diff --git a/auto_ts/__version__.py b/auto_ts/__version__.py index d92ddbf..ae43aea 100644 --- a/auto_ts/__version__.py +++ b/auto_ts/__version__.py @@ -5,6 +5,6 @@ __author__ = "Ram Seshadri" __description__ = "Build time series models for any data set, any size. Now using dask." __url__ = "https://github.com/Auto_ViML/Auto_TS.git" -__version__ = "0.0.82" +__version__ = "0.0.90" __license__ = "Apache License 2.0" __copyright__ = "2020-22 Google" diff --git a/auto_ts/utils/eda.py b/auto_ts/utils/eda.py index 3c80679..3fd707c 100644 --- a/auto_ts/utils/eda.py +++ b/auto_ts/utils/eda.py @@ -2,6 +2,8 @@ import numpy as np # type: ignore import pandas as pd # type: ignore import seaborn as sns # type: ignore +from itertools import cycle +import matplotlib.pyplot as plt # This gives an error when running from a python script. # Maybe, this should be set in the jupyter notebook directly. diff --git a/auto_ts/utils/etl.py b/auto_ts/utils/etl.py index f566909..cc0548d 100644 --- a/auto_ts/utils/etl.py +++ b/auto_ts/utils/etl.py @@ -11,7 +11,7 @@ import numpy as np import pandas as pd # type: ignore from sklearn.model_selection import TimeSeriesSplit # type: ignore - +import pdb ##### This function loads a time series data and sets the index as a time series def load_ts_data(filename, ts_column, sep, target, dask_xgboost_flag=0): diff --git a/setup.py b/setup.py index aa7f475..e14f040 100644 --- a/setup.py +++ b/setup.py @@ -26,10 +26,11 @@ "prophet", "scikit-learn>=0.24.0", "statsmodels", - "xgboost>=1.5.1", + "xgboost>=2.0", "prettytable", "dask>=2022.1.0", "pyyaml>=5.4.1", + "GPUtil>=1.4.0", "distributed>=2022.2.0", ], classifiers=[ diff --git a/updates.md b/updates.md index 7f77a56..0aaa252 100644 --- a/updates.md +++ b/updates.md @@ -1,5 +1,8 @@
We have now added `XGBoost with GPU` support to Auto_TS. Auto_TS will automatically detect if there is a GPU in your Kaggle kernel or your local machine and will run XGBoost with GPU support. Hope this speeds up your computations!. +
We have now added `Google Cloud Run` support to Auto_TS. You can simply use the instructions in this page to deploy Auto_TS models on Google Cloud Run. Many thanks to abdulrahman305 for providing a Pull Request to add this functionality to Auto_TS.