-
Notifications
You must be signed in to change notification settings - Fork 269
/
dataset.html
260 lines (239 loc) · 13.9 KB
/
dataset.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
<!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 0.9.2" />
<title>ktrain.tabular.dataset 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.tabular.dataset</code></h1>
</header>
<section id="section-intro">
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">from ..imports import *
from ..dataset import SequenceDataset
class TabularDataset(SequenceDataset):
def __init__(self, df, cat_columns, cont_columns, label_columns, batch_size=32, shuffle=False):
# error checks
if not isinstance(df, pd.DataFrame): raise ValueError('df must be pandas Dataframe')
all_columns = cat_columns + cont_columns + label_columns
missing_columns = []
for col in df.columns.values:
if col not in all_columns: missing_columns.append(col)
if len(missing_columns) > 0: raise ValueError('df is missing these columns: %s' % (missing_columns))
# set variables
super().__init__(batch_size=batch_size)
self.indices = np.arange(df.shape[0])
self.df = df
self.cat_columns = cat_columns
self.cont_columns = cont_columns
self.label_columns = label_columns
self.shuffle = shuffle
def __len__(self):
return math.ceil(self.df.shape[0] / self.batch_size)
def __getitem__(self, idx):
inds = self.indices[idx * self.batch_size:(idx + 1) * self.batch_size]
batch_x = []
df = self.df[self.cat_columns+self.cont_columns].iloc[inds]
for cat_name in self.cat_columns:
codes = np.stack([c.cat.codes.values for n,c in df[[cat_name]].items()], 1).astype(np.int64) + 1
batch_x.append(codes)
if len(self.cont_columns) > 0:
conts = np.stack([c.astype('float32').values for n,c in df[self.cont_columns].items()], 1)
batch_x.append(conts)
batch_y = self.df[self.label_columns].iloc[inds].values
batch_x = batch_x[0] if len(batch_x)==1 else tuple(batch_x)
return batch_x, batch_y
def nsamples(self):
return self.df.shape[0]
def get_y(self):
return self.df[self.label_columns].values
def on_epoch_end(self):
if self.shuffle: np.random.shuffle(self.indices)
def xshape(self):
return self.df.shape
def nclasses(self):
return self.get_y().shape[1]</code></pre>
</details>
</section>
<section>
</section>
<section>
</section>
<section>
</section>
<section>
<h2 class="section-title" id="header-classes">Classes</h2>
<dl>
<dt id="ktrain.tabular.dataset.TabularDataset"><code class="flex name class">
<span>class <span class="ident">TabularDataset</span></span>
<span>(</span><span>df, cat_columns, cont_columns, label_columns, batch_size=32, shuffle=False)</span>
</code></dt>
<dd>
<div class="desc"><pre><code>Base class for custom datasets in ktrain.
If subclass of Dataset implements a method to to_tfdataset
that converts the data to a tf.Dataset, then this will be
invoked by Learner instances just prior to training so
fit() will train using a tf.Dataset representation of your data.
Sequence methods such as __get_item__ and __len__
must still be implemented.
The signature of to_tfdataset is as follows:
def to_tfdataset(self, training=True)
See ktrain.text.preprocess.TransformerDataset as an example.
</code></pre></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">class TabularDataset(SequenceDataset):
def __init__(self, df, cat_columns, cont_columns, label_columns, batch_size=32, shuffle=False):
# error checks
if not isinstance(df, pd.DataFrame): raise ValueError('df must be pandas Dataframe')
all_columns = cat_columns + cont_columns + label_columns
missing_columns = []
for col in df.columns.values:
if col not in all_columns: missing_columns.append(col)
if len(missing_columns) > 0: raise ValueError('df is missing these columns: %s' % (missing_columns))
# set variables
super().__init__(batch_size=batch_size)
self.indices = np.arange(df.shape[0])
self.df = df
self.cat_columns = cat_columns
self.cont_columns = cont_columns
self.label_columns = label_columns
self.shuffle = shuffle
def __len__(self):
return math.ceil(self.df.shape[0] / self.batch_size)
def __getitem__(self, idx):
inds = self.indices[idx * self.batch_size:(idx + 1) * self.batch_size]
batch_x = []
df = self.df[self.cat_columns+self.cont_columns].iloc[inds]
for cat_name in self.cat_columns:
codes = np.stack([c.cat.codes.values for n,c in df[[cat_name]].items()], 1).astype(np.int64) + 1
batch_x.append(codes)
if len(self.cont_columns) > 0:
conts = np.stack([c.astype('float32').values for n,c in df[self.cont_columns].items()], 1)
batch_x.append(conts)
batch_y = self.df[self.label_columns].iloc[inds].values
batch_x = batch_x[0] if len(batch_x)==1 else tuple(batch_x)
return batch_x, batch_y
def nsamples(self):
return self.df.shape[0]
def get_y(self):
return self.df[self.label_columns].values
def on_epoch_end(self):
if self.shuffle: np.random.shuffle(self.indices)
def xshape(self):
return self.df.shape
def nclasses(self):
return self.get_y().shape[1]</code></pre>
</details>
<h3>Ancestors</h3>
<ul class="hlist">
<li><a title="ktrain.dataset.SequenceDataset" href="../dataset.html#ktrain.dataset.SequenceDataset">SequenceDataset</a></li>
<li><a title="ktrain.dataset.Dataset" href="../dataset.html#ktrain.dataset.Dataset">Dataset</a></li>
<li>tensorflow.python.keras.utils.data_utils.Sequence</li>
</ul>
<h3>Methods</h3>
<dl>
<dt id="ktrain.tabular.dataset.TabularDataset.get_y"><code class="name flex">
<span>def <span class="ident">get_y</span></span>(<span>self)</span>
</code></dt>
<dd>
<div class="desc"></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def get_y(self):
return self.df[self.label_columns].values</code></pre>
</details>
</dd>
<dt id="ktrain.tabular.dataset.TabularDataset.nsamples"><code class="name flex">
<span>def <span class="ident">nsamples</span></span>(<span>self)</span>
</code></dt>
<dd>
<div class="desc"></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def nsamples(self):
return self.df.shape[0]</code></pre>
</details>
</dd>
<dt id="ktrain.tabular.dataset.TabularDataset.on_epoch_end"><code class="name flex">
<span>def <span class="ident">on_epoch_end</span></span>(<span>self)</span>
</code></dt>
<dd>
<div class="desc"><p>Method called at the end of every epoch.</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def on_epoch_end(self):
if self.shuffle: np.random.shuffle(self.indices)</code></pre>
</details>
</dd>
</dl>
<h3>Inherited members</h3>
<ul class="hlist">
<li><code><b><a title="ktrain.dataset.SequenceDataset" href="../dataset.html#ktrain.dataset.SequenceDataset">SequenceDataset</a></b></code>:
<ul class="hlist">
<li><code><a title="ktrain.dataset.SequenceDataset.nclasses" href="../dataset.html#ktrain.dataset.Dataset.nclasses">nclasses</a></code></li>
<li><code><a title="ktrain.dataset.SequenceDataset.ondisk" href="../dataset.html#ktrain.dataset.Dataset.ondisk">ondisk</a></code></li>
<li><code><a title="ktrain.dataset.SequenceDataset.xshape" href="../dataset.html#ktrain.dataset.Dataset.xshape">xshape</a></code></li>
</ul>
</li>
</ul>
</dd>
</dl>
</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.tabular" href="index.html">ktrain.tabular</a></code></li>
</ul>
</li>
<li><h3><a href="#header-classes">Classes</a></h3>
<ul>
<li>
<h4><code><a title="ktrain.tabular.dataset.TabularDataset" href="#ktrain.tabular.dataset.TabularDataset">TabularDataset</a></code></h4>
<ul class="">
<li><code><a title="ktrain.tabular.dataset.TabularDataset.get_y" href="#ktrain.tabular.dataset.TabularDataset.get_y">get_y</a></code></li>
<li><code><a title="ktrain.tabular.dataset.TabularDataset.nsamples" href="#ktrain.tabular.dataset.TabularDataset.nsamples">nsamples</a></code></li>
<li><code><a title="ktrain.tabular.dataset.TabularDataset.on_epoch_end" href="#ktrain.tabular.dataset.TabularDataset.on_epoch_end">on_epoch_end</a></code></li>
</ul>
</li>
</ul>
</li>
</ul>
</nav>
</main>
<footer id="footer">
<p>Generated by <a href="https://pdoc3.github.io/pdoc"><cite>pdoc</cite> 0.9.2</a>.</p>
</footer>
</body>
</html>