-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathopen_form.html
302 lines (291 loc) · 22.5 KB
/
open_form.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
<!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.open_form 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.open_form</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.open_form.OpenFormCostComputer"><code class="flex name class">
<span>class <span class="ident">OpenFormCostComputer</span></span>
<span>(</span><span>input_costs, output_costs, tokenizers=None, tokenize=True, store_all=False, constant_cost=False)</span>
</code></dt>
<dd>
<div class="desc"><p>Initializes an instance of the OpenFormCostComputer class.
Computes the cost of running a model on a question.</p>
<p>Parameters:
- input_costs (list): A list of input costs per token for each model.
- output_costs (list): A list of output costs per token for each model.
- tokenizers (list, optional): A list of tokenizers. Defaults to None.
- tokenize (bool, optional): A flag indicating whether to tokenize. Defaults to True.
- store_all (bool, optional): A flag indicating whether to store all computed costs.
Defaults to False.
- 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 OpenFormCostComputer(BaseCostComputer):
def __init__(self, input_costs, output_costs, tokenizers=None, tokenize=True,
store_all=False, constant_cost=False):
"""
Initializes an instance of the OpenFormCostComputer class.
Computes the cost of running a model on a question.
Parameters:
- input_costs (list): A list of input costs per token for each model.
- output_costs (list): A list of output costs per token for each model.
- tokenizers (list, optional): A list of tokenizers. Defaults to None.
- tokenize (bool, optional): A flag indicating whether to tokenize. Defaults to True.
- store_all (bool, optional): A flag indicating whether to store all computed costs.
Defaults to False.
- 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.input_costs = input_costs
self.output_costs = output_costs
self.tokenizers = tokenizers
self.average_output_cost = None
self.tokenize = tokenize
self.computed_costs = []
self.store_all = store_all
self.constant_cost = constant_cost
assert tokenizers is not None or not tokenize
def fit(self, questions, model_answers, measure=None):
self.average_output_cost = []
self.constant_costs = []
for model in range(len(model_answers[0])):
tokenized_answers = [model_answers[i][model][0] for i in range(len(model_answers))]
self.computed_costs.append(dict())
if self.tokenize:
tokenized_answers = self.tokenizers[model](tokenized_answers, padding=False)['input_ids']
average_output_cost = np.mean([self.output_costs[model] * len(tokenized_answer) for tokenized_answer in tokenized_answers])
self.average_output_cost.append(average_output_cost / (len(model_answers)))
tokenized_questions = questions
if len(tokenized_questions) > 0 and not isinstance(tokenized_questions[0], str):
tokenized_questions = [question[0] for question in tokenized_questions]
if self.tokenize:
tokenized_questions = self.tokenizers[model](tokenized_questions, padding=False)['input_ids']
average_input_cost = np.mean([self.input_costs[model] * len(tokenized_question) for tokenized_question in tokenized_questions])
self.constant_costs.append(average_input_cost + average_output_cost)
def predict(self, questions, model_answers):
length_models = len(model_answers[0])
all_costs = []
for i in range(len(questions)):
models_run = ','.join([str(int(model_answers[i][model] is not None))
for model in range(length_models)])
tokenized_question = None
tokenized_model_answers = None
costs = []
for model in range(length_models):
if self.constant_cost:
cost = self.constant_costs[model]
costs.append(cost)
continue
question = questions[i]
if not isinstance(question, str):
question = question[0]
if (self.training or self.store_all) and question in self.computed_costs[model] and \
models_run in self.computed_costs[model][question]:
costs.append(self.computed_costs[model][question][models_run])
continue
if tokenized_question is None:
tokenized_question = question
tokenized_model_answers = [answer[0] if answer is not None else None
for answer in model_answers[i]]
if self.tokenize:
tokenized_question = [self.tokenizers[model]([question], padding=False)['input_ids'][0] for model in range(length_models)]
tokenized_model_answers = [
self.tokenizers[model]([answer[0]], padding=False)['input_ids'][0]
if answer is not None else None
for answer, model in zip(model_answers[i], range(length_models))
]
cost = self.input_costs[model] * len(tokenized_question[model])
if model_answers[i][model] is None and models_run.count('1') == 0:
cost += self.average_output_cost[model]
elif model_answers[i][model] is None:
cost += self.output_costs[model] * np.mean([len(answer)
for answer in tokenized_model_answers
if answer is not None])
else:
cost += self.output_costs[model] * len(tokenized_model_answers[model])
costs.append(cost)
if self.store_all or self.training:
if question in self.computed_costs[model]:
self.computed_costs[model][question][models_run] = cost
else:
self.computed_costs[model][question] = {models_run: cost}
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.open_form.OpenFormQualityComputer"><code class="flex name class">
<span>class <span class="ident">OpenFormQualityComputer</span></span>
<span>(</span><span>model_class=sklearn.linear_model._logistic.LogisticRegression, require_constant_not_run=False, question_indicator='Question:', answer_indicator='Answer:', remove_options=['\nA:', '\nA.'], max_depth=None, n_samples=100, store_all=False, **kwargs)</span>
</code></dt>
<dd>
<div class="desc"><p>Initializes the OpenFormQualityComputer class.
For a description of all parameters, we refer to the ClassificationQualityComputer class.</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">class OpenFormQualityComputer(ClassificationQualityComputer):
def __init__(self, model_class=LogisticRegression,
require_constant_not_run=False,
question_indicator=r'Question:', answer_indicator=r'Answer:',
remove_options=['\nA:', '\nA.'],
max_depth=None, n_samples=100, store_all=False, **kwargs):
"""
Initializes the OpenFormQualityComputer class.
For a description of all parameters, we refer to the ClassificationQualityComputer class.
"""
super().__init__(
model_class=model_class,
require_constant_not_run=require_constant_not_run,
question_indicator=question_indicator,
answer_indicator=answer_indicator,
remove_options=remove_options,
max_depth=max_depth,
n_samples=n_samples,
store_all=store_all,
)
def parse_question(self, question, remove_options=True):
if not isinstance(question, str):
question = question[0]
question = question.split(self.question_indicator)[-1]
if self.remove_options is not None and remove_options:
for option in self.remove_options:
question = question.split(option)[0].strip()
question = question.split(self.answer_indicator)[0].strip()
return question
def agreement_features(self, n_models, models_answers_sample):
features = []
for i in range(n_models):
for j in range(i + 1, n_models):
if models_answers_sample[i] is not None and models_answers_sample[j] is not None:
features.append(models_answers_sample[i][2] == models_answers_sample[j][2])
return features
def certainty_features(self, model, models_answers_sample):
if models_answers_sample[model] is None:
return []
else:
logprobs = models_answers_sample[model][1]
if len(logprobs) == 0:
return [0 for _ in range(8)]
return [np.sum(logprobs) / 100, np.mean(logprobs),
np.min(logprobs), np.median(logprobs),
np.quantile(logprobs, 0.25), np.quantile(logprobs, 0.1),
np.log(len(logprobs)),
int(models_answers_sample[model][2] is not None)]</code></pre>
</details>
<h3>Ancestors</h3>
<ul class="hlist">
<li><a title="selection.classification.ClassificationQualityComputer" href="classification.html#selection.classification.ClassificationQualityComputer">ClassificationQualityComputer</a></li>
<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>Inherited members</h3>
<ul class="hlist">
<li><code><b><a title="selection.classification.ClassificationQualityComputer" href="classification.html#selection.classification.ClassificationQualityComputer">ClassificationQualityComputer</a></b></code>:
<ul class="hlist">
<li><code><a title="selection.classification.ClassificationQualityComputer.agreement_features" href="classification.html#selection.classification.ClassificationQualityComputer.agreement_features">agreement_features</a></code></li>
<li><code><a title="selection.classification.ClassificationQualityComputer.base_features" href="classification.html#selection.classification.ClassificationQualityComputer.base_features">base_features</a></code></li>
<li><code><a title="selection.classification.ClassificationQualityComputer.certainty_features" href="classification.html#selection.classification.ClassificationQualityComputer.certainty_features">certainty_features</a></code></li>
<li><code><a title="selection.classification.ClassificationQualityComputer.compute_sigma" href="classification.html#selection.classification.ClassificationQualityComputer.compute_sigma">compute_sigma</a></code></li>
<li><code><a title="selection.classification.ClassificationQualityComputer.entropy" href="classification.html#selection.classification.ClassificationQualityComputer.entropy">entropy</a></code></li>
<li><code><a title="selection.classification.ClassificationQualityComputer.fit" href="base_computer.html#selection.base_computer.BaseComputer.fit">fit</a></code></li>
<li><code><a title="selection.classification.ClassificationQualityComputer.fit_covariances" href="quality_computer.html#selection.quality_computer.BaseQualityComputer.fit_covariances">fit_covariances</a></code></li>
<li><code><a title="selection.classification.ClassificationQualityComputer.generate_sample_input_output" href="classification.html#selection.classification.ClassificationQualityComputer.generate_sample_input_output">generate_sample_input_output</a></code></li>
<li><code><a title="selection.classification.ClassificationQualityComputer.is_independent" href="base_computer.html#selection.base_computer.BaseComputer.is_independent">is_independent</a></code></li>
<li><code><a title="selection.classification.ClassificationQualityComputer.js_divergence" href="classification.html#selection.classification.ClassificationQualityComputer.js_divergence">js_divergence</a></code></li>
<li><code><a title="selection.classification.ClassificationQualityComputer.kl_divergence" href="classification.html#selection.classification.ClassificationQualityComputer.kl_divergence">kl_divergence</a></code></li>
<li><code><a title="selection.classification.ClassificationQualityComputer.parse_question" href="classification.html#selection.classification.ClassificationQualityComputer.parse_question">parse_question</a></code></li>
<li><code><a title="selection.classification.ClassificationQualityComputer.predict" href="base_computer.html#selection.base_computer.BaseComputer.predict">predict</a></code></li>
<li><code><a title="selection.classification.ClassificationQualityComputer.predict_covariances" href="quality_computer.html#selection.quality_computer.BaseQualityComputer.predict_covariances">predict_covariances</a></code></li>
<li><code><a title="selection.classification.ClassificationQualityComputer.predict_model" href="classification.html#selection.classification.ClassificationQualityComputer.predict_model">predict_model</a></code></li>
<li><code><a title="selection.classification.ClassificationQualityComputer.predict_n_answers" href="classification.html#selection.classification.ClassificationQualityComputer.predict_n_answers">predict_n_answers</a></code></li>
<li><code><a title="selection.classification.ClassificationQualityComputer.predict_supermodels" href="quality_computer.html#selection.quality_computer.BaseQualityComputer.predict_supermodels">predict_supermodels</a></code></li>
<li><code><a title="selection.classification.ClassificationQualityComputer.prepare_data" href="classification.html#selection.classification.ClassificationQualityComputer.prepare_data">prepare_data</a></code></li>
<li><code><a title="selection.classification.ClassificationQualityComputer.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.open_form.OpenFormCostComputer" href="#selection.open_form.OpenFormCostComputer">OpenFormCostComputer</a></code></h4>
</li>
<li>
<h4><code><a title="selection.open_form.OpenFormQualityComputer" href="#selection.open_form.OpenFormQualityComputer">OpenFormQualityComputer</a></code></h4>
</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>