JPMC-quant/XX_quant_report.script.py

__generated_with = "0.19.7"

# %%
import marimo as mo
import polars as pl
from pathlib import Path
import argparse
import json
import re
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

# %% 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'
QSF_FILE = 'data/exports/OneDrive_2026-01-21/Soft Launch Data/JPMC_Chase_Brand_Personality_Quant_Round_1.qsf'


# %%
# 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)

# Central filter configuration - add new filters here only
# Format: 'cli_arg_name': 'QualtricsSurvey.options_* attribute name'
FILTER_CONFIG = {
    'age': 'options_age',
    'gender': 'options_gender',
    'ethnicity': 'options_ethnicity',
    'income': 'options_income',
    'consumer': 'options_consumer',
    'business_owner': 'options_business_owner',
    'ai_user': 'options_ai_user',
    'investable_assets': 'options_investable_assets',
    'industry': 'options_industry',
}

def parse_cli_args():
    parser = argparse.ArgumentParser(description='Generate quant report with optional filters')
    
    # Dynamically add filter arguments from config
    for filter_name in FILTER_CONFIG:
        parser.add_argument(f'--{filter_name}', type=str, default=None, help=f'JSON list of {filter_name} values')
    
    parser.add_argument('--filter-name', type=str, default=None, help='Name for this filter combination (used for .txt description file)')
    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:
        # Check if running in Jupyter by looking for ipykernel
        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, voice_ranking_filter=None)
    except NameError:
        args = parser.parse_args()
        # Parse JSON strings to lists
        for filter_name in FILTER_CONFIG:
            val = getattr(args, filter_name)
            setattr(args, filter_name, json.loads(val) if val else None)
        return args

cli_args = parse_cli_args()
BEST_CHOSEN_CHARACTER = cli_args.best_character



# %%
S = QualtricsSurvey(RESULTS_FILE, QSF_FILE, figures_dir=cli_args.figures_dir)
try:
    data_all = S.load_data()
except NotImplementedError as e:
    mo.stop(True, mo.md(f"**⚠️ {str(e)}**"))


# %% Build filtered dataset based on CLI args

# CLI args: None means "no filter applied" - filter_data() will skip None filters

# Build filter values dict dynamically from FILTER_CONFIG
_active_filters = {filter_name: getattr(cli_args, filter_name) for filter_name in FILTER_CONFIG}

# %% Apply filters
_d = S.filter_data(data_all, **_active_filters)

# Write filter description file if filter-name is provided
if cli_args.filter_name and S.fig_save_dir:
    # Get the filter slug (e.g., "All_Respondents", "Cons-Starter", etc.)
    _filter_slug = S._get_filter_slug()
    _filter_slug_dir = S.fig_save_dir / _filter_slug
    _filter_slug_dir.mkdir(parents=True, exist_ok=True)
    
    # Build filter description
    _filter_desc_lines = [
        f"Filter: {cli_args.filter_name}",
        "",
        "Applied Filters:",
    ]
    _short_desc_parts = []
    for filter_name, options_attr in FILTER_CONFIG.items():
        all_options = getattr(S, options_attr)
        values = _active_filters[filter_name]
        display_name = filter_name.replace('_', ' ').title()
        # None means no filter applied (same as "All")
        if values is not None and values != all_options:
            _short_desc_parts.append(f"{display_name}: {', '.join(values)}")
            _filter_desc_lines.append(f"  {display_name}: {', '.join(values)}")
        else:
            _filter_desc_lines.append(f"  {display_name}: All")
    
    # Write detailed description INSIDE the filter-slug directory
    # Sanitize filter name for filename usage (replace / and other chars)
    _safe_filter_name = re.sub(r'[^\w\s-]', '_', cli_args.filter_name)
    _filter_file = _filter_slug_dir / f"{_safe_filter_name}.txt"
    _filter_file.write_text('\n'.join(_filter_desc_lines))
    
    # Append to summary index file at figures/<export_date>/filter_index.txt
    _summary_file = S.fig_save_dir / "filter_index.txt"
    _short_desc = "; ".join(_short_desc_parts) if _short_desc_parts else "All Respondents"
    _summary_line = f"{_filter_slug}  |  {cli_args.filter_name}  |  {_short_desc}\n"
    
    # Append or create the summary file
    if _summary_file.exists():
        _existing = _summary_file.read_text()
        # Avoid duplicate entries for same slug
        if _filter_slug not in _existing:
            with _summary_file.open('a') as f:
                f.write(_summary_line)
    else:
        _header = "Filter Index\n" + "=" * 80 + "\n\n"
        _header += "Directory  |  Filter Name  |  Description\n"
        _header += "-" * 80 + "\n"
        _summary_file.write_text(_header + _summary_line)

# %% Apply straight-liner threshold filter (if specified)
# Removes respondents who straight-lined >= N question groups across
# speaking style and voice scale questions.
if cli_args.sl_threshold is not None:
    _sl_n = cli_args.sl_threshold
    S.sl_threshold = _sl_n  # Store on Survey so filter slug/description include it
    print(f"Applying straight-liner filter: excluding respondents with ≥{_sl_n} straight-lined question groups...")
    _n_before = _d.select(pl.len()).collect().item()

    # Extract question groups with renamed columns for check_straight_liners
    _sl_ss_or, _ = S.get_ss_orange_red(_d)
    _sl_ss_gb, _ = S.get_ss_green_blue(_d)
    _sl_vs, _ = S.get_voice_scale_1_10(_d)
    _sl_all_q = _sl_ss_or.join(_sl_ss_gb, on='_recordId').join(_sl_vs, on='_recordId')

    _, _sl_df = check_straight_liners(_sl_all_q, max_score=5)

    if _sl_df is not None and not _sl_df.is_empty():
        # Count straight-lined question groups per respondent
        _sl_counts = (
            _sl_df
            .group_by("Record ID")
            .agg(pl.len().alias("sl_count"))
            .filter(pl.col("sl_count") >= _sl_n)
            .select(pl.col("Record ID").alias("_recordId"))
        )
        # Anti-join to remove offending respondents
        _d = _d.collect().join(_sl_counts, on="_recordId", how="anti").lazy()
        # Update filtered data on the Survey object so sample size is correct
        S.data_filtered = _d
        _n_after = _d.select(pl.len()).collect().item()
        print(f"  Removed {_n_before - _n_after} respondents ({_n_before} → {_n_after})")
    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()



# %%
# 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"
)

# %%
# Gender-filtered correlation plots (Male vs Female voices)
from reference import VOICE_GENDER_MAPPING

MALE_VOICES = [v for v, g in VOICE_GENDER_MAPPING.items() if g == "Male"]
FEMALE_VOICES = [v for v, g in VOICE_GENDER_MAPPING.items() if g == "Female"]

# Filter joined data by voice gender
joined_scale_male = joined_scale.filter(pl.col("Voice").is_in(MALE_VOICES))
joined_scale_female = joined_scale.filter(pl.col("Voice").is_in(FEMALE_VOICES))
joined_ranking_male = joined_ranking.filter(pl.col("Voice").is_in(MALE_VOICES))
joined_ranking_female = joined_ranking.filter(pl.col("Voice").is_in(FEMALE_VOICES))

# Colors vs Scale 1-10 (grouped by voice gender)
S.plot_speaking_style_color_correlation_by_gender(
    data_male=joined_scale_male,
    data_female=joined_scale_female,
    speaking_styles=SPEAKING_STYLES,
    target_column="Voice_Scale_Score",
    title="Correlation: Speaking Style Colors and Voice Scale 1-10 (by Voice Gender)",
    filename="correlation_speaking_style_and_voice_scale_1-10_by_voice_gender_color",
)

# Colors vs Ranking Points (grouped by voice gender)
S.plot_speaking_style_color_correlation_by_gender(
    data_male=joined_ranking_male,
    data_female=joined_ranking_female,
    speaking_styles=SPEAKING_STYLES,
    target_column="Ranking_Points",
    title="Correlation: Speaking Style Colors and Voice Ranking Points (by Voice Gender)",
    filename="correlation_speaking_style_and_voice_ranking_points_by_voice_gender_color",
)

# %%
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_scale_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)

# %%
# Individual Traits vs Scale 1-10 (grouped by voice gender)
_content = """### Individual Traits vs Scale 1-10 (by Voice Gender)\n\n"""

for _style, _traits in SPEAKING_STYLES.items():
    _fig = S.plot_speaking_style_scale_correlation_by_gender(
        data_male=joined_scale_male,
        data_female=joined_scale_female,
        style_color=_style,
        style_traits=_traits,
        title=f"Correlation: Speaking Style {_style} and Voice Scale 1-10 (by Voice Gender)",
        filename=f"correlation_speaking_style_and_voice_scale_1-10_by_voice_gender_{_style.lower()}",
    )
    _content += f"""
#### Speaking Style **{_style}**:

{mo.ui.altair_chart(_fig)}

"""
mo.md(_content)

# %%
# Individual Traits vs Ranking Points (grouped by voice gender)
_content = """### Individual Traits vs Ranking Points (by Voice Gender)\n\n"""

for _style, _traits in SPEAKING_STYLES.items():
    _fig = S.plot_speaking_style_ranking_correlation_by_gender(
        data_male=joined_ranking_male,
        data_female=joined_ranking_female,
        style_color=_style,
        style_traits=_traits,
        title=f"Correlation: Speaking Style {_style} and Voice Ranking Points (by Voice Gender)",
        filename=f"correlation_speaking_style_and_voice_ranking_points_by_voice_gender_{_style.lower()}",
    )
    _content += f"""
#### Speaking Style **{_style}**:

{mo.ui.altair_chart(_fig)}

"""
mo.md(_content)

# %%
# ## Correlations when "Best Brand Character" is chosen
# For each of the 4 brand characters, filter the dataset to only those respondents 
# who selected that character as their #1 choice.

# %%
# Prepare character-filtered data subsets
char_rank_for_filter = S.get_character_ranking(data)[0].collect()

CHARACTER_FILTER_MAP = {
    'Familiar Friend': 'Character_Ranking_Familiar_Friend',
    'The Coach': 'Character_Ranking_The_Coach',
    'Personal Assistant': 'Character_Ranking_The_Personal_Assistant',
    'Bank Teller': 'Character_Ranking_The_Bank_Teller',
}

def get_filtered_data_for_character(char_name: str) -> tuple[pl.DataFrame, pl.DataFrame, int]:
    """Filter joined_scale and joined_ranking to respondents who ranked char_name #1."""
    col = CHARACTER_FILTER_MAP[char_name]
    respondents = char_rank_for_filter.filter(pl.col(col) == 1).select('_recordId')
    n = respondents.height
    filtered_scale = joined_scale.join(respondents, on='_recordId', how='inner')
    filtered_ranking = joined_ranking.join(respondents, on='_recordId', how='inner')
    return filtered_scale, filtered_ranking, n

def _char_filename(char_name: str, suffix: str) -> str:
    """Generate filename for character-filtered plots (without n-value).
    
    Format: bc_ranked_1_{suffix}__{char_slug}
    This groups all plot types together in directory listings.
    """
    char_slug = char_name.lower().replace(' ', '_')
    return f"bc_ranked_1_{suffix}__{char_slug}"



# %%
# ### Voice Weighted Ranking Score (by Best Character)
for char_name in CHARACTER_FILTER_MAP:
    _, _, n = get_filtered_data_for_character(char_name)
    # Get top3 voices for this character subset using _recordIds
    respondents = char_rank_for_filter.filter(
        pl.col(CHARACTER_FILTER_MAP[char_name]) == 1
    ).select('_recordId')
    # Collect top3_voices if it's a LazyFrame, then join
    top3_df = top3_voices.collect() if isinstance(top3_voices, pl.LazyFrame) else top3_voices
    filtered_top3 = top3_df.join(respondents, on='_recordId', how='inner')
    weighted = calculate_weighted_ranking_scores(filtered_top3)
    S.plot_weighted_ranking_score(
        data=weighted,
        title=f'"{char_name}" Ranked #1 (n={n})<br>Most Popular Voice - Weighted Score (1st=3pts, 2nd=2pts, 3rd=1pt)',
        filename=_char_filename(char_name, "voice_weighted_ranking_score"),
        color_gender=COLOR_GENDER,
    )

# %%
# ### Voice Scale 1-10 Average Scores (by Best Character)
for char_name in CHARACTER_FILTER_MAP:
    _, _, n = get_filtered_data_for_character(char_name)
    # Get voice scale data for this character subset using _recordIds
    respondents = char_rank_for_filter.filter(
        pl.col(CHARACTER_FILTER_MAP[char_name]) == 1
    ).select('_recordId')
    # Collect voice_1_10 if it's a LazyFrame, then join
    voice_1_10_df = voice_1_10.collect() if isinstance(voice_1_10, pl.LazyFrame) else voice_1_10
    filtered_voice_1_10 = voice_1_10_df.join(respondents, on='_recordId', how='inner')
    S.plot_average_scores_with_counts(
        data=filtered_voice_1_10,
        title=f'"{char_name}" Ranked #1 (n={n})<br>Voice General Impression (Scale 1-10)',
        filename=_char_filename(char_name, "voice_scale_1-10"),
        x_label='Voice',
        domain=[1, 10],
        color_gender=COLOR_GENDER,
    )



# %%
# ### Speaking Style Colors vs Scale 1-10 (only for Best Character)
for char_name in CHARACTER_FILTER_MAP:
    if char_name.lower().replace(' ', '_') != BEST_CHOSEN_CHARACTER:
        continue
    
    filtered_scale, _, n = get_filtered_data_for_character(char_name)
    color_corr, _ = utils.transform_speaking_style_color_correlation(filtered_scale, SPEAKING_STYLES)
    S.plot_speaking_style_color_correlation(
        data=color_corr,
        title=f'"{char_name}" Ranked #1 (n={n})<br>Correlation: Speaking Style Colors vs Voice Scale 1-10',
        filename=_char_filename(char_name, "colors_vs_voice_scale_1-10"),
    )

# %%
# ### Speaking Style Colors vs Ranking Points (only for Best Character)
for char_name in CHARACTER_FILTER_MAP:
    if char_name.lower().replace(' ', '_') != BEST_CHOSEN_CHARACTER:
        continue
    
    _, filtered_ranking, n = get_filtered_data_for_character(char_name)
    color_corr, _ = utils.transform_speaking_style_color_correlation(
        filtered_ranking, SPEAKING_STYLES, target_column="Ranking_Points"
    )
    S.plot_speaking_style_color_correlation(
        data=color_corr,
        title=f'"{char_name}" Ranked #1 (n={n})<br>Correlation: Speaking Style Colors vs Voice Ranking Points',
        filename=_char_filename(char_name, "colors_vs_voice_ranking_points"),
    )

# %%
# ### Individual Traits vs Scale 1-10 (only for Best Character)
for _style, _traits in SPEAKING_STYLES.items():
    print(f"--- Speaking Style: {_style} ---")
    for char_name in CHARACTER_FILTER_MAP:
        if char_name.lower().replace(' ', '_') != BEST_CHOSEN_CHARACTER:
            continue
        
        filtered_scale, _, n = get_filtered_data_for_character(char_name)
        S.plot_speaking_style_scale_correlation(
            data=filtered_scale,
            style_color=_style,
            style_traits=_traits,
            title=f'"{char_name}" Ranked #1 (n={n})<br>Correlation: {_style} vs Voice Scale 1-10',
            filename=_char_filename(char_name, f"{_style.lower()}_vs_voice_scale_1-10"),
        )

# %%
# ### Individual Traits vs Ranking Points (only for Best Character)
for _style, _traits in SPEAKING_STYLES.items():
    print(f"--- Speaking Style: {_style} ---")
    for char_name in CHARACTER_FILTER_MAP:
        if char_name.lower().replace(' ', '_') != BEST_CHOSEN_CHARACTER:
            continue
        
        _, filtered_ranking, n = get_filtered_data_for_character(char_name)
        S.plot_speaking_style_ranking_correlation(
            data=filtered_ranking,
            style_color=_style,
            style_traits=_traits,
            title=f'"{char_name}" Ranked #1 (n={n})<br>Correlation: {_style} vs Voice Ranking Points',
            filename=_char_filename(char_name, f"{_style.lower()}_vs_voice_ranking_points"),
        )


# %%