Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
XGBoost exporter and unit tests are added to repository
- Loading branch information
1 parent
592e9bc
commit acd675a
Showing
6 changed files
with
868 additions
and
0 deletions.
There are no files selected for viewing
Empty file.
Empty file.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,131 @@ | ||
| cylinders,displacement,horsepower,weight,acceleration,model year,origin | ||
| 6,163.0,133.0,3410.0,15.8,78,2 | ||
| 4,113.0,95.0,2278.0,15.5,72,3 | ||
| 6,250.0,88.0,3139.0,14.5,71,1 | ||
| 8,262.0,110.0,3221.0,13.5,75,1 | ||
| 4,91.0,67.0,1965.0,15.0,82,3 | ||
| 4,97.0,78.0,1940.0,14.5,77,2 | ||
| 4,113.0,95.0,2228.0,14.0,71,3 | ||
| 4,140.0,92.0,2572.0,14.9,76,1 | ||
| 4,120.0,97.0,2506.0,14.5,72,3 | ||
| 4,140.0,88.0,2720.0,15.4,78,1 | ||
| 6,258.0,110.0,3632.0,18.0,74,1 | ||
| 8,351.0,138.0,3955.0,13.2,79,1 | ||
| 4,79.0,58.0,1755.0,16.9,81,3 | ||
| 8,400.0,150.0,3761.0,9.5,70,1 | ||
| 6,232.0,100.0,2901.0,16.0,74,1 | ||
| 4,107.0,86.0,2464.0,15.5,76,2 | ||
| 8,305.0,140.0,4215.0,13.0,76,1 | ||
| 8,390.0,190.0,3850.0,8.5,70,1 | ||
| 4,98.0,83.0,2219.0,16.5,74,2 | ||
| 4,108.0,75.0,2350.0,16.8,81,3 | ||
| 8,429.0,208.0,4633.0,11.0,72,1 | ||
| 6,225.0,105.0,3121.0,16.5,73,1 | ||
| 4,108.0,93.0,2391.0,15.5,74,3 | ||
| 6,225.0,105.0,3613.0,16.5,74,1 | ||
| 8,350.0,175.0,4100.0,13.0,73,1 | ||
| 8,400.0,190.0,4422.0,12.5,72,1 | ||
| 4,91.0,67.0,1850.0,13.8,80,3 | ||
| 8,302.0,129.0,3725.0,13.4,79,1 | ||
| 4,90.0,71.0,2223.0,16.5,75,2 | ||
| 6,225.0,105.0,3439.0,15.5,71,1 | ||
| 4,83.0,61.0,2003.0,19.0,74,3 | ||
| 8,318.0,150.0,4237.0,14.5,73,1 | ||
| 8,318.0,145.0,4140.0,13.7,77,1 | ||
| 4,121.0,115.0,2671.0,13.5,75,2 | ||
| 6,232.0,100.0,3288.0,15.5,71,1 | ||
| 6,145.0,76.0,3160.0,19.6,81,2 | ||
| 8,400.0,170.0,4668.0,11.5,75,1 | ||
| 4,140.0,72.0,2401.0,19.5,73,1 | ||
| 4,91.0,67.0,1995.0,16.2,82,3 | ||
| 4,98.0,68.0,2135.0,16.6,78,3 | ||
| 8,318.0,135.0,3830.0,15.2,79,1 | ||
| 4,114.0,91.0,2582.0,14.0,73,2 | ||
| 4,97.0,46.0,1835.0,20.5,70,2 | ||
| 8,318.0,150.0,4077.0,14.0,72,1 | ||
| 4,98.0,70.0,2120.0,15.5,80,1 | ||
| 4,119.0,97.0,2405.0,14.9,78,3 | ||
| 4,89.0,60.0,1968.0,18.8,80,3 | ||
| 4,140.0,90.0,2264.0,15.5,71,1 | ||
| 6,225.0,95.0,3264.0,16.0,75,1 | ||
| 4,78.0,52.0,1985.0,19.4,78,3 | ||
| 6,168.0,116.0,2900.0,12.6,81,3 | ||
| 4,144.0,96.0,2665.0,13.9,82,3 | ||
| 4,105.0,70.0,2200.0,13.2,79,1 | ||
| 4,121.0,112.0,2933.0,14.5,72,2 | ||
| 4,79.0,67.0,1950.0,19.0,74,3 | ||
| 4,134.0,90.0,2711.0,15.5,80,3 | ||
| 8,302.0,140.0,3449.0,10.5,70,1 | ||
| 6,173.0,115.0,2595.0,11.3,79,1 | ||
| 8,318.0,150.0,4457.0,13.5,74,1 | ||
| 4,140.0,88.0,2870.0,18.1,80,1 | ||
| 8,360.0,215.0,4615.0,14.0,70,1 | ||
| 4,156.0,105.0,2745.0,16.7,78,1 | ||
| 4,107.0,75.0,2205.0,14.5,82,3 | ||
| 4,97.0,78.0,2300.0,14.5,74,2 | ||
| 4,85.0,70.0,1990.0,17.0,76,3 | ||
| 8,383.0,180.0,4955.0,11.5,71,1 | ||
| 6,198.0,95.0,3102.0,16.5,74,1 | ||
| 6,200.0,95.0,3155.0,18.2,78,1 | ||
| 8,304.0,120.0,3962.0,13.9,76,1 | ||
| 8,400.0,167.0,4906.0,12.5,73,1 | ||
| 4,97.0,88.0,2100.0,16.5,72,3 | ||
| 6,250.0,88.0,3302.0,15.5,71,1 | ||
| 6,262.0,85.0,3015.0,17.0,82,1 | ||
| 8,350.0,165.0,4209.0,12.0,71,1 | ||
| 4,116.0,90.0,2123.0,14.0,71,2 | ||
| 8,318.0,140.0,4080.0,13.7,78,1 | ||
| 4,79.0,70.0,2074.0,19.5,71,2 | ||
| 4,97.0,67.0,1985.0,16.4,77,3 | ||
| 6,231.0,105.0,3380.0,15.8,78,1 | ||
| 3,70.0,97.0,2330.0,13.5,72,3 | ||
| 8,318.0,150.0,3777.0,12.5,73,1 | ||
| 8,340.0,160.0,3609.0,8.0,70,1 | ||
| 6,146.0,97.0,2815.0,14.5,77,3 | ||
| 8,350.0,180.0,3664.0,11.0,73,1 | ||
| 8,302.0,129.0,3169.0,12.0,75,1 | ||
| 4,140.0,75.0,2542.0,17.0,74,1 | ||
| 6,232.0,112.0,2835.0,14.7,82,1 | ||
| 4,151.0,90.0,2556.0,13.2,79,1 | ||
| 4,105.0,63.0,2125.0,14.7,82,1 | ||
| 4,122.0,88.0,2500.0,15.1,80,2 | ||
| 6,163.0,125.0,3140.0,13.6,78,2 | ||
| 4,120.0,74.0,2635.0,18.3,81,3 | ||
| 4,151.0,84.0,2635.0,16.4,81,1 | ||
| 4,121.0,98.0,2945.0,14.5,75,2 | ||
| 8,360.0,150.0,3940.0,13.0,79,1 | ||
| 4,98.0,76.0,2144.0,14.7,80,2 | ||
| 6,168.0,132.0,2910.0,11.4,80,3 | ||
| 4,107.0,90.0,2430.0,14.5,70,2 | ||
| 4,97.0,75.0,2155.0,16.4,76,3 | ||
| 8,400.0,230.0,4278.0,9.5,73,1 | ||
| 4,140.0,89.0,2755.0,15.8,77,1 | ||
| 4,85.0,65.0,1975.0,19.4,81,3 | ||
| 8,429.0,198.0,4341.0,10.0,70,1 | ||
| 4,97.0,54.0,2254.0,23.5,72,2 | ||
| 4,140.0,90.0,2408.0,19.5,72,1 | ||
| 4,140.0,86.0,2790.0,15.6,82,1 | ||
| 8,304.0,150.0,4257.0,15.5,74,1 | ||
| 4,151.0,90.0,2735.0,18.0,82,1 | ||
| 6,232.0,90.0,3210.0,17.2,78,1 | ||
| 4,85.0,52.0,2035.0,22.2,76,1 | ||
| 4,120.0,88.0,2160.0,14.5,82,3 | ||
| 4,151.0,90.0,3003.0,20.1,80,1 | ||
| 6,225.0,110.0,3620.0,18.7,78,1 | ||
| 6,231.0,110.0,3907.0,21.0,75,1 | ||
| 4,107.0,72.0,2290.0,17.0,80,3 | ||
| 8,360.0,175.0,3821.0,11.0,73,1 | ||
| 4,105.0,75.0,2230.0,14.5,78,1 | ||
| 4,111.0,80.0,2155.0,14.8,77,1 | ||
| 8,302.0,130.0,4295.0,14.9,77,1 | ||
| 4,91.0,69.0,2130.0,14.7,79,2 | ||
| 8,260.0,110.0,4060.0,19.0,77,1 | ||
| 8,304.0,150.0,3433.0,12.0,70,1 | ||
| 8,400.0,180.0,4220.0,11.1,77,1 | ||
| 8,351.0,153.0,4129.0,13.0,72,1 | ||
| 8,318.0,140.0,3735.0,13.2,78,1 | ||
| 4,97.0,67.0,2065.0,17.8,81,3 | ||
| 6,250.0,72.0,3158.0,19.5,75,1 | ||
| 8,307.0,130.0,3504.0,12.0,70,1 | ||
| 4,151.0,90.0,2950.0,17.3,82,1 | ||
| 8,304.0,150.0,3672.0,11.5,72,1 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,151 @@ | ||
| sepal_length,sepal_width,petal_length,petal_width,species | ||
| 5.1,3.5,1.4,0.2,setosa | ||
| 4.9,3.0,1.4,0.2,setosa | ||
| 4.7,3.2,1.3,0.2,setosa | ||
| 4.6,3.1,1.5,0.2,setosa | ||
| 5.0,3.6,1.4,0.2,setosa | ||
| 5.4,3.9,1.7,0.4,setosa | ||
| 4.6,3.4,1.4,0.3,setosa | ||
| 5.0,3.4,1.5,0.2,setosa | ||
| 4.4,2.9,1.4,0.2,setosa | ||
| 4.9,3.1,1.5,0.1,setosa | ||
| 5.4,3.7,1.5,0.2,setosa | ||
| 4.8,3.4,1.6,0.2,setosa | ||
| 4.8,3.0,1.4,0.1,setosa | ||
| 4.3,3.0,1.1,0.1,setosa | ||
| 5.8,4.0,1.2,0.2,setosa | ||
| 5.7,4.4,1.5,0.4,setosa | ||
| 5.4,3.9,1.3,0.4,setosa | ||
| 5.1,3.5,1.4,0.3,setosa | ||
| 5.7,3.8,1.7,0.3,setosa | ||
| 5.1,3.8,1.5,0.3,setosa | ||
| 5.4,3.4,1.7,0.2,setosa | ||
| 5.1,3.7,1.5,0.4,setosa | ||
| 4.6,3.6,1.0,0.2,setosa | ||
| 5.1,3.3,1.7,0.5,setosa | ||
| 4.8,3.4,1.9,0.2,setosa | ||
| 5.0,3.0,1.6,0.2,setosa | ||
| 5.0,3.4,1.6,0.4,setosa | ||
| 5.2,3.5,1.5,0.2,setosa | ||
| 5.2,3.4,1.4,0.2,setosa | ||
| 4.7,3.2,1.6,0.2,setosa | ||
| 4.8,3.1,1.6,0.2,setosa | ||
| 5.4,3.4,1.5,0.4,setosa | ||
| 5.2,4.1,1.5,0.1,setosa | ||
| 5.5,4.2,1.4,0.2,setosa | ||
| 4.9,3.1,1.5,0.2,setosa | ||
| 5.0,3.2,1.2,0.2,setosa | ||
| 5.5,3.5,1.3,0.2,setosa | ||
| 4.9,3.6,1.4,0.1,setosa | ||
| 4.4,3.0,1.3,0.2,setosa | ||
| 5.1,3.4,1.5,0.2,setosa | ||
| 5.0,3.5,1.3,0.3,setosa | ||
| 4.5,2.3,1.3,0.3,setosa | ||
| 4.4,3.2,1.3,0.2,setosa | ||
| 5.0,3.5,1.6,0.6,setosa | ||
| 5.1,3.8,1.9,0.4,setosa | ||
| 4.8,3.0,1.4,0.3,setosa | ||
| 5.1,3.8,1.6,0.2,setosa | ||
| 4.6,3.2,1.4,0.2,setosa | ||
| 5.3,3.7,1.5,0.2,setosa | ||
| 5.0,3.3,1.4,0.2,setosa | ||
| 7.0,3.2,4.7,1.4,versicolor | ||
| 6.4,3.2,4.5,1.5,versicolor | ||
| 6.9,3.1,4.9,1.5,versicolor | ||
| 5.5,2.3,4.0,1.3,versicolor | ||
| 6.5,2.8,4.6,1.5,versicolor | ||
| 5.7,2.8,4.5,1.3,versicolor | ||
| 6.3,3.3,4.7,1.6,versicolor | ||
| 4.9,2.4,3.3,1.0,versicolor | ||
| 6.6,2.9,4.6,1.3,versicolor | ||
| 5.2,2.7,3.9,1.4,versicolor | ||
| 5.0,2.0,3.5,1.0,versicolor | ||
| 5.9,3.0,4.2,1.5,versicolor | ||
| 6.0,2.2,4.0,1.0,versicolor | ||
| 6.1,2.9,4.7,1.4,versicolor | ||
| 5.6,2.9,3.6,1.3,versicolor | ||
| 6.7,3.1,4.4,1.4,versicolor | ||
| 5.6,3.0,4.5,1.5,versicolor | ||
| 5.8,2.7,4.1,1.0,versicolor | ||
| 6.2,2.2,4.5,1.5,versicolor | ||
| 5.6,2.5,3.9,1.1,versicolor | ||
| 5.9,3.2,4.8,1.8,versicolor | ||
| 6.1,2.8,4.0,1.3,versicolor | ||
| 6.3,2.5,4.9,1.5,versicolor | ||
| 6.1,2.8,4.7,1.2,versicolor | ||
| 6.4,2.9,4.3,1.3,versicolor | ||
| 6.6,3.0,4.4,1.4,versicolor | ||
| 6.8,2.8,4.8,1.4,versicolor | ||
| 6.7,3.0,5.0,1.7,versicolor | ||
| 6.0,2.9,4.5,1.5,versicolor | ||
| 5.7,2.6,3.5,1.0,versicolor | ||
| 5.5,2.4,3.8,1.1,versicolor | ||
| 5.5,2.4,3.7,1.0,versicolor | ||
| 5.8,2.7,3.9,1.2,versicolor | ||
| 6.0,2.7,5.1,1.6,versicolor | ||
| 5.4,3.0,4.5,1.5,versicolor | ||
| 6.0,3.4,4.5,1.6,versicolor | ||
| 6.7,3.1,4.7,1.5,versicolor | ||
| 6.3,2.3,4.4,1.3,versicolor | ||
| 5.6,3.0,4.1,1.3,versicolor | ||
| 5.5,2.5,4.0,1.3,versicolor | ||
| 5.5,2.6,4.4,1.2,versicolor | ||
| 6.1,3.0,4.6,1.4,versicolor | ||
| 5.8,2.6,4.0,1.2,versicolor | ||
| 5.0,2.3,3.3,1.0,versicolor | ||
| 5.6,2.7,4.2,1.3,versicolor | ||
| 5.7,3.0,4.2,1.2,versicolor | ||
| 5.7,2.9,4.2,1.3,versicolor | ||
| 6.2,2.9,4.3,1.3,versicolor | ||
| 5.1,2.5,3.0,1.1,versicolor | ||
| 5.7,2.8,4.1,1.3,versicolor | ||
| 6.3,3.3,6.0,2.5,virginica | ||
| 5.8,2.7,5.1,1.9,virginica | ||
| 7.1,3.0,5.9,2.1,virginica | ||
| 6.3,2.9,5.6,1.8,virginica | ||
| 6.5,3.0,5.8,2.2,virginica | ||
| 7.6,3.0,6.6,2.1,virginica | ||
| 4.9,2.5,4.5,1.7,virginica | ||
| 7.3,2.9,6.3,1.8,virginica | ||
| 6.7,2.5,5.8,1.8,virginica | ||
| 7.2,3.6,6.1,2.5,virginica | ||
| 6.5,3.2,5.1,2.0,virginica | ||
| 6.4,2.7,5.3,1.9,virginica | ||
| 6.8,3.0,5.5,2.1,virginica | ||
| 5.7,2.5,5.0,2.0,virginica | ||
| 5.8,2.8,5.1,2.4,virginica | ||
| 6.4,3.2,5.3,2.3,virginica | ||
| 6.5,3.0,5.5,1.8,virginica | ||
| 7.7,3.8,6.7,2.2,virginica | ||
| 7.7,2.6,6.9,2.3,virginica | ||
| 6.0,2.2,5.0,1.5,virginica | ||
| 6.9,3.2,5.7,2.3,virginica | ||
| 5.6,2.8,4.9,2.0,virginica | ||
| 7.7,2.8,6.7,2.0,virginica | ||
| 6.3,2.7,4.9,1.8,virginica | ||
| 6.7,3.3,5.7,2.1,virginica | ||
| 7.2,3.2,6.0,1.8,virginica | ||
| 6.2,2.8,4.8,1.8,virginica | ||
| 6.1,3.0,4.9,1.8,virginica | ||
| 6.4,2.8,5.6,2.1,virginica | ||
| 7.2,3.0,5.8,1.6,virginica | ||
| 7.4,2.8,6.1,1.9,virginica | ||
| 7.9,3.8,6.4,2.0,virginica | ||
| 6.4,2.8,5.6,2.2,virginica | ||
| 6.3,2.8,5.1,1.5,virginica | ||
| 6.1,2.6,5.6,1.4,virginica | ||
| 7.7,3.0,6.1,2.3,virginica | ||
| 6.3,3.4,5.6,2.4,virginica | ||
| 6.4,3.1,5.5,1.8,virginica | ||
| 6.0,3.0,4.8,1.8,virginica | ||
| 6.9,3.1,5.4,2.1,virginica | ||
| 6.7,3.1,5.6,2.4,virginica | ||
| 6.9,3.1,5.1,2.3,virginica | ||
| 5.8,2.7,5.1,1.9,virginica | ||
| 6.8,3.2,5.9,2.3,virginica | ||
| 6.7,3.3,5.7,2.5,virginica | ||
| 6.7,3.0,5.2,2.3,virginica | ||
| 6.3,2.5,5.0,1.9,virginica | ||
| 6.5,3.0,5.2,2.0,virginica | ||
| 6.2,3.4,5.4,2.3,virginica | ||
| 5.9,3.0,5.1,1.8,virginica |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,71 @@ | ||
| import unittest | ||
| from xgboost import XGBRegressor,XGBClassifier | ||
| from nyoka.nyoka import PMML43Ext as pml | ||
| import nyoka.nyoka.xgboost.xgboost_to_pmml as xgb | ||
| import pandas as pd | ||
| from sklearn.model_selection import train_test_split | ||
|
|
||
| class TestMethods(unittest.TestCase): | ||
|
|
||
| def test_XGBoost(self): | ||
| model=XGBClassifier() | ||
| sk_model=iris_dataset(model) | ||
| derived_col_names=['sepal_length','petal_length'] | ||
| col_names=['sepal_length','petal_length'] | ||
| target_name='species' | ||
| mining_imp_value=() | ||
| categoric_values=() | ||
|
|
||
| self.assertEqual( | ||
| len(xgb.get_segments_for_xgbc(sk_model,derived_col_names,col_names,target_name,mining_imp_value,categoric_values)), | ||
| 4) | ||
| self.assertEqual( | ||
| xgb.get_segments_for_xgbc(sk_model,derived_col_names,col_names,target_name,mining_imp_value,categoric_values)[ | ||
| 3].get_id(),4) | ||
| self.assertEqual( | ||
| xgb.get_segments_for_xgbc(sk_model, derived_col_names, col_names, target_name, mining_imp_value,categoric_values)[ | ||
| 3].get_RegressionModel().get_RegressionTable()[0].get_intercept(), '0.0') | ||
|
|
||
|
|
||
|
|
||
| self.assertEqual( | ||
| xgb.mining_Field_For_First_Segment(col_names).__class__.__name__, | ||
| pml.MiningSchema().__class__.__name__) | ||
| self.assertEqual( | ||
| xgb.mining_Field_For_First_Segment(col_names).get_MiningField()[0].get_name(), | ||
| 'sepal_length') | ||
| self.assertEqual(len(xgb.mining_Field_For_First_Segment(['a','b','d','e']).get_MiningField()) | ||
| ,4) | ||
|
|
||
|
|
||
| self.assertEqual( | ||
| type(xgb.generate_Segments_Equal_To_Estimators([],derived_col_names,col_names)), | ||
| type([])) | ||
|
|
||
|
|
||
| self.assertEqual( | ||
| xgb.add_segmentation(sk_model,[],[],pml.Output,1).__class__.__name__, | ||
| pml.Segment().__class__.__name__) | ||
| self.assertEqual( | ||
| xgb.add_segmentation(sk_model,[],[],pml.Output,1).get_MiningModel().__class__.__name__, | ||
| pml.MiningModel().__class__.__name__) | ||
| self.assertEqual(xgb.add_segmentation(sk_model, [], [], pml.Output, 1).get_id(), | ||
| 2) | ||
|
|
||
| self.assertEqual(type(xgb.get_regrs_tabl(sk_model,col_names,'species',categoric_values)),type([])) | ||
|
|
||
|
|
||
|
|
||
| def iris_dataset(sk_model): | ||
| df = pd.read_csv('iris.csv') | ||
| feature_names = df.columns.drop('species') | ||
| feature_names = feature_names._data | ||
| target_name = 'species' | ||
| x_train, x_test, y_train, y_test = train_test_split(df[feature_names], df[target_name], test_size=0.33, | ||
| random_state=101) | ||
| sk_model=sk_model.fit(x_train,y_train) | ||
| return sk_model | ||
|
|
||
|
|
||
| if __name__=='__main__': | ||
| unittest.main(warnings='ignore') |
Oops, something went wrong.