File size: 12,449 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 | """
Distribution visualization components using Plotly
Creates charts for intent, language, and other distributions
"""
import plotly.graph_objects as go
import plotly.express as px
from plotly.subplots import make_subplots
import pandas as pd
import json
from pathlib import Path
class DistributionCharts:
"""
Creates distribution visualizations
"""
def __init__(self, config_path=None):
"""
Initialize with configuration
Args:
config_path: Path to configuration file
"""
if config_path is None:
config_path = Path(__file__).parent.parent / "config" / "viz_config.json"
with open(config_path, 'r') as f:
self.config = json.load(f)
self.intent_colors = self.config['color_schemes']['intent']
self.platform_colors = self.config['color_schemes']['platform']
self.brand_colors = self.config['color_schemes']['brand']
self.intent_order = self.config['intent_order']
self.chart_height = self.config['dashboard']['chart_height']
def create_intent_bar_chart(self, df, title="Intent Distribution", orientation='h'):
"""
Create horizontal bar chart for intent distribution (handles multi-label)
Args:
df: Sentiment dataframe
title: Chart title
orientation: 'h' for horizontal, 'v' for vertical
Returns:
plotly.graph_objects.Figure
"""
# Explode intents
df_exploded = df.copy()
df_exploded['intent'] = df_exploded['intent'].str.split(',')
df_exploded = df_exploded.explode('intent')
df_exploded['intent'] = df_exploded['intent'].str.strip()
# Count intents
intent_counts = df_exploded['intent'].value_counts()
# Order by intent_order
ordered_intents = [i for i in self.intent_order if i in intent_counts.index]
intent_counts = intent_counts[ordered_intents]
colors = [self.intent_colors.get(i, '#CCCCCC') for i in intent_counts.index]
if orientation == 'h':
fig = go.Figure(data=[go.Bar(
y=intent_counts.index,
x=intent_counts.values,
orientation='h',
marker=dict(color=colors),
text=intent_counts.values,
textposition='auto',
hovertemplate='<b>%{y}</b><br>Count: %{x}<extra></extra>'
)])
fig.update_layout(
title=title,
xaxis_title="Number of Comments",
yaxis_title="Intent",
height=self.chart_height,
yaxis={'categoryorder': 'total ascending'}
)
else:
fig = go.Figure(data=[go.Bar(
x=intent_counts.index,
y=intent_counts.values,
marker=dict(color=colors),
text=intent_counts.values,
textposition='auto',
hovertemplate='<b>%{x}</b><br>Count: %{y}<extra></extra>'
)])
fig.update_layout(
title=title,
xaxis_title="Intent",
yaxis_title="Number of Comments",
height=self.chart_height
)
return fig
def create_intent_pie_chart(self, df, title="Intent Distribution"):
"""
Create pie chart for intent distribution
Args:
df: Sentiment dataframe
title: Chart title
Returns:
plotly.graph_objects.Figure
"""
# Explode intents
df_exploded = df.copy()
df_exploded['intent'] = df_exploded['intent'].str.split(',')
df_exploded = df_exploded.explode('intent')
df_exploded['intent'] = df_exploded['intent'].str.strip()
intent_counts = df_exploded['intent'].value_counts()
# Order by intent_order
ordered_intents = [i for i in self.intent_order if i in intent_counts.index]
intent_counts = intent_counts[ordered_intents]
colors = [self.intent_colors.get(i, '#CCCCCC') for i in intent_counts.index]
fig = go.Figure(data=[go.Pie(
labels=intent_counts.index,
values=intent_counts.values,
marker=dict(colors=colors),
textinfo='label+percent',
textposition='auto',
hovertemplate='<b>%{label}</b><br>Count: %{value}<br>Percentage: %{percent}<extra></extra>'
)])
fig.update_layout(
title=title,
height=self.chart_height,
showlegend=True,
legend=dict(orientation="v", yanchor="middle", y=0.5, xanchor="left", x=1.05)
)
return fig
def create_platform_distribution(self, df, title="Comments by Platform"):
"""
Create bar chart for platform distribution
Args:
df: Sentiment dataframe
title: Chart title
Returns:
plotly.graph_objects.Figure
"""
platform_counts = df['platform'].value_counts()
colors = [self.platform_colors.get(p, self.platform_colors['default']) for p in platform_counts.index]
fig = go.Figure(data=[go.Bar(
x=platform_counts.index,
y=platform_counts.values,
marker=dict(color=colors),
text=platform_counts.values,
textposition='auto',
hovertemplate='<b>%{x}</b><br>Comments: %{y}<extra></extra>'
)])
fig.update_layout(
title=title,
xaxis_title="Platform",
yaxis_title="Number of Comments",
height=self.chart_height
)
return fig
def create_brand_distribution(self, df, title="Comments by Brand"):
"""
Create bar chart for brand distribution
Args:
df: Sentiment dataframe
title: Chart title
Returns:
plotly.graph_objects.Figure
"""
brand_counts = df['brand'].value_counts()
colors = [self.brand_colors.get(b, self.brand_colors['default']) for b in brand_counts.index]
fig = go.Figure(data=[go.Bar(
x=brand_counts.index,
y=brand_counts.values,
marker=dict(color=colors),
text=brand_counts.values,
textposition='auto',
hovertemplate='<b>%{x}</b><br>Comments: %{y}<extra></extra>'
)])
fig.update_layout(
title=title,
xaxis_title="Brand",
yaxis_title="Number of Comments",
height=self.chart_height
)
return fig
def create_language_distribution(self, df, top_n=10, title="Language Distribution"):
"""
Create bar chart for language distribution
Args:
df: Sentiment dataframe
top_n: Number of top languages to show
title: Chart title
Returns:
plotly.graph_objects.Figure
"""
if 'detected_language' not in df.columns:
return go.Figure().add_annotation(
text="No language data available",
xref="paper", yref="paper",
x=0.5, y=0.5, showarrow=False
)
lang_counts = df['detected_language'].value_counts().head(top_n)
fig = go.Figure(data=[go.Bar(
x=lang_counts.index,
y=lang_counts.values,
marker=dict(color='#2196F3'),
text=lang_counts.values,
textposition='auto',
hovertemplate='<b>%{x}</b><br>Comments: %{y}<extra></extra>'
)])
fig.update_layout(
title=title,
xaxis_title="Language",
yaxis_title="Number of Comments",
height=self.chart_height
)
return fig
def create_combined_distribution_sunburst(self, df, title="Hierarchical Distribution"):
"""
Create sunburst chart showing hierarchical distribution
(Brand > Platform > Sentiment)
Args:
df: Sentiment dataframe
title: Chart title
Returns:
plotly.graph_objects.Figure
"""
# Prepare data for sunburst
sunburst_data = df.groupby(['brand', 'platform', 'sentiment_polarity']).size().reset_index(name='count')
fig = px.sunburst(
sunburst_data,
path=['brand', 'platform', 'sentiment_polarity'],
values='count',
title=title,
height=500
)
fig.update_layout(
margin=dict(t=50, l=0, r=0, b=0)
)
return fig
def create_brand_platform_matrix(self, df, title="Brand-Platform Comment Matrix"):
"""
Create heatmap showing comment distribution across brands and platforms
Args:
df: Sentiment dataframe
title: Chart title
Returns:
plotly.graph_objects.Figure
"""
# Create pivot table
matrix_data = pd.crosstab(df['brand'], df['platform'])
fig = go.Figure(data=go.Heatmap(
z=matrix_data.values,
x=matrix_data.columns,
y=matrix_data.index,
colorscale='Blues',
text=matrix_data.values,
texttemplate='%{text}',
textfont={"size": 14},
hovertemplate='<b>%{y} - %{x}</b><br>Comments: %{z}<extra></extra>',
colorbar=dict(title="Comments")
))
fig.update_layout(
title=title,
xaxis_title="Platform",
yaxis_title="Brand",
height=self.chart_height
)
return fig
def create_reply_required_chart(self, df, group_by='brand', title="Comments Requiring Reply"):
"""
Create stacked bar chart showing reply requirements
Args:
df: Sentiment dataframe
group_by: Column to group by
title: Chart title
Returns:
plotly.graph_objects.Figure
"""
# Create aggregation
reply_data = df.groupby([group_by, 'requires_reply']).size().reset_index(name='count')
reply_pivot = reply_data.pivot(index=group_by, columns='requires_reply', values='count').fillna(0)
fig = go.Figure()
if False in reply_pivot.columns:
fig.add_trace(go.Bar(
name='No Reply Needed',
x=reply_pivot.index,
y=reply_pivot[False],
marker_color='#81C784',
hovertemplate='<b>%{x}</b><br>No Reply: %{y}<extra></extra>'
))
if True in reply_pivot.columns:
fig.add_trace(go.Bar(
name='Reply Required',
x=reply_pivot.index,
y=reply_pivot[True],
marker_color='#FF7043',
hovertemplate='<b>%{x}</b><br>Reply Required: %{y}<extra></extra>'
))
fig.update_layout(
title=title,
xaxis_title=group_by.capitalize(),
yaxis_title="Number of Comments",
barmode='stack',
height=self.chart_height,
legend=dict(title="Reply Status", orientation="v", yanchor="top", y=1, xanchor="left", x=1.02)
)
return fig
def create_engagement_scatter(self, content_summary_df, title="Content Engagement Analysis"):
"""
Create scatter plot showing content engagement
Args:
content_summary_df: DataFrame with content summary statistics
title: Chart title
Returns:
plotly.graph_objects.Figure
"""
fig = px.scatter(
content_summary_df,
x='total_comments',
y='negative_percentage',
size='reply_required_count',
color='negative_percentage',
hover_data=['content_description'],
title=title,
labels={
'total_comments': 'Total Comments',
'negative_percentage': 'Negative Sentiment %',
'reply_required_count': 'Replies Required'
},
color_continuous_scale='RdYlGn_r',
height=self.chart_height
)
fig.update_layout(
xaxis_title="Total Comments",
yaxis_title="Negative Sentiment %",
coloraxis_colorbar=dict(title="Negative %")
)
return fig |