Spaces:
Sleeping
Sleeping
File size: 8,169 Bytes
3670fc5 | 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 | import matplotlib.pyplot as plt
import numpy as np
from wordcloud import WordCloud
from collections import Counter
from typing import List, Dict, Tuple, Optional
import gc
from config import config
from utils import handle_errors, managed_figure
class ThemeContext:
"""Theme management context"""
def __init__(self, theme: str = 'default'):
self.theme = theme
self.colors = config.THEMES.get(theme, config.THEMES['default'])
class PlotFactory:
"""Factory for creating plots with proper memory management"""
@staticmethod
@handle_errors(default_return=None)
def create_sentiment_bars(probs: np.ndarray, theme: ThemeContext) -> plt.Figure:
"""Create sentiment probability bars"""
with managed_figure(figsize=config.FIGURE_SIZE_SINGLE) as fig:
ax = fig.add_subplot(111)
labels = ["Negative", "Positive"]
colors = [theme.colors['neg'], theme.colors['pos']]
bars = ax.bar(labels, probs, color=colors, alpha=0.8)
ax.set_title("Sentiment Probabilities", fontweight='bold')
ax.set_ylabel("Probability")
ax.set_ylim(0, 1)
for bar, prob in zip(bars, probs):
ax.text(bar.get_x() + bar.get_width()/2., bar.get_height() + 0.02,
f'{prob:.3f}', ha='center', va='bottom', fontweight='bold')
fig.tight_layout()
return fig
@staticmethod
@handle_errors(default_return=None)
def create_confidence_gauge(confidence: float, sentiment: str, theme: ThemeContext) -> plt.Figure:
"""Create confidence gauge"""
with managed_figure(figsize=config.FIGURE_SIZE_SINGLE) as fig:
ax = fig.add_subplot(111)
theta = np.linspace(0, np.pi, 100)
colors = [theme.colors['neg'] if i < 50 else theme.colors['pos'] for i in range(100)]
for i in range(len(theta)-1):
ax.fill_between([theta[i], theta[i+1]], [0, 0], [0.8, 0.8],
color=colors[i], alpha=0.7)
pos = np.pi * (0.5 + (0.4 if sentiment == 'Positive' else -0.4) * confidence)
ax.plot([pos, pos], [0, 0.6], 'k-', linewidth=6)
ax.plot(pos, 0.6, 'ko', markersize=10)
ax.set_xlim(0, np.pi)
ax.set_ylim(0, 1)
ax.set_title(f'{sentiment} - Confidence: {confidence:.3f}', fontweight='bold')
ax.set_xticks([0, np.pi/2, np.pi])
ax.set_xticklabels(['Negative', 'Neutral', 'Positive'])
ax.axis('off')
fig.tight_layout()
return fig
@staticmethod
@handle_errors(default_return=None)
def create_lime_keyword_chart(lime_words: List[Tuple[str, float]], sentiment: str, theme: ThemeContext) -> Optional[plt.Figure]:
"""Create horizontal bar chart for LIME key contributing words"""
if not lime_words:
return None
with managed_figure(figsize=config.FIGURE_SIZE_SINGLE) as fig:
ax = fig.add_subplot(111)
words = [word for word, score in lime_words]
scores = [score for word, score in lime_words]
color = theme.colors['pos'] if sentiment == 'Positive' else theme.colors['neg']
bars = ax.barh(range(len(words)), scores, color=color, alpha=0.7)
ax.set_yticks(range(len(words)))
ax.set_yticklabels(words)
ax.set_xlabel('LIME Attention Weight')
ax.set_title(f'LIME: Top Contributing Words ({sentiment})', fontweight='bold')
for i, (bar, score) in enumerate(zip(bars, scores)):
ax.text(bar.get_width() + 0.001, bar.get_y() + bar.get_height()/2.,
f'{score:.3f}', ha='left', va='center', fontsize=9)
ax.invert_yaxis()
ax.grid(axis='x', alpha=0.3)
fig.tight_layout()
return fig
@staticmethod
@handle_errors(default_return=None)
def create_shap_keyword_chart(shap_words: List[Tuple[str, float]], sentiment: str, theme: ThemeContext) -> Optional[plt.Figure]:
"""Create horizontal bar chart for SHAP key contributing words"""
if not shap_words:
return None
with managed_figure(figsize=config.FIGURE_SIZE_SINGLE) as fig:
ax = fig.add_subplot(111)
words = [word for word, score in shap_words]
scores = [score for word, score in shap_words]
color = theme.colors['pos'] if sentiment == 'Positive' else theme.colors['neg']
bars = ax.barh(range(len(words)), scores, color=color, alpha=0.7)
ax.set_yticks(range(len(words)))
ax.set_yticklabels(words)
ax.set_xlabel('SHAP Value')
ax.set_title(f'SHAP: Top Contributing Words ({sentiment})', fontweight='bold')
for i, (bar, score) in enumerate(zip(bars, scores)):
ax.text(bar.get_width() + 0.001, bar.get_y() + bar.get_height()/2.,
f'{score:.3f}', ha='left', va='center', fontsize=9)
ax.invert_yaxis()
ax.grid(axis='x', alpha=0.3)
fig.tight_layout()
return fig
@staticmethod
@handle_errors(default_return=None)
def create_wordcloud(text: str, sentiment: str, theme: ThemeContext) -> Optional[plt.Figure]:
"""Create word cloud"""
if len(text.split()) < 3:
return None
colormap = 'Greens' if sentiment == 'Positive' else 'Reds'
wc = WordCloud(width=800, height=400, background_color='white',
colormap=colormap, max_words=30).generate(text)
with managed_figure(figsize=config.WORDCLOUD_SIZE) as fig:
ax = fig.add_subplot(111)
ax.imshow(wc, interpolation='bilinear')
ax.axis('off')
ax.set_title(f'{sentiment} Word Cloud', fontweight='bold')
fig.tight_layout()
return fig
@staticmethod
@handle_errors(default_return=None)
def create_batch_analysis(results: List[Dict], theme: ThemeContext) -> plt.Figure:
"""Create comprehensive batch visualization"""
with managed_figure(figsize=config.FIGURE_SIZE_BATCH) as fig:
gs = fig.add_gridspec(2, 2, hspace=0.3, wspace=0.3)
# Sentiment distribution
ax1 = fig.add_subplot(gs[0, 0])
sent_counts = Counter([r['sentiment'] for r in results])
colors = [theme.colors['pos'], theme.colors['neg']]
ax1.pie(sent_counts.values(), labels=sent_counts.keys(),
autopct='%1.1f%%', colors=colors[:len(sent_counts)])
ax1.set_title('Sentiment Distribution')
# Confidence histogram
ax2 = fig.add_subplot(gs[0, 1])
confs = [r['confidence'] for r in results]
ax2.hist(confs, bins=8, alpha=0.7, color='skyblue', edgecolor='black')
ax2.set_title('Confidence Distribution')
ax2.set_xlabel('Confidence')
# Sentiment over time
ax3 = fig.add_subplot(gs[1, :])
pos_probs = [r['pos_prob'] for r in results]
indices = range(len(results))
colors_scatter = [theme.colors['pos'] if r['sentiment'] == 'Positive'
else theme.colors['neg'] for r in results]
ax3.scatter(indices, pos_probs, c=colors_scatter, alpha=0.7, s=60)
ax3.axhline(y=0.5, color='gray', linestyle='--', alpha=0.5)
ax3.set_title('Sentiment Progression')
ax3.set_xlabel('Review Index')
ax3.set_ylabel('Positive Probability')
return fig |