danaderp
/
ds4se
mirror of https://github.com/WM-SEMERU/ds4se.git


  
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

	
            ---

title: Data Representation

keywords: fastai
sidebar: home_sidebar

summary: "This module is dedicated to represent software artifacts into proper abstract structure such as vectors or graphs. Possible subfolders:"
---
<!--

#################################################
### THIS FILE WAS AUTOGENERATED! DO NOT EDIT! ###
#################################################
# file to edit: nbs/2.2_repr.roberta.eval.ipynb
# command to build the docs after a change: nbdev_build_docs

-->

<div class="container" id="notebook-container">
    
<div class="cell border-box-sizing code_cell rendered">

</div>
<div class="cell border-box-sizing code_cell rendered">

</div>
<div class="cell border-box-sizing code_cell rendered">

</div>
<div class="cell border-box-sizing code_cell rendered">

<div class="output_wrapper">
<div class="output">

<div class="output_area">


<div class="output_markdown rendered_html output_subarea ">
<h2 id="Vectorizor" class="doc_header"><code>class</code> <code>Vectorizor</code><a href="https://github.com/ncoop57/ds4se/tree/master/ds4se/repr/roberta/eval.py#L16" class="source_link" style="float:right">[source]</a></h2><blockquote><p><code>Vectorizor</code>(<strong><code>vectorizor</code></strong>) :: <code>ABC</code></p>
</blockquote>
<p>Helper class that provides a standard way to create an ABC using
inheritance.</p>

</div>

</div>

</div>
</div>

</div>
<div class="cell border-box-sizing code_cell rendered">

</div>
<div class="cell border-box-sizing code_cell rendered">

<div class="output_wrapper">
<div class="output">

<div class="output_area">


<div class="output_markdown rendered_html output_subarea ">
<h2 id="BertVectorizor" class="doc_header"><code>class</code> <code>BertVectorizor</code><a href="https://github.com/ncoop57/ds4se/tree/master/ds4se/repr/roberta/eval.py#L27" class="source_link" style="float:right">[source]</a></h2><blockquote><p><code>BertVectorizor</code>(<strong><code>vectorizor</code></strong>) :: <a href="repr.roberta.eval.html#Vectorizor"><code>Vectorizor</code></a></p>
</blockquote>
<p>Vectorization subclass that handles vectorizing using BERT</p>

</div>

</div>

</div>
</div>

</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">

<div class="inner_cell">
    <div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">path</span> <span class="o">=</span> <span class="n">Path</span><span class="p">(</span><span class="s1">&#39;/tf/data/models/JavaBert-v1&#39;</span><span class="p">)</span>
</pre></div>

    </div>
</div>
</div>

</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">

<div class="inner_cell">
    <div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">vectorizor</span> <span class="o">=</span> <span class="n">BertVectorizor</span><span class="p">(</span><span class="n">pipeline</span><span class="p">(</span>
    <span class="s2">&quot;feature-extraction&quot;</span><span class="p">,</span>
    <span class="n">model</span><span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">path</span><span class="p">),</span>
    <span class="n">tokenizer</span><span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
<span class="p">))</span>
</pre></div>

    </div>
</div>
</div>

<div class="output_wrapper">
<div class="output">

<div class="output_area">

<div class="output_subarea output_stream output_stderr output_text">
<pre>Model name &#39;/tf/data/models/JavaBert-v1&#39; was not found in model name list (bert-base-uncased, bert-large-uncased, bert-base-cased, bert-large-cased, bert-base-multilingual-uncased, bert-base-multilingual-cased, bert-base-chinese, bert-base-german-cased, bert-large-uncased-whole-word-masking, bert-large-cased-whole-word-masking, bert-large-uncased-whole-word-masking-finetuned-squad, bert-large-cased-whole-word-masking-finetuned-squad, bert-base-cased-finetuned-mrpc, bert-base-german-dbmdz-cased, bert-base-german-dbmdz-uncased, bert-base-japanese, bert-base-japanese-whole-word-masking, bert-base-japanese-char, bert-base-japanese-char-whole-word-masking, bert-base-finnish-cased-v1, bert-base-finnish-uncased-v1, bert-base-dutch-cased, openai-gpt, transfo-xl-wt103, gpt2, gpt2-medium, gpt2-large, gpt2-xl, distilgpt2, ctrl, xlnet-base-cased, xlnet-large-cased, xlm-mlm-en-2048, xlm-mlm-ende-1024, xlm-mlm-enfr-1024, xlm-mlm-enro-1024, xlm-mlm-tlm-xnli15-1024, xlm-mlm-xnli15-1024, xlm-clm-enfr-1024, xlm-clm-ende-1024, xlm-mlm-17-1280, xlm-mlm-100-1280, roberta-base, roberta-large, roberta-large-mnli, distilroberta-base, roberta-base-openai-detector, roberta-large-openai-detector, distilbert-base-uncased, distilbert-base-uncased-distilled-squad, distilbert-base-german-cased, distilbert-base-multilingual-cased, distilbert-base-uncased-finetuned-sst-2-english, albert-base-v1, albert-large-v1, albert-xlarge-v1, albert-xxlarge-v1, albert-base-v2, albert-large-v2, albert-xlarge-v2, albert-xxlarge-v2, camembert-base, umberto-commoncrawl-cased-v1, umberto-wikipedia-uncased-v1, t5-small, t5-base, t5-large, t5-3b, t5-11b, xlm-roberta-base, xlm-roberta-large, xlm-roberta-large-finetuned-conll02-dutch, xlm-roberta-large-finetuned-conll02-spanish, xlm-roberta-large-finetuned-conll03-english, xlm-roberta-large-finetuned-conll03-german, flaubert-small-cased, flaubert-base-uncased, flaubert-base-cased, flaubert-large-cased). We assumed &#39;/tf/data/models/JavaBert-v1/modelcard.json&#39; was a path or url to a model card file named modelcard.json or a directory containing such a file but couldn&#39;t find any such file at this path or url.
Creating an empty model card.
</pre>
</div>
</div>

</div>
</div>

</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">

<div class="inner_cell">
    <div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">vectorizor</span><span class="o">.</span><span class="n">vectorize</span><span class="p">(</span><span class="s2">&quot;public static void main&quot;</span><span class="p">)</span>
</pre></div>

    </div>
</div>
</div>

<div class="output_wrapper">
<div class="output">

<div class="output_area">


<div class="output_text output_subarea output_execute_result">
<pre>array([[[-0.06092769,  0.06083986,  0.00415461, ..., -0.20505397,
         -0.07404258,  0.00412495],
        [-0.14041282, -0.30901086,  0.15790603, ..., -0.81615841,
          0.20173268, -0.22748585],
        [-0.14098363, -0.10925935,  0.05055226, ..., -1.0249418 ,
          0.1391564 , -0.17706262],
        [ 0.03331072, -0.69691283,  0.06129989, ..., -0.69145656,
          0.21840306,  0.34364673],
        [ 0.08206836, -0.20463242,  0.11808557, ..., -0.54706663,
          0.1055802 ,  0.20152366],
        [-0.06292978,  0.05663186, -0.01715738, ..., -0.24839528,
         -0.07256251, -0.03093658]]])</pre>
</div>

</div>

</div>
</div>

</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">

<div class="inner_cell">
    <div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="o">!</span> nbdev_build_docs
</pre></div>

    </div>
</div>
</div>

</div>
</div>