Difference between revisions of "Orange: Logistic Regression"
Onnowpurbo (talk | contribs) (→Contoh) |
Onnowpurbo (talk | contribs) |
||
| (3 intermediate revisions by the same user not shown) | |||
| Line 2: | Line 2: | ||
| − | + | Widget Logistic Regression mengimplementasikan algoritma klasifikasi logistic regression dengan regularisasi LASSO (L1) atau ridge (L2). | |
==Input== | ==Input== | ||
| Line 15: | Line 15: | ||
Coefficients: logistic regression coefficients | Coefficients: logistic regression coefficients | ||
| − | Logistic Regression | + | Widget Logistic Regression learn (mempelajari) Logistic Regression model dari data. Widget Logistic Regression hanya dapat bekerja / berfungsi untuk task classification. |
[[File:LogisticRegression-stamped.png|center|200px|thumb]] | [[File:LogisticRegression-stamped.png|center|200px|thumb]] | ||
| Line 25: | Line 25: | ||
==Contoh== | ==Contoh== | ||
| − | Widget digunakan sama seperti widget lainnya untuk menginduksi classifier. | + | Widget Logistic Regression digunakan sama seperti widget lainnya untuk menginduksi classifier. Berikut adalah contoh yang menunjukkan hasil prediksi dengan logistic regression pada dataset hayes-roth. Pertama-tama load hayes-roth_learn dengan widget File dan meneruskan data ke Widget Logistic Regression. Lalu kita meneruskan model hasil training ke Widget Predictions. |
| − | Selanjutnya kita ingin memprediksi nilai class di dataset baru. Kita load hayes-roth_test di Widget File ke dua dan menyambungkannya ke Widget Predictions. Kita | + | Selanjutnya kita ingin memprediksi nilai class di dataset baru. Kita load hayes-roth_test di Widget File ke dua dan menyambungkannya ke Widget Predictions. Kita sekarang dapat mengamati nilai class hasil prediksi Widget Logistic Regression langsung di Widget Predictions. |
| − | [[File:LogisticRegression-classification.png|center| | + | [[File:LogisticRegression-classification.png|center|600px|thumb]] |
Contoh Workflow lain, | Contoh Workflow lain, | ||
[[File:OrangeLogisticRegression.png|center|400px|thumb]] | [[File:OrangeLogisticRegression.png|center|400px|thumb]] | ||
| + | |||
| + | ==Youtube== | ||
| + | |||
| + | * [https://www.youtube.com/watch?v=N8TkXh-8XD4 YOUTUBE: ORANGE penyiapan data untuk penilaian award] | ||
| + | * [https://www.youtube.com/watch?v=p2YAcpab3gE YOUTUBE: ORANGE AI in awarding process] | ||
==Referensi== | ==Referensi== | ||
Latest revision as of 05:00, 9 April 2020
Sumber: https://docs.biolab.si//3/visual-programming/widgets/model/logisticregression.html
Widget Logistic Regression mengimplementasikan algoritma klasifikasi logistic regression dengan regularisasi LASSO (L1) atau ridge (L2).
Input
Data: input dataset Preprocessor: preprocessing method(s)
Output
Learner: logistic regression learning algorithm Model: trained model Coefficients: logistic regression coefficients
Widget Logistic Regression learn (mempelajari) Logistic Regression model dari data. Widget Logistic Regression hanya dapat bekerja / berfungsi untuk task classification.
- A name under which the learner appears in other widgets. The default name is “Logistic Regression”.
- Regularization type (either L1 or L2). Set the cost strength (default is C=1).
- Press Apply to commit changes. If Apply Automatically is ticked, changes will be communicated automatically.
Contoh
Widget Logistic Regression digunakan sama seperti widget lainnya untuk menginduksi classifier. Berikut adalah contoh yang menunjukkan hasil prediksi dengan logistic regression pada dataset hayes-roth. Pertama-tama load hayes-roth_learn dengan widget File dan meneruskan data ke Widget Logistic Regression. Lalu kita meneruskan model hasil training ke Widget Predictions.
Selanjutnya kita ingin memprediksi nilai class di dataset baru. Kita load hayes-roth_test di Widget File ke dua dan menyambungkannya ke Widget Predictions. Kita sekarang dapat mengamati nilai class hasil prediksi Widget Logistic Regression langsung di Widget Predictions.
Contoh Workflow lain,
