-
Notifications
You must be signed in to change notification settings - Fork 1
/
GetTrainAndTestData.html
151 lines (136 loc) · 9.68 KB
/
GetTrainAndTestData.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
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<html><head><title>Python: module GetTrainAndTestData</title>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head><body bgcolor="#f0f0f8">
<table width="100%" cellspacing=0 cellpadding=2 border=0 summary="heading">
<tr bgcolor="#7799ee">
<td valign=bottom> <br>
<font color="#ffffff" face="helvetica, arial"> <br><big><big><strong>GetTrainAndTestData</strong></big></big></font></td
><td align=right valign=bottom
><font color="#ffffff" face="helvetica, arial"><a href=".">index</a><br><a href="file:e%3A%5Cmyproject%5Cws_20_21%5Cknowledgedistillation%5Cgettrainandtestdata.py">e:\myproject\ws_20_21\knowledgedistillation\gettrainandtestdata.py</a></font></td></tr></table>
<p></p>
<p>
<table width="100%" cellspacing=0 cellpadding=2 border=0 summary="section">
<tr bgcolor="#ee77aa">
<td colspan=3 valign=bottom> <br>
<font color="#ffffff" face="helvetica, arial"><big><strong>Classes</strong></big></font></td></tr>
<tr><td bgcolor="#ee77aa"><tt> </tt></td><td> </td>
<td width="100%"><dl>
<dt><font face="helvetica, arial"><a href="torch.utils.data.dataset.html#Dataset">torch.utils.data.dataset.Dataset</a>(<a href="typing.html#Generic">typing.Generic</a>)
</font></dt><dd>
<dl>
<dt><font face="helvetica, arial"><a href="GetTrainAndTestData.html#CSVDataset">CSVDataset</a>
</font></dt></dl>
</dd>
</dl>
<p>
<table width="100%" cellspacing=0 cellpadding=2 border=0 summary="section">
<tr bgcolor="#ffc8d8">
<td colspan=3 valign=bottom> <br>
<font color="#000000" face="helvetica, arial"><a name="CSVDataset">class <strong>CSVDataset</strong></a>(<a href="torch.utils.data.dataset.html#Dataset">torch.utils.data.dataset.Dataset</a>)</font></td></tr>
<tr bgcolor="#ffc8d8"><td rowspan=2><tt> </tt></td>
<td colspan=2><tt><a href="#CSVDataset">CSVDataset</a>(*args, **kwds)<br>
<br>
An abstract class representing a :class:`<a href="torch.utils.data.dataset.html#Dataset">Dataset</a>`.<br>
<br>
All datasets that represent a map from keys to data samples should subclass<br>
it. All subclasses should overwrite :meth:`__getitem__`, supporting fetching a<br>
data sample for a given key. Subclasses could also optionally overwrite<br>
:meth:`__len__`, which is expected to return the size of the dataset by many<br>
:class:`~torch.utils.data.Sampler` implementations and the default options<br>
of :class:`~torch.utils.data.DataLoader`.<br>
<br>
.. note::<br>
:class:`~torch.utils.data.DataLoader` by default constructs a index<br>
sampler that yields integral indices. To make it work with a map-style<br>
dataset with non-integral indices/keys, a custom sampler must be provided.<br> </tt></td></tr>
<tr><td> </td>
<td width="100%"><dl><dt>Method resolution order:</dt>
<dd><a href="GetTrainAndTestData.html#CSVDataset">CSVDataset</a></dd>
<dd><a href="torch.utils.data.dataset.html#Dataset">torch.utils.data.dataset.Dataset</a></dd>
<dd><a href="typing.html#Generic">typing.Generic</a></dd>
<dd><a href="builtins.html#object">builtins.object</a></dd>
</dl>
<hr>
Methods defined here:<br>
<dl><dt><a name="CSVDataset-__getitem__"><strong>__getitem__</strong></a>(self, idx)</dt><dd><tt>This function returns the sample at the index idx</tt></dd></dl>
<dl><dt><a name="CSVDataset-__init__"><strong>__init__</strong></a>(self, path)</dt><dd><tt>Pytorch provides class <a href="torch.utils.data.dataset.html#Dataset">Dataset</a>, which we are extending here and<br>
customizing, with respect to our dataset. We are loading the csv<br>
file as dataframe, we are storing the inputs to X(attributes according<br>
to which we are making predictions), and y(original targets). We are<br>
scaling our input variables using StandardScaler(). Original targets are<br>
not scaled, as the target value is 0 or 1.<br>
<br>
Parameters<br>
----------<br>
path : path to the heart.csv file<br>
<br>
Returns<br>
-------<br>
None.</tt></dd></dl>
<dl><dt><a name="CSVDataset-__len__"><strong>__len__</strong></a>(self)</dt><dd><tt>This function returns the number of rows in the dataset (number of samples<br>
we are working with).</tt></dd></dl>
<dl><dt><a name="CSVDataset-get__inputs"><strong>get__inputs</strong></a>(self, idx)</dt><dd><tt>This function returns the sample, without original target, at the index idx.</tt></dd></dl>
<dl><dt><a name="CSVDataset-get_splits"><strong>get_splits</strong></a>(self, n_test=0.3)</dt><dd><tt>This function determines sizes for training and testing data, according<br>
to the n_test. Usually, 30%(0.3) of data is used for testing, 70% is used<br>
for training.<br>
<br>
Parameters<br>
----------<br>
n_test : percentage of data used for testing(real number between 0 and 1)<br>
<br>
Returns<br>
-------<br>
indexes for train and test rows</tt></dd></dl>
<hr>
Data and other attributes defined here:<br>
<dl><dt><strong>__parameters__</strong> = ()</dl>
<hr>
Methods inherited from <a href="torch.utils.data.dataset.html#Dataset">torch.utils.data.dataset.Dataset</a>:<br>
<dl><dt><a name="CSVDataset-__add__"><strong>__add__</strong></a>(self, other: 'Dataset[T_co]') -> 'ConcatDataset[T_co]'</dt></dl>
<hr>
Data descriptors inherited from <a href="torch.utils.data.dataset.html#Dataset">torch.utils.data.dataset.Dataset</a>:<br>
<dl><dt><strong>__dict__</strong></dt>
<dd><tt>dictionary for instance variables (if defined)</tt></dd>
</dl>
<dl><dt><strong>__weakref__</strong></dt>
<dd><tt>list of weak references to the object (if defined)</tt></dd>
</dl>
<hr>
Data and other attributes inherited from <a href="torch.utils.data.dataset.html#Dataset">torch.utils.data.dataset.Dataset</a>:<br>
<dl><dt><strong>__orig_bases__</strong> = (typing.Generic[+T_co],)</dl>
<hr>
Class methods inherited from <a href="typing.html#Generic">typing.Generic</a>:<br>
<dl><dt><a name="CSVDataset-__class_getitem__"><strong>__class_getitem__</strong></a>(params)<font color="#909090"><font face="helvetica, arial"> from <a href="builtins.html#type">builtins.type</a></font></font></dt></dl>
<dl><dt><a name="CSVDataset-__init_subclass__"><strong>__init_subclass__</strong></a>(*args, **kwargs)<font color="#909090"><font face="helvetica, arial"> from <a href="builtins.html#type">builtins.type</a></font></font></dt><dd><tt>This method is called when a class is subclassed.<br>
<br>
The default implementation does nothing. It may be<br>
overridden to extend subclasses.</tt></dd></dl>
<hr>
Static methods inherited from <a href="typing.html#Generic">typing.Generic</a>:<br>
<dl><dt><a name="CSVDataset-__new__"><strong>__new__</strong></a>(cls, *args, **kwds)</dt><dd><tt>Create and return a new object. See help(type) for accurate signature.</tt></dd></dl>
</td></tr></table></td></tr></table><p>
<table width="100%" cellspacing=0 cellpadding=2 border=0 summary="section">
<tr bgcolor="#eeaa77">
<td colspan=3 valign=bottom> <br>
<font color="#ffffff" face="helvetica, arial"><big><strong>Functions</strong></big></font></td></tr>
<tr><td bgcolor="#eeaa77"><tt> </tt></td><td> </td>
<td width="100%"><dl><dt><a name="-prepare_data"><strong>prepare_data</strong></a>(path)</dt><dd><tt>Pytorch provides DataLoader class. The aim of this class is to load<br>
<a href="torch.utils.data.dataset.html#Dataset">Dataset</a> instance during the model training and evaluation. Indexes<br>
for rows of data, which will be used for training and testing,<br>
returned by get_splits function, are passed to DataLoader, along with<br>
batch_size (we have opted to propagate one by one sample through the<br>
network) and shuffle parameter, which tells us whether the data should<br>
be shuffled every epoch. As that is better learning strategy, we have<br>
opted to shuffle the training dataset every epoch.<br>
<br>
Parameters<br>
----------<br>
path : path to the heart.csv file<br>
<br>
Returns<br>
-------<br>
train_dl : training dataset<br>
test_dl : test dataset</tt></dd></dl>
</td></tr></table>
</body></html>