Skip to content

Commit ef9d5cd

Browse files
ajdapretnarajdapretnar
committed
[DOC] Parameter Fitter
1 parent 0e522bb commit ef9d5cd

File tree

5 files changed

+92
-5
lines changed

5 files changed

+92
-5
lines changed

‎source/widgets/evaluate/images/ParameterFitter-Example.png‎

155 KB
Loading

‎source/widgets/evaluate/images/ParameterFitter-stamped.png‎

95.5 KB
Loading

‎source/widgets/evaluate/images/ParameterFitter.png‎

-34.3 KB
Binary file not shown.

‎source/widgets/evaluate/parameterfitter.md‎

Lines changed: 16 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -8,11 +8,22 @@ Find the best hyper-parameters for a model.
88
- Data: input data
99
- Learner: learning algorithm
1010

11-
Parameter fitter shows performance of a learning algorithms with different settings of a hyper-parameter. The widget is currently limited to a single integer parameter. Not all learning algorithms support hyper-parameter tuning.
11+
Parameter fitter shows performance of a learning algorithms with different settings of a hyper-parameter. The widget is currently limited to a single integer parameter. Not all learning algorithms support hyper-parameter tuning (currently, only [Random Forest](../model/randomforest.md) and [PLS](../model/pls.md)). The widget shows a plot of the model's performance at different values of the parameter. The graph shows AUC for classification problems and R2 for regression.
1212

13-
![](images/ParameterFitter.png)
13+
![](images/ParameterFitter-stamped.png)
1414

1515
1. Choose the parameter to fit.
16-
2. Define the lower and the upper limit; step size is determined automatically.
17-
3. Alternatively, specifies the values for the parameter. The widget also accepts `...`, e.g. `1, 2, 3, ..., 10` or `40, 60, ..., 100`. When the parameter has a minimal value (e.g. the number of components cannot be negative), one can also omit the lower bound, e.g. `..., 80, 100`; and if the parameter has a maximal value, one can omit the upper bound, e.g. `2, 4, 6, ...,`.
18-
4. A plot showing the performance at different values of the parameter. The graph shows AUC for classification problems and R2 for regression.
16+
*Range*: Define the lower and the upper limit; step size is determined automatically.
17+
*Manual*: Alternatively, specify the values for the parameter. The widget also accepts `...`, e.g. `1, 2, 3, ..., 10` or `40, 60, ..., 100`. When the parameter has a minimal value (e.g. the number of components cannot be negative), one can also omit the lower bound, e.g. `..., 80, 100`; and if the parameter has a maximal value, one can omit the upper bound, e.g. `2, 4, 6, ...,`.
18+
2. If *Apply Automatically* is ticked, changes are communicated automatically. Alternatively, click *Apply*.
19+
20+
Example
21+
-------
22+
23+
Here is a simple example on how to fit parameters using the **Parameter Fitter** widget. We are using the *heart-disease* data for this example and loading it with the [File](../data/file.md) widget. We pass the data to Parameter Fitter. The widget also needs a learner to fit, the [Random Forest](../model/randomforest.md) in this case.
24+
25+
Parameter Fitter enables observing performance for a varying number of trees. We set the range from 1 to 10, namely we will observe performance for every number of trees up to 10.
26+
27+
We see there's a slight peak in AUC value for cross-validation at 3 trees, while 8 trees seem to be optimal overall.
28+
29+
![](images/ParameterFitter-Example.png)

‎source/widgets/evaluate/workflows/parameterfitter.ows‎

Lines changed: 76 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,76 @@
1+
<?xml version='1.0' encoding='utf-8'?>
2+
<scheme version="2.0" title="" description="">
3+
<nodes>
4+
<node id="0" name="Parameter Fitter" qualified_name="Orange.widgets.evaluate.owparameterfitter.OWParameterFitter" project_name="Orange3" version="" title="Parameter Fitter" position="(311.0, 64.0)" />
5+
<node id="1" name="File" qualified_name="Orange.widgets.data.owfile.OWFile" project_name="Orange3" version="" title="File" position="(58.0, 58.0)" />
6+
<node id="2" name="Random Forest" qualified_name="Orange.widgets.model.owrandomforest.OWRandomForest" project_name="Orange3" version="" title="Random Forest" position="(164.0, 93.0)" />
7+
</nodes>
8+
<links>
9+
<link id="0" source_node_id="1" sink_node_id="0" source_channel="Data" sink_channel="Data" enabled="true" source_channel_id="data" sink_channel_id="data" />
10+
<link id="1" source_node_id="2" sink_node_id="0" source_channel="Learner" sink_channel="Learner" enabled="true" source_channel_id="learner" sink_channel_id="learner" />
11+
</links>
12+
<annotations />
13+
<thumbnail />
14+
<node_properties>
15+
<properties node_id="0" format="literal">{'auto_commit': True, 'controlAreaVisible': True, 'manual_steps': '', 'maximum': 10, 'minimum': 1, 'parameter_index': 0, 'savedWidgetGeometry': b'\x01\xd9\xd0\xcb\x00\x03\x00\x00\x00\x00\x00\xe7\x00\x00\x01?\x00\x00\x04W\x00\x00\x03O\x00\x00\x00\xe7\x00\x00\x01[\x00\x00\x04W\x00\x00\x03O\x00\x00\x00\x00\x00\x00\x00\x00\x05\xe8\x00\x00\x00\xe7\x00\x00\x01[\x00\x00\x04W\x00\x00\x03O', 'type': 0, 'visual_settings': {}, '__version__': 1}</properties>
16+
<properties node_id="1" format="pickle">gASVzwsAAAAAAAB9lCiMEmNvbnRyb2xBcmVhVmlzaWJsZZSIjAxyZWNlbnRfcGF0aHOUXZQojB5v
17+
cmFuZ2V3aWRnZXQudXRpbHMuZmlsZWRpYWxvZ3OUjApSZWNlbnRQYXRolJOUKYGUfZQojAdhYnNw
18+
YXRolIw8L1VzZXJzL2FqZGEvb3JhbmdlL29yYW5nZTMvT3JhbmdlL2RhdGFzZXRzL2hlYXJ0X2Rp
19+
c2Vhc2UudGFilIwGcHJlZml4lIwPc2FtcGxlLWRhdGFzZXRzlIwHcmVscGF0aJSMEWhlYXJ0X2Rp
20+
c2Vhc2UudGFilIwFdGl0bGWUjACUjAVzaGVldJRoEIwLZmlsZV9mb3JtYXSUTnViaAYpgZR9lCho
21+
CYw2L1VzZXJzL2FqZGEvb3JhbmdlL29yYW5nZTMvT3JhbmdlL2RhdGFzZXRzL2hvdXNpbmcudGFi
22+
lGgLaAxoDYwLaG91c2luZy50YWKUaA9oEGgRaBBoEk51YmgGKYGUfZQoaAmMMy9Vc2Vycy9hamRh
23+
L29yYW5nZS9vcmFuZ2UzL09yYW5nZS9kYXRhc2V0cy9pcmlzLnRhYpRoC2gMaA2MCGlyaXMudGFi
24+
lGgPaBBoEWgQaBJOdWJoBimBlH2UKGgJjDYvVXNlcnMvYWpkYS9vcmFuZ2Uvb3JhbmdlMy9PcmFu
25+
Z2UvZGF0YXNldHMvdGl0YW5pYy50YWKUaAtoDGgNjAt0aXRhbmljLnRhYpRoD2gQaBFoEGgSTnVi
26+
aAYpgZR9lChoCYw9L1VzZXJzL2FqZGEvb3JhbmdlL29yYW5nZTMvT3JhbmdlL2RhdGFzZXRzL2Jy
27+
b3duLXNlbGVjdGVkLnRhYpRoC2gMaA2MEmJyb3duLXNlbGVjdGVkLnRhYpRoD2gQaBFoEGgSTnVi
28+
aAYpgZR9lChoCYwyL1VzZXJzL2FqZGEvb3JhbmdlL29yYW5nZTMvT3JhbmdlL2RhdGFzZXRzL3pv
29+
by50YWKUaAtoDGgNjAd6b28udGFilGgPaBBoEWgQaBJOdWJljAtyZWNlbnRfdXJsc5RdlIwTc2F2
30+
ZWRXaWRnZXRHZW9tZXRyeZRDQgHZ0MsAAwAAAAACigAAAFAAAAThAAADCAAAAooAAABsAAAE4QAA
31+
AwgAAAAAAAAAAAXoAAACigAAAGwAAAThAAADCJSMC3NoZWV0X25hbWVzlH2UjAZzb3VyY2WUSwCM
32+
A3VybJRoEIwNZG9tYWluX2VkaXRvcpR9lIwLX192ZXJzaW9uX1+USwGMEGNvbnRleHRfc2V0dGlu
33+
Z3OUXZQojBVvcmFuZ2V3aWRnZXQuc2V0dGluZ3OUjAdDb250ZXh0lJOUKYGUfZQojAZ2YWx1ZXOU
34+
fZQojAl2YXJpYWJsZXOUXZRoL32UaDtdlChdlCiMA2FnZZSMFE9yYW5nZS5kYXRhLnZhcmlhYmxl
35+
lIwSQ29udGludW91c1ZhcmlhYmxllJOUSwBoEIhlXZQojAZnZW5kZXKUaEGMEERpc2NyZXRlVmFy
36+
aWFibGWUk5RLAIwMZmVtYWxlLCBtYWxllIllXZQojApjaGVzdCBwYWlulGhHSwCMNGFzeW1wdG9t
37+
YXRpYywgYXR5cGljYWwgYW5nLCBub24tYW5naW5hbCwgdHlwaWNhbCBhbmeUiWVdlCiMCHJlc3Qg
38+
U0JQlGhDSwBoEIhlXZQojAtjaG9sZXN0ZXJvbJRoQ0sAaBCIZV2UKIwZZmFzdGluZyBibG9vZCBz
39+
dWdhciA+IDEyMJRoR0sAjAQwLCAxlIhlXZQojAhyZXN0IEVDR5RoR0sAjCxub3JtYWwsIGxlZnQg
40+
dmVudCBoeXBlcnRyb3BoeSwgU1QtVCBhYm5vcm1hbJSJZV2UKIwGbWF4IEhSlGhDSwBoEIhlXZQo
41+
jA1leGVyYyBpbmQgYW5nlGhHSwCMBDAsIDGUiGVdlCiMDlNUIGJ5IGV4ZXJjaXNllGhDSwBoEIhl
42+
XZQojBFzbG9wZSBwZWFrIGV4YyBTVJRoR0sAjBx1cHNsb3BpbmcsIGZsYXQsIGRvd25zbG9waW5n
43+
lIllXZQojBVtYWpvciB2ZXNzZWxzIGNvbG9yZWSUaENLAGgQiGVdlCiMBHRoYWyUaEdLAIwnbm9y
44+
bWFsLCByZXZlcnNhYmxlIGRlZmVjdCwgZml4ZWQgZGVmZWN0lIllXZQojBJkaWFtZXRlciBuYXJy
45+
b3dpbmeUaEdLAYwEMCwgMZSIZWVzaDFLAXWMCmF0dHJpYnV0ZXOUKIwDYWdllEsChpSMBmdlbmRl
46+
cpRdlCiMBmZlbWFsZZSMBG1hbGWUZYaUjApjaGVzdCBwYWlulF2UKIwMYXN5bXB0b21hdGljlIwM
47+
YXR5cGljYWwgYW5nlIwLbm9uLWFuZ2luYWyUjAt0eXBpY2FsIGFuZ5RlhpSMCHJlc3QgU0JQlEsC
48+
hpSMC2Nob2xlc3Rlcm9slEsChpSMGWZhc3RpbmcgYmxvb2Qgc3VnYXIgPiAxMjCUXZQojAEwlIwB
49+
MZRlhpSMCHJlc3QgRUNHlF2UKIwGbm9ybWFslIwVbGVmdCB2ZW50IGh5cGVydHJvcGh5lIwNU1Qt
50+
VCBhYm5vcm1hbJRlhpSMBm1heCBIUpRLAoaUjA1leGVyYyBpbmQgYW5nlF2UKGh9aH5lhpSMDlNU
51+
IGJ5IGV4ZXJjaXNllEsChpSMEXNsb3BlIHBlYWsgZXhjIFNUlF2UKIwJdXBzbG9waW5nlIwEZmxh
52+
dJSMC2Rvd25zbG9waW5nlGWGlIwVbWFqb3IgdmVzc2VscyBjb2xvcmVklEsChpSMBHRoYWyUXZQo
53+
jAZub3JtYWyUjBFyZXZlcnNhYmxlIGRlZmVjdJSMDGZpeGVkIGRlZmVjdJRlhpR0lIwFbWV0YXOU
54+
KYwKY2xhc3NfdmFyc5SMEmRpYW1ldGVyIG5hcnJvd2luZ5RdlChofWh+ZYaUhZSMEm1vZGlmaWVk
55+
X3ZhcmlhYmxlc5RdlHViaDYpgZR9lChoOX2UKGg7XZRoL32UaDtdlChdlCiMBENSSU2UaENLAGgQ
56+
iGVdlCiMAlpOlGhDSwBoEIhlXZQojAVJTkRVU5RoQ0sAaBCIZV2UKIwEQ0hBU5RoQ0sAaBCIZV2U
57+
KIwDTk9YlGhDSwBoEIhlXZQojAJSTZRoQ0sAaBCIZV2UKIwDQUdFlGhDSwBoEIhlXZQojANESVOU
58+
aENLAGgQiGVdlCiMA1JBRJRoQ0sAaBCIZV2UKIwDVEFYlGhDSwBoEIhlXZQojAdQVFJBVElPlGhD
59+
SwBoEIhlXZQojAFClGhDSwBoEIhlXZQojAVMU1RBVJRoQ0sAaBCIZV2UKIwETUVEVpRoQ0sBaBCI
60+
ZWVzaDFLAXVoaCiMBENSSU2USwKGlIwCWk6USwKGlIwFSU5EVVOUSwKGlIwEQ0hBU5RLAoaUjANO
61+
T1iUSwKGlIwCUk2USwKGlIwDQUdFlEsChpSMA0RJU5RLAoaUjANSQUSUSwKGlIwDVEFYlEsChpSM
62+
B1BUUkFUSU+USwKGlGjBSwKGlIwFTFNUQVSUSwKGlHSUaJwpaJ2MBE1FRFaUSwKGlIWUaKJdlHVi
63+
aDYpgZR9lChoOX2UKGg7XZRoL32UaDtdlChdlCiMDHNlcGFsIGxlbmd0aJRoQ0sAaBCIZV2UKIwL
64+
c2VwYWwgd2lkdGiUaENLAGgQiGVdlCiMDHBldGFsIGxlbmd0aJRoQ0sAaBCIZV2UKIwLcGV0YWwg
65+
d2lkdGiUaENLAGgQiGVdlCiMBGlyaXOUaEdLAYwsSXJpcy1zZXRvc2EsIElyaXMtdmVyc2ljb2xv
66+
ciwgSXJpcy12aXJnaW5pY2GUiWVlc2gxSwF1aGgojAxzZXBhbCBsZW5ndGiUSwKGlIwLc2VwYWwg
67+
d2lkdGiUSwKGlIwMcGV0YWwgbGVuZ3RolEsChpSMC3BldGFsIHdpZHRolEsChpR0lGicKWidjARp
68+
cmlzlF2UKIwLSXJpcy1zZXRvc2GUjA9JcmlzLXZlcnNpY29sb3KUjA5JcmlzLXZpcmdpbmljYZRl
69+
hpSFlGiiXZR1YmV1Lg==
70+
</properties>
71+
<properties node_id="2" format="literal">{'auto_apply': True, 'class_weight': False, 'controlAreaVisible': True, 'index_output': 0, 'learner_name': '', 'max_depth': 3, 'max_features': 5, 'min_samples_split': 5, 'n_estimators': 10, 'savedWidgetGeometry': None, 'use_max_depth': False, 'use_max_features': False, 'use_min_samples_split': True, 'use_random_state': False, '__version__': 1}</properties>
72+
</node_properties>
73+
<session_state>
74+
<window_groups />
75+
</session_state>
76+
</scheme>

0 commit comments

Comments
 (0)