-
Notifications
You must be signed in to change notification settings - Fork 269
/
data.html
759 lines (715 loc) · 37.5 KB
/
data.html
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
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1" />
<meta name="generator" content="pdoc 0.10.0" />
<title>ktrain.graph.data API documentation</title>
<meta name="description" content="" />
<link rel="preload stylesheet" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/11.0.1/sanitize.min.css" integrity="sha256-PK9q560IAAa6WVRRh76LtCaI8pjTJ2z11v0miyNNjrs=" crossorigin>
<link rel="preload stylesheet" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/11.0.1/typography.min.css" integrity="sha256-7l/o7C8jubJiy74VsKTidCy1yBkRtiUGbVkYBylBqUg=" crossorigin>
<link rel="stylesheet preload" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/10.1.1/styles/github.min.css" crossorigin>
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:30px;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:1em 0 .50em 0}h3{font-size:1.4em;margin:25px 0 10px 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .3s ease-in-out}a:hover{color:#e82}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900}pre code{background:#f8f8f8;font-size:.8em;line-height:1.4em}code{background:#f2f2f1;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{background:#f8f8f8;border:0;border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0;padding:1ex}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-weight:bold;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em .5em;margin-bottom:1em}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.item .name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul{padding-left:1.5em}.toc > ul > li{margin-top:.5em}}</style>
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/10.1.1/highlight.min.js" integrity="sha256-Uv3H6lx7dJmRfRvH8TH6kJD1TSK1aFcwgx+mdg3epi8=" crossorigin></script>
<script>window.addEventListener('DOMContentLoaded', () => hljs.initHighlighting())</script>
</head>
<body>
<main>
<article id="content">
<header>
<h1 class="title">Module <code>ktrain.graph.data</code></h1>
</header>
<section id="section-intro">
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">from .. import utils as U
from ..imports import *
from .preprocessor import LinkPreprocessor, NodePreprocessor
def graph_nodes_from_csv(
nodes_filepath,
links_filepath,
use_lcc=True,
sample_size=10,
train_pct=0.1,
sep=",",
holdout_pct=None,
holdout_for_inductive=False,
missing_label_value=None,
random_state=None,
verbose=1,
):
"""
```
Loads graph data from CSV files.
Returns generators for nodes in graph for use with GraphSAGE model.
Args:
nodes_filepath(str): file path to training CSV containing node attributes
links_filepath(str): file path to training CSV describing links among nodes
use_lcc(bool): If True, consider the largest connected component only.
sample_size(int): Number of nodes to sample at each neighborhood level
train_pct(float): Proportion of nodes to use for training.
Default is 0.1.
sep (str): delimiter for CSVs. Default is comma.
holdout_pct(float): Percentage of nodes to remove and return separately
for later transductive/inductive inference.
Example --> train_pct=0.1 and holdout_pct=0.2:
Out of 1000 nodes, 200 (holdout_pct*1000) will be held out.
Of the remaining 800, 80 (train_pct*800) will be used for training
and 720 ((1-train_pct)*800) will be used for validation.
200 nodes will be used for transductive or inductive inference.
Note that holdout_pct is ignored if at least one node has
a missing label in nodes_filepath, in which case
these nodes are assumed to be the holdout set.
holdout_for_inductive(bool): If True, the holdout nodes will be removed from
training graph and their features will not be visible
during training. Only features of training and
validation nodes will be visible.
If False, holdout nodes will be included in graph
and their features (but not labels) are accessible
during training.
random_state (int): random seed for train/test split
verbose (boolean): verbosity
Return:
tuple of NodeSequenceWrapper objects for train and validation sets and NodePreprocessor
If holdout_pct is not None or number of nodes with missing labels is non-zero,
fourth and fifth return values are pd.DataFrame and nx.Graph
comprising the held out nodes.
```
"""
# ----------------------------------------------------------------
# read graph structure
# ----------------------------------------------------------------
try:
import networkx as nx
except ImportError:
raise ImportError("Please install networkx: pip install networkx")
nx_sep = None if sep in [" ", "\t"] else sep
g_nx = nx.read_edgelist(path=links_filepath, delimiter=nx_sep)
# read node attributes
# node_attr = pd.read_csv(nodes_filepath, sep=sep, header=None)
# store class labels within graph nodes
# values = { str(row.tolist()[0]): row.tolist()[-1] for _, row in node_attr.iterrows()}
# nx.set_node_attributes(g_nx, values, 'target')
# select largest connected component
if use_lcc:
g_nx_ccs = (g_nx.subgraph(c).copy() for c in nx.connected_components(g_nx))
g_nx = max(g_nx_ccs, key=len)
if verbose:
print(
"Largest subgraph statistics: {} nodes, {} edges".format(
g_nx.number_of_nodes(), g_nx.number_of_edges()
)
)
# ----------------------------------------------------------------
# read node attributes and split into train/validation
# ----------------------------------------------------------------
node_attr = pd.read_csv(nodes_filepath, sep=sep, header=None)
num_features = len(node_attr.columns.values) - 2 # subract ID and target
feature_names = ["w_{}".format(ii) for ii in range(num_features)]
column_names = feature_names + ["target"]
node_data = pd.read_csv(nodes_filepath, header=None, names=column_names, sep=sep)
node_data.index = node_data.index.map(str)
node_data = node_data[node_data.index.isin(list(g_nx.nodes()))]
# ----------------------------------------------------------------
# check for holdout nodes
# ----------------------------------------------------------------
num_null = node_data[node_data.target.isnull()].shape[0]
num_missing = 0
if missing_label_value is not None:
num_missing = node_data[node_data.target == missing_label_value].shape[0]
if num_missing > 0 and num_null > 0:
raise ValueError(
"Param missing_label_value is not None but there are "
+ "NULLs in last column. Replace these with missing_label_value."
)
if (num_null > 0 or num_missing > 0) and holdout_pct is not None:
warnings.warn(
"Number of nodes in having NULL or missing_label_value in target "
+ "column is non-zero. Using these as holdout nodes and ignoring holdout_pct."
)
# ----------------------------------------------------------------
# set df and G and optionally holdout nodes
# ----------------------------------------------------------------
if num_null > 0:
df_annotated = node_data[~node_data.target.isnull()]
df_holdout = node_data[~node_data.target.isnull()]
G_holdout = g_nx
df_G = df_annotated if holdout_for_inductive else node_data
G = g_nx.subgraph(df_annotated.index).copy() if holdout_for_inductive else g_nx
U.vprint(
"using %s nodes with target=NULL as holdout set" % (num_null),
verbose=verbose,
)
elif num_missing > 0:
df_annotated = node_data[node_data.target != missing_label_value]
df_holdout = node_data[node_data.target == missing_label_value]
G_holdout = g_nx
df_G = df_annotated if holdout_for_inductive else node_data
G = g_nx.subgraph(df_annotated.index).copy() if holdout_for_inductive else g_nx
U.vprint(
"using %s nodes with missing target as holdout set" % (num_missing),
verbose=verbose,
)
elif holdout_pct is not None:
df_annotated = node_data.sample(
frac=1 - holdout_pct, replace=False, random_state=None
)
df_holdout = node_data[~node_data.index.isin(df_annotated.index)]
G_holdout = g_nx
df_G = df_annotated if holdout_for_inductive else node_data
G = g_nx.subgraph(df_annotated.index).copy() if holdout_for_inductive else g_nx
else:
if holdout_for_inductive:
warnings.warn(
"holdout_for_inductive is True but no nodes were heldout "
"because holdout_pct is None and no missing targets"
)
df_annotated = node_data
df_holdout = None
G_holdout = None
df_G = node_data
G = g_nx
# ----------------------------------------------------------------
# split into train and validation
# ----------------------------------------------------------------
tr_data, te_data = sklearn.model_selection.train_test_split(
df_annotated,
train_size=train_pct,
test_size=None,
stratify=df_annotated["target"],
random_state=random_state,
)
# te_data, test_data = sklearn.model_selection.train_test_split(test_data,
# train_size=0.2,
# test_size=None,
# stratify=test_data["target"],
# random_state=100)
# ----------------------------------------------------------------
# print summary
# ----------------------------------------------------------------
if verbose:
print("Size of training graph: %s nodes" % (G.number_of_nodes()))
print("Training nodes: %s" % (tr_data.shape[0]))
print("Validation nodes: %s" % (te_data.shape[0]))
if df_holdout is not None and G_holdout is not None:
print(
"Nodes treated as unlabeled for testing/inference: %s"
% (df_holdout.shape[0])
)
if holdout_for_inductive:
print(
"Size of graph with added holdout nodes: %s"
% (G_holdout.number_of_nodes())
)
print(
"Holdout node features are not visible during training (inductive inference)"
)
else:
print(
"Holdout node features are visible during training (transductive inference)"
)
print()
# ----------------------------------------------------------------
# Preprocess training and validation datasets using NodePreprocessor
# ----------------------------------------------------------------
preproc = NodePreprocessor(
G, df_G, sample_size=sample_size, missing_label_value=missing_label_value
)
trn = preproc.preprocess_train(list(tr_data.index))
val = preproc.preprocess_valid(list(te_data.index))
if df_holdout is not None and G_holdout is not None:
return (trn, val, preproc, df_holdout, G_holdout)
else:
return (trn, val, preproc)
def graph_links_from_csv(
nodes_filepath,
links_filepath,
sample_sizes=[10, 20],
train_pct=0.1,
val_pct=0.1,
sep=",",
holdout_pct=None,
holdout_for_inductive=False,
missing_label_value=None,
random_state=None,
verbose=1,
):
"""
```
Loads graph data from CSV files.
Returns generators for links in graph for use with GraphSAGE model.
Args:
nodes_filepath(str): file path to training CSV containing node attributes
links_filepath(str): file path to training CSV describing links among nodes
sample_sizes(int): Number of nodes to sample at each neighborhood level.
train_pct(float): Proportion of edges to use for training.
Default is 0.1.
Note that train_pct is applied after val_pct is applied.
val_pct(float): Proportion of edges to use for validation
sep (str): delimiter for CSVs. Default is comma.
random_state (int): random seed for train/test split
verbose (boolean): verbosity
Return:
tuple of EdgeSequenceWrapper objects for train and validation sets and LinkPreprocessor
```
"""
try:
import networkx as nx
except ImportError:
raise ImportError("Please install networkx: pip install networkx")
# import stellargraph
try:
import stellargraph as sg
from stellargraph.data import EdgeSplitter
except:
raise Exception(SG_ERRMSG)
if version.parse(sg.__version__) < version.parse("0.8"):
raise Exception(SG_ERRMSG)
# ----------------------------------------------------------------
# read graph structure
# ----------------------------------------------------------------
nx_sep = None if sep in [" ", "\t"] else sep
G = nx.read_edgelist(path=links_filepath, delimiter=nx_sep)
print(nx.info(G))
# ----------------------------------------------------------------
# read node attributes
# ----------------------------------------------------------------
node_attr = pd.read_csv(nodes_filepath, sep=sep, header=None)
num_features = (
len(node_attr.columns.values) - 1
) # subract ID and treat all other columns as features
feature_names = ["w_{}".format(ii) for ii in range(num_features)]
node_data = pd.read_csv(nodes_filepath, header=None, names=feature_names, sep=sep)
node_data.index = node_data.index.map(str)
df = node_data[node_data.index.isin(list(G.nodes()))]
for col in feature_names:
if not isinstance(node_data[col].values[0], str):
continue
df = pd.concat(
[df, df[col].astype("str").str.get_dummies().add_prefix(col + "_")],
axis=1,
sort=False,
)
df = df.drop([col], axis=1)
feature_names = df.columns.values
node_data = df
node_features = node_data[feature_names].values
for nid, f in zip(node_data.index, node_features):
G.node[nid][sg.globalvar.TYPE_ATTR_NAME] = "node"
G.node[nid]["feature"] = f
# ----------------------------------------------------------------
# train/validation sets
# ----------------------------------------------------------------
edge_splitter_test = EdgeSplitter(G)
G_test, edge_ids_test, edge_labels_test = edge_splitter_test.train_test_split(
p=val_pct, method="global", keep_connected=True
)
edge_splitter_train = EdgeSplitter(G_test)
G_train, edge_ids_train, edge_labels_train = edge_splitter_train.train_test_split(
p=train_pct, method="global", keep_connected=True
)
epp = LinkPreprocessor(G, sample_sizes=sample_sizes)
trn = epp.preprocess_train(G_train, edge_ids_train, edge_labels_train)
val = epp.preprocess_valid(G_test, edge_ids_test, edge_labels_test)
return (trn, val, epp)</code></pre>
</details>
</section>
<section>
</section>
<section>
</section>
<section>
<h2 class="section-title" id="header-functions">Functions</h2>
<dl>
<dt id="ktrain.graph.data.graph_links_from_csv"><code class="name flex">
<span>def <span class="ident">graph_links_from_csv</span></span>(<span>nodes_filepath, links_filepath, sample_sizes=[10, 20], train_pct=0.1, val_pct=0.1, sep=',', holdout_pct=None, holdout_for_inductive=False, missing_label_value=None, random_state=None, verbose=1)</span>
</code></dt>
<dd>
<div class="desc"><pre><code>Loads graph data from CSV files.
Returns generators for links in graph for use with GraphSAGE model.
Args:
nodes_filepath(str): file path to training CSV containing node attributes
links_filepath(str): file path to training CSV describing links among nodes
sample_sizes(int): Number of nodes to sample at each neighborhood level.
train_pct(float): Proportion of edges to use for training.
Default is 0.1.
Note that train_pct is applied after val_pct is applied.
val_pct(float): Proportion of edges to use for validation
sep (str): delimiter for CSVs. Default is comma.
random_state (int): random seed for train/test split
verbose (boolean): verbosity
Return:
tuple of EdgeSequenceWrapper objects for train and validation sets and LinkPreprocessor
</code></pre></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def graph_links_from_csv(
nodes_filepath,
links_filepath,
sample_sizes=[10, 20],
train_pct=0.1,
val_pct=0.1,
sep=",",
holdout_pct=None,
holdout_for_inductive=False,
missing_label_value=None,
random_state=None,
verbose=1,
):
"""
```
Loads graph data from CSV files.
Returns generators for links in graph for use with GraphSAGE model.
Args:
nodes_filepath(str): file path to training CSV containing node attributes
links_filepath(str): file path to training CSV describing links among nodes
sample_sizes(int): Number of nodes to sample at each neighborhood level.
train_pct(float): Proportion of edges to use for training.
Default is 0.1.
Note that train_pct is applied after val_pct is applied.
val_pct(float): Proportion of edges to use for validation
sep (str): delimiter for CSVs. Default is comma.
random_state (int): random seed for train/test split
verbose (boolean): verbosity
Return:
tuple of EdgeSequenceWrapper objects for train and validation sets and LinkPreprocessor
```
"""
try:
import networkx as nx
except ImportError:
raise ImportError("Please install networkx: pip install networkx")
# import stellargraph
try:
import stellargraph as sg
from stellargraph.data import EdgeSplitter
except:
raise Exception(SG_ERRMSG)
if version.parse(sg.__version__) < version.parse("0.8"):
raise Exception(SG_ERRMSG)
# ----------------------------------------------------------------
# read graph structure
# ----------------------------------------------------------------
nx_sep = None if sep in [" ", "\t"] else sep
G = nx.read_edgelist(path=links_filepath, delimiter=nx_sep)
print(nx.info(G))
# ----------------------------------------------------------------
# read node attributes
# ----------------------------------------------------------------
node_attr = pd.read_csv(nodes_filepath, sep=sep, header=None)
num_features = (
len(node_attr.columns.values) - 1
) # subract ID and treat all other columns as features
feature_names = ["w_{}".format(ii) for ii in range(num_features)]
node_data = pd.read_csv(nodes_filepath, header=None, names=feature_names, sep=sep)
node_data.index = node_data.index.map(str)
df = node_data[node_data.index.isin(list(G.nodes()))]
for col in feature_names:
if not isinstance(node_data[col].values[0], str):
continue
df = pd.concat(
[df, df[col].astype("str").str.get_dummies().add_prefix(col + "_")],
axis=1,
sort=False,
)
df = df.drop([col], axis=1)
feature_names = df.columns.values
node_data = df
node_features = node_data[feature_names].values
for nid, f in zip(node_data.index, node_features):
G.node[nid][sg.globalvar.TYPE_ATTR_NAME] = "node"
G.node[nid]["feature"] = f
# ----------------------------------------------------------------
# train/validation sets
# ----------------------------------------------------------------
edge_splitter_test = EdgeSplitter(G)
G_test, edge_ids_test, edge_labels_test = edge_splitter_test.train_test_split(
p=val_pct, method="global", keep_connected=True
)
edge_splitter_train = EdgeSplitter(G_test)
G_train, edge_ids_train, edge_labels_train = edge_splitter_train.train_test_split(
p=train_pct, method="global", keep_connected=True
)
epp = LinkPreprocessor(G, sample_sizes=sample_sizes)
trn = epp.preprocess_train(G_train, edge_ids_train, edge_labels_train)
val = epp.preprocess_valid(G_test, edge_ids_test, edge_labels_test)
return (trn, val, epp)</code></pre>
</details>
</dd>
<dt id="ktrain.graph.data.graph_nodes_from_csv"><code class="name flex">
<span>def <span class="ident">graph_nodes_from_csv</span></span>(<span>nodes_filepath, links_filepath, use_lcc=True, sample_size=10, train_pct=0.1, sep=',', holdout_pct=None, holdout_for_inductive=False, missing_label_value=None, random_state=None, verbose=1)</span>
</code></dt>
<dd>
<div class="desc"><pre><code>Loads graph data from CSV files.
Returns generators for nodes in graph for use with GraphSAGE model.
Args:
nodes_filepath(str): file path to training CSV containing node attributes
links_filepath(str): file path to training CSV describing links among nodes
use_lcc(bool): If True, consider the largest connected component only.
sample_size(int): Number of nodes to sample at each neighborhood level
train_pct(float): Proportion of nodes to use for training.
Default is 0.1.
sep (str): delimiter for CSVs. Default is comma.
holdout_pct(float): Percentage of nodes to remove and return separately
for later transductive/inductive inference.
Example --> train_pct=0.1 and holdout_pct=0.2:
Out of 1000 nodes, 200 (holdout_pct*1000) will be held out.
Of the remaining 800, 80 (train_pct*800) will be used for training
and 720 ((1-train_pct)*800) will be used for validation.
200 nodes will be used for transductive or inductive inference.
Note that holdout_pct is ignored if at least one node has
a missing label in nodes_filepath, in which case
these nodes are assumed to be the holdout set.
holdout_for_inductive(bool): If True, the holdout nodes will be removed from
training graph and their features will not be visible
during training. Only features of training and
validation nodes will be visible.
If False, holdout nodes will be included in graph
and their features (but not labels) are accessible
during training.
random_state (int): random seed for train/test split
verbose (boolean): verbosity
Return:
tuple of NodeSequenceWrapper objects for train and validation sets and NodePreprocessor
If holdout_pct is not None or number of nodes with missing labels is non-zero,
fourth and fifth return values are pd.DataFrame and nx.Graph
comprising the held out nodes.
</code></pre></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def graph_nodes_from_csv(
nodes_filepath,
links_filepath,
use_lcc=True,
sample_size=10,
train_pct=0.1,
sep=",",
holdout_pct=None,
holdout_for_inductive=False,
missing_label_value=None,
random_state=None,
verbose=1,
):
"""
```
Loads graph data from CSV files.
Returns generators for nodes in graph for use with GraphSAGE model.
Args:
nodes_filepath(str): file path to training CSV containing node attributes
links_filepath(str): file path to training CSV describing links among nodes
use_lcc(bool): If True, consider the largest connected component only.
sample_size(int): Number of nodes to sample at each neighborhood level
train_pct(float): Proportion of nodes to use for training.
Default is 0.1.
sep (str): delimiter for CSVs. Default is comma.
holdout_pct(float): Percentage of nodes to remove and return separately
for later transductive/inductive inference.
Example --> train_pct=0.1 and holdout_pct=0.2:
Out of 1000 nodes, 200 (holdout_pct*1000) will be held out.
Of the remaining 800, 80 (train_pct*800) will be used for training
and 720 ((1-train_pct)*800) will be used for validation.
200 nodes will be used for transductive or inductive inference.
Note that holdout_pct is ignored if at least one node has
a missing label in nodes_filepath, in which case
these nodes are assumed to be the holdout set.
holdout_for_inductive(bool): If True, the holdout nodes will be removed from
training graph and their features will not be visible
during training. Only features of training and
validation nodes will be visible.
If False, holdout nodes will be included in graph
and their features (but not labels) are accessible
during training.
random_state (int): random seed for train/test split
verbose (boolean): verbosity
Return:
tuple of NodeSequenceWrapper objects for train and validation sets and NodePreprocessor
If holdout_pct is not None or number of nodes with missing labels is non-zero,
fourth and fifth return values are pd.DataFrame and nx.Graph
comprising the held out nodes.
```
"""
# ----------------------------------------------------------------
# read graph structure
# ----------------------------------------------------------------
try:
import networkx as nx
except ImportError:
raise ImportError("Please install networkx: pip install networkx")
nx_sep = None if sep in [" ", "\t"] else sep
g_nx = nx.read_edgelist(path=links_filepath, delimiter=nx_sep)
# read node attributes
# node_attr = pd.read_csv(nodes_filepath, sep=sep, header=None)
# store class labels within graph nodes
# values = { str(row.tolist()[0]): row.tolist()[-1] for _, row in node_attr.iterrows()}
# nx.set_node_attributes(g_nx, values, 'target')
# select largest connected component
if use_lcc:
g_nx_ccs = (g_nx.subgraph(c).copy() for c in nx.connected_components(g_nx))
g_nx = max(g_nx_ccs, key=len)
if verbose:
print(
"Largest subgraph statistics: {} nodes, {} edges".format(
g_nx.number_of_nodes(), g_nx.number_of_edges()
)
)
# ----------------------------------------------------------------
# read node attributes and split into train/validation
# ----------------------------------------------------------------
node_attr = pd.read_csv(nodes_filepath, sep=sep, header=None)
num_features = len(node_attr.columns.values) - 2 # subract ID and target
feature_names = ["w_{}".format(ii) for ii in range(num_features)]
column_names = feature_names + ["target"]
node_data = pd.read_csv(nodes_filepath, header=None, names=column_names, sep=sep)
node_data.index = node_data.index.map(str)
node_data = node_data[node_data.index.isin(list(g_nx.nodes()))]
# ----------------------------------------------------------------
# check for holdout nodes
# ----------------------------------------------------------------
num_null = node_data[node_data.target.isnull()].shape[0]
num_missing = 0
if missing_label_value is not None:
num_missing = node_data[node_data.target == missing_label_value].shape[0]
if num_missing > 0 and num_null > 0:
raise ValueError(
"Param missing_label_value is not None but there are "
+ "NULLs in last column. Replace these with missing_label_value."
)
if (num_null > 0 or num_missing > 0) and holdout_pct is not None:
warnings.warn(
"Number of nodes in having NULL or missing_label_value in target "
+ "column is non-zero. Using these as holdout nodes and ignoring holdout_pct."
)
# ----------------------------------------------------------------
# set df and G and optionally holdout nodes
# ----------------------------------------------------------------
if num_null > 0:
df_annotated = node_data[~node_data.target.isnull()]
df_holdout = node_data[~node_data.target.isnull()]
G_holdout = g_nx
df_G = df_annotated if holdout_for_inductive else node_data
G = g_nx.subgraph(df_annotated.index).copy() if holdout_for_inductive else g_nx
U.vprint(
"using %s nodes with target=NULL as holdout set" % (num_null),
verbose=verbose,
)
elif num_missing > 0:
df_annotated = node_data[node_data.target != missing_label_value]
df_holdout = node_data[node_data.target == missing_label_value]
G_holdout = g_nx
df_G = df_annotated if holdout_for_inductive else node_data
G = g_nx.subgraph(df_annotated.index).copy() if holdout_for_inductive else g_nx
U.vprint(
"using %s nodes with missing target as holdout set" % (num_missing),
verbose=verbose,
)
elif holdout_pct is not None:
df_annotated = node_data.sample(
frac=1 - holdout_pct, replace=False, random_state=None
)
df_holdout = node_data[~node_data.index.isin(df_annotated.index)]
G_holdout = g_nx
df_G = df_annotated if holdout_for_inductive else node_data
G = g_nx.subgraph(df_annotated.index).copy() if holdout_for_inductive else g_nx
else:
if holdout_for_inductive:
warnings.warn(
"holdout_for_inductive is True but no nodes were heldout "
"because holdout_pct is None and no missing targets"
)
df_annotated = node_data
df_holdout = None
G_holdout = None
df_G = node_data
G = g_nx
# ----------------------------------------------------------------
# split into train and validation
# ----------------------------------------------------------------
tr_data, te_data = sklearn.model_selection.train_test_split(
df_annotated,
train_size=train_pct,
test_size=None,
stratify=df_annotated["target"],
random_state=random_state,
)
# te_data, test_data = sklearn.model_selection.train_test_split(test_data,
# train_size=0.2,
# test_size=None,
# stratify=test_data["target"],
# random_state=100)
# ----------------------------------------------------------------
# print summary
# ----------------------------------------------------------------
if verbose:
print("Size of training graph: %s nodes" % (G.number_of_nodes()))
print("Training nodes: %s" % (tr_data.shape[0]))
print("Validation nodes: %s" % (te_data.shape[0]))
if df_holdout is not None and G_holdout is not None:
print(
"Nodes treated as unlabeled for testing/inference: %s"
% (df_holdout.shape[0])
)
if holdout_for_inductive:
print(
"Size of graph with added holdout nodes: %s"
% (G_holdout.number_of_nodes())
)
print(
"Holdout node features are not visible during training (inductive inference)"
)
else:
print(
"Holdout node features are visible during training (transductive inference)"
)
print()
# ----------------------------------------------------------------
# Preprocess training and validation datasets using NodePreprocessor
# ----------------------------------------------------------------
preproc = NodePreprocessor(
G, df_G, sample_size=sample_size, missing_label_value=missing_label_value
)
trn = preproc.preprocess_train(list(tr_data.index))
val = preproc.preprocess_valid(list(te_data.index))
if df_holdout is not None and G_holdout is not None:
return (trn, val, preproc, df_holdout, G_holdout)
else:
return (trn, val, preproc)</code></pre>
</details>
</dd>
</dl>
</section>
<section>
</section>
</article>
<nav id="sidebar">
<h1>Index</h1>
<div class="toc">
<ul></ul>
</div>
<ul id="index">
<li><h3>Super-module</h3>
<ul>
<li><code><a title="ktrain.graph" href="index.html">ktrain.graph</a></code></li>
</ul>
</li>
<li><h3><a href="#header-functions">Functions</a></h3>
<ul class="">
<li><code><a title="ktrain.graph.data.graph_links_from_csv" href="#ktrain.graph.data.graph_links_from_csv">graph_links_from_csv</a></code></li>
<li><code><a title="ktrain.graph.data.graph_nodes_from_csv" href="#ktrain.graph.data.graph_nodes_from_csv">graph_nodes_from_csv</a></code></li>
</ul>
</li>
</ul>
</nav>
</main>
<footer id="footer">
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.10.0</a>.</p>
</footer>
</body>
</html>