Skip to content

A programming framework for agentic AI

api doc for chacha (#105)

Chi Wangc26720c2999f
diff --git a/README.md b/README.md
index 593a6a566..094cf7d33 100644
--- a/README.md
+++ b/README.md
@@ -87,7 +87,7 @@ automl_settings = {
X_train, y_train = load_iris(return_X_y=True)
# Train with labeled input data
automl.fit(X_train=X_train, y_train=y_train,
- **automl_settings)
+ **automl_settings)
# Predict
print(automl.predict_proba(X_train))
# Export the best model
@@ -111,7 +111,7 @@ automl_settings = {
X_train, y_train = load_boston(return_X_y=True)
# Train with labeled input data
automl.fit(X_train=X_train, y_train=y_train,
- **automl_settings)
+ **automl_settings)
# Predict
print(automl.predict(X_train))
# Export the best model
@@ -140,7 +140,7 @@ For more technical details, please check our papers.
```
* [Frugal Optimization for Cost-related Hyperparameters](https://arxiv.org/abs/2005.01571). Qingyun Wu, Chi Wang, Silu Huang. AAAI 2021.
* [Economical Hyperparameter Optimization With Blended Search Strategy](https://www.microsoft.com/en-us/research/publication/economical-hyperparameter-optimization-with-blended-search-strategy/). Chi Wang, Qingyun Wu, Silu Huang, Amin Saied. ICLR 2021.
-* ChaCha for online AutoML. Qingyun Wu, Chi Wang, John Langford, Paul Mineiro and Marco Rossi. To appear in ICML 2021.
+* [ChaCha for Online AutoML](https://arxiv.org/pdf/2106.04815.pdf). Qingyun Wu, Chi Wang, John Langford, Paul Mineiro and Marco Rossi. To appear in ICML 2021.
## Contributing
@@ -180,7 +180,7 @@ If all the tests are passed, please also test run notebook/flaml_automl to make
* Chi Wang
* Qingyun Wu
-Contributors (alphabetical order): Sebastien Bubeck, Surajit Chaudhuri, Nadiia Chepurko, Ofer Dekel, Alex Deng, Anshuman Dutt, Nicolo Fusi, Jianfeng Gao, Johannes Gehrke, Silu Huang, Dongwoo Kim, Christian Konig, John Langford, Amin Saied, Neil Tenenholtz, Markus Weimer, Haozhe Zhang, Erkang Zhu.
+Contributors (alphabetical order): Sebastien Bubeck, Surajit Chaudhuri, Nadiia Chepurko, Ofer Dekel, Alex Deng, Anshuman Dutt, Nicolo Fusi, Jianfeng Gao, Johannes Gehrke, Silu Huang, Dongwoo Kim, Christian Konig, John Langford, Xueqing Liu, Paul Mineiro, Amin Saied, Neil Tenenholtz, Olga Vrousgou, Markus Weimer, Haozhe Zhang, Erkang Zhu.
## License
diff --git a/docs/index.rst b/docs/index.rst
index c4ae47a98..5b297675a 100644
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -22,7 +22,7 @@ AutoML
Tune
-------
+----
.. autofunction:: flaml.tune.run
@@ -38,8 +38,15 @@ Tune
:members:
+Online AutoML
+-------------
+
+.. autoclass:: flaml.AutoVW
+ :members:
+
+
NLP
-------
+---
.. autoclass:: flaml.nlp.AutoTransformers
:members:
diff --git a/flaml/model.py b/flaml/model.py
index 8d32f3f38..57fd34ca9 100644
--- a/flaml/model.py
+++ b/flaml/model.py
@@ -171,6 +171,9 @@ class BaseEstimator:
class SKLearnEstimator(BaseEstimator):
+ def __init__(self, task='binary:logistic', **params):
+ super().__init__(task, **params)
+
def _preprocess(self, X):
if isinstance(X, pd.DataFrame):
X = X.copy()
@@ -231,12 +234,7 @@ class LGBMEstimator(BaseEstimator):
n_estimators = int(round(config['n_estimators']))
return (num_leaves * 3 + (num_leaves - 1) * 4 + 1.0) * n_estimators * 8
- def __init__(
- self, task='binary:logistic', n_jobs=1,
- n_estimators=2, num_leaves=2, min_child_samples=20, learning_rate=0.1,
- subsample=1.0, reg_lambda=1.0, reg_alpha=0.0,
- colsample_bytree=1.0, log_max_bin=8, **params
- ):
+ def __init__(self, task='binary:logistic', log_max_bin=8, **params):
super().__init__(task, **params)
# Default: ‘regression’ for LGBMRegressor,
# ‘binary’ or ‘multiclass’ for LGBMClassifier
@@ -248,20 +246,16 @@ class LGBMEstimator(BaseEstimator):
objective = 'multiclass'
else:
objective = 'regression'
- self.params = {
- "n_estimators": int(round(n_estimators)),
- "num_leaves": int(round(num_leaves)),
- 'objective': params.get("objective", objective),
- 'n_jobs': n_jobs,
- 'learning_rate': float(learning_rate),
- 'reg_alpha': float(reg_alpha),
- 'reg_lambda': float(reg_lambda),
- 'min_child_samples': int(round(min_child_samples)),
- 'colsample_bytree': float(colsample_bytree),
- 'subsample': float(subsample),
- }
- self.params['max_bin'] = params['max_bin'] if 'max_bin' in params else (
- 1 << int(round(log_max_bin))) - 1
+ if "n_estimators" in self.params:
+ self.params["n_estimators"] = int(round(self.params["n_estimators"]))
+ if "num_leaves" in self.params:
+ self.params["num_leaves"] = int(round(self.params["num_leaves"]))
+ if "min_child_samples" in self.params:
+ self.params["min_child_samples"] = int(round(self.params["min_child_samples"]))
+ if "objective" not in self.params:
+ self.params["objective"] = objective
+ if "max_bin" not in self.params:
+ self.params['max_bin'] = 1 << int(round(log_max_bin)) - 1
if 'regression' in task:
self.estimator_class = LGBMRegressor
else:
@@ -369,7 +363,7 @@ class XGBoostEstimator(SKLearnEstimator):
):
super().__init__(task, **params)
self._n_estimators = int(round(n_estimators))
- self.params = {
+ self.params.update({
'max_leaves': int(round(max_leaves)),
'max_depth': params.get('max_depth', 0),
'grow_policy': params.get("grow_policy", 'lossguide'),
@@ -385,7 +379,7 @@ class XGBoostEstimator(SKLearnEstimator):
'colsample_bylevel': float(colsample_bylevel),
'colsample_bytree': float(colsample_bytree),
'objective': params.get("objective")
- }
+ })
if all_thread:
del self.params['nthread']
@@ -445,7 +439,8 @@ class XGBoostSklearnEstimator(SKLearnEstimator, LGBMEstimator):
**params
):
super().__init__(task, **params)
- self.params = {
+ self.params = params
+ self.params.update({
"n_estimators": int(round(n_estimators)),
'max_leaves': int(round(max_leaves)),
'max_depth': 0,
@@ -462,7 +457,7 @@ class XGBoostSklearnEstimator(SKLearnEstimator, LGBMEstimator):
'colsample_bylevel': float(colsample_bylevel),
'colsample_bytree': float(colsample_bytree),
'use_label_encoder': params.get('use_label_encoder', False),
- }
+ })
if 'regression' in task:
self.estimator_class = xgb.XGBRegressor
@@ -513,11 +508,12 @@ class RandomForestEstimator(SKLearnEstimator, LGBMEstimator):
n_estimators=4, max_features=1.0, criterion='gini', **params
):
super().__init__(task, **params)
- self.params = {
+ self.params = params
+ self.params.update({
"n_estimators": int(round(n_estimators)),
"n_jobs": n_jobs,
'max_features': float(max_features),
- }
+ })
if 'regression' in task:
self.estimator_class = RandomForestRegressor
else:
@@ -565,13 +561,13 @@ class LRL1Classifier(SKLearnEstimator):
**params
):
super().__init__(task, **params)
- self.params = {
+ self.params.update({
'penalty': params.get("penalty", 'l1'),
'tol': float(tol),
'C': float(C),
'solver': params.get("solver", 'saga'),
'n_jobs': n_jobs,
- }
+ })
if 'regression' in task:
self.estimator_class = None
raise NotImplementedError('LR does not support regression task')
@@ -594,13 +590,13 @@ class LRL2Classifier(SKLearnEstimator):
**params
):
super().__init__(task, **params)
- self.params = {
+ self.params.update({
'penalty': params.get("penalty", 'l2'),
'tol': float(tol),
'C': float(C),
'solver': params.get("solver", 'lbfgs'),
'n_jobs': n_jobs,
- }
+ })
if 'regression' in task:
self.estimator_class = None
raise NotImplementedError('LR does not support regression task')
@@ -648,14 +644,14 @@ class CatBoostEstimator(BaseEstimator):
n_estimators=8192, learning_rate=0.1, early_stopping_rounds=4, **params
):
super().__init__(task, **params)
- self.params = {
+ self.params.update({
"early_stopping_rounds": int(round(early_stopping_rounds)),
"n_estimators": n_estimators,
'learning_rate': learning_rate,
'thread_count': n_jobs,
'verbose': params.get('verbose', False),
'random_seed': params.get("random_seed", 10242048),
- }
+ })
if 'regression' in task:
from catboost import CatBoostRegressor
self.estimator_class = CatBoostRegressor
@@ -759,11 +755,12 @@ class KNeighborsEstimator(BaseEstimator):
self, task='binary:logistic', n_jobs=1, n_neighbors=5, **params
):
super().__init__(task, **params)
- self.params = {
+ self.params = params
+ self.params.update({
'n_neighbors': int(round(n_neighbors)),
'weights': params.get('weights', 'distance'),
'n_jobs': n_jobs,
- }
+ })
if 'regression' in task:
from sklearn.neighbors import KNeighborsRegressor
self.estimator_class = KNeighborsRegressor
diff --git a/flaml/onlineml/README.md b/flaml/onlineml/README.md
index 926721055..4544f8fa6 100644
--- a/flaml/onlineml/README.md
+++ b/flaml/onlineml/README.md
@@ -4,7 +4,15 @@ FLAML includes *ChaCha* which is an automatic hyperparameter tuning solution for
For more technical details about *ChaCha*, please check our paper.
-* ChaCha for online AutoML. Qingyun Wu, Chi Wang, John Langford, Paul Mineiro and Marco Rossi. To appear in ICML 2021.
+* [ChaCha for Online AutoML](https://arxiv.org/pdf/2106.04815.pdf). Qingyun Wu, Chi Wang, John Langford, Paul Mineiro and Marco Rossi. To appear in ICML 2021.
+```
+@inproceedings{wu2021chacha,
+ title={ChaCha for online AutoML},
+ author={Qingyun Wu and Chi Wang and John Langford and Paul Mineiro and Marco Rossi},
+ year={2021},
+ booktitle={ICML},
+}
+```
## `AutoVW`
diff --git a/notebook/flaml_autovw.ipynb b/notebook/flaml_autovw.ipynb
index 843b9157d..508628e93 100644
--- a/notebook/flaml_autovw.ipynb
+++ b/notebook/flaml_autovw.ipynb
@@ -48,7 +48,7 @@
"## 2. Online regression with AutoVW\n",
"### Load data from openml and preprocess\n",
"\n",
- "Download [dataset_sales](https://www.openml.org/d/42183) from OpenML."
+ "Download [NewFuelCar](https://www.openml.org/d/41506) from OpenML."
]
},
{
@@ -412,4 +412,4 @@
},
"nbformat": 4,
"nbformat_minor": 2
-}
+}
\ No newline at end of file
diff --git a/test/test_automl.py b/test/test_automl.py
index 7e3bfdc51..6916ba9ec 100644
--- a/test/test_automl.py
+++ b/test/test_automl.py
@@ -273,7 +273,6 @@ class TestAutoML(unittest.TestCase):
automl_experiment = AutoML()
automl_settings = {
"time_budget": 2,
- "metric": 'mse',
"task": 'regression',
"log_file_name": "test/boston.log",
"log_training_metric": True,
diff --git a/test/test_autovw.py b/test/test_autovw.py
index bc7524e22..3f294535e 100644
--- a/test/test_autovw.py
+++ b/test/test_autovw.py
@@ -5,7 +5,6 @@ import scipy.sparse
import pandas as pd
from sklearn.metrics import mean_squared_error, mean_absolute_error
-import time
import logging
from flaml.tune import loguniform, polynomial_expansion_set
from vowpalwabbit import pyvw
@@ -13,6 +12,7 @@ from flaml import AutoVW
import string
import os
import openml
+
VW_DS_DIR = 'test/data/'
NS_LIST = list(string.ascii_lowercase) + list(string.ascii_uppercase)
logger = logging.getLogger(__name__)