H2O Sonar Demo of Scikit-learn Models
[1]:
import pandas
import webbrowser
from sklearn.ensemble import GradientBoostingClassifier
from h2o_sonar import interpret
from h2o_sonar.lib.api.models import ExplainableModel
[2]:
# dataset
dataset_path = "../../data/predictive/creditcard.csv"
df = pandas.read_csv(dataset_path)
# directory where to store interpretation results
results_location = "../../results"
[3]:
# Set X and y
target_col = "default payment next month"
X, y = df.drop(target_col,axis=1), df[target_col]
[4]:
# Build model
gradient_booster = GradientBoostingClassifier(learning_rate=0.1)
gradient_booster.fit(X, y)
[4]:
GradientBoostingClassifier()In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
Parameters
[5]:
# Run interpretation
interpretation = interpret.run_interpretation(
dataset=dataset_path,
model=gradient_booster,
target_col=target_col,
results_location=results_location,
used_features=list(X.columns),
)
/home/user/h/mli/git/h2o-sonar-FLOSS/.venv/lib/python3.11/site-packages/ragas/metrics/__init__.py:1: LangChainDeprecationWarning: As of langchain-core 0.3.0, LangChain uses pydantic v2 internally. The langchain_core.pydantic_v1 module was a compatibility shim for pydantic v1, and should no longer be used. Please update the code to import from Pydantic directly.
For example, replace imports like: `from langchain_core.pydantic_v1 import BaseModel`
with: `from pydantic import BaseModel`
or the v1 compatibility namespace if you are working in a code base that has not been fully upgraded to pydantic 2 yet. from pydantic.v1 import BaseModel
from ragas.metrics._answer_correctness import AnswerCorrectness, answer_correctness
/home/user/h/mli/git/h2o-sonar-FLOSS/.venv/lib/python3.11/site-packages/ragas/metrics/__init__.py:4: LangChainDeprecationWarning: As of langchain-core 0.3.0, LangChain uses pydantic v2 internally. The langchain.pydantic_v1 module was a compatibility shim for pydantic v1, and should no longer be used. Please update the code to import from Pydantic directly.
For example, replace imports like: `from langchain.pydantic_v1 import BaseModel`
with: `from pydantic import BaseModel`
or the v1 compatibility namespace if you are working in a code base that has not been fully upgraded to pydantic 2 yet. from pydantic.v1 import BaseModel
from ragas.metrics._context_entities_recall import (
Preparing and checking DIA features (None): dataset= | BILL_AMT4 BILL_AMT5 AGE PAY_AMT6 SEX BILL_AMT3 default payment next month PAY_AMT3 PAY_AMT1 LIMIT_BAL … PAY_4 PAY_0 EDUCATION MARRIAGE PAY_2
| int32 int32 int32 int32 int32 int32 int8 int32 int32 int32 int32 int32 int32 int32 int32
---- + --------- --------- ----- -------- ----- --------- -------------------------- -------- -------- --------- ----- ----- --------- -------- -----
0 | 0 0 24 0 2 689 1 0 0 20000 … -1 -2 2 1 2
1 | 3272 3455 26 2000 2 2682 1 1000 0 120000 … 0 -1 2 2 2
2 | 14331 14948 34 5000 2 13559 0 1000 1518 90000 … 0 0 2 2 0
3 | 28314 28959 37 1000 2 49291 0 1200 2000 50000 … 0 1 2 1 0
4 | 20940 19146 57 679 1 35835 0 10000 2000 50000 … 0 2 2 1 0
5 | 19394 19619 37 800 1 57608 0 657 2500 50000 … 0 3 1 2 0
6 | 542653 483003 29 13770 1 445007 0 38000 55000 500000 … 0 4 1 2 0
7 | 221 -159 23 1542 2 601 0 0 380 100000 … 0 5 2 2 -1
8 | 12211 11793 28 1000 2 12108 0 432 3329 140000 … 0 6 3 1 0
9 | 0 13007 35 0 1 0 0 0 0 20000 … -2 7 3 2 -2
10 | 2513 1828 34 66 2 5535 0 50 2306 200000 … 0 8 3 2 0
11 | 8517 22287 51 3640 2 9966 0 8583 21818 260000 … -1 -1 1 2 -1
12 | 6500 6500 41 0 2 6500 0 6500 1000 630000 … -1 -1 2 2 0
13 | 66782 36137 30 0 1 65701 1 3000 3200 70000 … 0 1 2 2 2
14 | 59696 56875 29 3000 1 63561 0 3000 3000 250000 … 0 0 1 2 0
… | … … … … … … … … … … … … … … … …
9995 | 0 0 31 1419 2 0 0 0 241 140000 … -2 1 1 2 -2
9996 | 0 0 37 0 2 0 0 0 0 80000 … -2 -2 2 2 -2
9997 | 151078 176717 44 4200 1 142520 0 10000 6437 200000 … 0 0 3 1 0
9998 | 0 0 26 0 2 0 1 0 0 80000 … -2 -1 2 2 2
9999 | 19506 19255 36 3000 1 19750 0 3000 3000 230000 … 0 0 2 1 0
[10000 rows x 25 columns]
dataset_meta={
"shape": "(10000, 25)",
"row_count": 10000,
"column_names": [
"ID",
"LIMIT_BAL",
"SEX",
"EDUCATION",
"MARRIAGE",
"AGE",
"PAY_0",
"PAY_2",
"PAY_3",
"PAY_4",
"PAY_5",
"PAY_6",
"BILL_AMT1",
"BILL_AMT2",
"BILL_AMT3",
"BILL_AMT4",
"BILL_AMT5",
"BILL_AMT6",
"PAY_AMT1",
"PAY_AMT2",
"PAY_AMT3",
"PAY_AMT4",
"PAY_AMT5",
"PAY_AMT6",
"default payment next month"
],
"column_types": [
"int",
"int",
"int",
"int",
"int",
"int",
"int",
"int",
"int",
"int",
"int",
"int",
"int",
"int",
"int",
"int",
"int",
"int",
"int",
"int",
"int",
"int",
"int",
"int",
"int"
],
"column_uniques": [
10000,
72,
2,
7,
4,
54,
11,
11,
11,
11,
10,
10,
8371,
8215,
8072,
7913,
7764,
7550,
3763,
3581,
3305,
3247,
3258,
3174,
2
],
"columns_cat": [],
"columns_num": [],
"file_path": "../../data/predictive/creditcard.csv",
"file_name": "",
"file_size": 944719,
"missing_values": [
"",
"?",
"None",
"nan",
"NA",
"N/A",
"unknown",
"inf",
"-inf",
"1.7976931348623157e+308",
"-1.7976931348623157e+308"
],
"columns_meta": [
{
"name": "ID",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": true,
"is_numeric": true,
"is_categorical": false,
"count": 10000,
"frequency": 0,
"unique": 10000,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "LIMIT_BAL",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 72,
"frequency": 0,
"unique": 72,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "SEX",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 2,
"frequency": 0,
"unique": 2,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "EDUCATION",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 7,
"frequency": 0,
"unique": 7,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "MARRIAGE",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 4,
"frequency": 0,
"unique": 4,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "AGE",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 54,
"frequency": 0,
"unique": 54,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "PAY_0",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 11,
"frequency": 0,
"unique": 11,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "PAY_2",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 11,
"frequency": 0,
"unique": 11,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "PAY_3",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 11,
"frequency": 0,
"unique": 11,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "PAY_4",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 11,
"frequency": 0,
"unique": 11,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "PAY_5",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 10,
"frequency": 0,
"unique": 10,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "PAY_6",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 10,
"frequency": 0,
"unique": 10,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "BILL_AMT1",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 8371,
"frequency": 0,
"unique": 8371,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "BILL_AMT2",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 8215,
"frequency": 0,
"unique": 8215,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "BILL_AMT3",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 8072,
"frequency": 0,
"unique": 8072,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "BILL_AMT4",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 7913,
"frequency": 0,
"unique": 7913,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "BILL_AMT5",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 7764,
"frequency": 0,
"unique": 7764,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "BILL_AMT6",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 7550,
"frequency": 0,
"unique": 7550,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "PAY_AMT1",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 3763,
"frequency": 0,
"unique": 3763,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "PAY_AMT2",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 3581,
"frequency": 0,
"unique": 3581,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "PAY_AMT3",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 3305,
"frequency": 0,
"unique": 3305,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "PAY_AMT4",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 3247,
"frequency": 0,
"unique": 3247,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "PAY_AMT5",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 3258,
"frequency": 0,
"unique": 3258,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "PAY_AMT6",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 3174,
"frequency": 0,
"unique": 3174,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
},
{
"name": "default payment next month",
"data_type": "int",
"logical_types": [],
"format": "",
"is_id": false,
"is_numeric": true,
"is_categorical": false,
"count": 2,
"frequency": 0,
"unique": 2,
"max": null,
"min": null,
"mean": null,
"std": null,
"histogram_counts": [],
"histogram_ticks": []
}
],
"original_dataset_sampled": false,
"original_dataset_path": "",
"original_dataset_size": 0,
"original_dataset_shape": [
10000,
25
]
}
Using dataset ENTITY to prepare DIA features: column_names=['ID', 'LIMIT_BAL', 'SEX', 'EDUCATION', 'MARRIAGE', 'AGE', 'PAY_0', 'PAY_2', 'PAY_3', 'PAY_4', 'PAY_5', 'PAY_6', 'BILL_AMT1', 'BILL_AMT2', 'BILL_AMT3', 'BILL_AMT4', 'BILL_AMT5', 'BILL_AMT6', 'PAY_AMT1', 'PAY_AMT2', 'PAY_AMT3', 'PAY_AMT4', 'PAY_AMT5', 'PAY_AMT6', 'default payment next month'] column_uniques=[10000, 72, 2, 7, 4, 54, 11, 11, 11, 11, 10, 10, 8371, 8215, 8072, 7913, 7764, 7550, 3763, 3581, 3305, 3247, 3258, 3174, 2]
DIA group columns prepared using dataset ENTITY: {'default payment next month', 'PAY_3', 'PAY_4', 'PAY_5', 'PAY_0', 'EDUCATION', 'PAY_2', 'PAY_6', 'MARRIAGE', 'SEX'}
DIA group columns to SKIP: {'default payment next month', 'model_pred'}
DIA group columns as BOOLs: [<h2o_sonar.methods.fairness._dia.BoolEntry object at 0x7fe547ed4d90>, <h2o_sonar.methods.fairness._dia.BoolEntry object at 0x7fe547ed5710>, <h2o_sonar.methods.fairness._dia.BoolEntry object at 0x7fe547ed50d0>, <h2o_sonar.methods.fairness._dia.BoolEntry object at 0x7fe547ed62d0>, <h2o_sonar.methods.fairness._dia.BoolEntry object at 0x7fe547ed7c90>, <h2o_sonar.methods.fairness._dia.BoolEntry object at 0x7fe547ed7e90>, <h2o_sonar.methods.fairness._dia.BoolEntry object at 0x7fe547ed4f50>, <h2o_sonar.methods.fairness._dia.BoolEntry object at 0x7fe547ed7750>, <h2o_sonar.methods.fairness._dia.BoolEntry object at 0x7fe547ed56d0>]
X does not have valid feature names, but GradientBoostingClassifier was fitted with feature names
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
Checking whether there is an H2O instance running at http://localhost:54331..... not found.
Attempting to start a local H2O server...
Java Version: openjdk version "10" 2018-03-20; OpenJDK Runtime Environment 18.3 (build 10+44); OpenJDK 64-Bit Server VM 18.3 (build 10+44, mixed mode)
Starting server from /home/user/h/mli/git/h2o-sonar-FLOSS/.venv/lib/python3.11/site-packages/h2o/backend/bin/h2o.jar
Ice root: /tmp/tmpua22_k7b
JVM stdout: /tmp/tmpua22_k7b/h2o_user_started_from_python.out
JVM stderr: /tmp/tmpua22_k7b/h2o_user_started_from_python.err
Server is running at http://127.0.0.1:54331
successful.o H2O server at http://127.0.0.1:54331 ...
| H2O_cluster_uptime: | 01 secs |
| H2O_cluster_timezone: | Europe/Prague |
| H2O_data_parsing_timezone: | UTC |
| H2O_cluster_version: | 3.46.0.9 |
| H2O_cluster_version_age: | 2 months and 4 days |
| H2O_cluster_name: | H2O_from_python_user_5cihsm |
| H2O_cluster_total_nodes: | 1 |
| H2O_cluster_free_memory: | 4 Gb |
| H2O_cluster_total_cores: | 16 |
| H2O_cluster_allowed_cores: | 16 |
| H2O_cluster_status: | locked, healthy |
| H2O_connection_url: | http://127.0.0.1:54331 |
| H2O_connection_proxy: | {"http": null, "https": null} |
| H2O_internal_security: | False |
| Python_version: | 3.11.11 final |
Connecting to H2O server at http://localhost:54331 ... successful.
| H2O_cluster_uptime: | 01 secs |
| H2O_cluster_timezone: | Europe/Prague |
| H2O_data_parsing_timezone: | UTC |
| H2O_cluster_version: | 3.46.0.9 |
| H2O_cluster_version_age: | 2 months and 4 days |
| H2O_cluster_name: | H2O_from_python_user_5cihsm |
| H2O_cluster_total_nodes: | 1 |
| H2O_cluster_free_memory: | 4 Gb |
| H2O_cluster_total_cores: | 16 |
| H2O_cluster_allowed_cores: | 16 |
| H2O_cluster_status: | locked, healthy |
| H2O_connection_url: | http://localhost:54331 |
| H2O_connection_proxy: | {"http": null, "https": null} |
| H2O_internal_security: | False |
| Python_version: | 3.11.11 final |
Connecting to H2O server at http://localhost:54331 ... successful.
X does not have valid feature names, but GradientBoostingClassifier was fitted with feature names
| H2O_cluster_uptime: | 01 secs |
| H2O_cluster_timezone: | Europe/Prague |
| H2O_data_parsing_timezone: | UTC |
| H2O_cluster_version: | 3.46.0.9 |
| H2O_cluster_version_age: | 2 months and 4 days |
| H2O_cluster_name: | H2O_from_python_user_5cihsm |
| H2O_cluster_total_nodes: | 1 |
| H2O_cluster_free_memory: | 4 Gb |
| H2O_cluster_total_cores: | 16 |
| H2O_cluster_allowed_cores: | 16 |
| H2O_cluster_status: | locked, healthy |
| H2O_connection_url: | http://localhost:54331 |
| H2O_connection_proxy: | {"http": null, "https": null} |
| H2O_internal_security: | False |
| Python_version: | 3.11.11 final |
Parse progress: |████████████████████████████████████████████████████████████████| (done) 100%
Parse progress: |████████████████████████████████████████████████████████████████| (done) 100%
drf Model Build progress: |██████████████████████████████████████████████████████| (done) 100%
Parse progress: |████████████████████████████████████████████████████████████████| (done) 100%
Converting H2O frame to pandas dataframe using single-thread. For faster conversion using multi-thread, install polars and pyarrow and use it as pandas_df = h2o_df.as_data_frame(use_multi_thread=True)
Connecting to H2O server at http://localhost:54331 ... successful.
X does not have valid feature names, but GradientBoostingClassifier was fitted with feature names
| H2O_cluster_uptime: | 06 secs |
| H2O_cluster_timezone: | Europe/Prague |
| H2O_data_parsing_timezone: | UTC |
| H2O_cluster_version: | 3.46.0.9 |
| H2O_cluster_version_age: | 2 months and 4 days |
| H2O_cluster_name: | H2O_from_python_user_5cihsm |
| H2O_cluster_total_nodes: | 1 |
| H2O_cluster_free_memory: | 4 Gb |
| H2O_cluster_total_cores: | 16 |
| H2O_cluster_allowed_cores: | 16 |
| H2O_cluster_status: | locked, healthy |
| H2O_connection_url: | http://localhost:54331 |
| H2O_connection_proxy: | {"http": null, "https": null} |
| H2O_internal_security: | False |
| Python_version: | 3.11.11 final |
Parse progress: |████████████████████████████████████████████████████████████████| (done) 100%
████████████████████████████████████████████████████████████████| (done) 100%
drf Model Build progress: |
We have detected that your response column has only 2 unique values (0/1). If you wish to train a binary model instead of a regression model, convert your target column to categorical before training.
██████████████████████████████████████████████████████| (done) 100%
████████████████████████████████████████████████████████████████| (done) 100%
Converting H2O frame to pandas dataframe using single-thread. For faster conversion using multi-thread, install polars and pyarrow and use it as pandas_df = h2o_df.as_data_frame(use_multi_thread=True)
More than 20 figures have been opened. Figures created through the pyplot interface (`matplotlib.pyplot.figure`) are retained until explicitly closed and may consume too much memory. (To control this warning, see the rcParam `figure.max_open_warning`). Consider using `matplotlib.pyplot.close()`.
X does not have valid feature names, but GradientBoostingClassifier was fitted with feature names
X does not have valid feature names, but GradientBoostingClassifier was fitted with feature names
X does not have valid feature names, but GradientBoostingClassifier was fitted with feature names
X does not have valid feature names, but GradientBoostingClassifier was fitted with feature names
X does not have valid feature names, but GradientBoostingClassifier was fitted with feature names
X does not have valid feature names, but GradientBoostingClassifier was fitted with feature names
X does not have valid feature names, but GradientBoostingClassifier was fitted with feature names
X does not have valid feature names, but GradientBoostingClassifier was fitted with feature names
X does not have valid feature names, but GradientBoostingClassifier was fitted with feature names
X does not have valid feature names, but GradientBoostingClassifier was fitted with feature names
X does not have valid feature names, but GradientBoostingClassifier was fitted with feature names
[6]:
# open interpretation HTML report in web browser
webbrowser.open(interpretation.result.get_html_report_location())
[6]:
True
[7]:
# View results directory
!tree {interpretation.persistence.base_dir}
../../results/h2o-sonar/mli_experiment_fa511a22-4241-43e3-bd85-73e500a0d5b5
├── explainer_h2o_sonar_explainers_dia_explainer_DiaExplainer_6b5044a8-eb62-4d01-a8e4-62be3c496484
│ ├── global_disparate_impact_analysis
│ │ ├── text_plain
│ │ │ └── explanation.txt
│ │ └── text_plain.meta
│ ├── global_html_fragment
│ │ ├── text_html
│ │ │ ├── dia-0-accuracy.png
│ │ │ ├── dia-0-adverse_impact.png
│ │ │ ├── dia-0-false_discovery_rate.png
│ │ │ ├── dia-0-false_negative_rate.png
│ │ │ ├── dia-0-false_omissions_rate.png
│ │ │ ├── dia-0-false_positive_rate.png
│ │ │ ├── dia-0-negative_predicted_value.png
│ │ │ ├── dia-0-n.png
│ │ │ ├── dia-0-precision.png
│ │ │ ├── dia-0-specificity.png
│ │ │ ├── dia-0-true_positive_rate.png
│ │ │ ├── dia-1-accuracy.png
│ │ │ ├── dia-1-adverse_impact.png
│ │ │ ├── dia-1-false_discovery_rate.png
│ │ │ ├── dia-1-false_negative_rate.png
│ │ │ ├── dia-1-false_omissions_rate.png
│ │ │ ├── dia-1-false_positive_rate.png
│ │ │ ├── dia-1-negative_predicted_value.png
│ │ │ ├── dia-1-n.png
│ │ │ ├── dia-1-precision.png
│ │ │ ├── dia-1-specificity.png
│ │ │ ├── dia-1-true_positive_rate.png
│ │ │ ├── dia-2-accuracy.png
│ │ │ ├── dia-2-adverse_impact.png
│ │ │ ├── dia-2-false_discovery_rate.png
│ │ │ ├── dia-2-false_negative_rate.png
│ │ │ ├── dia-2-false_omissions_rate.png
│ │ │ ├── dia-2-false_positive_rate.png
│ │ │ ├── dia-2-negative_predicted_value.png
│ │ │ ├── dia-2-n.png
│ │ │ ├── dia-2-precision.png
│ │ │ ├── dia-2-specificity.png
│ │ │ ├── dia-2-true_positive_rate.png
│ │ │ ├── dia-3-accuracy.png
│ │ │ ├── dia-3-adverse_impact.png
│ │ │ ├── dia-3-false_discovery_rate.png
│ │ │ ├── dia-3-false_negative_rate.png
│ │ │ ├── dia-3-false_omissions_rate.png
│ │ │ ├── dia-3-false_positive_rate.png
│ │ │ ├── dia-3-negative_predicted_value.png
│ │ │ ├── dia-3-n.png
│ │ │ ├── dia-3-precision.png
│ │ │ ├── dia-3-specificity.png
│ │ │ ├── dia-3-true_positive_rate.png
│ │ │ ├── dia-4-accuracy.png
│ │ │ ├── dia-4-adverse_impact.png
│ │ │ ├── dia-4-false_discovery_rate.png
│ │ │ ├── dia-4-false_negative_rate.png
│ │ │ ├── dia-4-false_omissions_rate.png
│ │ │ ├── dia-4-false_positive_rate.png
│ │ │ ├── dia-4-negative_predicted_value.png
│ │ │ ├── dia-4-n.png
│ │ │ ├── dia-4-precision.png
│ │ │ ├── dia-4-specificity.png
│ │ │ ├── dia-4-true_positive_rate.png
│ │ │ ├── dia-5-accuracy.png
│ │ │ ├── dia-5-adverse_impact.png
│ │ │ ├── dia-5-false_discovery_rate.png
│ │ │ ├── dia-5-false_negative_rate.png
│ │ │ ├── dia-5-false_omissions_rate.png
│ │ │ ├── dia-5-false_positive_rate.png
│ │ │ ├── dia-5-negative_predicted_value.png
│ │ │ ├── dia-5-n.png
│ │ │ ├── dia-5-precision.png
│ │ │ ├── dia-5-specificity.png
│ │ │ ├── dia-5-true_positive_rate.png
│ │ │ ├── dia-6-accuracy.png
│ │ │ ├── dia-6-adverse_impact.png
│ │ │ ├── dia-6-false_discovery_rate.png
│ │ │ ├── dia-6-false_negative_rate.png
│ │ │ ├── dia-6-false_omissions_rate.png
│ │ │ ├── dia-6-false_positive_rate.png
│ │ │ ├── dia-6-negative_predicted_value.png
│ │ │ ├── dia-6-n.png
│ │ │ ├── dia-6-precision.png
│ │ │ ├── dia-6-specificity.png
│ │ │ ├── dia-6-true_positive_rate.png
│ │ │ ├── dia-7-accuracy.png
│ │ │ ├── dia-7-adverse_impact.png
│ │ │ ├── dia-7-false_discovery_rate.png
│ │ │ ├── dia-7-false_negative_rate.png
│ │ │ ├── dia-7-false_omissions_rate.png
│ │ │ ├── dia-7-false_positive_rate.png
│ │ │ ├── dia-7-negative_predicted_value.png
│ │ │ ├── dia-7-n.png
│ │ │ ├── dia-7-precision.png
│ │ │ ├── dia-7-specificity.png
│ │ │ ├── dia-7-true_positive_rate.png
│ │ │ ├── dia-8-accuracy.png
│ │ │ ├── dia-8-adverse_impact.png
│ │ │ ├── dia-8-false_discovery_rate.png
│ │ │ ├── dia-8-false_negative_rate.png
│ │ │ ├── dia-8-false_omissions_rate.png
│ │ │ ├── dia-8-false_positive_rate.png
│ │ │ ├── dia-8-negative_predicted_value.png
│ │ │ ├── dia-8-n.png
│ │ │ ├── dia-8-precision.png
│ │ │ ├── dia-8-specificity.png
│ │ │ ├── dia-8-true_positive_rate.png
│ │ │ └── explanation.html
│ │ └── text_html.meta
│ ├── insights
│ │ └── insights_and_actions.json
│ ├── log
│ │ └── explainer_run_6b5044a8-eb62-4d01-a8e4-62be3c496484.log
│ ├── problems
│ │ └── problems_and_actions.json
│ ├── result_descriptor.json
│ └── work
│ ├── dia_entity.json
│ ├── EDUCATION
│ │ ├── 0
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 1
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 2
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 3
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 4
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 5
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 6
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ └── metrics.jay
│ ├── MARRIAGE
│ │ ├── 0
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 1
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 2
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 3
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ └── metrics.jay
│ ├── PAY_0
│ │ ├── 0
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 1
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 10
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 2
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 3
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 4
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 5
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 6
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 7
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 8
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 9
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ └── metrics.jay
│ ├── PAY_2
│ │ ├── 0
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 1
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 10
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 2
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 3
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 4
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 5
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 6
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 7
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 8
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 9
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ └── metrics.jay
│ ├── PAY_3
│ │ ├── 0
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 1
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 10
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 2
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 3
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 4
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 5
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 6
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 7
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 8
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 9
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ └── metrics.jay
│ ├── PAY_4
│ │ ├── 0
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 1
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 10
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 2
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 3
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 4
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 5
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 6
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 7
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 8
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 9
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ └── metrics.jay
│ ├── PAY_5
│ │ ├── 0
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 1
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 2
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 3
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 4
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 5
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 6
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 7
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 8
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 9
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ └── metrics.jay
│ ├── PAY_6
│ │ ├── 0
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 1
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 2
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 3
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 4
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 5
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 6
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 7
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 8
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ ├── 9
│ │ │ ├── cm.jay
│ │ │ ├── disparity.jay
│ │ │ ├── me_smd.jay
│ │ │ └── parity.jay
│ │ └── metrics.jay
│ └── SEX
│ ├── 0
│ │ ├── cm.jay
│ │ ├── disparity.jay
│ │ ├── me_smd.jay
│ │ └── parity.jay
│ ├── 1
│ │ ├── cm.jay
│ │ ├── disparity.jay
│ │ ├── me_smd.jay
│ │ └── parity.jay
│ └── metrics.jay
├── explainer_h2o_sonar_explainers_dt_surrogate_explainer_DecisionTreeSurrogateExplainer_609ea6cb-da74-4c1b-9bd5-1b99a04f6689
│ ├── global_custom_archive
│ │ ├── application_zip
│ │ │ └── explanation.zip
│ │ └── application_zip.meta
│ ├── global_decision_tree
│ │ ├── application_json
│ │ │ ├── dt_class_0.json
│ │ │ └── explanation.json
│ │ └── application_json.meta
│ ├── global_html_fragment
│ │ ├── text_html
│ │ │ ├── dt-class-0.png
│ │ │ └── explanation.html
│ │ └── text_html.meta
│ ├── insights
│ │ └── insights_and_actions.json
│ ├── local_decision_tree
│ │ ├── application_json
│ │ │ └── explanation.json
│ │ └── application_json.meta
│ ├── log
│ │ └── explainer_run_609ea6cb-da74-4c1b-9bd5-1b99a04f6689.log
│ ├── problems
│ │ └── problems_and_actions.json
│ ├── result_descriptor.json
│ └── work
│ ├── dt-class-0.dot
│ ├── dt-class-0.dot.pdf
│ ├── dtModel.json
│ ├── dtpaths_frame.bin
│ ├── dtPathsFrame.csv
│ ├── dtsurr_mojo.zip
│ ├── dtSurrogate.json
│ └── dt_surrogate_rules.zip
├── explainer_h2o_sonar_explainers_pd_ice_explainer_PdIceExplainer_1751a878-a456-48b9-bcbc-22b482b905ca
│ ├── global_html_fragment
│ │ ├── text_html
│ │ │ ├── explanation.html
│ │ │ ├── pd-feature-0-class-0.png
│ │ │ ├── pd-feature-1-class-0.png
│ │ │ ├── pd-feature-2-class-0.png
│ │ │ ├── pd-feature-3-class-0.png
│ │ │ ├── pd-feature-4-class-0.png
│ │ │ ├── pd-feature-5-class-0.png
│ │ │ ├── pd-feature-6-class-0.png
│ │ │ ├── pd-feature-7-class-0.png
│ │ │ ├── pd-feature-8-class-0.png
│ │ │ └── pd-feature-9-class-0.png
│ │ └── text_html.meta
│ ├── global_partial_dependence
│ │ ├── application_json
│ │ │ ├── explanation.json
│ │ │ ├── pd_feature_0_class_0.json
│ │ │ ├── pd_feature_1_class_0.json
│ │ │ ├── pd_feature_2_class_0.json
│ │ │ ├── pd_feature_3_class_0.json
│ │ │ ├── pd_feature_4_class_0.json
│ │ │ ├── pd_feature_5_class_0.json
│ │ │ ├── pd_feature_6_class_0.json
│ │ │ ├── pd_feature_7_class_0.json
│ │ │ ├── pd_feature_8_class_0.json
│ │ │ └── pd_feature_9_class_0.json
│ │ └── application_json.meta
│ ├── insights
│ │ └── insights_and_actions.json
│ ├── local_individual_conditional_explanation
│ │ ├── application_vnd_h2oai_json_datatable_jay
│ │ │ ├── explanation.json
│ │ │ ├── ice_feature_0_class_0.jay
│ │ │ ├── ice_feature_1_class_0.jay
│ │ │ ├── ice_feature_2_class_0.jay
│ │ │ ├── ice_feature_3_class_0.jay
│ │ │ ├── ice_feature_4_class_0.jay
│ │ │ ├── ice_feature_5_class_0.jay
│ │ │ ├── ice_feature_6_class_0.jay
│ │ │ ├── ice_feature_7_class_0.jay
│ │ │ ├── ice_feature_8_class_0.jay
│ │ │ ├── ice_feature_9_class_0.jay
│ │ │ └── y_hat.jay
│ │ └── application_vnd_h2oai_json_datatable_jay.meta
│ ├── log
│ │ └── explainer_run_1751a878-a456-48b9-bcbc-22b482b905ca.log
│ ├── problems
│ │ └── problems_and_actions.json
│ ├── result_descriptor.json
│ └── work
│ ├── h2o_sonar-ice-dai-model-10.jay
│ ├── h2o_sonar-ice-dai-model-1.jay
│ ├── h2o_sonar-ice-dai-model-2.jay
│ ├── h2o_sonar-ice-dai-model-3.jay
│ ├── h2o_sonar-ice-dai-model-4.jay
│ ├── h2o_sonar-ice-dai-model-5.jay
│ ├── h2o_sonar-ice-dai-model-6.jay
│ ├── h2o_sonar-ice-dai-model-7.jay
│ ├── h2o_sonar-ice-dai-model-8.jay
│ ├── h2o_sonar-ice-dai-model-9.jay
│ ├── h2o_sonar-ice-dai-model.json
│ ├── h2o_sonar-pd-dai-model.json
│ └── mli_dataset_y_hat.jay
├── explainer_h2o_sonar_explainers_residual_dt_surrogate_explainer_ResidualDecisionTreeSurrogateExplainer_512a55cc-8ada-4afb-bd60-9ad805fdaea7
│ ├── global_custom_archive
│ │ ├── application_zip
│ │ │ └── explanation.zip
│ │ └── application_zip.meta
│ ├── global_decision_tree
│ │ ├── application_json
│ │ │ ├── dt_class_0.json
│ │ │ └── explanation.json
│ │ └── application_json.meta
│ ├── global_html_fragment
│ │ ├── text_html
│ │ │ ├── dt-class-0.png
│ │ │ └── explanation.html
│ │ └── text_html.meta
│ ├── insights
│ │ └── insights_and_actions.json
│ ├── local_decision_tree
│ │ ├── application_json
│ │ │ └── explanation.json
│ │ └── application_json.meta
│ ├── log
│ │ └── explainer_run_512a55cc-8ada-4afb-bd60-9ad805fdaea7.log
│ ├── problems
│ │ └── problems_and_actions.json
│ ├── result_descriptor.json
│ └── work
│ ├── dt-class-0.dot
│ ├── dt-class-0.dot.pdf
│ ├── dtModel.json
│ ├── dtpaths_frame.bin
│ ├── dtPathsFrame.csv
│ ├── dtsurr_mojo.zip
│ ├── dtSurrogate.json
│ └── dt_surrogate_rules.zip
├── explainer_h2o_sonar_explainers_summary_shap_explainer_SummaryShapleyExplainer_88a80df6-343b-4e88-b261-4d5cafcfdddc
│ ├── global_html_fragment
│ │ ├── text_html
│ │ │ ├── explanation.html
│ │ │ ├── feature_0_class_0.png
│ │ │ ├── feature_10_class_0.png
│ │ │ ├── feature_11_class_0.png
│ │ │ ├── feature_12_class_0.png
│ │ │ ├── feature_13_class_0.png
│ │ │ ├── feature_14_class_0.png
│ │ │ ├── feature_15_class_0.png
│ │ │ ├── feature_16_class_0.png
│ │ │ ├── feature_17_class_0.png
│ │ │ ├── feature_18_class_0.png
│ │ │ ├── feature_19_class_0.png
│ │ │ ├── feature_1_class_0.png
│ │ │ ├── feature_20_class_0.png
│ │ │ ├── feature_21_class_0.png
│ │ │ ├── feature_22_class_0.png
│ │ │ ├── feature_23_class_0.png
│ │ │ ├── feature_2_class_0.png
│ │ │ ├── feature_3_class_0.png
│ │ │ ├── feature_4_class_0.png
│ │ │ ├── feature_5_class_0.png
│ │ │ ├── feature_6_class_0.png
│ │ │ ├── feature_7_class_0.png
│ │ │ ├── feature_8_class_0.png
│ │ │ ├── feature_9_class_0.png
│ │ │ └── shapley-class-0.png
│ │ └── text_html.meta
│ ├── global_summary_feature_importance
│ │ ├── application_json
│ │ │ ├── explanation.json
│ │ │ ├── feature_0_class_0.png
│ │ │ ├── feature_10_class_0.png
│ │ │ ├── feature_11_class_0.png
│ │ │ ├── feature_12_class_0.png
│ │ │ ├── feature_13_class_0.png
│ │ │ ├── feature_14_class_0.png
│ │ │ ├── feature_15_class_0.png
│ │ │ ├── feature_16_class_0.png
│ │ │ ├── feature_17_class_0.png
│ │ │ ├── feature_18_class_0.png
│ │ │ ├── feature_19_class_0.png
│ │ │ ├── feature_1_class_0.png
│ │ │ ├── feature_20_class_0.png
│ │ │ ├── feature_21_class_0.png
│ │ │ ├── feature_22_class_0.png
│ │ │ ├── feature_23_class_0.png
│ │ │ ├── feature_2_class_0.png
│ │ │ ├── feature_3_class_0.png
│ │ │ ├── feature_4_class_0.png
│ │ │ ├── feature_5_class_0.png
│ │ │ ├── feature_6_class_0.png
│ │ │ ├── feature_7_class_0.png
│ │ │ ├── feature_8_class_0.png
│ │ │ ├── feature_9_class_0.png
│ │ │ ├── summary_feature_importance_class_0_offset_0.json
│ │ │ ├── summary_feature_importance_class_0_offset_1.json
│ │ │ └── summary_feature_importance_class_0_offset_2.json
│ │ ├── application_json.meta
│ │ ├── application_vnd_h2oai_json_datatable_jay
│ │ │ ├── explanation.json
│ │ │ └── summary_feature_importance_class_0.jay
│ │ ├── application_vnd_h2oai_json_datatable_jay.meta
│ │ ├── text_markdown
│ │ │ ├── explanation.md
│ │ │ └── shapley-class-0.png
│ │ └── text_markdown.meta
│ ├── insights
│ │ └── insights_and_actions.json
│ ├── log
│ │ └── explainer_run_88a80df6-343b-4e88-b261-4d5cafcfdddc.log
│ ├── problems
│ │ └── problems_and_actions.json
│ ├── result_descriptor.json
│ └── work
│ ├── raw_shapley_contribs_class_0.jay
│ ├── raw_shapley_contribs_index.json
│ ├── report.md
│ └── shapley-class-0.png
├── interpretation.html
├── interpretation.json
└── tmp
144 directories, 595 files
[8]:
# Check for successful explainers
interpretation.get_successful_explainer_ids()
[8]:
['h2o_sonar.explainers.dia_explainer.DiaExplainer',
'h2o_sonar.explainers.residual_dt_surrogate_explainer.ResidualDecisionTreeSurrogateExplainer',
'h2o_sonar.explainers.dt_surrogate_explainer.DecisionTreeSurrogateExplainer',
'h2o_sonar.explainers.summary_shap_explainer.SummaryShapleyExplainer',
'h2o_sonar.explainers.pd_ice_explainer.PdIceExplainer']
[9]:
# Check for any failures
interpretation.get_failed_explainer_ids()
[9]:
[]
[10]:
# View params passed into Interpretation job
interpretation.common_params.dump()
[10]:
{'model': GradientBoostingClassifier(),
'models': None,
'dataset': '../../data/predictive/creditcard.csv',
'validset': None,
'testset': None,
'use_raw_features': True,
'target_col': 'default payment next month',
'weight_col': '',
'prediction_col': '',
'drop_cols': [],
'sample_num_rows': 0,
'results_location': '../../results',
'extra_params': None,
'used_features': ['ID',
'LIMIT_BAL',
'SEX',
'EDUCATION',
'MARRIAGE',
'AGE',
'PAY_0',
'PAY_2',
'PAY_3',
'PAY_4',
'PAY_5',
'PAY_6',
'BILL_AMT1',
'BILL_AMT2',
'BILL_AMT3',
'BILL_AMT4',
'BILL_AMT5',
'BILL_AMT6',
'PAY_AMT1',
'PAY_AMT2',
'PAY_AMT3',
'PAY_AMT4',
'PAY_AMT5',
'PAY_AMT6'],
'cfg_items_dict': {'model': <h2o_sonar.lib.api.commons.Param at 0x7fe68e04d290>,
'models': <h2o_sonar.lib.api.commons.Param at 0x7fe68e10bd50>,
'dataset': <h2o_sonar.lib.api.commons.Param at 0x7fe68e04d310>,
'target_col': <h2o_sonar.lib.api.commons.Param at 0x7fe68e04da90>,
'validset': <h2o_sonar.lib.api.commons.Param at 0x7fe68e04db10>,
'testset': <h2o_sonar.lib.api.commons.Param at 0x7fe68e04db50>,
'use_raw_features': <h2o_sonar.lib.api.commons.Param at 0x7fe68e04db90>,
'weight_col': <h2o_sonar.lib.api.commons.Param at 0x7fe68e04dbd0>,
'prediction_col': <h2o_sonar.lib.api.commons.Param at 0x7fe68e04dc10>,
'drop_cols': <h2o_sonar.lib.api.commons.Param at 0x7fe68e04dc50>,
'sample_num_rows': <h2o_sonar.lib.api.commons.Param at 0x7fe68e04dc90>,
'results_location': <h2o_sonar.lib.api.commons.Param at 0x7fe68e04dcd0>,
'used_features': <h2o_sonar.lib.api.commons.Param at 0x7fe68e04dd10>}}
[ ]: