-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathswebench.html
312 lines (299 loc) · 20.2 KB
/
swebench.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
<!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="pdoc3 0.11.1">
<title>selection.swebench API documentation</title>
<meta name="description" content="">
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;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:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 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 .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#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-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 1em;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}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.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/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
<script>window.addEventListener('DOMContentLoaded', () => {
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
hljs.highlightAll();
})</script>
</head>
<body>
<main>
<article id="content">
<header>
<h1 class="title">Module <code>selection.swebench</code></h1>
</header>
<section id="section-intro">
</section>
<section>
</section>
<section>
</section>
<section>
</section>
<section>
<h2 class="section-title" id="header-classes">Classes</h2>
<dl>
<dt id="selection.swebench.SWEBenchCostComputer"><code class="flex name class">
<span>class <span class="ident">SWEBenchCostComputer</span></span>
<span>(</span><span>store_all=False, constant_cost=False)</span>
</code></dt>
<dd>
<div class="desc"><p>Initializes an instance of the SWEBenchCostComputer class.
Computes the cost of running a model on a question.</p>
<p>Parameters:
- store_all (bool, optional): A flag indicating whether to store all computed costs.
- constant_cost (bool, optional): A flag indicating whether to set the computed cost to a constant for each model.
Defaults to False.</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">class SWEBenchCostComputer(BaseCostComputer):
def __init__(self, store_all=False, constant_cost=False):
"""
Initializes an instance of the SWEBenchCostComputer class.
Computes the cost of running a model on a question.
Parameters:
- store_all (bool, optional): A flag indicating whether to store all computed costs.
- constant_cost (bool, optional): A flag indicating whether to set the computed cost to a constant for each model.
Defaults to False.
"""
super().__init__()
self.store_all = store_all
self.constant_cost = constant_cost
self.prediction_models = []
def fit(self, questions, model_answers, measure):
for i, model in enumerate(model_answers[0]):
prediction_models = dict()
for n_models_run in range(1, len(model_answers[0]) + 1):
for combination in combinations(range(len(model_answers[0])), n_models_run):
if i in combination:
continue
measure_x = np.array([[float(model_answers[j][k][-1]) for k in combination] for j in range(len(questions))])
measure_y = measure[:, i]
prediction_model = LinearRegression()
prediction_model.fit(measure_x, measure_y)
prediction_models[combination] = prediction_model
lengths = [len(question[1]) / 1000 for question in questions]
y = measure[:, i]
X = np.array(lengths).reshape(-1, 1)
prediction_model_length = LinearRegression()
prediction_model_length.fit(X, y)
self.prediction_models.append((prediction_model_length, prediction_models))
def predict(self, questions, model_answers):
length_models = len(model_answers[0])
all_costs = []
for i in range(len(questions)):
costs = []
models_run = [j for j in range(length_models) if model_answers[i][j] is not None]
# sort models_run
models_run = sorted(models_run)
for j in range(length_models):
if j in models_run:
costs.append(float(model_answers[i][j][-1]))
elif any([model_answers[i][other_model] is not None for other_model in range(length_models)]):
features = [float(model_answers[i][other_model][-1]) for other_model in models_run]
costs.append(float(self.prediction_models[j][1][tuple(models_run)].predict([features])[0]))
else:
length_q = len(questions[i][1]) / 1000
costs.append(float(self.prediction_models[j][0].predict([[length_q]])[0]))
all_costs.append(costs)
return np.array(all_costs)</code></pre>
</details>
<h3>Ancestors</h3>
<ul class="hlist">
<li><a title="selection.cost_computer.BaseCostComputer" href="cost_computer.html#selection.cost_computer.BaseCostComputer">BaseCostComputer</a></li>
<li><a title="selection.base_computer.BaseComputer" href="base_computer.html#selection.base_computer.BaseComputer">BaseComputer</a></li>
</ul>
<h3>Inherited members</h3>
<ul class="hlist">
<li><code><b><a title="selection.cost_computer.BaseCostComputer" href="cost_computer.html#selection.cost_computer.BaseCostComputer">BaseCostComputer</a></b></code>:
<ul class="hlist">
<li><code><a title="selection.cost_computer.BaseCostComputer.fit" href="base_computer.html#selection.base_computer.BaseComputer.fit">fit</a></code></li>
<li><code><a title="selection.cost_computer.BaseCostComputer.is_independent" href="base_computer.html#selection.base_computer.BaseComputer.is_independent">is_independent</a></code></li>
<li><code><a title="selection.cost_computer.BaseCostComputer.predict" href="cost_computer.html#selection.cost_computer.BaseCostComputer.predict">predict</a></code></li>
<li><code><a title="selection.cost_computer.BaseCostComputer.trigger_training" href="base_computer.html#selection.base_computer.BaseComputer.trigger_training">trigger_training</a></code></li>
</ul>
</li>
</ul>
</dd>
<dt id="selection.swebench.SWEBenchQualityComputer"><code class="flex name class">
<span>class <span class="ident">SWEBenchQualityComputer</span></span>
<span>(</span><span>max_depth=None, n_samples=100, require_constant_not_run=False, repo_names=['django/django', 'sympy/sympy', 'astropy/astropy', 'psf/requests', 'pytest-dev/pytest', 'pylint-dev/pylint', 'sphinx-doc/sphinx', 'scikit-learn/scikit-learn', 'matplotlib/matplotlib', 'pydata/xarray', 'pallets/flask', 'mwaskom/seaborn'])</span>
</code></dt>
<dd>
<div class="desc"><p>Initialize the SweBench Quality Computer class.</p>
<h2 id="parameters">Parameters</h2>
<p>max_depth (int, optional): The maximum depth of the model. Defaults to None.
n_samples (int, optional): The number of samples to use for computed expected value of max. Defaults to 100.
require_constant_not_run (bool, optional): Flag to require constant not run. Defaults to False.
repo_names (list of str, optional): List of repository names in the benchmark. Defaults to a predefined list of popular repositories.</p>
<h2 id="attributes">Attributes</h2>
<dl>
<dt><strong><code>max_depth</code></strong> : <code>int</code></dt>
<dd>The maximum depth of the model.</dd>
<dt><strong><code>repo_names</code></strong> : <code>list</code> of <code>str</code></dt>
<dd>List of repository names to use.</dd>
<dt><strong><code>require_constant_not_run</code></strong> : <code>bool</code></dt>
<dd>Flag to require constant not run.</dd>
<dt><strong><code>prediction_models</code></strong> : <code>list</code></dt>
<dd>List to store prediction models.</dd>
<dt><strong><code>variances</code></strong> : <code>list</code></dt>
<dd>List to store variances.</dd>
</dl></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">class SWEBenchQualityComputer(BaseQualityComputer):
def __init__(self, max_depth=None, n_samples=100,
require_constant_not_run=False,
repo_names=["django/django",
"sympy/sympy",
"astropy/astropy",
"psf/requests",
"pytest-dev/pytest",
"pylint-dev/pylint",
"sphinx-doc/sphinx",
"scikit-learn/scikit-learn",
"matplotlib/matplotlib",
"pydata/xarray",
"pallets/flask",
"mwaskom/seaborn"]):
"""
Initialize the SweBench Quality Computer class.
Parameters:
max_depth (int, optional): The maximum depth of the model. Defaults to None.
n_samples (int, optional): The number of samples to use for computed expected value of max. Defaults to 100.
require_constant_not_run (bool, optional): Flag to require constant not run. Defaults to False.
repo_names (list of str, optional): List of repository names in the benchmark. Defaults to a predefined list of popular repositories.
Attributes:
max_depth (int): The maximum depth of the model.
repo_names (list of str): List of repository names to use.
require_constant_not_run (bool): Flag to require constant not run.
prediction_models (list): List to store prediction models.
variances (list): List to store variances.
"""
super().__init__(
n_samples=n_samples,
)
self.max_depth = max_depth
self.repo_names = repo_names
self.require_constant_not_run = require_constant_not_run
self.prediction_models = []
self.variances = []
def fit(self, questions, model_answers, measure):
for i, model in enumerate(model_answers[0]):
X = [self.base_features(question) for question in questions]
y = measure[:, i]
linear = LogisticRegression(max_iter=5000)
linear.fit(X, y)
self.prediction_models.append(linear)
self.variances.append(np.var(y - linear.predict_proba(X)[:, 1]))
def predict(self, questions, model_answers):
length_models = len(model_answers[0])
all_qualities = []
all_variances = []
for i in range(len(questions)):
qualities = []
variances = np.zeros((length_models, length_models))
for j in range(length_models):
if model_answers[i][j] is not None:
result = float(model_answers[i][j][0])
qualities.append(result)
variances[j][j] = 1e-6
else:
features = self.base_features(questions[i])
qualities.append(self.prediction_models[j].predict_proba([features])[0, 1])
variances[j][j] = self.variances[j]
all_qualities.append(qualities)
all_variances.append(variances)
return np.array(all_qualities), np.array(all_variances)
def base_features(self, question):
"""
Generate a list of base features for a given question, index, and model.
Parameters:
question (str or tuple): The question to generate features for.
If a tuple is provided, the first element is the question string
and the remaining elements are additional features.
Returns:
features (list): A list of features for the given question, index, and model.
"""
if self.require_constant_not_run:
return [1]
features = [len(question[1]) / 1000]
for repo_name in self.repo_names:
features.append(int(repo_name.replace("/", "__") in question[0]))
return features</code></pre>
</details>
<h3>Ancestors</h3>
<ul class="hlist">
<li><a title="selection.quality_computer.BaseQualityComputer" href="quality_computer.html#selection.quality_computer.BaseQualityComputer">BaseQualityComputer</a></li>
<li><a title="selection.base_computer.BaseComputer" href="base_computer.html#selection.base_computer.BaseComputer">BaseComputer</a></li>
</ul>
<h3>Methods</h3>
<dl>
<dt id="selection.swebench.SWEBenchQualityComputer.base_features"><code class="name flex">
<span>def <span class="ident">base_features</span></span>(<span>self, question)</span>
</code></dt>
<dd>
<div class="desc"><p>Generate a list of base features for a given question, index, and model.</p>
<h2 id="parameters">Parameters</h2>
<p>question (str or tuple): The question to generate features for.
If a tuple is provided, the first element is the question string
and the remaining elements are additional features.</p>
<h2 id="returns">Returns</h2>
<p>features (list): A list of features for the given question, index, and model.</p></div>
</dd>
</dl>
<h3>Inherited members</h3>
<ul class="hlist">
<li><code><b><a title="selection.quality_computer.BaseQualityComputer" href="quality_computer.html#selection.quality_computer.BaseQualityComputer">BaseQualityComputer</a></b></code>:
<ul class="hlist">
<li><code><a title="selection.quality_computer.BaseQualityComputer.fit" href="base_computer.html#selection.base_computer.BaseComputer.fit">fit</a></code></li>
<li><code><a title="selection.quality_computer.BaseQualityComputer.fit_covariances" href="quality_computer.html#selection.quality_computer.BaseQualityComputer.fit_covariances">fit_covariances</a></code></li>
<li><code><a title="selection.quality_computer.BaseQualityComputer.is_independent" href="base_computer.html#selection.base_computer.BaseComputer.is_independent">is_independent</a></code></li>
<li><code><a title="selection.quality_computer.BaseQualityComputer.predict" href="base_computer.html#selection.base_computer.BaseComputer.predict">predict</a></code></li>
<li><code><a title="selection.quality_computer.BaseQualityComputer.predict_covariances" href="quality_computer.html#selection.quality_computer.BaseQualityComputer.predict_covariances">predict_covariances</a></code></li>
<li><code><a title="selection.quality_computer.BaseQualityComputer.predict_supermodels" href="quality_computer.html#selection.quality_computer.BaseQualityComputer.predict_supermodels">predict_supermodels</a></code></li>
<li><code><a title="selection.quality_computer.BaseQualityComputer.trigger_training" href="base_computer.html#selection.base_computer.BaseComputer.trigger_training">trigger_training</a></code></li>
</ul>
</li>
</ul>
</dd>
</dl>
</section>
</article>
<nav id="sidebar">
<div class="toc">
<ul></ul>
</div>
<ul id="index">
<li><h3>Super-module</h3>
<ul>
<li><code><a title="selection" href="index.html">selection</a></code></li>
</ul>
</li>
<li><h3><a href="#header-classes">Classes</a></h3>
<ul>
<li>
<h4><code><a title="selection.swebench.SWEBenchCostComputer" href="#selection.swebench.SWEBenchCostComputer">SWEBenchCostComputer</a></code></h4>
</li>
<li>
<h4><code><a title="selection.swebench.SWEBenchQualityComputer" href="#selection.swebench.SWEBenchQualityComputer">SWEBenchQualityComputer</a></code></h4>
<ul class="">
<li><code><a title="selection.swebench.SWEBenchQualityComputer.base_features" href="#selection.swebench.SWEBenchQualityComputer.base_features">base_features</a></code></li>
</ul>
</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> 0.11.1</a>.</p>
</footer>
</body>
</html>