File size: 15,348 Bytes
9858829 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 | """
Demographic visualization charts for sentiment analysis
Handles age, timezone, and experience level visualizations
"""
import plotly.graph_objects as go
import plotly.express as px
import json
from pathlib import Path
class DemographicCharts:
"""
Creates demographic-related visualizations for musora_app data
"""
def __init__(self):
"""Initialize with configuration"""
config_path = Path(__file__).parent.parent / "config" / "viz_config.json"
with open(config_path, 'r') as f:
self.config = json.load(f)
self.sentiment_colors = self.config['color_schemes']['sentiment_polarity']
self.sentiment_order = self.config['sentiment_order']
self.chart_height = self.config['dashboard']['chart_height']
def create_age_distribution_chart(self, age_dist_df, title="Age Distribution"):
"""
Create bar chart for age group distribution
Args:
age_dist_df: DataFrame with age_group, count, percentage columns
title: Chart title
Returns:
plotly.graph_objects.Figure
"""
if age_dist_df.empty:
return self._create_empty_chart(title, "No demographic data available")
# Define custom age group order
age_order = ['18-24', '25-34', '35-44', '45-54', '55+']
# Sort by custom order
age_dist_df['age_group'] = pd.Categorical(
age_dist_df['age_group'],
categories=age_order,
ordered=True
)
age_dist_df = age_dist_df.sort_values('age_group')
fig = go.Figure()
fig.add_trace(go.Bar(
x=age_dist_df['age_group'],
y=age_dist_df['count'],
text=age_dist_df.apply(lambda row: f"{row['count']}<br>({row['percentage']:.1f}%)", axis=1),
textposition='auto',
marker=dict(
color='#4A90E2',
line=dict(color='#2E5C8A', width=1)
),
hovertemplate='<b>%{x}</b><br>Comments: %{y}<br>Percentage: %{customdata:.1f}%<extra></extra>',
customdata=age_dist_df['percentage']
))
fig.update_layout(
title=title,
xaxis_title="Age Group",
yaxis_title="Number of Comments",
height=self.chart_height,
showlegend=False,
hovermode='x'
)
return fig
def create_age_sentiment_chart(self, age_sentiment_df, title="Sentiment by Age Group"):
"""
Create stacked bar chart showing sentiment distribution for each age group
Args:
age_sentiment_df: DataFrame with age_group, sentiment_polarity, count, percentage
title: Chart title
Returns:
plotly.graph_objects.Figure
"""
if age_sentiment_df.empty:
return self._create_empty_chart(title, "No demographic data available")
# Define custom age group order
age_order = ['18-24', '25-34', '35-44', '45-54', '55+']
fig = go.Figure()
# Create a trace for each sentiment
for sentiment in self.sentiment_order:
sentiment_data = age_sentiment_df[age_sentiment_df['sentiment_polarity'] == sentiment]
if not sentiment_data.empty:
fig.add_trace(go.Bar(
name=sentiment.replace('_', ' ').title(),
x=sentiment_data['age_group'],
y=sentiment_data['percentage'],
marker=dict(color=self.sentiment_colors.get(sentiment, '#999999')),
hovertemplate='<b>%{fullData.name}</b><br>Age: %{x}<br>Percentage: %{y:.1f}%<extra></extra>'
))
fig.update_layout(
title=title,
xaxis=dict(
title="Age Group",
categoryorder='array',
categoryarray=age_order
),
yaxis=dict(
title="Percentage (%)",
range=[0, 100]
),
barmode='stack',
height=self.chart_height,
hovermode='x unified',
legend=dict(
orientation="h",
yanchor="bottom",
y=1.02,
xanchor="right",
x=1
)
)
return fig
def create_timezone_chart(self, timezone_df, title="Top Timezones", top_n=15):
"""
Create horizontal bar chart for top timezones
Args:
timezone_df: DataFrame with timezone, count, percentage columns
title: Chart title
top_n: Number of top timezones to display
Returns:
plotly.graph_objects.Figure
"""
if timezone_df.empty:
return self._create_empty_chart(title, "No timezone data available")
# Take top N and reverse for better display (highest at top)
display_df = timezone_df.head(top_n).iloc[::-1]
fig = go.Figure()
fig.add_trace(go.Bar(
y=display_df['timezone'],
x=display_df['count'],
orientation='h',
text=display_df.apply(lambda row: f"{row['count']} ({row['percentage']:.1f}%)", axis=1),
textposition='auto',
marker=dict(
color='#50C878',
line=dict(color='#2E7D4E', width=1)
),
hovertemplate='<b>%{y}</b><br>Comments: %{x}<br>Percentage: %{customdata:.1f}%<extra></extra>',
customdata=display_df['percentage']
))
fig.update_layout(
title=title,
xaxis_title="Number of Comments",
yaxis_title="Timezone",
height=max(self.chart_height, top_n * 25), # Dynamic height based on number of timezones
showlegend=False,
hovermode='y'
)
return fig
def create_region_distribution_chart(self, region_df, title="Distribution by Region"):
"""
Create pie chart for timezone region distribution
Args:
region_df: DataFrame with timezone_region, count, percentage columns
title: Chart title
Returns:
plotly.graph_objects.Figure
"""
if region_df.empty:
return self._create_empty_chart(title, "No region data available")
# Define color palette for regions
colors = px.colors.qualitative.Set3
fig = go.Figure()
fig.add_trace(go.Pie(
labels=region_df['timezone_region'],
values=region_df['count'],
textinfo='label+percent',
hovertemplate='<b>%{label}</b><br>Comments: %{value}<br>Percentage: %{percent}<extra></extra>',
marker=dict(colors=colors)
))
fig.update_layout(
title=title,
height=self.chart_height,
showlegend=True,
legend=dict(
orientation="v",
yanchor="middle",
y=0.5,
xanchor="left",
x=1
)
)
return fig
def create_region_sentiment_chart(self, region_sentiment_df, title="Sentiment by Region"):
"""
Create grouped bar chart showing sentiment distribution for each region
Args:
region_sentiment_df: DataFrame with timezone_region, sentiment_polarity, count, percentage
title: Chart title
Returns:
plotly.graph_objects.Figure
"""
if region_sentiment_df.empty:
return self._create_empty_chart(title, "No region sentiment data available")
fig = go.Figure()
# Create a trace for each sentiment
for sentiment in self.sentiment_order:
sentiment_data = region_sentiment_df[region_sentiment_df['sentiment_polarity'] == sentiment]
if not sentiment_data.empty:
fig.add_trace(go.Bar(
name=sentiment.replace('_', ' ').title(),
x=sentiment_data['timezone_region'],
y=sentiment_data['percentage'],
marker=dict(color=self.sentiment_colors.get(sentiment, '#999999')),
hovertemplate='<b>%{fullData.name}</b><br>Region: %{x}<br>Percentage: %{y:.1f}%<extra></extra>'
))
fig.update_layout(
title=title,
xaxis_title="Region",
yaxis=dict(
title="Percentage (%)",
range=[0, 100]
),
barmode='stack',
height=self.chart_height,
hovermode='x unified',
legend=dict(
orientation="h",
yanchor="bottom",
y=1.02,
xanchor="right",
x=1
)
)
return fig
def create_experience_distribution_chart(self, exp_df, title="Experience Level Distribution", use_groups=False):
"""
Create bar chart for experience level distribution
Args:
exp_df: DataFrame with experience_level/experience_group, count, percentage columns
title: Chart title
use_groups: If True, display grouped experience levels
Returns:
plotly.graph_objects.Figure
"""
if exp_df.empty:
return self._create_empty_chart(title, "No experience data available")
field = 'experience_group' if use_groups else 'experience_level'
# Define custom order for grouped experience
if use_groups:
exp_order = ['Beginner (0-3)', 'Intermediate (4-7)', 'Advanced (8-10)']
exp_df[field] = pd.Categorical(
exp_df[field],
categories=exp_order,
ordered=True
)
exp_df = exp_df.sort_values(field)
else:
# Sort by experience level numerically
exp_df = exp_df.sort_values(field)
fig = go.Figure()
fig.add_trace(go.Bar(
x=exp_df[field],
y=exp_df['count'],
text=exp_df.apply(lambda row: f"{row['count']}<br>({row['percentage']:.1f}%)", axis=1),
textposition='auto',
marker=dict(
color='#9B59B6',
line=dict(color='#6C3483', width=1)
),
hovertemplate='<b>%{x}</b><br>Comments: %{y}<br>Percentage: %{customdata:.1f}%<extra></extra>',
customdata=exp_df['percentage']
))
fig.update_layout(
title=title,
xaxis_title="Experience Level" if not use_groups else "Experience Group",
yaxis_title="Number of Comments",
height=self.chart_height,
showlegend=False,
hovermode='x'
)
return fig
def create_experience_sentiment_chart(self, exp_sentiment_df, title="Sentiment by Experience Level", use_groups=False):
"""
Create stacked bar chart showing sentiment distribution for each experience level
Args:
exp_sentiment_df: DataFrame with experience_level/experience_group, sentiment_polarity, count, percentage
title: Chart title
use_groups: If True, use grouped experience levels
Returns:
plotly.graph_objects.Figure
"""
if exp_sentiment_df.empty:
return self._create_empty_chart(title, "No experience sentiment data available")
field = 'experience_group' if use_groups else 'experience_level'
fig = go.Figure()
# Create a trace for each sentiment
for sentiment in self.sentiment_order:
sentiment_data = exp_sentiment_df[exp_sentiment_df['sentiment_polarity'] == sentiment]
if not sentiment_data.empty:
fig.add_trace(go.Bar(
name=sentiment.replace('_', ' ').title(),
x=sentiment_data[field],
y=sentiment_data['percentage'],
marker=dict(color=self.sentiment_colors.get(sentiment, '#999999')),
hovertemplate='<b>%{fullData.name}</b><br>Experience: %{x}<br>Percentage: %{y:.1f}%<extra></extra>'
))
# Define custom order for grouped experience
if use_groups:
exp_order = ['Beginner (0-3)', 'Intermediate (4-7)', 'Advanced (8-10)']
xaxis_config = dict(
title="Experience Group",
categoryorder='array',
categoryarray=exp_order
)
else:
xaxis_config = dict(title="Experience Level")
fig.update_layout(
title=title,
xaxis=xaxis_config,
yaxis=dict(
title="Percentage (%)",
range=[0, 100]
),
barmode='stack',
height=self.chart_height,
hovermode='x unified',
legend=dict(
orientation="h",
yanchor="bottom",
y=1.02,
xanchor="right",
x=1
)
)
return fig
def create_demographics_heatmap(self, df, row_field, col_field, title="Demographics Heatmap"):
"""
Create heatmap for cross-demographic analysis
Args:
df: DataFrame with demographic fields and sentiment
row_field: Field for rows (e.g., 'age_group')
col_field: Field for columns (e.g., 'experience_group')
title: Chart title
Returns:
plotly.graph_objects.Figure
"""
if df.empty:
return self._create_empty_chart(title, "No data available for heatmap")
# Create pivot table
pivot = df.pivot_table(
index=row_field,
columns=col_field,
values='count',
aggfunc='sum',
fill_value=0
)
fig = go.Figure(data=go.Heatmap(
z=pivot.values,
x=pivot.columns,
y=pivot.index,
colorscale='Blues',
text=pivot.values,
texttemplate='%{text}',
textfont={"size": 10},
hovertemplate='<b>%{y}</b> × <b>%{x}</b><br>Comments: %{z}<extra></extra>'
))
fig.update_layout(
title=title,
xaxis_title=col_field.replace('_', ' ').title(),
yaxis_title=row_field.replace('_', ' ').title(),
height=self.chart_height
)
return fig
def _create_empty_chart(self, title, message):
"""
Create an empty chart with a message
Args:
title: Chart title
message: Message to display
Returns:
plotly.graph_objects.Figure
"""
fig = go.Figure()
fig.add_annotation(
text=message,
xref="paper",
yref="paper",
x=0.5,
y=0.5,
showarrow=False,
font=dict(size=14, color="gray")
)
fig.update_layout(
title=title,
height=self.chart_height,
xaxis=dict(visible=False),
yaxis=dict(visible=False)
)
return fig
# Import pandas for use in methods (needed for Categorical)
import pandas as pd
|