Spaces:
Sleeping
Sleeping
File size: 10,290 Bytes
48909ac |
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 |
"""
Visualization module for the Business Intelligence Dashboard.
This module creates various types of charts and visualizations
using the Strategy Pattern for different chart types.
"""
from abc import ABC, abstractmethod
from typing import Dict, List, Optional, Tuple, Any
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
import plotly.graph_objects as go
from plotly.subplots import make_subplots
from utils import detect_column_types
from constants import (
HISTOGRAM_BINS,
MAX_CATEGORY_DISPLAY,
MIN_NUMERICAL_COLUMNS_FOR_CORRELATION
)
class VisualizationStrategy(ABC):
"""Abstract base class for visualization strategies."""
@abstractmethod
def create_chart(
self,
df: pd.DataFrame,
x_column: Optional[str] = None,
y_column: Optional[str] = None,
aggregation: str = 'sum',
**kwargs
) -> go.Figure:
"""
Create a visualization.
Args:
df: Input DataFrame
x_column: X-axis column
y_column: Y-axis column
aggregation: Aggregation method (sum, mean, count, median)
**kwargs: Additional parameters
Returns:
Plotly figure object
"""
pass
class TimeSeriesStrategy(VisualizationStrategy):
"""Strategy for creating time series plots."""
def create_chart(
self,
df: pd.DataFrame,
x_column: Optional[str] = None,
y_column: Optional[str] = None,
aggregation: str = 'sum',
**kwargs
) -> go.Figure:
"""Create time series plot."""
if x_column is None or y_column is None:
raise ValueError("Both x_column and y_column required for time series")
# Convert date column
df = df.copy()
df[x_column] = pd.to_datetime(df[x_column], errors='coerce')
df = df.dropna(subset=[x_column, y_column])
# Aggregate if needed
if aggregation != 'none':
df = df.groupby(x_column)[y_column].agg(aggregation).reset_index()
fig = px.line(
df,
x=x_column,
y=y_column,
title=f'Time Series: {y_column} over {x_column}',
labels={x_column: x_column, y_column: y_column}
)
fig.update_layout(
xaxis_title=x_column,
yaxis_title=y_column,
hovermode='x unified',
template='plotly_white'
)
return fig
class DistributionStrategy(VisualizationStrategy):
"""Strategy for creating distribution plots."""
def create_chart(
self,
df: pd.DataFrame,
x_column: Optional[str] = None,
y_column: Optional[str] = None,
aggregation: str = 'sum',
sub_chart_type: str = 'histogram',
**kwargs
) -> go.Figure:
"""Create distribution plot (histogram or box plot)."""
if x_column is None:
raise ValueError("x_column required for distribution plot")
# Get sub_chart_type from kwargs if provided, otherwise use parameter
# Check both 'sub_chart_type' (new) and 'chart_type' (legacy) for compatibility
sub_chart_type = kwargs.pop('sub_chart_type', kwargs.pop('chart_type', sub_chart_type))
df = df.copy()
df = df.dropna(subset=[x_column])
if sub_chart_type == 'histogram':
fig = px.histogram(
df,
x=x_column,
title=f'Distribution of {x_column}',
labels={x_column: x_column, 'count': 'Frequency'},
nbins=HISTOGRAM_BINS
)
else: # box plot
fig = px.box(
df,
y=x_column,
title=f'Box Plot of {x_column}',
labels={x_column: x_column}
)
fig.update_layout(
template='plotly_white',
showlegend=False
)
return fig
class CategoryAnalysisStrategy(VisualizationStrategy):
"""Strategy for creating category analysis charts."""
def create_chart(
self,
df: pd.DataFrame,
x_column: Optional[str] = None,
y_column: Optional[str] = None,
aggregation: str = 'sum',
sub_chart_type: str = 'bar',
**kwargs
) -> go.Figure:
"""Create category analysis (bar chart or pie chart)."""
if x_column is None:
raise ValueError("x_column required for category analysis")
# Get sub_chart_type from kwargs if provided, otherwise use parameter
# Check both 'sub_chart_type' (new) and 'chart_type' (legacy) for compatibility
sub_chart_type = kwargs.pop('sub_chart_type', kwargs.pop('chart_type', sub_chart_type))
df = df.copy()
df = df.dropna(subset=[x_column])
if y_column:
# Aggregate by category
if aggregation != 'none':
df_agg = df.groupby(x_column)[y_column].agg(aggregation).reset_index()
df_agg.columns = [x_column, y_column]
else:
df_agg = df[[x_column, y_column]]
# Sort by value
df_agg = df_agg.sort_values(y_column, ascending=False).head(MAX_CATEGORY_DISPLAY)
if sub_chart_type == 'bar':
fig = px.bar(
df_agg,
x=x_column,
y=y_column,
title=f'{y_column} by {x_column}',
labels={x_column: x_column, y_column: y_column}
)
else: # pie
fig = px.pie(
df_agg,
names=x_column,
values=y_column,
title=f'{y_column} Distribution by {x_column}'
)
else:
# Count by category
value_counts = df[x_column].value_counts().head(MAX_CATEGORY_DISPLAY)
if sub_chart_type == 'bar':
fig = px.bar(
x=value_counts.index,
y=value_counts.values,
title=f'Count by {x_column}',
labels={'x': x_column, 'y': 'Count'}
)
else: # pie
fig = px.pie(
values=value_counts.values,
names=value_counts.index,
title=f'Distribution of {x_column}'
)
fig.update_layout(template='plotly_white')
return fig
class ScatterStrategy(VisualizationStrategy):
"""Strategy for creating scatter plots."""
def create_chart(
self,
df: pd.DataFrame,
x_column: Optional[str] = None,
y_column: Optional[str] = None,
aggregation: str = 'sum',
color_column: Optional[str] = None,
**kwargs
) -> go.Figure:
"""Create scatter plot."""
if x_column is None or y_column is None:
raise ValueError("Both x_column and y_column required for scatter plot")
df = df.copy()
df = df.dropna(subset=[x_column, y_column])
fig = px.scatter(
df,
x=x_column,
y=y_column,
color=color_column,
title=f'Scatter Plot: {y_column} vs {x_column}',
labels={x_column: x_column, y_column: y_column},
hover_data=df.columns.tolist()
)
fig.update_layout(template='plotly_white')
return fig
class CorrelationHeatmapStrategy(VisualizationStrategy):
"""Strategy for creating correlation heatmaps."""
def create_chart(
self,
df: pd.DataFrame,
x_column: Optional[str] = None,
y_column: Optional[str] = None,
aggregation: str = 'sum',
**kwargs
) -> go.Figure:
"""Create correlation heatmap."""
numerical, _, _ = detect_column_types(df)
if len(numerical) < MIN_NUMERICAL_COLUMNS_FOR_CORRELATION:
raise ValueError(
f"Need at least {MIN_NUMERICAL_COLUMNS_FOR_CORRELATION} "
"numerical columns for correlation"
)
corr_matrix = df[numerical].corr()
fig = px.imshow(
corr_matrix,
title='Correlation Heatmap',
labels=dict(x="Column", y="Column", color="Correlation"),
color_continuous_scale='RdBu',
aspect="auto"
)
fig.update_layout(template='plotly_white')
return fig
class VisualizationFactory:
"""Factory class for creating visualizations using Strategy Pattern."""
def __init__(self):
"""Initialize with visualization strategies."""
self._strategies = {
'time_series': TimeSeriesStrategy(),
'distribution': DistributionStrategy(),
'category': CategoryAnalysisStrategy(),
'scatter': ScatterStrategy(),
'correlation': CorrelationHeatmapStrategy()
}
def create_visualization(
self,
chart_type: str,
df: pd.DataFrame,
x_column: Optional[str] = None,
y_column: Optional[str] = None,
aggregation: str = 'sum',
**kwargs
) -> go.Figure:
"""
Create visualization using appropriate strategy.
Args:
chart_type: Type of chart to create
df: Input DataFrame
x_column: X-axis column
y_column: Y-axis column
aggregation: Aggregation method
**kwargs: Additional parameters
Returns:
Plotly figure object
"""
if chart_type not in self._strategies:
raise ValueError(f"Unknown chart type: {chart_type}")
strategy = self._strategies[chart_type]
return strategy.create_chart(
df,
x_column=x_column,
y_column=y_column,
aggregation=aggregation,
**kwargs
)
|