File size: 12,849 Bytes
2493822
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ee305a4
ea7f5b6
 
 
ee305a4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ea7f5b6
ee305a4
 
 
 
 
ea7f5b6
 
 
 
 
 
 
 
 
 
 
 
 
ee305a4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ea7f5b6
 
 
 
 
ee305a4
ea7f5b6
 
 
ee305a4
ea7f5b6
ee305a4
ea7f5b6
ee305a4
 
 
 
ea7f5b6
 
ee305a4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ea7f5b6
2493822
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ea7f5b6
 
 
 
 
ee305a4
ea7f5b6
 
ee305a4
ea7f5b6
 
 
 
 
 
ee305a4
ea7f5b6
ee305a4
ea7f5b6
ee305a4
ea7f5b6
ee305a4
ea7f5b6
 
ee305a4
ea7f5b6
ee305a4
ea7f5b6
 
2493822
 
ea7f5b6
 
 
ee305a4
ea7f5b6
 
ee305a4
ea7f5b6
 
2493822
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ea7f5b6
 
ee305a4
ea7f5b6
 
ee305a4
 
ea7f5b6
 
2493822
 
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
# import plotly.graph_objects as go
# import textwrap
# import re
# from collections import defaultdict

# def generate_subplot(paraphrased_sentence, scheme_sentences, sampled_sentence, highlight_info):
#     # Combine nodes into one list with appropriate labels
#     nodes = [paraphrased_sentence] + scheme_sentences + sampled_sentence
#     nodes[0] += ' L0'  # Paraphrased sentence is level 0
#     para_len = len(scheme_sentences)
#     for i in range(1, para_len + 1):
#         nodes[i] += ' L1'  # Scheme sentences are level 1
#     for i in range(para_len + 1, len(nodes)):
#         nodes[i] += ' L2'  # Sampled sentences are level 2

#     # Define the highlight_words function
#     def highlight_words(sentence, color_map):
#         for word, color in color_map.items():
#             sentence = re.sub(f"\\b{word}\\b", f"{{{{{word}}}}}", sentence, flags=re.IGNORECASE)
#         return sentence

#     # Clean and wrap nodes, and highlight specified words globally
#     cleaned_nodes = [re.sub(r'\sL[0-9]$', '', node) for node in nodes]
#     global_color_map = dict(highlight_info)
#     highlighted_nodes = [highlight_words(node, global_color_map) for node in cleaned_nodes]
#     wrapped_nodes = ['<br>'.join(textwrap.wrap(node, width=30)) for node in highlighted_nodes]

#     # Function to determine tree levels and create edges dynamically
#     def get_levels_and_edges(nodes):
#         levels = {}
#         edges = []
#         for i, node in enumerate(nodes):
#             level = int(node.split()[-1][1])
#             levels[i] = level

#         # Add edges from L0 to all L1 nodes
#         root_node = next(i for i, level in levels.items() if level == 0)
#         for i, level in levels.items():
#             if level == 1:
#                 edges.append((root_node, i))

#         # Add edges from each L1 node to their corresponding L2 nodes
#         l1_indices = [i for i, level in levels.items() if level == 1]
#         l2_indices = [i for i, level in levels.items() if level == 2]

#         for i, l1_node in enumerate(l1_indices):
#             l2_start = i * 4
#             for j in range(4):
#                 l2_index = l2_start + j
#                 if l2_index < len(l2_indices):
#                     edges.append((l1_node, l2_indices[l2_index]))

#         # Add edges from each L2 node to their corresponding L3 nodes
#         l2_indices = [i for i, level in levels.items() if level == 2]
#         l3_indices = [i for i, level in levels.items() if level == 3]

#         l2_to_l3_map = {l2_node: [] for l2_node in l2_indices}

#         # Map L3 nodes to L2 nodes
#         for l3_node in l3_indices:
#             l2_node = l3_node % len(l2_indices)
#             l2_to_l3_map[l2_indices[l2_node]].append(l3_node)

#         for l2_node, l3_nodes in l2_to_l3_map.items():
#             for l3_node in l3_nodes:
#                 edges.append((l2_node, l3_node))

#         return levels, edges

#     # Get levels and dynamic edges
#     levels, edges = get_levels_and_edges(nodes)
#     max_level = max(levels.values(), default=0)

#     # Calculate positions
#     positions = {}
#     level_heights = defaultdict(int)
#     for node, level in levels.items():
#         level_heights[level] += 1

#     y_offsets = {level: - (height - 1) / 2 for level, height in level_heights.items()}
#     x_gap = 2
#     l1_y_gap = 10
#     l2_y_gap = 6

#     for node, level in levels.items():
#         if level == 1:
#             positions[node] = (-level * x_gap, y_offsets[level] * l1_y_gap)
#         elif level == 2:
#             positions[node] = (-level * x_gap, y_offsets[level] * l2_y_gap)
#         else:
#             positions[node] = (-level * x_gap, y_offsets[level] * l2_y_gap)
#         y_offsets[level] += 1

#     # Function to highlight words in a wrapped node string
#     def color_highlighted_words(node, color_map):
#         parts = re.split(r'(\{\{.*?\}\})', node)
#         colored_parts = []
#         for part in parts:
#             match = re.match(r'\{\{(.*?)\}\}', part)
#             if match:
#                 word = match.group(1)
#                 color = color_map.get(word, 'black')
#                 colored_parts.append(f"<span style='color: {color};'>{word}</span>")
#             else:
#                 colored_parts.append(part)
#         return ''.join(colored_parts)

#     # Create figure
#     fig = go.Figure()

#     # Add nodes to the figure
#     for i, node in enumerate(wrapped_nodes):
#         colored_node = color_highlighted_words(node, global_color_map)
#         x, y = positions[i]
#         fig.add_trace(go.Scatter(
#             x=[-x],  # Reflect the x coordinate
#             y=[y],
#             mode='markers',
#             marker=dict(size=10, color='blue'),
#             hoverinfo='none'
#         ))
#         fig.add_annotation(
#             x=-x,  # Reflect the x coordinate
#             y=y,
#             text=colored_node,
#             showarrow=False,
#             xshift=15,
#             align="center",
#             font=dict(size=8),
#             bordercolor='black',
#             borderwidth=1,
#             borderpad=2,
#             bgcolor='white',
#             width=150
#         )

#     # Add edges to the figure
#     for edge in edges:
#         x0, y0 = positions[edge[0]]
#         x1, y1 = positions[edge[1]]
#         fig.add_trace(go.Scatter(
#             x=[-x0, -x1],  # Reflect the x coordinates
#             y=[y0, y1],
#             mode='lines',
#             line=dict(color='black', width=1)
#         ))

#     fig.update_layout(
#         showlegend=False,
#         margin=dict(t=20, b=20, l=20, r=20),
#         xaxis=dict(showgrid=False, zeroline=False, showticklabels=False),
#         yaxis=dict(showgrid=False, zeroline=False, showticklabels=False),
#         width=1200,  # Adjusted width to accommodate more levels
#         height=1000   # Adjusted height to accommodate more levels
#     )

#     return fig

import plotly.graph_objects as go
import textwrap
import re
from collections import defaultdict

def generate_subplot(paraphrased_sentence, scheme_sentences, sampled_sentence, highlight_info):
    # Combine nodes into one list with appropriate labels
    nodes = [paraphrased_sentence] + scheme_sentences + sampled_sentence
    nodes[0] += ' L0'  # Paraphrased sentence is level 0
    para_len = len(scheme_sentences)
    for i in range(1, para_len + 1):
        nodes[i] += ' L1'  # Scheme sentences are level 1
    for i in range(para_len + 1, len(nodes)):
        nodes[i] += ' L2'  # Sampled sentences are level 2

    # Define the highlight_words function
    def highlight_words(sentence, color_map):
        for word, color in color_map.items():
            sentence = re.sub(f"\\b{word}\\b", f"{{{{{word}}}}}", sentence, flags=re.IGNORECASE)
        return sentence

    # Clean and wrap nodes, and highlight specified words globally
    cleaned_nodes = [re.sub(r'\sL[0-9]$', '', node) for node in nodes]
    global_color_map = dict(highlight_info)
    highlighted_nodes = [highlight_words(node, global_color_map) for node in cleaned_nodes]
    wrapped_nodes = ['<br>'.join(textwrap.wrap(node, width=30)) for node in highlighted_nodes]

    # Function to determine tree levels and create edges dynamically
    def get_levels_and_edges(nodes):
        levels = {}
        edges = []
        for i, node in enumerate(nodes):
            level = int(node.split()[-1][1])
            levels[i] = level

        # Add edges from L0 to all L1 nodes
        root_node = next(i for i, level in levels.items() if level == 0)
        for i, level in levels.items():
            if level == 1:
                edges.append((root_node, i))

        # Add edges from each L1 node to their corresponding L2 nodes
        l1_indices = [i for i, level in levels.items() if level == 1]
        l2_indices = [i for i, level in levels.items() if level == 2]

        for i, l1_node in enumerate(l1_indices):
            l2_start = i * 4
            for j in range(4):
                l2_index = l2_start + j
                if l2_index < len(l2_indices):
                    edges.append((l1_node, l2_indices[l2_index]))

        # Add edges from each L2 node to their corresponding L3 nodes
        l2_indices = [i for i, level in levels.items() if level == 2]
        l3_indices = [i for i, level in levels.items() if level == 3]

        l2_to_l3_map = {l2_node: [] for l2_node in l2_indices}

        # Map L3 nodes to L2 nodes
        for l3_node in l3_indices:
            l2_node = l3_node % len(l2_indices)
            l2_to_l3_map[l2_indices[l2_node]].append(l3_node)

        for l2_node, l3_nodes in l2_to_l3_map.items():
            for l3_node in l3_nodes:
                edges.append((l2_node, l3_node))

        return levels, edges

    # Get levels and dynamic edges
    levels, edges = get_levels_and_edges(nodes)
    max_level = max(levels.values(), default=0)

    # Calculate positions
    positions = {}
    level_heights = defaultdict(int)
    for node, level in levels.items():
        level_heights[level] += 1

    y_offsets = {level: - (height - 1) / 2 for level, height in level_heights.items()}
    x_gap = 2
    l1_y_gap = 10
    l2_y_gap = 6

    for node, level in levels.items():
        if level == 1:
            positions[node] = (-level * x_gap, y_offsets[level] * l1_y_gap)
        elif level == 2:
            positions[node] = (-level * x_gap, y_offsets[level] * l2_y_gap)
        else:
            positions[node] = (-level * x_gap, y_offsets[level] * l2_y_gap)
        y_offsets[level] += 1

    # Function to highlight words in a wrapped node string
    def color_highlighted_words(node, color_map):
        parts = re.split(r'(\{\{.*?\}\})', node)
        colored_parts = []
        for part in parts:
            match = re.match(r'\{\{(.*?)\}\}', part)
            if match:
                word = match.group(1)
                color = color_map.get(word, 'black')
                colored_parts.append(f"<span style='color: {color};'>{word}</span>")
            else:
                colored_parts.append(part)
        return ''.join(colored_parts)

    # Define the text for each edge
    edge_texts = [
        "Highest Entropy Masking",
        "Pseudo-random Masking",
        "Random Masking",
        "Greedy Sampling",
        "Temperature Sampling",
        "Exponential Minimum Sampling",
        "Inverse Transform Sampling",
        "Greedy Sampling",
        "Temperature Sampling",
        "Exponential Minimum Sampling",
        "Inverse Transform Sampling",
        "Greedy Sampling",
        "Temperature Sampling",
        "Exponential Minimum Sampling",
        "Inverse Transform Sampling"
    ]

    # Create figure
    fig = go.Figure()

    # Add nodes to the figure
    for i, node in enumerate(wrapped_nodes):
        colored_node = color_highlighted_words(node, global_color_map)
        x, y = positions[i]
        fig.add_trace(go.Scatter(
            x=[-x],  # Reflect the x coordinate
            y=[y],
            mode='markers',
            marker=dict(size=10, color='blue'),
            hoverinfo='none'
        ))
        fig.add_annotation(
            x=-x,  # Reflect the x coordinate
            y=y,
            text=colored_node,
            showarrow=False,
            xshift=15,
            align="center",
            font=dict(size=8),
            bordercolor='black',
            borderwidth=1,
            borderpad=2,
            bgcolor='white',
            width=150
        )

    # Add edges and text above each edge
    for i, edge in enumerate(edges):
        x0, y0 = positions[edge[0]]
        x1, y1 = positions[edge[1]]
        fig.add_trace(go.Scatter(
            x=[-x0, -x1],  # Reflect the x coordinates
            y=[y0, y1],
            mode='lines',
            line=dict(color='black', width=1)
        ))

        # Calculate the midpoint of the edge
        mid_x = (-x0 + -x1) / 2
        mid_y = (y0 + y1) / 2

        # Adjust y position to shift text upwards
        text_y_position = mid_y + 0.8  # Increase this value to shift the text further upwards

        # Add text annotation above the edge
        fig.add_annotation(
            x=mid_x,
            y=text_y_position,
            text=edge_texts[i],  # Use the text specific to this edge
            showarrow=False,
            font=dict(size=10),
            align="center"
        )

    fig.update_layout(
        showlegend=False,
        margin=dict(t=20, b=20, l=20, r=20),
        xaxis=dict(showgrid=False, zeroline=False, showticklabels=False),
        yaxis=dict(showgrid=False, zeroline=False, showticklabels=False),
        width=1200,  # Adjusted width to accommodate more levels
        height=1000   # Adjusted height to accommodate more levels
    )

    return fig