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

male/female colored plots

Browse Source
This commit is contained in:
Luigi Maiorano
2026-02-03 00:40:51 +01:00
parent 77fdd6e8f6
commit acf9c45844
5 changed files with 394 additions and 111 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
03_quant_report.py
View File

@@ -458,6 +458,12 @@ def _():
return
@app.cell
def _():
COLOR_GENDER = True
return (COLOR_GENDER,)
@app.cell
def _():
mo.md(r"""
@@ -473,8 +479,8 @@ def _(S, data):
@app.cell
def _(S, v_18_8_3):
S.plot_voice_selection_counts(v_18_8_3, title="Top 8 Voice Selection from 18 Voices", x_label='Voice')
def _(COLOR_GENDER, S, v_18_8_3):
S.plot_voice_selection_counts(v_18_8_3, title="Top 8 Voice Selection from 18 Voices", x_label='Voice', color_gender=COLOR_GENDER)
return
@@ -487,8 +493,8 @@ def _():
@app.cell
def _(S, v_18_8_3):
S.plot_top3_selection_counts(v_18_8_3, title="Top 3 Voice Selection Counts from 8 Voices", x_label='Voice')
def _(COLOR_GENDER, S, v_18_8_3):
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)
return
@@ -508,8 +514,8 @@ def _(S, data):
@app.cell
def _(S, top3_voices_weighted):
S.plot_weighted_ranking_score(top3_voices_weighted, title="Most Popular Voice - Weighted Popularity Score<br>(1st = 3pts, 2nd = 2pts, 3rd = 1pt)")
def _(COLOR_GENDER, S, top3_voices_weighted):
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)
return
@@ -524,8 +530,8 @@ def _():
@app.cell
def _(S, top3_voices):
S.plot_ranking_distribution(top3_voices, x_label='Voice', title="Distribution of Voice Rankings (1st, 2nd, 3rd)")
def _(COLOR_GENDER, S, top3_voices):
S.plot_ranking_distribution(top3_voices, x_label='Voice', title="Distribution of Top 3 Voice Rankings (1st, 2nd, 3rd)", color_gender=COLOR_GENDER)
return
@@ -580,8 +586,8 @@ def _():
@app.cell
def _(S, top3_voices):
S.plot_most_ranked_1(top3_voices, title="Most Popular Voice<br>(Number of Times Ranked 1st)", x_label='Voice')
def _(COLOR_GENDER, S, top3_voices):
S.plot_most_ranked_1(top3_voices, title="Most Popular Voice<br>(Number of Times Ranked 1st)", x_label='Voice', color_gender=COLOR_GENDER)
return
@@ -594,10 +600,10 @@ def _():
@app.cell
def _(S, data):
def _(COLOR_GENDER, S, data):
# 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)")
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)
return (voice_1_10,)

8
04_PPTX_Update_Images.py
View File

@@ -21,8 +21,8 @@ def _():
@app.cell
def _():
TAG_SOURCE = Path('data/reports/Perception-Research-Report_2-2_tagged.pptx')
TAG_TARGET = Path('data/reports/Perception-Research-Report_2-2_tagged_2.pptx')
TAG_SOURCE = Path('data/reports/Perception-Research-Report_2-2.pptx')
TAG_TARGET = Path('data/reports/Perception-Research-Report_2-2_tagged.pptx')
TAG_IMAGE_DIR = Path('figures/2-2-26')
return TAG_IMAGE_DIR, TAG_SOURCE, TAG_TARGET
@@ -43,8 +43,8 @@ def _():
@app.cell
def _():
REPLACE_SOURCE = Path('data/reports/Perception-Research-Report_2-2_tagged_2.pptx')
REPLACE_TARGET = Path('data/reports/Perception-Research-Report_2-2.pptx')
REPLACE_SOURCE = Path('data/reports/Perception-Research-Report_2-2.pptx')
REPLACE_TARGET = Path('data/reports/Perception-Research-Report_2-2_updated.pptx')
NEW_IMAGES_DIR = Path('figures/2-2-26')
return NEW_IMAGES_DIR, REPLACE_SOURCE, REPLACE_TARGET

280
plots.py
View File

@@ -8,6 +8,7 @@ import altair as alt
import pandas as pd
import polars as pl
from theme import ColorPalette
from reference import VOICE_GENDER_MAPPING
import hashlib
@@ -260,6 +261,61 @@ class QualtricsPlotsMixin:
label = label.replace('_', ' ').strip()
return label
def _get_voice_gender(self, voice_label: str) -> str:
"""Get the gender of a voice from its label.
Parameters:
voice_label: Voice label (e.g., 'V14', 'Voice 14', etc.)
Returns:
'Male' or 'Female', defaults to 'Male' if not found
"""
# Extract voice code (e.g., 'V14' from 'Voice 14' or 'V14')
voice_code = None
# Try to find VXX pattern
match = re.search(r'V(\d+)', voice_label)
if match:
voice_code = f"V{match.group(1)}"
else:
# Try to extract number and prepend V
match = re.search(r'(\d+)', voice_label)
if match:
voice_code = f"V{match.group(1)}"
if voice_code and voice_code in VOICE_GENDER_MAPPING:
return VOICE_GENDER_MAPPING[voice_code]
return "Male" # Default to Male if unknown
def _get_gender_color(self, gender: str, color_type: str = "primary") -> str:
"""Get the appropriate color based on gender.
Parameters:
gender: 'Male' or 'Female'
color_type: One of 'primary', 'rank_1', 'rank_2', 'rank_3', 'neutral'
Returns:
Hex color string
"""
color_map = {
"Male": {
"primary": ColorPalette.GENDER_MALE,
"rank_1": ColorPalette.GENDER_MALE_RANK_1,
"rank_2": ColorPalette.GENDER_MALE_RANK_2,
"rank_3": ColorPalette.GENDER_MALE_RANK_3,
"neutral": ColorPalette.GENDER_MALE_NEUTRAL,
},
"Female": {
"primary": ColorPalette.GENDER_FEMALE,
"rank_1": ColorPalette.GENDER_FEMALE_RANK_1,
"rank_2": ColorPalette.GENDER_FEMALE_RANK_2,
"rank_3": ColorPalette.GENDER_FEMALE_RANK_3,
"neutral": ColorPalette.GENDER_FEMALE_NEUTRAL,
}
}
return color_map.get(gender, color_map["Male"]).get(color_type, ColorPalette.PRIMARY)
def plot_average_scores_with_counts(
self,
data: pl.LazyFrame | pl.DataFrame | None = None,
@@ -270,8 +326,13 @@ class QualtricsPlotsMixin:
height: int | None = None,
width: int | str | None = None,
domain: list[float] | None = None,
color_gender: bool = False,
) -> alt.Chart:
"""Create a bar plot showing average scores and count of non-null values for each column."""
"""Create a bar plot showing average scores and count of non-null values for each column.
Parameters:
color_gender: If True, color bars by voice gender (blue=male, pink=female).
"""
df = self._ensure_dataframe(data)
# Calculate stats for each column (exclude _recordId)
@@ -280,10 +341,12 @@ class QualtricsPlotsMixin:
avg_score = df[col].mean()
non_null_count = df[col].drop_nulls().len()
label = self._clean_voice_label(col)
gender = self._get_voice_gender(label) if color_gender else None
stats.append({
'voice': label,
'average': avg_score,
'count': non_null_count
'count': non_null_count,
'gender': gender
})
# Convert to pandas for Altair (sort by average descending)
@@ -293,6 +356,23 @@ class QualtricsPlotsMixin:
domain = [stats_df['average'].min(), stats_df['average'].max()]
# Base bar chart - use y2 to explicitly start bars at domain minimum
if color_gender:
bars = alt.Chart(stats_df).mark_bar().encode(
x=alt.X('voice:N', title=x_label, sort='-y'),
y=alt.Y('average:Q', title=y_label, scale=alt.Scale(domain=domain)),
y2=alt.datum(domain[0]), # Bars start at domain minimum (bottom edge)
color=alt.Color('gender:N',
scale=alt.Scale(domain=['Male', 'Female'],
range=[ColorPalette.GENDER_MALE, ColorPalette.GENDER_FEMALE]),
legend=alt.Legend(orient='top', direction='horizontal', title='Gender')),
tooltip=[
alt.Tooltip('voice:N', title='Voice'),
alt.Tooltip('average:Q', title='Average', format='.2f'),
alt.Tooltip('count:Q', title='Count'),
alt.Tooltip('gender:N', title='Gender')
]
)
else:
bars = alt.Chart(stats_df).mark_bar(color=color).encode(
x=alt.X('voice:N', title=x_label, sort='-y'),
y=alt.Y('average:Q', title=y_label, scale=alt.Scale(domain=domain)),
@@ -390,8 +470,14 @@ class QualtricsPlotsMixin:
y_label: str = "Number of Votes",
height: int | None = None,
width: int | str | None = None,
color_gender: bool = False,
) -> alt.Chart:
"""Create a stacked bar chart showing the distribution of rankings (1st to 3rd)."""
"""Create a stacked bar chart showing the distribution of rankings (1st to 3rd).
Parameters:
color_gender: If True, color bars by voice gender with rank intensity
(blue shades=male, pink shades=female).
"""
df = self._ensure_dataframe(data)
stats = []
@@ -406,10 +492,11 @@ class QualtricsPlotsMixin:
if total > 0:
label = self._clean_voice_label(col)
stats.append({'item': label, 'rank': 'Rank 1 (Best)', 'count': r1, 'rank1': r1})
stats.append({'item': label, 'rank': 'Rank 2', 'count': r2, 'rank1': r1})
stats.append({'item': label, 'rank': 'Rank 3', 'count': r3, 'rank1': r1})
# stats.append({'item': label, 'rank': 'Rank 4 (Worst)', 'count': r4, 'rank1': r1})
gender = self._get_voice_gender(label) if color_gender else None
stats.append({'item': label, 'rank': 'Rank 1 (Best)', 'count': r1, 'total': total, 'gender': gender, 'rank_order': 1})
stats.append({'item': label, 'rank': 'Rank 2', 'count': r2, 'total': total, 'gender': gender, 'rank_order': 2})
stats.append({'item': label, 'rank': 'Rank 3', 'count': r3, 'total': total, 'gender': gender, 'rank_order': 3})
# stats.append({'item': label, 'rank': 'Rank 4 (Worst)', 'count': r4, 'total': total, 'gender': gender, 'rank_order': 4})
if not stats:
return alt.Chart(pd.DataFrame({'text': ['No data']})).mark_text().encode(text='text:N')
@@ -419,14 +506,48 @@ class QualtricsPlotsMixin:
# Interactive legend selection - click to filter
selection = alt.selection_point(fields=['rank'], bind='legend')
if color_gender:
# Add gender_rank column for combined color encoding
stats_df['gender_rank'] = stats_df['gender'] + ' - ' + stats_df['rank']
# Define combined domain and range for gender + rank
domain = [
'Male - Rank 1 (Best)', 'Male - Rank 2', 'Male - Rank 3',
'Female - Rank 1 (Best)', 'Female - Rank 2', 'Female - Rank 3'
]
range_colors = [
ColorPalette.GENDER_MALE_RANK_1, ColorPalette.GENDER_MALE_RANK_2, ColorPalette.GENDER_MALE_RANK_3,
ColorPalette.GENDER_FEMALE_RANK_1, ColorPalette.GENDER_FEMALE_RANK_2, ColorPalette.GENDER_FEMALE_RANK_3
]
chart = alt.Chart(stats_df).mark_bar().encode(
x=alt.X('item:N', title=x_label, sort=alt.EncodingSortField(field='rank1', order='descending')),
x=alt.X('item:N', title=x_label, sort=alt.EncodingSortField(field='total', order='descending')),
y=alt.Y('count:Q', title=y_label, stack='zero'),
color=alt.Color('gender_rank:N',
scale=alt.Scale(domain=domain, range=range_colors),
legend=alt.Legend(orient='top', direction='horizontal', title=None, columns=3)),
order=alt.Order('rank_order:Q', sort='ascending'),
opacity=alt.condition(selection, alt.value(1), alt.value(0.2)),
tooltip=[
alt.Tooltip('item:N', title='Item'),
alt.Tooltip('rank:N', title='Rank'),
alt.Tooltip('count:Q', title='Count'),
alt.Tooltip('gender:N', title='Gender')
]
).add_params(selection).properties(
title=self._process_title(title),
width=width or 800,
height=height or getattr(self, 'plot_height', 400)
)
else:
chart = alt.Chart(stats_df).mark_bar().encode(
x=alt.X('item:N', title=x_label, sort=alt.EncodingSortField(field='total', order='descending')),
y=alt.Y('count:Q', title=y_label, stack='zero'),
color=alt.Color('rank:N',
scale=alt.Scale(domain=['Rank 1 (Best)', 'Rank 2', 'Rank 3'],
range=[ColorPalette.RANK_1, ColorPalette.RANK_2, ColorPalette.RANK_3]),
legend=alt.Legend(orient='top', direction='horizontal', title=None)),
order=alt.Order('rank:N', sort='ascending'),
order=alt.Order('rank_order:Q', sort='ascending'),
opacity=alt.condition(selection, alt.value(1), alt.value(0.2)),
tooltip=[
alt.Tooltip('item:N', title='Item'),
@@ -450,8 +571,14 @@ class QualtricsPlotsMixin:
y_label: str = "Count of 1st Place Rankings",
height: int | None = None,
width: int | str | None = None,
color_gender: bool = False,
) -> alt.Chart:
"""Create a bar chart showing which item was ranked #1 the most. Top 3 highlighted."""
"""Create a bar chart showing which item was ranked #1 the most. Top 3 highlighted.
Parameters:
color_gender: If True, color bars by voice gender with highlight/neutral intensity
(blue shades=male, pink shades=female).
"""
df = self._ensure_dataframe(data)
stats = []
@@ -460,7 +587,8 @@ class QualtricsPlotsMixin:
for col in ranking_cols:
count_rank_1 = df.filter(pl.col(col) == 1).height
label = self._clean_voice_label(col)
stats.append({'item': label, 'count': count_rank_1})
gender = self._get_voice_gender(label) if color_gender else None
stats.append({'item': label, 'count': count_rank_1, 'gender': gender})
# Convert and sort
stats_df = pl.DataFrame(stats).sort('count', descending=True)
@@ -474,6 +602,34 @@ class QualtricsPlotsMixin:
.alias('category')
).to_pandas()
if color_gender:
# Add gender_category column for combined color encoding
stats_df['gender_category'] = stats_df['gender'] + ' - ' + stats_df['category']
# Define combined domain and range for gender + category
domain = ['Male - Top 3', 'Male - Other', 'Female - Top 3', 'Female - Other']
range_colors = [
ColorPalette.GENDER_MALE, ColorPalette.GENDER_MALE_NEUTRAL,
ColorPalette.GENDER_FEMALE, ColorPalette.GENDER_FEMALE_NEUTRAL
]
chart = alt.Chart(stats_df).mark_bar().encode(
x=alt.X('item:N', title=x_label, sort='-y'),
y=alt.Y('count:Q', title=y_label),
color=alt.Color('gender_category:N',
scale=alt.Scale(domain=domain, range=range_colors),
legend=alt.Legend(orient='top', direction='horizontal', title=None)),
tooltip=[
alt.Tooltip('item:N', title='Item'),
alt.Tooltip('count:Q', title='1st Place Votes'),
alt.Tooltip('gender:N', title='Gender')
]
).properties(
title=self._process_title(title),
width=width or 800,
height=height or getattr(self, 'plot_height', 400)
)
else:
# Bar chart with conditional color
chart = alt.Chart(stats_df).mark_bar().encode(
x=alt.X('item:N', title=x_label, sort='-y'),
@@ -504,10 +660,34 @@ class QualtricsPlotsMixin:
color: str = ColorPalette.PRIMARY,
height: int | None = None,
width: int | str | None = None,
color_gender: bool = False,
) -> alt.Chart:
"""Create a bar chart showing the weighted ranking score for each character."""
"""Create a bar chart showing the weighted ranking score for each character.
Parameters:
color_gender: If True, color bars by voice gender (blue=male, pink=female).
"""
weighted_df = self._ensure_dataframe(data).to_pandas()
if color_gender:
# Add gender column based on Character name
weighted_df['gender'] = weighted_df['Character'].apply(self._get_voice_gender)
# Bar chart with gender coloring
bars = alt.Chart(weighted_df).mark_bar().encode(
x=alt.X('Character:N', title=x_label, sort='-y'),
y=alt.Y('Weighted Score:Q', title=y_label),
color=alt.Color('gender:N',
scale=alt.Scale(domain=['Male', 'Female'],
range=[ColorPalette.GENDER_MALE, ColorPalette.GENDER_FEMALE]),
legend=alt.Legend(orient='top', direction='horizontal', title='Gender')),
tooltip=[
alt.Tooltip('Character:N'),
alt.Tooltip('Weighted Score:Q', title='Score'),
alt.Tooltip('gender:N', title='Gender')
]
)
else:
# Bar chart
bars = alt.Chart(weighted_df).mark_bar(color=color).encode(
x=alt.X('Character:N', title=x_label, sort='-y'),
@@ -545,8 +725,14 @@ class QualtricsPlotsMixin:
y_label: str = "Number of Times Chosen",
height: int | None = None,
width: int | str | None = None,
color_gender: bool = False,
) -> alt.Chart:
"""Create a bar plot showing the frequency of voice selections."""
"""Create a bar plot showing the frequency of voice selections.
Parameters:
color_gender: If True, color bars by voice gender with highlight/neutral intensity
(blue shades=male, pink shades=female).
"""
df = self._ensure_dataframe(data)
if target_column not in df.columns:
@@ -573,6 +759,36 @@ class QualtricsPlotsMixin:
.to_pandas()
)
if color_gender:
# Add gender column based on voice label
stats_df['gender'] = stats_df[target_column].apply(self._get_voice_gender)
# Add gender_category column for combined color encoding
stats_df['gender_category'] = stats_df['gender'] + ' - ' + stats_df['category']
# Define combined domain and range for gender + category
domain = ['Male - Top 8', 'Male - Other', 'Female - Top 8', 'Female - Other']
range_colors = [
ColorPalette.GENDER_MALE, ColorPalette.GENDER_MALE_NEUTRAL,
ColorPalette.GENDER_FEMALE, ColorPalette.GENDER_FEMALE_NEUTRAL
]
chart = alt.Chart(stats_df).mark_bar().encode(
x=alt.X(f'{target_column}:N', title=x_label, sort='-y'),
y=alt.Y('count:Q', title=y_label),
color=alt.Color('gender_category:N',
scale=alt.Scale(domain=domain, range=range_colors),
legend=alt.Legend(orient='top', direction='horizontal', title=None)),
tooltip=[
alt.Tooltip(f'{target_column}:N', title='Voice'),
alt.Tooltip('count:Q', title='Selections'),
alt.Tooltip('gender:N', title='Gender')
]
).properties(
title=self._process_title(title),
width=width or 800,
height=height or getattr(self, 'plot_height', 400)
)
else:
chart = alt.Chart(stats_df).mark_bar().encode(
x=alt.X(f'{target_column}:N', title=x_label, sort='-y'),
y=alt.Y('count:Q', title=y_label),
@@ -602,8 +818,14 @@ class QualtricsPlotsMixin:
y_label: str = "Count of Mentions in Top 3",
height: int | None = None,
width: int | str | None = None,
color_gender: bool = False,
) -> alt.Chart:
"""Question: Which 3 voices are chosen the most out of 18?"""
"""Question: Which 3 voices are chosen the most out of 18?
Parameters:
color_gender: If True, color bars by voice gender with highlight/neutral intensity
(blue shades=male, pink shades=female).
"""
df = self._ensure_dataframe(data)
if target_column not in df.columns:
@@ -629,6 +851,36 @@ class QualtricsPlotsMixin:
.to_pandas()
)
if color_gender:
# Add gender column based on voice label
stats_df['gender'] = stats_df[target_column].apply(self._get_voice_gender)
# Add gender_category column for combined color encoding
stats_df['gender_category'] = stats_df['gender'] + ' - ' + stats_df['category']
# Define combined domain and range for gender + category
domain = ['Male - Top 3', 'Male - Other', 'Female - Top 3', 'Female - Other']
range_colors = [
ColorPalette.GENDER_MALE, ColorPalette.GENDER_MALE_NEUTRAL,
ColorPalette.GENDER_FEMALE, ColorPalette.GENDER_FEMALE_NEUTRAL
]
chart = alt.Chart(stats_df).mark_bar().encode(
x=alt.X(f'{target_column}:N', title=x_label, sort='-y'),
y=alt.Y('count:Q', title=y_label),
color=alt.Color('gender_category:N',
scale=alt.Scale(domain=domain, range=range_colors),
legend=alt.Legend(orient='top', direction='horizontal', title=None)),
tooltip=[
alt.Tooltip(f'{target_column}:N', title='Voice'),
alt.Tooltip('count:Q', title='In Top 3'),
alt.Tooltip('gender:N', title='Gender')
]
).properties(
title=self._process_title(title),
width=width or 800,
height=height or getattr(self, 'plot_height', 400)
)
else:
chart = alt.Chart(stats_df).mark_bar().encode(
x=alt.X(f'{target_column}:N', title=x_label, sort='-y'),
y=alt.Y('count:Q', title=y_label),

18
theme.py
View File

@@ -59,6 +59,24 @@ class ColorPalette:
"#457B9D", # Steel Blue
]
# Gender-based colors (Male = Blue tones, Female = Pink tones)
# Primary colors by gender
GENDER_MALE = "#0077B6" # Medium Blue (same as PRIMARY)
GENDER_FEMALE = "#B6007A" # Medium Pink
# Ranking colors by gender (Darkest -> Lightest)
GENDER_MALE_RANK_1 = "#004C6D" # Dark Blue
GENDER_MALE_RANK_2 = "#0077B6" # Medium Blue
GENDER_MALE_RANK_3 = "#669BBC" # Light Steel Blue
GENDER_FEMALE_RANK_1 = "#6D004C" # Dark Pink
GENDER_FEMALE_RANK_2 = "#B6007A" # Medium Pink
GENDER_FEMALE_RANK_3 = "#BC669B" # Light Pink
# Neutral colors by gender (for non-highlighted items)
GENDER_MALE_NEUTRAL = "#B8C9D9" # Grey-Blue
GENDER_FEMALE_NEUTRAL = "#D9B8C9" # Grey-Pink
def jpmc_altair_theme():
"""JPMC brand theme for Altair charts."""

7
utils.py
View File

@@ -508,9 +508,16 @@ def update_ppt_alt_text(ppt_path: Union[str, Path], image_source_dir: Union[str,
print(f"Error updating alt text for {original_path}: {e}")
else:
# Check if image already has alt text set - if so, skip reporting as unmatched
existing_alt = _get_shape_alt_text(shape)
if existing_alt:
# Image already has alt text, no need to report as unmatched
continue
shape_id = getattr(shape, 'shape_id', getattr(shape, 'id', 'Unknown ID'))
shape_name = shape.name if shape.name else f"Unnamed Shape (ID: {shape_id})"
hash_type = "pHash" if use_perceptual_hash else "SHA1"
unmatched_images.append({
'slide': i+1,
'shape_name': shape_name,