Skip to content

A programming framework for agentic AI

support latest xgboost version (#599)

Chi Wangc45741a67b0a
diff --git a/.github/workflows/python-package.yml b/.github/workflows/python-package.yml
index 19f3a3f40..8b1b2ce6a 100644
--- a/.github/workflows/python-package.yml
+++ b/.github/workflows/python-package.yml
@@ -16,7 +16,7 @@ jobs:
strategy:
matrix:
os: [ubuntu-latest, macos-latest, windows-2019]
- python-version: ["3.6", "3.7", "3.8", "3.9", "3.10"]
+ python-version: ["3.7", "3.8", "3.9", "3.10"]
steps:
- uses: actions/checkout@v2
diff --git a/README.md b/README.md
index f8397286f..5149e23d0 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,7 @@
[![PyPI version](https://badge.fury.io/py/FLAML.svg)](https://badge.fury.io/py/FLAML)
![Conda version](https://img.shields.io/conda/vn/conda-forge/flaml)
[![Build](https://github.com/microsoft/FLAML/actions/workflows/python-package.yml/badge.svg)](https://github.com/microsoft/FLAML/actions/workflows/python-package.yml)
-![Python Version](https://img.shields.io/badge/3.6%20%7C%203.7%20%7C%203.8%20%7C%203.9%20%7C%203.10-blue)
+![Python Version](https://img.shields.io/badge/3.7%20%7C%203.8%20%7C%203.9%20%7C%203.10-blue)
[![Downloads](https://pepy.tech/badge/flaml)](https://pepy.tech/project/flaml)
[![Join the chat at https://gitter.im/FLAMLer/community](https://badges.gitter.im/FLAMLer/community.svg)](https://gitter.im/FLAMLer/community?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
@@ -27,7 +27,7 @@ FLAML has a .NET implementation as well from [ML.NET Model Builder](https://dotn
## Installation
-FLAML requires **Python version >= 3.6**. It can be installed from pip:
+FLAML requires **Python version >= 3.7**. It can be installed from pip:
```bash
pip install flaml
diff --git a/flaml/ml.py b/flaml/ml.py
index 8e5e2df6d..75d67f4be 100644
--- a/flaml/ml.py
+++ b/flaml/ml.py
@@ -1,5 +1,5 @@
# !
-# * Copyright (c) Microsoft Corporation. All rights reserved.
+# * Copyright (c) FLAML authors. All rights reserved.
# * Licensed under the MIT License. See LICENSE file in the
# * project root for license information.
import time
@@ -39,7 +39,7 @@ from .model import (
TransformersEstimator,
TransformersEstimatorModelSelection,
)
-from .data import CLASSIFICATION, group_counts, TS_FORECAST, TS_VALUE_COL
+from .data import CLASSIFICATION, group_counts, TS_FORECAST
import logging
logger = logging.getLogger(__name__)
diff --git a/flaml/model.py b/flaml/model.py
index 0bf7669db..f73187898 100644
--- a/flaml/model.py
+++ b/flaml/model.py
@@ -155,7 +155,8 @@ class BaseEstimator:
X_train = self._preprocess(X_train)
model = self.estimator_class(**self.params)
if logger.level == logging.DEBUG:
- logger.debug(f"flaml.model - {model} fit started")
+ # xgboost 1.6 doesn't display all the params in the model str
+ logger.debug(f"flaml.model - {model} fit started with params {self.params}")
model.fit(X_train, y_train, **kwargs)
if logger.level == logging.DEBUG:
logger.debug(f"flaml.model - {model} fit finished")
@@ -1111,12 +1112,23 @@ class LGBMEstimator(BaseEstimator):
kwargs.pop("callbacks")
else:
callbacks = self._callbacks(start_time, deadline)
+ if isinstance(self, XGBoostSklearnEstimator):
+ from xgboost import __version__
+
+ if __version__ >= "1.6.0":
+ # since xgboost>=1.6.0, callbacks can't be passed in fit()
+ self.params["callbacks"] = callbacks
+ callbacks = None
self._fit(
X_train,
y_train,
callbacks=callbacks,
**kwargs,
)
+ if callbacks is None:
+ # for xgboost>=1.6.0, pop callbacks to enable pickle
+ callbacks = self.params.pop("callbacks")
+ self._model.set_params(callbacks=callbacks[:-1])
best_iteration = (
self._model.get_booster().best_iteration
if isinstance(self, XGBoostSklearnEstimator)
@@ -1233,7 +1245,9 @@ class XGBoostEstimator(SKLearnEstimator):
start_time = time.time()
deadline = start_time + budget if budget else np.inf
if issparse(X_train):
- self.params["tree_method"] = "auto"
+ if xgb.__version__ < "1.6.0":
+ # "auto" fails for sparse input since xgboost 1.6.0
+ self.params["tree_method"] = "auto"
else:
X_train = self._preprocess(X_train)
if "sample_weight" in kwargs:
@@ -1337,9 +1351,11 @@ class XGBoostSklearnEstimator(SKLearnEstimator, LGBMEstimator):
self.estimator_class = xgb.XGBRanker
elif task in CLASSIFICATION:
self.estimator_class = xgb.XGBClassifier
+ self._xgb_version = xgb.__version__
def fit(self, X_train, y_train, budget=None, **kwargs):
- if issparse(X_train):
+ if issparse(X_train) and self._xgb_version < "1.6.0":
+ # "auto" fails for sparse input since xgboost 1.6.0
self.params["tree_method"] = "auto"
if kwargs.get("gpu_per_trial"):
self.params["tree_method"] = "gpu_hist"
diff --git a/flaml/version.py b/flaml/version.py
index 9e604c040..e13bd590c 100644
--- a/flaml/version.py
+++ b/flaml/version.py
@@ -1 +1 @@
-__version__ = "1.0.7"
+__version__ = "1.0.8"
diff --git a/notebook/automl_classification.ipynb b/notebook/automl_classification.ipynb
index bd7eb89c9..fc145cf67 100644
--- a/notebook/automl_classification.ipynb
+++ b/notebook/automl_classification.ipynb
@@ -26,7 +26,7 @@
"\n",
"In this notebook, we use one real data example (binary classification) to showcase how to use FLAML library.\n",
"\n",
- "FLAML requires `Python>=3.6`. To run this notebook example, please install flaml with the `notebook` option:\n",
+ "FLAML requires `Python>=3.7`. To run this notebook example, please install flaml with the `notebook` option:\n",
"```bash\n",
"pip install flaml[notebook]\n",
"```"
diff --git a/notebook/automl_lightgbm.ipynb b/notebook/automl_lightgbm.ipynb
index 29ab0c9f3..c043a6778 100644
--- a/notebook/automl_lightgbm.ipynb
+++ b/notebook/automl_lightgbm.ipynb
@@ -27,7 +27,7 @@
"\n",
"In this notebook, we demonstrate how to use FLAML library to tune hyperparameters of LightGBM with a regression example.\n",
"\n",
- "FLAML requires `Python>=3.6`. To run this notebook example, please install flaml with the `notebook` option:\n",
+ "FLAML requires `Python>=3.7`. To run this notebook example, please install flaml with the `notebook` option:\n",
"```bash\n",
"pip install flaml[notebook]\n",
"```"
diff --git a/notebook/automl_nlp.ipynb b/notebook/automl_nlp.ipynb
index 19aef0565..0076de3ce 100644
--- a/notebook/automl_nlp.ipynb
+++ b/notebook/automl_nlp.ipynb
@@ -26,7 +26,7 @@
"\n",
"In this notebook, we demonstrate how to use the FLAML library to fine tune an NLP language model with hyperparameter search. We have tested this notebook on a server with 4 NVidia V100 GPU (32GB) and 400GB CPU Ram.\n",
"\n",
- "FLAML requires `Python>=3.6`. To run this notebook example, please install flaml with the `nlp,ray,notebook` and `blendsearch` option:\n",
+ "FLAML requires `Python>=3.7`. To run this notebook example, please install flaml with the `nlp,ray,notebook` and `blendsearch` option:\n",
"```bash\n",
"pip install flaml[nlp,ray,notebook,blendsearch];\n",
"```"
diff --git a/notebook/automl_time_series_forecast.ipynb b/notebook/automl_time_series_forecast.ipynb
index ccb9bc2c3..81ba9e536 100644
--- a/notebook/automl_time_series_forecast.ipynb
+++ b/notebook/automl_time_series_forecast.ipynb
@@ -21,7 +21,7 @@
"\n",
"In this notebook, we demonstrate how to use FLAML library for time series forecasting tasks: univariate time series forecasting (only time), multivariate time series forecasting (with exogneous variables) and forecasting discrete values.\n",
"\n",
- "FLAML requires Python>=3.6. To run this notebook example, please install flaml with the notebook and forecast option:\n"
+ "FLAML requires Python>=3.7. To run this notebook example, please install flaml with the notebook and forecast option:\n"
]
},
{
diff --git a/notebook/automl_xgboost.ipynb b/notebook/automl_xgboost.ipynb
index 7cabe86bc..8e6697de7 100644
--- a/notebook/automl_xgboost.ipynb
+++ b/notebook/automl_xgboost.ipynb
@@ -27,7 +27,7 @@
"\n",
"In this notebook, we demonstrate how to use FLAML library to tune hyperparameters of XGBoost with a regression example.\n",
"\n",
- "FLAML requires `Python>=3.6`. To run this notebook example, please install flaml with the `notebook` option:\n",
+ "FLAML requires `Python>=3.7`. To run this notebook example, please install flaml with the `notebook` option:\n",
"```bash\n",
"pip install flaml[notebook]\n",
"```"
diff --git a/notebook/autovw.ipynb b/notebook/autovw.ipynb
index 43f359c1e..5ee95d9d4 100644
--- a/notebook/autovw.ipynb
+++ b/notebook/autovw.ipynb
@@ -8,7 +8,7 @@
}
},
"source": [
- "Copyright (c) 2020-2021 Microsoft Corporation. All rights reserved. \n",
+ "Copyright (c) Microsoft Corporation. All rights reserved. \n",
"\n",
"Licensed under the MIT License.\n",
"\n",
@@ -22,7 +22,7 @@
"\n",
"*ChaCha for online AutoML. Qingyun Wu, Chi Wang, John Langford, Paul Mineiro and Marco Rossi. To appear in ICML 2021.*\n",
"\n",
- "AutoVW is implemented in FLAML. FLAML requires `Python>=3.6`. To run this notebook example, please install:"
+ "AutoVW is implemented in FLAML. FLAML requires `Python>=3.7`. To run this notebook example, please install:"
]
},
{
diff --git a/notebook/integrate_azureml.ipynb b/notebook/integrate_azureml.ipynb
index 938fbb8d2..da4bcafe5 100644
--- a/notebook/integrate_azureml.ipynb
+++ b/notebook/integrate_azureml.ipynb
@@ -8,7 +8,7 @@
}
},
"source": [
- "Copyright (c) 2020-2021 Microsoft Corporation. All rights reserved. \n",
+ "Copyright (c) Microsoft Corporation. All rights reserved. \n",
"\n",
"Licensed under the MIT License.\n",
"\n",
@@ -27,7 +27,7 @@
"\n",
"In this notebook, we use one real data example (binary classification) to showcase how to use FLAML library together with AzureML.\n",
"\n",
- "FLAML requires `Python>=3.6`. To run this notebook example, please install flaml with the [azureml] option:\n",
+ "FLAML requires `Python>=3.7`. To run this notebook example, please install flaml with the [azureml] option:\n",
"```bash\n",
"pip install flaml[azureml]\n",
"```"
diff --git a/notebook/integrate_sklearn.ipynb b/notebook/integrate_sklearn.ipynb
index 0d85bb083..4f0e0b98f 100644
--- a/notebook/integrate_sklearn.ipynb
+++ b/notebook/integrate_sklearn.ipynb
@@ -39,7 +39,7 @@
"\n",
"In this notebook, we use one real data example (binary classification) to showcase how to use FLAML library.\n",
"\n",
- "FLAML requires `Python>=3.6`. To run this notebook example, please install flaml with the `notebook` option:\n",
+ "FLAML requires `Python>=3.7`. To run this notebook example, please install flaml with the `notebook` option:\n",
"```bash\n",
"pip install flaml[notebook]\n",
"```"
diff --git a/notebook/research/acl2021.ipynb b/notebook/research/acl2021.ipynb
index d8ad5b94a..d1374eba5 100644
--- a/notebook/research/acl2021.ipynb
+++ b/notebook/research/acl2021.ipynb
@@ -4,7 +4,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "Copyright (c) 2020-2021. All rights reserved.\n",
+ "Copyright (c). All rights reserved.\n",
"\n",
"Licensed under the MIT License.\n",
"\n",
@@ -22,7 +22,7 @@
"\n",
"*Running this notebook takes about one hour.\n",
"\n",
- "FLAML requires `Python>=3.6`. To run this notebook example, please install flaml with the `notebook` and `nlp` options:\n",
+ "FLAML requires `Python>=3.7`. To run this notebook example, please install flaml with the `notebook` and `nlp` options:\n",
"\n",
"```bash\n",
"pip install flaml[nlp]==0.7.1 # in higher version of flaml, the API for nlp tasks changed\n",
@@ -364,10 +364,10 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "\u001B[2m\u001B[36m(pid=50964)\u001B[0m {'eval_loss': 0.5942569971084595, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.10434782608695652}\n",
- "\u001B[2m\u001B[36m(pid=50964)\u001B[0m {'eval_loss': 0.5942569971084595, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.10434782608695652}\n",
- "\u001B[2m\u001B[36m(pid=50948)\u001B[0m {'eval_loss': 0.649192214012146, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.2}\n",
- "\u001B[2m\u001B[36m(pid=50948)\u001B[0m {'eval_loss': 0.649192214012146, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.2}\n"
+ "\u001b[2m\u001b[36m(pid=50964)\u001b[0m {'eval_loss': 0.5942569971084595, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.10434782608695652}\n",
+ "\u001b[2m\u001b[36m(pid=50964)\u001b[0m {'eval_loss': 0.5942569971084595, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.10434782608695652}\n",
+ "\u001b[2m\u001b[36m(pid=50948)\u001b[0m {'eval_loss': 0.649192214012146, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.2}\n",
+ "\u001b[2m\u001b[36m(pid=50948)\u001b[0m {'eval_loss': 0.649192214012146, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.2}\n"
]
},
{
@@ -485,12 +485,12 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "\u001B[2m\u001B[36m(pid=54411)\u001B[0m {'eval_loss': 0.624100387096405, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.5}\n",
- "\u001B[2m\u001B[36m(pid=54411)\u001B[0m {'eval_loss': 0.624100387096405, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.5}\n",
- "\u001B[2m\u001B[36m(pid=54411)\u001B[0m {'eval_loss': 0.624100387096405, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.5}\n",
- "\u001B[2m\u001B[36m(pid=54417)\u001B[0m {'eval_loss': 0.5938675999641418, 'eval_accuracy': 0.7156862745098039, 'eval_f1': 0.8258258258258258, 'epoch': 0.5}\n",
- "\u001B[2m\u001B[36m(pid=54417)\u001B[0m {'eval_loss': 0.5938675999641418, 'eval_accuracy': 0.7156862745098039, 'eval_f1': 0.8258258258258258, 'epoch': 0.5}\n",
- "\u001B[2m\u001B[36m(pid=54417)\u001B[0m {'eval_loss': 0.5938675999641418, 'eval_accuracy': 0.7156862745098039, 'eval_f1': 0.8258258258258258, 'epoch': 0.5}\n"
+ "\u001b[2m\u001b[36m(pid=54411)\u001b[0m {'eval_loss': 0.624100387096405, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.5}\n",
+ "\u001b[2m\u001b[36m(pid=54411)\u001b[0m {'eval_loss': 0.624100387096405, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.5}\n",
+ "\u001b[2m\u001b[36m(pid=54411)\u001b[0m {'eval_loss': 0.624100387096405, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.5}\n",
+ "\u001b[2m\u001b[36m(pid=54417)\u001b[0m {'eval_loss': 0.5938675999641418, 'eval_accuracy': 0.7156862745098039, 'eval_f1': 0.8258258258258258, 'epoch': 0.5}\n",
+ "\u001b[2m\u001b[36m(pid=54417)\u001b[0m {'eval_loss': 0.5938675999641418, 'eval_accuracy': 0.7156862745098039, 'eval_f1': 0.8258258258258258, 'epoch': 0.5}\n",
+ "\u001b[2m\u001b[36m(pid=54417)\u001b[0m {'eval_loss': 0.5938675999641418, 'eval_accuracy': 0.7156862745098039, 'eval_f1': 0.8258258258258258, 'epoch': 0.5}\n"
]
},
{
@@ -590,18 +590,18 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "\u001B[2m\u001B[36m(pid=57835)\u001B[0m {'eval_loss': 0.5822290778160095, 'eval_accuracy': 0.7058823529411765, 'eval_f1': 0.8181818181818181, 'epoch': 0.5043478260869565}\n",
- "\u001B[2m\u001B[36m(pid=57835)\u001B[0m {'eval_loss': 0.5822290778160095, 'eval_accuracy': 0.7058823529411765, 'eval_f1': 0.8181818181818181, 'epoch': 0.5043478260869565}\n",
- "\u001B[2m\u001B[36m(pid=57835)\u001B[0m {'eval_loss': 0.5822290778160095, 'eval_accuracy': 0.7058823529411765, 'eval_f1': 0.8181818181818181, 'epoch': 0.5043478260869565}\n",
- "\u001B[2m\u001B[36m(pid=57835)\u001B[0m {'eval_loss': 0.5822290778160095, 'eval_accuracy': 0.7058823529411765, 'eval_f1': 0.8181818181818181, 'epoch': 0.5043478260869565}\n",
- "\u001B[2m\u001B[36m(pid=57836)\u001B[0m {'eval_loss': 0.6087244749069214, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.10344827586206896}\n",
- "\u001B[2m\u001B[36m(pid=57836)\u001B[0m {'eval_loss': 0.6087244749069214, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.10344827586206896}\n",
- "\u001B[2m\u001B[36m(pid=57836)\u001B[0m {'eval_loss': 0.6087244749069214, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.10344827586206896}\n",
- "\u001B[2m\u001B[36m(pid=57836)\u001B[0m {'eval_loss': 0.6087244749069214, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.10344827586206896}\n",
- "\u001B[2m\u001B[36m(pid=57839)\u001B[0m {'eval_loss': 0.5486209392547607, 'eval_accuracy': 0.7034313725490197, 'eval_f1': 0.8141321044546851, 'epoch': 0.5}\n",
- "\u001B[2m\u001B[36m(pid=57839)\u001B[0m {'eval_loss': 0.5486209392547607, 'eval_accuracy': 0.7034313725490197, 'eval_f1': 0.8141321044546851, 'epoch': 0.5}\n",
- "\u001B[2m\u001B[36m(pid=57839)\u001B[0m {'eval_loss': 0.5486209392547607, 'eval_accuracy': 0.7034313725490197, 'eval_f1': 0.8141321044546851, 'epoch': 0.5}\n",
- "\u001B[2m\u001B[36m(pid=57839)\u001B[0m {'eval_loss': 0.5486209392547607, 'eval_accuracy': 0.7034313725490197, 'eval_f1': 0.8141321044546851, 'epoch': 0.5}\n"
+ "\u001b[2m\u001b[36m(pid=57835)\u001b[0m {'eval_loss': 0.5822290778160095, 'eval_accuracy': 0.7058823529411765, 'eval_f1': 0.8181818181818181, 'epoch': 0.5043478260869565}\n",
+ "\u001b[2m\u001b[36m(pid=57835)\u001b[0m {'eval_loss': 0.5822290778160095, 'eval_accuracy': 0.7058823529411765, 'eval_f1': 0.8181818181818181, 'epoch': 0.5043478260869565}\n",
+ "\u001b[2m\u001b[36m(pid=57835)\u001b[0m {'eval_loss': 0.5822290778160095, 'eval_accuracy': 0.7058823529411765, 'eval_f1': 0.8181818181818181, 'epoch': 0.5043478260869565}\n",
+ "\u001b[2m\u001b[36m(pid=57835)\u001b[0m {'eval_loss': 0.5822290778160095, 'eval_accuracy': 0.7058823529411765, 'eval_f1': 0.8181818181818181, 'epoch': 0.5043478260869565}\n",
+ "\u001b[2m\u001b[36m(pid=57836)\u001b[0m {'eval_loss': 0.6087244749069214, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.10344827586206896}\n",
+ "\u001b[2m\u001b[36m(pid=57836)\u001b[0m {'eval_loss': 0.6087244749069214, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.10344827586206896}\n",
+ "\u001b[2m\u001b[36m(pid=57836)\u001b[0m {'eval_loss': 0.6087244749069214, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.10344827586206896}\n",
+ "\u001b[2m\u001b[36m(pid=57836)\u001b[0m {'eval_loss': 0.6087244749069214, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.10344827586206896}\n",
+ "\u001b[2m\u001b[36m(pid=57839)\u001b[0m {'eval_loss': 0.5486209392547607, 'eval_accuracy': 0.7034313725490197, 'eval_f1': 0.8141321044546851, 'epoch': 0.5}\n",
+ "\u001b[2m\u001b[36m(pid=57839)\u001b[0m {'eval_loss': 0.5486209392547607, 'eval_accuracy': 0.7034313725490197, 'eval_f1': 0.8141321044546851, 'epoch': 0.5}\n",
+ "\u001b[2m\u001b[36m(pid=57839)\u001b[0m {'eval_loss': 0.5486209392547607, 'eval_accuracy': 0.7034313725490197, 'eval_f1': 0.8141321044546851, 'epoch': 0.5}\n",
+ "\u001b[2m\u001b[36m(pid=57839)\u001b[0m {'eval_loss': 0.5486209392547607, 'eval_accuracy': 0.7034313725490197, 'eval_f1': 0.8141321044546851, 'epoch': 0.5}\n"
]
},
{
@@ -701,21 +701,21 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "\u001B[2m\u001B[36m(pid=61251)\u001B[0m {'eval_loss': 0.6236899495124817, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.5}\n",
- "\u001B[2m\u001B[36m(pid=61251)\u001B[0m {'eval_loss': 0.6236899495124817, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.5}\n",
- "\u001B[2m\u001B[36m(pid=61251)\u001B[0m {'eval_loss': 0.6236899495124817, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.5}\n",
- "\u001B[2m\u001B[36m(pid=61251)\u001B[0m {'eval_loss': 0.6236899495124817, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.5}\n",
- "\u001B[2m\u001B[36m(pid=61251)\u001B[0m {'eval_loss': 0.6236899495124817, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.5}\n",
- "\u001B[2m\u001B[36m(pid=61255)\u001B[0m {'eval_loss': 0.6249027848243713, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.3}\n",
- "\u001B[2m\u001B[36m(pid=61255)\u001B[0m {'eval_loss': 0.6249027848243713, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.3}\n",
- "\u001B[2m\u001B[36m(pid=61255)\u001B[0m {'eval_loss': 0.6249027848243713, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.3}\n",
- "\u001B[2m\u001B[36m(pid=61255)\u001B[0m {'eval_loss': 0.6249027848243713, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.3}\n",
- "\u001B[2m\u001B[36m(pid=61255)\u001B[0m {'eval_loss': 0.6249027848243713, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.3}\n",
- "\u001B[2m\u001B[36m(pid=61236)\u001B[0m {'eval_loss': 0.6138392686843872, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.20689655172413793}\n",
- "\u001B[2m\u001B[36m(pid=61236)\u001B[0m {'eval_loss': 0.6138392686843872, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.20689655172413793}\n",
- "\u001B[2m\u001B[36m(pid=61236)\u001B[0m {'eval_loss': 0.6138392686843872, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.20689655172413793}\n",
- "\u001B[2m\u001B[36m(pid=61236)\u001B[0m {'eval_loss': 0.6138392686843872, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.20689655172413793}\n",
- "\u001B[2m\u001B[36m(pid=61236)\u001B[0m {'eval_loss': 0.6138392686843872, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.20689655172413793}\n"
+ "\u001b[2m\u001b[36m(pid=61251)\u001b[0m {'eval_loss': 0.6236899495124817, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.5}\n",
+ "\u001b[2m\u001b[36m(pid=61251)\u001b[0m {'eval_loss': 0.6236899495124817, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.5}\n",
+ "\u001b[2m\u001b[36m(pid=61251)\u001b[0m {'eval_loss': 0.6236899495124817, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.5}\n",
+ "\u001b[2m\u001b[36m(pid=61251)\u001b[0m {'eval_loss': 0.6236899495124817, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.5}\n",
+ "\u001b[2m\u001b[36m(pid=61251)\u001b[0m {'eval_loss': 0.6236899495124817, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.5}\n",
+ "\u001b[2m\u001b[36m(pid=61255)\u001b[0m {'eval_loss': 0.6249027848243713, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.3}\n",
+ "\u001b[2m\u001b[36m(pid=61255)\u001b[0m {'eval_loss': 0.6249027848243713, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.3}\n",
+ "\u001b[2m\u001b[36m(pid=61255)\u001b[0m {'eval_loss': 0.6249027848243713, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.3}\n",
+ "\u001b[2m\u001b[36m(pid=61255)\u001b[0m {'eval_loss': 0.6249027848243713, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.3}\n",
+ "\u001b[2m\u001b[36m(pid=61255)\u001b[0m {'eval_loss': 0.6249027848243713, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.3}\n",
+ "\u001b[2m\u001b[36m(pid=61236)\u001b[0m {'eval_loss': 0.6138392686843872, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.20689655172413793}\n",
+ "\u001b[2m\u001b[36m(pid=61236)\u001b[0m {'eval_loss': 0.6138392686843872, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.20689655172413793}\n",
+ "\u001b[2m\u001b[36m(pid=61236)\u001b[0m {'eval_loss': 0.6138392686843872, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.20689655172413793}\n",
+ "\u001b[2m\u001b[36m(pid=61236)\u001b[0m {'eval_loss': 0.6138392686843872, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.20689655172413793}\n",
+ "\u001b[2m\u001b[36m(pid=61236)\u001b[0m {'eval_loss': 0.6138392686843872, 'eval_accuracy': 0.6838235294117647, 'eval_f1': 0.8122270742358079, 'epoch': 0.20689655172413793}\n"
]
},
{
@@ -806,4 +806,4 @@
},
"nbformat": 4,
"nbformat_minor": 1
-}
\ No newline at end of file
+}
diff --git a/notebook/zeroshot_lightgbm.ipynb b/notebook/zeroshot_lightgbm.ipynb
index 783f03700..c5cb63783 100644
--- a/notebook/zeroshot_lightgbm.ipynb
+++ b/notebook/zeroshot_lightgbm.ipynb
@@ -19,7 +19,7 @@
"\n",
"In this notebook, we demonstrate a basic use case of zero-shot AutoML with FLAML.\n",
"\n",
- "FLAML requires `Python>=3.6`. To run this notebook example, please install flaml and openml:"
+ "FLAML requires `Python>=3.7`. To run this notebook example, please install flaml and openml:"
]
},
{
diff --git a/setup.py b/setup.py
index 0a1ee4371..de126ca07 100644
--- a/setup.py
+++ b/setup.py
@@ -16,7 +16,7 @@ __version__ = version["__version__"]
install_requires = [
"NumPy>=1.17.0rc1",
"lightgbm>=2.3.1",
- "xgboost>=0.90,<=1.3.3",
+ "xgboost>=0.90",
"scipy>=1.4.1",
"pandas>=1.1.4",
"scikit-learn>=0.24",
@@ -110,5 +110,5 @@ setuptools.setup(
"License :: OSI Approved :: MIT License",
"Operating System :: OS Independent",
],
- python_requires=">=3.6",
+ python_requires=">=3.7",
)
diff --git a/test/automl/test_classification.py b/test/automl/test_classification.py
index 6eac50a57..e7b5e6345 100644
--- a/test/automl/test_classification.py
+++ b/test/automl/test_classification.py
@@ -87,10 +87,10 @@ class TestClassification(unittest.TestCase):
automl = AutoML()
automl_settings = {
- "time_budget": 6,
+ "time_budget": 3,
"task": "classification",
"n_jobs": 1,
- "estimator_list": ["catboost", "lrl2"],
+ "estimator_list": ["xgboost", "catboost", "kneighbor"],
"eval_method": "cv",
"n_splits": 3,
"metric": "accuracy",
@@ -99,43 +99,46 @@ class TestClassification(unittest.TestCase):
"ensemble": True,
}
automl.fit(X, y, **automl_settings)
+ del automl
automl = AutoML()
- try:
- import ray
-
- n_concurrent_trials = 2
- except ImportError:
- n_concurrent_trials = 1
automl_settings = {
- "time_budget": 2,
+ "time_budget": 6,
"task": "classification",
"n_jobs": 1,
- "estimator_list": ["lrl2", "kneighbor"],
+ "estimator_list": ["catboost", "lrl2"],
"eval_method": "cv",
"n_splits": 3,
"metric": "accuracy",
"log_training_metric": True,
- "verbose": 4,
+ # "verbose": 4,
"ensemble": True,
- "n_concurrent_trials": n_concurrent_trials,
}
automl.fit(X, y, **automl_settings)
+ del automl
automl = AutoML()
+ try:
+ import ray
+
+ n_concurrent_trials = 2
+ except ImportError:
+ n_concurrent_trials = 1
automl_settings = {
- "time_budget": 3,
+ "time_budget": 2,
"task": "classification",
"n_jobs": 1,
- "estimator_list": ["xgboost", "catboost", "kneighbor"],
+ "estimator_list": ["lrl2", "kneighbor"],
"eval_method": "cv",
"n_splits": 3,
"metric": "accuracy",
"log_training_metric": True,
- # "verbose": 4,
+ "verbose": 4,
"ensemble": True,
+ "n_concurrent_trials": n_concurrent_trials,
}
automl.fit(X, y, **automl_settings)
+ del automl
automl = AutoML()
automl_settings = {
@@ -151,6 +154,7 @@ class TestClassification(unittest.TestCase):
"ensemble": True,
}
automl.fit(X, y, **automl_settings)
+ del automl
def test_binary(self):
automl_experiment = AutoML()
@@ -208,7 +212,7 @@ class TestClassification(unittest.TestCase):
_ = automl_experiment.predict(fake_df)
def test_sparse_matrix_xgboost(self):
- automl_experiment = AutoML()
+ automl = AutoML()
automl_settings = {
"time_budget": 3,
"metric": "ap",
@@ -223,15 +227,28 @@ class TestClassification(unittest.TestCase):
import xgboost as xgb
callback = xgb.callback.TrainingCallback()
- automl_experiment.fit(
+ automl.fit(
X_train=X_train, y_train=y_train, callbacks=[callback], **automl_settings
)
- print(automl_experiment.predict(X_train))
- print(automl_experiment.model)
- print(automl_experiment.config_history)
- print(automl_experiment.best_model_for_estimator("xgboost"))
- print(automl_experiment.best_iteration)
- print(automl_experiment.best_estimator)
+ print(automl.predict(X_train))
+ print(automl.model)
+ print(automl.config_history)
+ print(automl.best_model_for_estimator("xgboost"))
+ print(automl.best_iteration)
+ print(automl.best_estimator)
+
+ # test an old version of xgboost
+ import subprocess
+ import sys
+
+ subprocess.check_call(
+ [sys.executable, "-m", "pip", "install", "xgboost==1.3.3", "--user"]
+ )
+ automl = AutoML()
+ automl.fit(X_train=X_train, y_train=y_train, **automl_settings)
+ subprocess.check_call(
+ [sys.executable, "-m", "pip", "install", "-U", "xgboost", "--user"]
+ )
def test_ray_classification(self):
X, y = load_breast_cancer(return_X_y=True)
@@ -353,5 +370,5 @@ class TestClassification(unittest.TestCase):
if __name__ == "__main__":
- unittest.main()
test = TestClassification()
+ test.test_preprocess()
diff --git a/test/tune/test_reproducibility.py b/test/tune/test_reproducibility.py
index 8a0b6230a..c0229b8cf 100644
--- a/test/tune/test_reproducibility.py
+++ b/test/tune/test_reproducibility.py
@@ -24,9 +24,7 @@ def _easy_objective(use_raytune, config):
return
-def test_tune(
- smoke_test=True, externally_setup_searcher=False, use_ray=False, use_raytune=False
-):
+def test_tune(externally_setup_searcher=False, use_ray=False, use_raytune=False):
from flaml import tune
from flaml.searcher.blendsearch import BlendSearch
@@ -95,7 +93,7 @@ def test_tune(
metric="mean_loss",
mode="min",
num_samples=10,
- time_budget_s=5,
+ # time_budget_s=5,
use_ray=use_ray,
config=search_space,
)
@@ -107,14 +105,14 @@ def test_tune(
def test_reproducibility():
- best_config_1 = test_tune(smoke_test=True)
- best_config_2 = test_tune(smoke_test=True)
+ best_config_1 = test_tune()
+ best_config_2 = test_tune()
print(best_config_1)
print(best_config_2)
assert best_config_1 == best_config_2, "flaml.tune not reproducible"
- best_config_1 = test_tune(smoke_test=True, externally_setup_searcher=True)
- best_config_2 = test_tune(smoke_test=True, externally_setup_searcher=True)
+ best_config_1 = test_tune(externally_setup_searcher=True)
+ best_config_2 = test_tune(externally_setup_searcher=True)
print(best_config_1)
print(best_config_2)
assert (
diff --git a/website/docs/Installation.md b/website/docs/Installation.md
index bccdadd47..73aad1500 100644
--- a/website/docs/Installation.md
+++ b/website/docs/Installation.md
@@ -1,6 +1,6 @@
# Installation
-FLAML requires **Python version >= 3.6**. It can be installed from pip:
+FLAML requires **Python version >= 3.7**. It can be installed from pip:
```bash
pip install flaml