S.get_voice_scale_1_10(data)[0]
df_scale_long = utils.process_voice_scale_data(vscales)
joined_scale = df_style.join(df_scale_long, on=["_recordId", "Voice"], how="inner")
df_ranking = utils.process_voice_ranking_data(top3_voices)
joined_ranking = df_style.join(df_ranking, on=['_recordId', 'Voice'], how='inner')
# %%
joined_ranking.head()
# %%
mo.md(r"""
### Colors vs Scale 1-10
""")
# %%
# Transform to get one row per color with average correlation
color_corr_scale, _ = utils.transform_speaking_style_color_correlation(joined_scale, SPEAKING_STYLES)
S.plot_speaking_style_color_correlation(
data=color_corr_scale,
title="Correlation: Speaking Style Colors and Voice Scale 1-10"
)
# %%
mo.md(r"""
### Colors vs Ranking Points
""")
# %%
color_corr_ranking, _ = utils.transform_speaking_style_color_correlation(
joined_ranking,
SPEAKING_STYLES,
target_column="Ranking_Points"
)
S.plot_speaking_style_color_correlation(
data=color_corr_ranking,
title="Correlation: Speaking Style Colors and Voice Ranking Points"
)
# %%
mo.md(r"""
### Individual Traits vs Scale 1-10
""")
# %%
_content = """"""
for _style, _traits in SPEAKING_STYLES.items():
# print(f"Correlation plot for {style}...")
_fig = S.plot_speaking_style_correlation(
data=joined_scale,
style_color=_style,
style_traits=_traits,
title=f"Correlation: Speaking Style {_style} and Voice Scale 1-10",
)
_content += f"""
#### Speaking Style **{_style}**:
{mo.ui.altair_chart(_fig)}
"""
mo.md(_content)
# %%
mo.md(r"""
### Individual Traits vs Ranking Points
""")
# %%
_content = """"""
for _style, _traits in SPEAKING_STYLES.items():
# print(f"Correlation plot for {style}...")
_fig = S.plot_speaking_style_ranking_correlation(
data=joined_ranking,
style_color=_style,
style_traits=_traits,
title=f"Correlation: Speaking Style {_style} and Voice Ranking Points",
)
_content += f"""
#### Speaking Style **{_style}**:
{mo.ui.altair_chart(_fig)}
"""
mo.md(_content)
# %%
mo.md(r"""
## Correlations when "Best Brand Character" is chosen
Select only the traits that fit with that character
""")
# %%
from reference import ORIGINAL_CHARACTER_TRAITS
chosen_bc_traits = ORIGINAL_CHARACTER_TRAITS[BEST_CHOSEN_CHARACTER]
# %%
STYLES_SUBSET = utils.filter_speaking_styles(SPEAKING_STYLES, chosen_bc_traits)
# %%
mo.md(r"""
### Individual Traits vs Ranking Points
""")
# %%
_content = ""
for _style, _traits in STYLES_SUBSET.items():
_fig = S.plot_speaking_style_ranking_correlation(
data=joined_ranking,
style_color=_style,
style_traits=_traits,
title=f"""Brand Character "{BEST_CHOSEN_CHARACTER.replace('_', ' ').title()}" - Correlation: Speaking Style {_style} and Voice Ranking Points"""
)
_content += f"""
{mo.ui.altair_chart(_fig)}
"""
mo.md(_content)
# %%
mo.md(r"""
### Individual Traits vs Scale 1-10
""")
# %%
_content = """"""
for _style, _traits in STYLES_SUBSET.items():
# print(f"Correlation plot for {style}...")
_fig = S.plot_speaking_style_correlation(
data=joined_scale,
style_color=_style,
style_traits=_traits,
title=f"""Brand Character "{BEST_CHOSEN_CHARACTER.replace('_', ' ').title()}" - Correlation: Speaking Style {_style} and Voice Scale 1-10""",
)
_content += f"""
{mo.ui.altair_chart(_fig)}
"""
mo.md(_content)
# %%
mo.md(r"""
### Colors vs Scale 1-10 (Best Character)
""")
# %%
# Transform to get one row per color with average correlation
_color_corr_scale, _ = utils.transform_speaking_style_color_correlation(joined_scale, STYLES_SUBSET)
S.plot_speaking_style_color_correlation(
data=_color_corr_scale,
title=f"""Brand Character "{BEST_CHOSEN_CHARACTER.replace('_', ' ').title()}" - Correlation: Speaking Style Colors and Voice Scale 1-10"""
)
# %%
mo.md(r"""
### Colors vs Ranking Points (Best Character)
""")
# %%
_color_corr_ranking, _ = utils.transform_speaking_style_color_correlation(
joined_ranking,
STYLES_SUBSET,
target_column="Ranking_Points"
)
S.plot_speaking_style_color_correlation(
data=_color_corr_ranking,
title=f"""Brand Character "{BEST_CHOSEN_CHARACTER.replace('_', ' ').title()}" - Correlation: Speaking Style Colors and Voice Ranking Points"""
)
Reference in New Issue View Git Blame Copy Permalink