line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
package Paws::MachineLearning::MLModel; |
2
|
1
|
|
|
1
|
|
433
|
use Moose; |
|
1
|
|
|
1
|
|
3
|
|
|
1
|
|
|
|
|
8
|
|
|
1
|
|
|
|
|
361
|
|
|
1
|
|
|
|
|
2
|
|
|
1
|
|
|
|
|
6
|
|
3
|
|
|
|
|
|
|
has Algorithm => (is => 'ro', isa => 'Str'); |
4
|
|
|
|
|
|
|
has ComputeTime => (is => 'ro', isa => 'Int'); |
5
|
|
|
|
|
|
|
has CreatedAt => (is => 'ro', isa => 'Str'); |
6
|
|
|
|
|
|
|
has CreatedByIamUser => (is => 'ro', isa => 'Str'); |
7
|
|
|
|
|
|
|
has EndpointInfo => (is => 'ro', isa => 'Paws::MachineLearning::RealtimeEndpointInfo'); |
8
|
|
|
|
|
|
|
has FinishedAt => (is => 'ro', isa => 'Str'); |
9
|
|
|
|
|
|
|
has InputDataLocationS3 => (is => 'ro', isa => 'Str'); |
10
|
|
|
|
|
|
|
has LastUpdatedAt => (is => 'ro', isa => 'Str'); |
11
|
|
|
|
|
|
|
has Message => (is => 'ro', isa => 'Str'); |
12
|
|
|
|
|
|
|
has MLModelId => (is => 'ro', isa => 'Str'); |
13
|
|
|
|
|
|
|
has MLModelType => (is => 'ro', isa => 'Str'); |
14
|
|
|
|
|
|
|
has Name => (is => 'ro', isa => 'Str'); |
15
|
|
|
|
|
|
|
has ScoreThreshold => (is => 'ro', isa => 'Num'); |
16
|
|
|
|
|
|
|
has ScoreThresholdLastUpdatedAt => (is => 'ro', isa => 'Str'); |
17
|
|
|
|
|
|
|
has SizeInBytes => (is => 'ro', isa => 'Int'); |
18
|
|
|
|
|
|
|
has StartedAt => (is => 'ro', isa => 'Str'); |
19
|
|
|
|
|
|
|
has Status => (is => 'ro', isa => 'Str'); |
20
|
|
|
|
|
|
|
has TrainingDataSourceId => (is => 'ro', isa => 'Str'); |
21
|
|
|
|
|
|
|
has TrainingParameters => (is => 'ro', isa => 'Paws::MachineLearning::TrainingParameters'); |
22
|
|
|
|
|
|
|
1; |
23
|
|
|
|
|
|
|
|
24
|
|
|
|
|
|
|
### main pod documentation begin ### |
25
|
|
|
|
|
|
|
|
26
|
|
|
|
|
|
|
=head1 NAME |
27
|
|
|
|
|
|
|
|
28
|
|
|
|
|
|
|
Paws::MachineLearning::MLModel |
29
|
|
|
|
|
|
|
|
30
|
|
|
|
|
|
|
=head1 USAGE |
31
|
|
|
|
|
|
|
|
32
|
|
|
|
|
|
|
This class represents one of two things: |
33
|
|
|
|
|
|
|
|
34
|
|
|
|
|
|
|
=head3 Arguments in a call to a service |
35
|
|
|
|
|
|
|
|
36
|
|
|
|
|
|
|
Use the attributes of this class as arguments to methods. You shouldn't make instances of this class. |
37
|
|
|
|
|
|
|
Each attribute should be used as a named argument in the calls that expect this type of object. |
38
|
|
|
|
|
|
|
|
39
|
|
|
|
|
|
|
As an example, if Att1 is expected to be a Paws::MachineLearning::MLModel object: |
40
|
|
|
|
|
|
|
|
41
|
|
|
|
|
|
|
$service_obj->Method(Att1 => { Algorithm => $value, ..., TrainingParameters => $value }); |
42
|
|
|
|
|
|
|
|
43
|
|
|
|
|
|
|
=head3 Results returned from an API call |
44
|
|
|
|
|
|
|
|
45
|
|
|
|
|
|
|
Use accessors for each attribute. If Att1 is expected to be an Paws::MachineLearning::MLModel object: |
46
|
|
|
|
|
|
|
|
47
|
|
|
|
|
|
|
$result = $service_obj->Method(...); |
48
|
|
|
|
|
|
|
$result->Att1->Algorithm |
49
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
=head1 DESCRIPTION |
51
|
|
|
|
|
|
|
|
52
|
|
|
|
|
|
|
Represents the output of a C<GetMLModel> operation. |
53
|
|
|
|
|
|
|
|
54
|
|
|
|
|
|
|
The content consists of the detailed metadata and the current status of |
55
|
|
|
|
|
|
|
the C<MLModel>. |
56
|
|
|
|
|
|
|
|
57
|
|
|
|
|
|
|
=head1 ATTRIBUTES |
58
|
|
|
|
|
|
|
|
59
|
|
|
|
|
|
|
|
60
|
|
|
|
|
|
|
=head2 Algorithm => Str |
61
|
|
|
|
|
|
|
|
62
|
|
|
|
|
|
|
The algorithm used to train the C<MLModel>. The following algorithm is |
63
|
|
|
|
|
|
|
supported: |
64
|
|
|
|
|
|
|
|
65
|
|
|
|
|
|
|
=over |
66
|
|
|
|
|
|
|
|
67
|
|
|
|
|
|
|
=item * C<SGD> -- Stochastic gradient descent. The goal of C<SGD> is to |
68
|
|
|
|
|
|
|
minimize the gradient of the loss function. |
69
|
|
|
|
|
|
|
|
70
|
|
|
|
|
|
|
=back |
71
|
|
|
|
|
|
|
|
72
|
|
|
|
|
|
|
|
73
|
|
|
|
|
|
|
|
74
|
|
|
|
|
|
|
=head2 ComputeTime => Int |
75
|
|
|
|
|
|
|
|
76
|
|
|
|
|
|
|
|
77
|
|
|
|
|
|
|
|
78
|
|
|
|
|
|
|
|
79
|
|
|
|
|
|
|
=head2 CreatedAt => Str |
80
|
|
|
|
|
|
|
|
81
|
|
|
|
|
|
|
The time that the C<MLModel> was created. The time is expressed in |
82
|
|
|
|
|
|
|
epoch time. |
83
|
|
|
|
|
|
|
|
84
|
|
|
|
|
|
|
|
85
|
|
|
|
|
|
|
=head2 CreatedByIamUser => Str |
86
|
|
|
|
|
|
|
|
87
|
|
|
|
|
|
|
The AWS user account from which the C<MLModel> was created. The account |
88
|
|
|
|
|
|
|
type can be either an AWS root account or an AWS Identity and Access |
89
|
|
|
|
|
|
|
Management (IAM) user account. |
90
|
|
|
|
|
|
|
|
91
|
|
|
|
|
|
|
|
92
|
|
|
|
|
|
|
=head2 EndpointInfo => L<Paws::MachineLearning::RealtimeEndpointInfo> |
93
|
|
|
|
|
|
|
|
94
|
|
|
|
|
|
|
The current endpoint of the C<MLModel>. |
95
|
|
|
|
|
|
|
|
96
|
|
|
|
|
|
|
|
97
|
|
|
|
|
|
|
=head2 FinishedAt => Str |
98
|
|
|
|
|
|
|
|
99
|
|
|
|
|
|
|
|
100
|
|
|
|
|
|
|
|
101
|
|
|
|
|
|
|
|
102
|
|
|
|
|
|
|
=head2 InputDataLocationS3 => Str |
103
|
|
|
|
|
|
|
|
104
|
|
|
|
|
|
|
The location of the data file or directory in Amazon Simple Storage |
105
|
|
|
|
|
|
|
Service (Amazon S3). |
106
|
|
|
|
|
|
|
|
107
|
|
|
|
|
|
|
|
108
|
|
|
|
|
|
|
=head2 LastUpdatedAt => Str |
109
|
|
|
|
|
|
|
|
110
|
|
|
|
|
|
|
The time of the most recent edit to the C<MLModel>. The time is |
111
|
|
|
|
|
|
|
expressed in epoch time. |
112
|
|
|
|
|
|
|
|
113
|
|
|
|
|
|
|
|
114
|
|
|
|
|
|
|
=head2 Message => Str |
115
|
|
|
|
|
|
|
|
116
|
|
|
|
|
|
|
A description of the most recent details about accessing the |
117
|
|
|
|
|
|
|
C<MLModel>. |
118
|
|
|
|
|
|
|
|
119
|
|
|
|
|
|
|
|
120
|
|
|
|
|
|
|
=head2 MLModelId => Str |
121
|
|
|
|
|
|
|
|
122
|
|
|
|
|
|
|
The ID assigned to the C<MLModel> at creation. |
123
|
|
|
|
|
|
|
|
124
|
|
|
|
|
|
|
|
125
|
|
|
|
|
|
|
=head2 MLModelType => Str |
126
|
|
|
|
|
|
|
|
127
|
|
|
|
|
|
|
Identifies the C<MLModel> category. The following are the available |
128
|
|
|
|
|
|
|
types: |
129
|
|
|
|
|
|
|
|
130
|
|
|
|
|
|
|
=over |
131
|
|
|
|
|
|
|
|
132
|
|
|
|
|
|
|
=item * C<REGRESSION> - Produces a numeric result. For example, "What |
133
|
|
|
|
|
|
|
price should a house be listed at?" |
134
|
|
|
|
|
|
|
|
135
|
|
|
|
|
|
|
=item * C<BINARY> - Produces one of two possible results. For example, |
136
|
|
|
|
|
|
|
"Is this a child-friendly web site?". |
137
|
|
|
|
|
|
|
|
138
|
|
|
|
|
|
|
=item * C<MULTICLASS> - Produces one of several possible results. For |
139
|
|
|
|
|
|
|
example, "Is this a HIGH-, LOW-, or MEDIUM-risk trade?". |
140
|
|
|
|
|
|
|
|
141
|
|
|
|
|
|
|
=back |
142
|
|
|
|
|
|
|
|
143
|
|
|
|
|
|
|
|
144
|
|
|
|
|
|
|
|
145
|
|
|
|
|
|
|
=head2 Name => Str |
146
|
|
|
|
|
|
|
|
147
|
|
|
|
|
|
|
A user-supplied name or description of the C<MLModel>. |
148
|
|
|
|
|
|
|
|
149
|
|
|
|
|
|
|
|
150
|
|
|
|
|
|
|
=head2 ScoreThreshold => Num |
151
|
|
|
|
|
|
|
|
152
|
|
|
|
|
|
|
|
153
|
|
|
|
|
|
|
|
154
|
|
|
|
|
|
|
|
155
|
|
|
|
|
|
|
=head2 ScoreThresholdLastUpdatedAt => Str |
156
|
|
|
|
|
|
|
|
157
|
|
|
|
|
|
|
The time of the most recent edit to the C<ScoreThreshold>. The time is |
158
|
|
|
|
|
|
|
expressed in epoch time. |
159
|
|
|
|
|
|
|
|
160
|
|
|
|
|
|
|
|
161
|
|
|
|
|
|
|
=head2 SizeInBytes => Int |
162
|
|
|
|
|
|
|
|
163
|
|
|
|
|
|
|
|
164
|
|
|
|
|
|
|
|
165
|
|
|
|
|
|
|
|
166
|
|
|
|
|
|
|
=head2 StartedAt => Str |
167
|
|
|
|
|
|
|
|
168
|
|
|
|
|
|
|
|
169
|
|
|
|
|
|
|
|
170
|
|
|
|
|
|
|
|
171
|
|
|
|
|
|
|
=head2 Status => Str |
172
|
|
|
|
|
|
|
|
173
|
|
|
|
|
|
|
The current status of an C<MLModel>. This element can have one of the |
174
|
|
|
|
|
|
|
following values: |
175
|
|
|
|
|
|
|
|
176
|
|
|
|
|
|
|
=over |
177
|
|
|
|
|
|
|
|
178
|
|
|
|
|
|
|
=item * C<PENDING> - Amazon Machine Learning (Amazon ML) submitted a |
179
|
|
|
|
|
|
|
request to create an C<MLModel>. |
180
|
|
|
|
|
|
|
|
181
|
|
|
|
|
|
|
=item * C<INPROGRESS> - The creation process is underway. |
182
|
|
|
|
|
|
|
|
183
|
|
|
|
|
|
|
=item * C<FAILED> - The request to create an C<MLModel> didn't run to |
184
|
|
|
|
|
|
|
completion. The model isn't usable. |
185
|
|
|
|
|
|
|
|
186
|
|
|
|
|
|
|
=item * C<COMPLETED> - The creation process completed successfully. |
187
|
|
|
|
|
|
|
|
188
|
|
|
|
|
|
|
=item * C<DELETED> - The C<MLModel> is marked as deleted. It isn't |
189
|
|
|
|
|
|
|
usable. |
190
|
|
|
|
|
|
|
|
191
|
|
|
|
|
|
|
=back |
192
|
|
|
|
|
|
|
|
193
|
|
|
|
|
|
|
|
194
|
|
|
|
|
|
|
|
195
|
|
|
|
|
|
|
=head2 TrainingDataSourceId => Str |
196
|
|
|
|
|
|
|
|
197
|
|
|
|
|
|
|
The ID of the training C<DataSource>. The C<CreateMLModel> operation |
198
|
|
|
|
|
|
|
uses the C<TrainingDataSourceId>. |
199
|
|
|
|
|
|
|
|
200
|
|
|
|
|
|
|
|
201
|
|
|
|
|
|
|
=head2 TrainingParameters => L<Paws::MachineLearning::TrainingParameters> |
202
|
|
|
|
|
|
|
|
203
|
|
|
|
|
|
|
A list of the training parameters in the C<MLModel>. The list is |
204
|
|
|
|
|
|
|
implemented as a map of key-value pairs. |
205
|
|
|
|
|
|
|
|
206
|
|
|
|
|
|
|
The following is the current set of training parameters: |
207
|
|
|
|
|
|
|
|
208
|
|
|
|
|
|
|
=over |
209
|
|
|
|
|
|
|
|
210
|
|
|
|
|
|
|
=item * |
211
|
|
|
|
|
|
|
|
212
|
|
|
|
|
|
|
C<sgd.maxMLModelSizeInBytes> - The maximum allowed size of the model. |
213
|
|
|
|
|
|
|
Depending on the input data, the size of the model might affect its |
214
|
|
|
|
|
|
|
performance. |
215
|
|
|
|
|
|
|
|
216
|
|
|
|
|
|
|
The value is an integer that ranges from C<100000> to C<2147483648>. |
217
|
|
|
|
|
|
|
The default value is C<33554432>. |
218
|
|
|
|
|
|
|
|
219
|
|
|
|
|
|
|
=item * |
220
|
|
|
|
|
|
|
|
221
|
|
|
|
|
|
|
C<sgd.maxPasses> - The number of times that the training process |
222
|
|
|
|
|
|
|
traverses the observations to build the C<MLModel>. The value is an |
223
|
|
|
|
|
|
|
integer that ranges from C<1> to C<10000>. The default value is C<10>. |
224
|
|
|
|
|
|
|
|
225
|
|
|
|
|
|
|
=item * |
226
|
|
|
|
|
|
|
|
227
|
|
|
|
|
|
|
C<sgd.shuffleType> - Whether Amazon ML shuffles the training data. |
228
|
|
|
|
|
|
|
Shuffling the data improves a model's ability to find the optimal |
229
|
|
|
|
|
|
|
solution for a variety of data types. The valid values are C<auto> and |
230
|
|
|
|
|
|
|
C<none>. The default value is C<none>. |
231
|
|
|
|
|
|
|
|
232
|
|
|
|
|
|
|
=item * |
233
|
|
|
|
|
|
|
|
234
|
|
|
|
|
|
|
C<sgd.l1RegularizationAmount> - The coefficient regularization L1 norm, |
235
|
|
|
|
|
|
|
which controls overfitting the data by penalizing large coefficients. |
236
|
|
|
|
|
|
|
This parameter tends to drive coefficients to zero, resulting in sparse |
237
|
|
|
|
|
|
|
feature set. If you use this parameter, start by specifying a small |
238
|
|
|
|
|
|
|
value, such as C<1.0E-08>. |
239
|
|
|
|
|
|
|
|
240
|
|
|
|
|
|
|
The value is a double that ranges from C<0> to C<MAX_DOUBLE>. The |
241
|
|
|
|
|
|
|
default is to not use L1 normalization. This parameter can't be used |
242
|
|
|
|
|
|
|
when C<L2> is specified. Use this parameter sparingly. |
243
|
|
|
|
|
|
|
|
244
|
|
|
|
|
|
|
=item * |
245
|
|
|
|
|
|
|
|
246
|
|
|
|
|
|
|
C<sgd.l2RegularizationAmount> - The coefficient regularization L2 norm, |
247
|
|
|
|
|
|
|
which controls overfitting the data by penalizing large coefficients. |
248
|
|
|
|
|
|
|
This tends to drive coefficients to small, nonzero values. If you use |
249
|
|
|
|
|
|
|
this parameter, start by specifying a small value, such as C<1.0E-08>. |
250
|
|
|
|
|
|
|
|
251
|
|
|
|
|
|
|
The value is a double that ranges from C<0> to C<MAX_DOUBLE>. The |
252
|
|
|
|
|
|
|
default is to not use L2 normalization. This parameter can't be used |
253
|
|
|
|
|
|
|
when C<L1> is specified. Use this parameter sparingly. |
254
|
|
|
|
|
|
|
|
255
|
|
|
|
|
|
|
=back |
256
|
|
|
|
|
|
|
|
257
|
|
|
|
|
|
|
|
258
|
|
|
|
|
|
|
|
259
|
|
|
|
|
|
|
|
260
|
|
|
|
|
|
|
=head1 SEE ALSO |
261
|
|
|
|
|
|
|
|
262
|
|
|
|
|
|
|
This class forms part of L<Paws>, describing an object used in L<Paws::MachineLearning> |
263
|
|
|
|
|
|
|
|
264
|
|
|
|
|
|
|
=head1 BUGS and CONTRIBUTIONS |
265
|
|
|
|
|
|
|
|
266
|
|
|
|
|
|
|
The source code is located here: https://github.com/pplu/aws-sdk-perl |
267
|
|
|
|
|
|
|
|
268
|
|
|
|
|
|
|
Please report bugs to: https://github.com/pplu/aws-sdk-perl/issues |
269
|
|
|
|
|
|
|
|
270
|
|
|
|
|
|
|
=cut |
271
|
|
|
|
|
|
|
|