Orange: SVM - Revision history

Onnowpurbo: /* Referensi */

2020-04-12T21:46:02Z

Referensi

← Older revision		Revision as of 21:46, 12 April 2020
Line 53:		Line 53:
	[[File:SVM-support-vectors.png\|center\|600px\|thumb]]		[[File:SVM-support-vectors.png\|center\|600px\|thumb]]

	==~~Referensi~~==		==Youtube==

	~~Introduction to~~ SVM ~~on StatSoft.~~		* [https://www.youtube.com/watch?v=mbuEa8L24fw YOUTUBE: ORANGE Prediksi Menggunakan SVM]


			==Referensi==

			Introduction to SVM on StatSoft.

	==Referensi==		==Referensi==

Onnowpurbo: /* Contoh */

2020-04-06T01:53:01Z

Contoh

← Older revision		Revision as of 01:53, 6 April 2020
Line 49:		Line 49:
	[[File:SVM-Predictions.png\|center\|600px\|thumb]]		[[File:SVM-Predictions.png\|center\|600px\|thumb]]

	Contoh berikut menunjukkan cara menggunakan widget SVM dalam kombinasi dengan widget Scatter Plot. Workflow berikut men-train model SVM pada data iris dan mengeluarkan support vector, yang merupakan contoh data yang digunakan sebagai support vector pada fase learning. Kita dapat mengamati contoh data ini dalam visualisasi widget Scatter Plot. Perhatikan bahwa agar workflow berfungsi dengan benar, kita harus mengatur link antara widget seperti yang ditunjukkan pada screenshot di bawah ini.		Contoh berikut menunjukkan cara menggunakan widget SVM dalam kombinasi dengan widget Scatter Plot. Workflow berikut men-train model widget SVM pada data iris dan mengeluarkan support vector, yang merupakan contoh data yang digunakan sebagai support vector pada fase learning. Kita dapat mengamati contoh data ini dalam visualisasi widget Scatter Plot. Perhatikan bahwa agar workflow berfungsi dengan benar, kita harus mengatur link antara widget seperti yang ditunjukkan pada screenshot di bawah ini.

	[[File:SVM-support-vectors.png\|center\|600px\|thumb]]		[[File:SVM-support-vectors.png\|center\|600px\|thumb]]

Onnowpurbo: /* Contoh */

2020-04-06T01:49:48Z

Contoh

← Older revision		Revision as of 01:49, 6 April 2020
Line 45:		Line 45:
	==Contoh==		==Contoh==

	Untuk contoh regresi, kita menggunakan dataset housing dan membagi data menjadi dua subset data (Data Sampel dan Data Sisa / Remaining) menggunakan widget Data Sampler. Sampel dikirim ke Widget SVM yang menghasilkan Model, yang kemudian digunakan dalam Widget ~~Prediksi~~ untuk memprediksi nilai pada Data Sisa. Skema serupa dapat digunakan jika data sudah dalam dua file terpisah; dalam hal ini, dua widget File akan digunakan daripada memecah data menggunakan Widget File - Widget Data Sampler.		Untuk contoh regresi, kita menggunakan dataset housing dan membagi data menjadi dua subset data (Data Sampel dan Data Sisa / Remaining) menggunakan widget Data Sampler. Sampel dikirim ke Widget SVM yang menghasilkan Model, yang kemudian digunakan dalam Widget Predictions untuk memprediksi nilai pada Data Sisa. Skema serupa dapat digunakan jika data sudah dalam dua file terpisah; dalam hal ini, dua widget File akan digunakan daripada memecah data menggunakan Widget File - Widget Data Sampler.

	[[File:SVM-Predictions.png\|center\|600px\|thumb]]		[[File:SVM-Predictions.png\|center\|600px\|thumb]]

Onnowpurbo: /* Contoh */

2020-04-05T10:13:54Z

Contoh

← Older revision		Revision as of 10:13, 5 April 2020
Line 47:		Line 47:
	Untuk contoh regresi, kita menggunakan dataset housing dan membagi data menjadi dua subset data (Data Sampel dan Data Sisa / Remaining) menggunakan widget Data Sampler. Sampel dikirim ke Widget SVM yang menghasilkan Model, yang kemudian digunakan dalam Widget Prediksi untuk memprediksi nilai pada Data Sisa. Skema serupa dapat digunakan jika data sudah dalam dua file terpisah; dalam hal ini, dua widget File akan digunakan daripada memecah data menggunakan Widget File - Widget Data Sampler.		Untuk contoh regresi, kita menggunakan dataset housing dan membagi data menjadi dua subset data (Data Sampel dan Data Sisa / Remaining) menggunakan widget Data Sampler. Sampel dikirim ke Widget SVM yang menghasilkan Model, yang kemudian digunakan dalam Widget Prediksi untuk memprediksi nilai pada Data Sisa. Skema serupa dapat digunakan jika data sudah dalam dua file terpisah; dalam hal ini, dua widget File akan digunakan daripada memecah data menggunakan Widget File - Widget Data Sampler.

	[[File:SVM-Predictions.png\|center\|~~200px~~\|thumb]]		[[File:SVM-Predictions.png\|center\|600px\|thumb]]

	Contoh berikut menunjukkan cara menggunakan widget SVM dalam kombinasi dengan widget Scatter Plot. Workflow berikut men-train model SVM pada data iris dan mengeluarkan support vector, yang merupakan contoh data yang digunakan sebagai support vector pada fase learning. Kita dapat mengamati contoh data ini dalam visualisasi widget Scatter Plot. Perhatikan bahwa agar workflow berfungsi dengan benar, kita harus mengatur link antara widget seperti yang ditunjukkan pada screenshot di bawah ini.		Contoh berikut menunjukkan cara menggunakan widget SVM dalam kombinasi dengan widget Scatter Plot. Workflow berikut men-train model SVM pada data iris dan mengeluarkan support vector, yang merupakan contoh data yang digunakan sebagai support vector pada fase learning. Kita dapat mengamati contoh data ini dalam visualisasi widget Scatter Plot. Perhatikan bahwa agar workflow berfungsi dengan benar, kita harus mengatur link antara widget seperti yang ditunjukkan pada screenshot di bawah ini.

	[[File:SVM-support-vectors.png\|center\|~~200px~~\|thumb]]		[[File:SVM-support-vectors.png\|center\|600px\|thumb]]

	==Referensi==		==Referensi==

Onnowpurbo at 10:13, 5 April 2020

2020-04-05T10:13:39Z

Onnowpurbo: /* Contoh */

2020-03-06T07:47:37Z

Contoh

← Older revision		Revision as of 07:47, 6 March 2020
Line 45:		Line 45:
	==Contoh==		==Contoh==

	~~In the first~~ (~~regression~~) ~~example~~, ~~we have used~~ housing ~~dataset and split the~~ data ~~into two~~ data ~~subsets~~ (Data ~~Sample and~~ Remaining ~~Data~~) ~~with~~ Data Sampler. ~~The sample was sent to~~ SVM ~~which produced a~~ Model, ~~which was then used in Predictions to predict the values in Remaining~~ Data. ~~A similar schema can be used if the~~ data ~~is already in two separate files~~; ~~in this case~~, ~~two~~ File ~~widgets would be used instead of the~~ File - Data Sampler ~~combination~~.		Dalam contoh pertama (regresi), kami telah menggunakan dataset housing dan membagi data menjadi dua subset data (Data Sampel dan Data Sisa / Remaining) dengan Data Sampler. Sampel dikirim ke Widget SVM yang menghasilkan Model, yang kemudian digunakan dalam Widget Prediksi untuk memprediksi nilai dalam Data Sisa. Skema serupa dapat digunakan jika data sudah dalam dua file terpisah; dalam hal ini, dua widget File akan digunakan daripada memecah data menggunakan Widget File - Widget Data Sampler.

	[[File:SVM-Predictions.png\|center\|200px\|thumb]]		[[File:SVM-Predictions.png\|center\|200px\|thumb]]

	~~The second example shows how to use~~ SVM ~~in combination with~~ Scatter Plot. ~~The following workflow trains a~~ SVM ~~model on~~ iris ~~data and outputs~~ support ~~vectors~~, ~~which are those~~ data ~~instances that were used as~~ support ~~vectors in the~~ learning ~~phase~~. ~~We can observe which are these~~ data ~~instances in a scatter plot visualization~~. ~~Note that for the~~ workflow ~~to work correctly~~, ~~you must set the links between widgets as demonstrated in the~~ screenshot ~~below~~.		Contoh kedua menunjukkan cara menggunakan SVM dalam kombinasi dengan Scatter Plot. Workflow berikut men-train model SVM pada data iris dan mengeluarkan support vector, yang merupakan contoh data yang digunakan sebagai support vector pada fase learning. Kita dapat mengamati contoh data ini dalam visualisasi Scatter Plot. Perhatikan bahwa agar workflow berfungsi dengan benar, kita harus mengatur link antara widget seperti yang ditunjukkan pada screenshot di bawah ini.

	[[File:SVM-support-vectors.png\|center\|200px\|thumb]]		[[File:SVM-support-vectors.png\|center\|200px\|thumb]]


	==Referensi==		==Referensi==

Onnowpurbo: /* Output */

2020-03-06T07:35:20Z

Output

← Older revision		Revision as of 07:35, 6 March 2020
Line 15:		Line 15:
	Support Vectors: instances used as support vectors		Support Vectors: instances used as support vectors

	Support ~~vector~~ machine (SVM) ~~is a~~ machine learning ~~technique that separates the attribute space with a~~ hyperplane, ~~thus maximizing the~~ margin ~~between the instances of different classes or~~ class ~~values~~. ~~The technique often yields supreme predictive performance results~~. Orange ~~embeds a popular implementation of~~ SVM ~~from the~~ LIBSVM ~~package~~. ~~This widget is its~~ graphical user interface.		Support Vector machine (SVM) adalah teknik machine learning yang memisahkan ruang atribut dengan hyperplane, sehingga memaksimalkan margin antara instance class yang berbeda atau nilai class. Teknik ini sering menghasilkan hasil kinerja prediksi tertinggi. Orange menanamkan implementasi populer SVM dari paket LIBSVM. Widget ini adalah graphical user interface-nya.

	~~For~~ regression ~~tasks~~, SVM ~~performs~~ linear regression ~~in a~~ high dimension feature space ~~using an~~ ε-insensitive loss. ~~Its estimation accuracy depends on a good setting of~~ C, ε ~~and~~ kernel ~~parameters~~. ~~The widget outputs~~ class ~~predictions based on a~~ SVM Regression.		Untuk task regression, SVM akan melakukan linear regression di high dimension feature space menggunakan ε-insensitive loss. Dia akan mengestimasi keakuratan tergantung pada settingan parameter C, ε dan kernel. Widget akan mengeluarkan prediksi class berdasarkan SVM Regression.

	~~The widget works for both~~ classification ~~and~~ regression ~~tasks~~.		Widget dapat berfungsi untuk task classification dan regression.

	[[File:SVM-stamped.png\|center\|200px\|thumb]]		[[File:SVM-stamped.png\|center\|200px\|thumb]]

Onnowpurbo at 00:58, 3 March 2020

2020-03-03T00:58:21Z

← Older revision		Revision as of 00:58, 3 March 2020
Line 2:		Line 2:


	Support Vector Machines ~~map inputs to~~ higher-dimensional feature ~~spaces~~.		Support Vector Machines melakukan mapping dari input ke higher-dimensional feature space.

	==Input==		==Input==

Onnowpurbo at 03:55, 28 January 2020

2020-01-28T03:55:14Z

← Older revision		Revision as of 03:55, 28 January 2020
Line 4:		Line 4:
	Support Vector Machines map inputs to higher-dimensional feature spaces.		Support Vector Machines map inputs to higher-dimensional feature spaces.

	~~Inputs~~		==Input==

	Data: input dataset		Data: input dataset
	Preprocessor: preprocessing method(s)		Preprocessor: preprocessing method(s)

	~~Outputs~~		==Output==

	Learner: linear regression learning algorithm		Learner: linear regression learning algorithm
	Model: trained model		Model: trained model
	Support Vectors: instances used as support vectors		Support Vectors: instances used as support vectors

	Support vector machine (SVM) is a machine learning technique that separates the attribute space with a hyperplane, thus maximizing the margin between the instances of different classes or class values. The technique often yields supreme predictive performance results. Orange embeds a popular implementation of SVM from the LIBSVM package. This widget is its graphical user interface.		Support vector machine (SVM) is a machine learning technique that separates the attribute space with a hyperplane, thus maximizing the margin between the instances of different classes or class values. The technique often yields supreme predictive performance results. Orange embeds a popular implementation of SVM from the LIBSVM package. This widget is its graphical user interface.
Line 23:		Line 23:
	[[File:SVM-stamped.png\|center\|200px\|thumb]]		[[File:SVM-stamped.png\|center\|200px\|thumb]]

	The learner can be given a name under which it will appear in other widgets. The default name is “SVM”.		* The learner can be given a name under which it will appear in other widgets. The default name is “SVM”.
	SVM type with test error settings. SVM and ν-SVM are based on different minimization of the error function. On the right side, you can set test error bounds:		* SVM type with test error settings. SVM and ν-SVM are based on different minimization of the error function. On the right side, you can set test error bounds:

	SVM:		** SVM:
	Cost: penalty term for loss and applies for classification and regression tasks.		*** Cost: penalty term for loss and applies for classification and regression tasks.
	ε: a parameter to the epsilon-SVR model, applies to regression tasks. Defines the distance from true values within which no penalty is associated with predicted values.		*** ε: a parameter to the epsilon-SVR model, applies to regression tasks. Defines the distance from true values within which no penalty is associated with predicted values.
	~~ν-SVM:~~
	~~Cost: penalty term for loss and applies only to regression tasks~~
	~~ν: a parameter to the ν-SVR model, applies to classification and regression tasks. An upper bound on the fraction of training errors and a lower bound of the fraction of support vectors.~~
	Kernel is a function that transforms attribute space to a new feature space to fit the maximum-margin hyperplane, thus allowing the algorithm to create the model with Linear, Polynomial, RBF and Sigmoid kernels. Functions that specify the kernel are presented upon selecting them, and the constants involved are:

	g for the gamma constant in kernel function (the recommended value is 1/k, where k is the number of the attributes, but since there may be no training set given to the widget the default is 0 and the user has to set this option manually),		** ν-SVM:
	c for the constant c0 in the kernel function (default 0), and		*** Cost: penalty term for loss and applies only to regression tasks
	d for the degree of the kernel (default 3).		*** ν: a parameter to the ν-SVR model, applies to classification and regression tasks. An upper bound on the fraction of training errors and a lower bound of the fraction of support vectors.
	Set permitted deviation from the expected value in Numerical Tolerance. Tick the box next to Iteration Limit to set the maximum number of iterations permitted.
	Produce a report.		* Kernel is a function that transforms attribute space to a new feature space to fit the maximum-margin hyperplane, thus allowing the algorithm to create the model with Linear, Polynomial, RBF and Sigmoid kernels. Functions that specify the kernel are presented upon selecting them, and the constants involved are:
	Click Apply to commit changes. If you tick the box on the left side of the Apply button, changes will be communicated automatically.		** g for the gamma constant in kernel function (the recommended value is 1/k, where k is the number of the attributes, but since there may be no training set given to the widget the default is 0 and the user has to set this option manually),
			** c for the constant c0 in the kernel function (default 0), and
			** d for the degree of the kernel (default 3).

			* Set permitted deviation from the expected value in Numerical Tolerance. Tick the box next to Iteration Limit to set the maximum number of iterations permitted.
			* Produce a report.
			* Click Apply to commit changes. If you tick the box on the left side of the Apply button, changes will be communicated automatically.

	==Contoh==		==Contoh==

Onnowpurbo at 02:42, 23 January 2020

2020-01-23T02:42:00Z

← Older revision		Revision as of 02:42, 23 January 2020
Line 7:		Line 7:

	Data: input dataset		Data: input dataset

	Preprocessor: preprocessing method(s)		Preprocessor: preprocessing method(s)

Line 13:		Line 12:

	Learner: linear regression learning algorithm		Learner: linear regression learning algorithm

	Model: trained model		Model: trained model

	Support Vectors: instances used as support vectors		Support Vectors: instances used as support vectors

Line 24:		Line 21:
	The widget works for both classification and regression tasks.		The widget works for both classification and regression tasks.

	~~../../_images/~~SVM-stamped.png		[[File:SVM-stamped.png\|center\|200px\|thumb]]

	The learner can be given a name under which it will appear in other widgets. The default name is “SVM”.		The learner can be given a name under which it will appear in other widgets. The default name is “SVM”.

	SVM type with test error settings. SVM and ν-SVM are based on different minimization of the error function. On the right side, you can set test error bounds:		SVM type with test error settings. SVM and ν-SVM are based on different minimization of the error function. On the right side, you can set test error bounds:

	SVM:		SVM:

	Cost: penalty term for loss and applies for classification and regression tasks.		Cost: penalty term for loss and applies for classification and regression tasks.

	ε: a parameter to the epsilon-SVR model, applies to regression tasks. Defines the distance from true values within which no penalty is associated with predicted values.		ε: a parameter to the epsilon-SVR model, applies to regression tasks. Defines the distance from true values within which no penalty is associated with predicted values.

	ν-SVM:		ν-SVM:

	Cost: penalty term for loss and applies only to regression tasks		Cost: penalty term for loss and applies only to regression tasks

	ν: a parameter to the ν-SVR model, applies to classification and regression tasks. An upper bound on the fraction of training errors and a lower bound of the fraction of support vectors.		ν: a parameter to the ν-SVR model, applies to classification and regression tasks. An upper bound on the fraction of training errors and a lower bound of the fraction of support vectors.

	Kernel is a function that transforms attribute space to a new feature space to fit the maximum-margin hyperplane, thus allowing the algorithm to create the model with Linear, Polynomial, RBF and Sigmoid kernels. Functions that specify the kernel are presented upon selecting them, and the constants involved are:		Kernel is a function that transforms attribute space to a new feature space to fit the maximum-margin hyperplane, thus allowing the algorithm to create the model with Linear, Polynomial, RBF and Sigmoid kernels. Functions that specify the kernel are presented upon selecting them, and the constants involved are:

	g for the gamma constant in kernel function (the recommended value is 1/k, where k is the number of the attributes, but since there may be no training set given to the widget the default is 0 and the user has to set this option manually),		g for the gamma constant in kernel function (the recommended value is 1/k, where k is the number of the attributes, but since there may be no training set given to the widget the default is 0 and the user has to set this option manually),

	c for the constant c0 in the kernel function (default 0), and		c for the constant c0 in the kernel function (default 0), and

	d for the degree of the kernel (default 3).		d for the degree of the kernel (default 3).

	Set permitted deviation from the expected value in Numerical Tolerance. Tick the box next to Iteration Limit to set the maximum number of iterations permitted.		Set permitted deviation from the expected value in Numerical Tolerance. Tick the box next to Iteration Limit to set the maximum number of iterations permitted.

	Produce a report.		Produce a report.

	Click Apply to commit changes. If you tick the box on the left side of the Apply button, changes will be communicated automatically.		Click Apply to commit changes. If you tick the box on the left side of the Apply button, changes will be communicated automatically.

	~~Examples~~		==Contoh==

	In the first (regression) example, we have used housing dataset and split the data into two data subsets (Data Sample and Remaining Data) with Data Sampler. The sample was sent to SVM which produced a Model, which was then used in Predictions to predict the values in Remaining Data. A similar schema can be used if the data is already in two separate files; in this case, two File widgets would be used instead of the File - Data Sampler combination.		In the first (regression) example, we have used housing dataset and split the data into two data subsets (Data Sample and Remaining Data) with Data Sampler. The sample was sent to SVM which produced a Model, which was then used in Predictions to predict the values in Remaining Data. A similar schema can be used if the data is already in two separate files; in this case, two File widgets would be used instead of the File - Data Sampler combination.

	~~../../_images/~~SVM-Predictions.png		[[File:SVM-Predictions.png\|center\|200px\|thumb]]

	The second example shows how to use SVM in combination with Scatter Plot. The following workflow trains a SVM model on iris data and outputs support vectors, which are those data instances that were used as support vectors in the learning phase. We can observe which are these data instances in a scatter plot visualization. Note that for the workflow to work correctly, you must set the links between widgets as demonstrated in the screenshot below.		The second example shows how to use SVM in combination with Scatter Plot. The following workflow trains a SVM model on iris data and outputs support vectors, which are those data instances that were used as support vectors in the learning phase. We can observe which are these data instances in a scatter plot visualization. Note that for the workflow to work correctly, you must set the links between widgets as demonstrated in the screenshot below.

	~~../../_images/~~SVM-support-vectors.png		[[File:SVM-support-vectors.png\|center\|200px\|thumb]]
	~~References~~

			==Referensi==

	Introduction to SVM on StatSoft.		Introduction to SVM on StatSoft.