diff options
| author | CoprDistGit <infra@openeuler.org> | 2023-06-08 06:50:07 +0000 |
|---|---|---|
| committer | CoprDistGit <infra@openeuler.org> | 2023-06-08 06:50:07 +0000 |
| commit | bb76852bca3dd7a5c5db408c43edcc118c82dc3d (patch) | |
| tree | 7bd675aa310f1ac7cc1ec6514f6583ed34a74dec | |
| parent | abcb07cb9c2585ab4f3fd3a11930d0befc57ffa1 (diff) | |
automatic import of python-auto-tsopeneuler20.03
| -rw-r--r-- | .gitignore | 1 | ||||
| -rw-r--r-- | python-auto-ts.spec | 437 | ||||
| -rw-r--r-- | sources | 2 |
3 files changed, 249 insertions, 191 deletions
@@ -1 +1,2 @@ /auto_ts-0.0.70.tar.gz +/auto_ts-0.0.71.tar.gz diff --git a/python-auto-ts.spec b/python-auto-ts.spec index 2c55950..4f241ba 100644 --- a/python-auto-ts.spec +++ b/python-auto-ts.spec @@ -1,14 +1,13 @@ %global _empty_manifest_terminate_build 0 Name: python-auto-ts -Version: 0.0.70 +Version: 0.0.71 Release: 1 Summary: Automatically Build Multiple Time Series models fast - now with Facebook Prophet! License: Apache License 2.0 URL: https://github.com/AutoViML/Auto_TS -Source0: https://mirrors.nju.edu.cn/pypi/web/packages/26/05/93284c1b2fe581bc9541a3bebea524712c10957e77afcca8b9258577b79f/auto_ts-0.0.70.tar.gz +Source0: https://mirrors.aliyun.com/pypi/web/packages/a5/79/e4d10cf0975625961f72504de012c0b0eefd20856cd0cddd93a88f2c93a1/auto_ts-0.0.71.tar.gz BuildArch: noarch -Requires: python3-prettytable Requires: python3-dask Requires: python3-distributed Requires: python3-ipython @@ -17,6 +16,7 @@ Requires: python3-matplotlib Requires: python3-numpy Requires: python3-pandas Requires: python3-pmdarima +Requires: python3-prettytable Requires: python3-prophet Requires: python3-pyyaml Requires: python3-scikit-learn @@ -26,17 +26,51 @@ Requires: python3-xgboost Requires: python3-xlrd %description -<!DOCTYPE html> -<html> -<head> -</head> -<body> +<h1 id="auto-ts">Auto_TS: Auto_TimeSeries</h1> +<p style="font-family:verdana">Automatically build multiple Time Series models using a Single Line of Code. Now updated with Dask. + + + +`auto_timeseries` is a complex model building utility for time series data. Since it automates many +Tasks involved in a complex endeavor, it assumes many intelligent defaults. But you can change them. +Auto_Timeseries will rapidly build predictive models based on Statsmodels ARIMA, Seasonal ARIMA, Prophet +and Scikit-Learn ML. It will automatically select the best model which gives best score specified. + +# Table of Contents +<ul> +<li><a href="#Latest">Latest updates</a></li> +<li><a href="#introduction">What is auto_ts</a></li> +<li><a href="#install">How to install auto_ts</a></li> +<li><a href="#usage">Usage</a></li> +<li><a href="#requirements">Requirements</a></li> +<li><a href="#tips">Tips</a></li> +<li><a href="#license">License</a></li> +<li><a href="#copyright">Copyright</a></li> +<li><a href="#disclaimer">Disclaimer</a></li> +</ul> + +## Latest +To know about the latest updates and features added to Auto_TS please go to this [page](updates.md). + +<h2 id="introduction">Introduction</h2> +<p>Auto_TimeSeries enables you to build and select multiple time series models using techniques such as ARIMA, SARIMAX, VAR, decomposable (trend+seasonality+holidays) models, and ensemble machine learning models.</p> +<p>Auto_TimeSeries is an Automated ML library for time series data. Auto_TimeSeries was initially conceived and developed by <a href="https://www.linkedin.com/in/ram-seshadri-nyc-nj/">Ram Seshadri</a> and was significantly expanded in functionality and scope and upgraded to its present status by <a href="https://github.com/ngupta23">Nikhil Gupta</a>.</p> +<p>auto-ts.Auto_TimeSeries is the main function that you will call with your train data. You can then choose what kind of models you want: stats, ml or Prophet based model. You can also tell it to automatically select the best model based on the scoring parameter you want it to be based on. It will return the best model and a dictionary containing predictions for the number of forecast_periods you mentioned (default=2). + +## Install + +``` +pip install auto-ts +``` + +Use `pip3 install auto-ts` if the above doesn’t work - +``` +pip install git+https://github.com/AutoViML/Auto_TS.git +``` -<h1 id="mar-update">March 2023 Update:</h1> -<p style="font-family:verdana">We have now upgraded FB Prophet to the latest version which is simply called prophet. <br> -If you are using Colab or Kaggle kernel and want to install auto_ts, please use the following steps (otherwise error!): +### Installing on Colab +If you are using Colab or Kaggle kernel and want to install auto_ts, please use the following steps (otherwise you will get an error!): ``` !pip install auto-ts --no-deps --ignore-installed @@ -45,46 +79,26 @@ If you are using Colab or Kaggle kernel and want to install auto_ts, please use !pip install pmdarima ``` -<h1 id="aug-update">Aug 2022 Update:</h1> -<p style="font-family:verdana">You can now add FB Prophet arguments directly into Auto_TimeSeries using the kwargs argument. See example below: - - + -<h1 id="auto-ts">Auto_TS: Auto_TimeSeries</h1> -<p style="font-family:verdana">Automatically build multiple Time Series models using a Single Line of Code. Now updated with Dask.</p> -<p>Auto_timeseries is a complex model building utility for time series data. Since it automates many -Tasks involved in a complex endeavor, it assumes many intelligent defaults. But you can change them. -Auto_Timeseries will rapidly build predictive models based on Statsmodels ARIMA, Seasonal ARIMA, Prophet -and Scikit-Learn ML. It will automatically select the best model which gives best score specified. -</p> -<p>New version 0.0.35 onwards has major updates: You can now load your file into Dask dataframes. Just provide the name of your file and if it is too large to fit into a pandas dataframe, Auto_TS will automatically detect and load it into a Dask dataframe. </p> -<p>Also, new since version 0.0.25 is the syntax of Auto_TimeSerie: It is now more like scikit-learn (with fit and predict). You will have to initialize an object and then call fit with your data and then predict again with data. Hope this makes it easier to remember and use.</p> -<h2 id="introduction">Introduction</h2> -<p>Auto_TimeSeries enables you to build and select multiple time series models using techniques such as ARIMA, SARIMAX, VAR, decomposable (trend+seasonality+holidays) models, and ensemble machine learning models.</p> -<p>Auto_TimeSeries is an Automated ML library for time series data. Auto_TimeSeries was initially conceived and developed by <a href="https://www.linkedin.com/in/ram-seshadri-nyc-nj/">Ram Seshadri</a> and was significantly expanded in functionality and scope and upgraded to its present status by <a href="https://github.com/ngupta23">Nikhil Gupta</a>.</p> -<p>auto-ts.Auto_TimeSeries is the main function that you will call with your train data. You can then choose what kind of models you want: stats, ml or Prophet based model. You can also tell it to automatically select the best model based on the scoring parameter you want it to be based on. It will return the best model and a dictionary containing predictions for the number of forecast_periods you mentioned (default=2).</p> -<h2 id="installation-instructions">INSTALLATION INSTRUCTIONS</h2> -<ol> -<li>Use “pip install auto-ts”</li> -<li>Use “pip3 install auto-ts” if the above doesn’t work</li> -<li>pip install git+git://github.com/AutoViML/Auto_TS</li> -</ol> -<h4>Note for Windows Users</h4> +### Installing on Windows <p>Windows users may experience difficulties with the Prophet and pystan dependency installations. Because of this, we recommend installing Prophet using instructions from the <a hreff="https://facebook.github.io/prophet/docs/installation.html"> Prophet documentation page</a> prior to installing auto-ts. For Anaconda users, this can be accomplished via: <ol> <li><p><code> conda install -c conda-forge prophet </code> </p></li> <li><p><code> pip install auto-ts </code> </p></li> </ol> -<h2 id="run">RUN</h2> -<p> First you need to import auto_timeseries from auto_ts library:<br> -<code> +<h2 id="usage">Usage</h2> + +### First you need to import auto_timeseries from auto_ts library:<br> + +``` from auto_ts import auto_timeseries -</code> -</p> -<p> -Second, Initialize an auto_timeseries model object which will hold all your parameters:</p> -<p><code> +``` + +### Second, Initialize an auto_timeseries model object which will hold all your parameters:</p> + +``` model = auto_timeseries( score_type='rmse', time_interval='Month', @@ -92,8 +106,9 @@ model = auto_timeseries( seasonal_period=12, model_type=['Prophet'], verbose=2) -</code></p> -Here are how the input parameters defined:<br> +``` + +#### Here are how the input parameters defined:<br> <ol> <li><b>score_type (default='rmse')</b>: The metric used for scoring the models. Type is string. Currently only the following two types are supported: @@ -152,8 +167,10 @@ Type can be either: [string, list] </li> <li><b>verbose (default=0)</b>: Indicates the verbosity of printing (Default = 0). Type is integer.</li> </ol> -The next step after defining the model object is to fit it with some real data: -<p><code><br> + +### The next step after defining the model object is to fit it with some real data: + +``` model.fit( traindata=train_data, ts_column=ts_column, @@ -161,8 +178,9 @@ model.fit( cv=5, sep="," ) -</code></p> -<br>Here are how the parameters defined: +``` + +Here are how the parameters defined: <ul> <li><b>traindata (required)</b>: It can be either a dataframe or a file. You must give the name of the file along with its data path in case if a file. It also accepts a pandas dataframe in case you already have a dataframe loaded in your notebook.</li> <li><b>ts_column (required)</b>: name of the datetime column in your dataset (it could be a name of column or index number in the columns index)</li> @@ -171,28 +189,29 @@ model.fit( </li> <li><b>sep (default=",")</b>: Sep is the separator in your traindata file. If your separator is ",", "\t", ";", make sure you enter it here. If not, it is ignored.</li> </ul> -The next step after training the model object is to make some predictions with test data:<br> -<p><code><br> + +### The next step after training the model object is to make some predictions with test data:<br> + +``` predictions = model.predict( testdata = can be either a dataframe or an integer standing for the forecast_period, model = 'best' or any other string that stands for the trained model ) -</code></p> +``` + Here are how the parameters are defined. You can choose to send either testdata in the form of a dataframe or send in an integer to decide how many periods you want to forecast. You need only <ul> <li><b>testdata (required)</b>: It can be either a dataframe containing test data or you can use an integer standing for the forecast_period (you want).</li> <li><b>model (optional, default = 'best')</b>: The name of the model you want to use among the many different models you have trained. Remember that the default is the best model. But you can choose any model that you want to forecast with. Type is String.</li> </ul> + <h2 id="requirements">Requirements</h2> -<p>dask</p> -<p>scikit-learn</p> -<p>Prophet</p> -<p>statsmodels</p> -<p>pmdarima</p> -<p>XGBoost</p> -<h1 id="license">License:</h1> +<p>dask, scikit-learn, prophet, statsmodels, pmdarima, XGBoost</p> + +<h2 id="license">License:</h2> <p>Apache License 2.0</p> -<h2 id="recommendations">Recommendations</h2> + +<h2 id="Tips">Tips</h2> <ul> <li>We recommend that you choose a small sample from your data set before attempting to run entire data. and the evaluation metric so it can select the best model. Currently models within “stats” are compared using AIC and BIC. However, models across different types are compared using RMSE. The results of models are shown using RMSE and Normalized RMSE (ratio of RMSE to the standard deviation of actuals).</li> <li>You must clean the data and not have any missing values. Make sure the target variable is numeric, otherwise, it won’t run. If there is more than one target variable in your data set, just specify only one for now, and if you know the time interval that is in your data, you can specify it. Otherwise it auto-ts will try to infer the time interval on its own.</li> @@ -205,12 +224,12 @@ Here are how the parameters are defined. You can choose to send either testdata <li>Optionally, you can give seasonal_period as any integer that measures the seasonality in the data. If not given, seasonal_period is assumed automatically as follows: Months = 12, Days = 30, Weeks = 52, Qtr = 4, Year = 1, Hours = 24, Minutes = 60 and Seconds = 60.</li> <li>If you want to give your own non-seasonal order, please input it as non_seasonal_pdq and for seasonal order, use seasonal_PDQ as the input. Use tuples. For example, seasonal_PDQ = (2,1,2) and non_seasonal_pdq = (0,0,3). It will accept only tuples. The default is None and Auto_Timeseries will automatically search for the best p,d,q (for Non Seasonal) and P, D, Q (for Seasonal) orders by searching for all parameters from 0 to 12 for each value of p,d,q and 0-3 for each P, Q and 0-1 for D.</li> </ul> + <h2 id="disclaimer">DISCLAIMER:</h2> <p>This is not an Officially supported Google project.</p> + <h2 id="copyright">Copyright</h2> <p>© Google</p> -</body> -</html> @@ -222,17 +241,51 @@ BuildRequires: python3-devel BuildRequires: python3-setuptools BuildRequires: python3-pip %description -n python3-auto-ts -<!DOCTYPE html> -<html> -<head> -</head> -<body> +<h1 id="auto-ts">Auto_TS: Auto_TimeSeries</h1> +<p style="font-family:verdana">Automatically build multiple Time Series models using a Single Line of Code. Now updated with Dask. + + + +`auto_timeseries` is a complex model building utility for time series data. Since it automates many +Tasks involved in a complex endeavor, it assumes many intelligent defaults. But you can change them. +Auto_Timeseries will rapidly build predictive models based on Statsmodels ARIMA, Seasonal ARIMA, Prophet +and Scikit-Learn ML. It will automatically select the best model which gives best score specified. - +# Table of Contents +<ul> +<li><a href="#Latest">Latest updates</a></li> +<li><a href="#introduction">What is auto_ts</a></li> +<li><a href="#install">How to install auto_ts</a></li> +<li><a href="#usage">Usage</a></li> +<li><a href="#requirements">Requirements</a></li> +<li><a href="#tips">Tips</a></li> +<li><a href="#license">License</a></li> +<li><a href="#copyright">Copyright</a></li> +<li><a href="#disclaimer">Disclaimer</a></li> +</ul> + +## Latest +To know about the latest updates and features added to Auto_TS please go to this [page](updates.md). + +<h2 id="introduction">Introduction</h2> +<p>Auto_TimeSeries enables you to build and select multiple time series models using techniques such as ARIMA, SARIMAX, VAR, decomposable (trend+seasonality+holidays) models, and ensemble machine learning models.</p> +<p>Auto_TimeSeries is an Automated ML library for time series data. Auto_TimeSeries was initially conceived and developed by <a href="https://www.linkedin.com/in/ram-seshadri-nyc-nj/">Ram Seshadri</a> and was significantly expanded in functionality and scope and upgraded to its present status by <a href="https://github.com/ngupta23">Nikhil Gupta</a>.</p> +<p>auto-ts.Auto_TimeSeries is the main function that you will call with your train data. You can then choose what kind of models you want: stats, ml or Prophet based model. You can also tell it to automatically select the best model based on the scoring parameter you want it to be based on. It will return the best model and a dictionary containing predictions for the number of forecast_periods you mentioned (default=2). + +## Install + +``` +pip install auto-ts +``` -<h1 id="mar-update">March 2023 Update:</h1> -<p style="font-family:verdana">We have now upgraded FB Prophet to the latest version which is simply called prophet. <br> -If you are using Colab or Kaggle kernel and want to install auto_ts, please use the following steps (otherwise error!): +Use `pip3 install auto-ts` if the above doesn’t work + +``` +pip install git+https://github.com/AutoViML/Auto_TS.git +``` + +### Installing on Colab +If you are using Colab or Kaggle kernel and want to install auto_ts, please use the following steps (otherwise you will get an error!): ``` !pip install auto-ts --no-deps --ignore-installed @@ -241,46 +294,26 @@ If you are using Colab or Kaggle kernel and want to install auto_ts, please use !pip install pmdarima ``` -<h1 id="aug-update">Aug 2022 Update:</h1> -<p style="font-family:verdana">You can now add FB Prophet arguments directly into Auto_TimeSeries using the kwargs argument. See example below: - - + -<h1 id="auto-ts">Auto_TS: Auto_TimeSeries</h1> -<p style="font-family:verdana">Automatically build multiple Time Series models using a Single Line of Code. Now updated with Dask.</p> -<p>Auto_timeseries is a complex model building utility for time series data. Since it automates many -Tasks involved in a complex endeavor, it assumes many intelligent defaults. But you can change them. -Auto_Timeseries will rapidly build predictive models based on Statsmodels ARIMA, Seasonal ARIMA, Prophet -and Scikit-Learn ML. It will automatically select the best model which gives best score specified. -</p> -<p>New version 0.0.35 onwards has major updates: You can now load your file into Dask dataframes. Just provide the name of your file and if it is too large to fit into a pandas dataframe, Auto_TS will automatically detect and load it into a Dask dataframe. </p> -<p>Also, new since version 0.0.25 is the syntax of Auto_TimeSerie: It is now more like scikit-learn (with fit and predict). You will have to initialize an object and then call fit with your data and then predict again with data. Hope this makes it easier to remember and use.</p> -<h2 id="introduction">Introduction</h2> -<p>Auto_TimeSeries enables you to build and select multiple time series models using techniques such as ARIMA, SARIMAX, VAR, decomposable (trend+seasonality+holidays) models, and ensemble machine learning models.</p> -<p>Auto_TimeSeries is an Automated ML library for time series data. Auto_TimeSeries was initially conceived and developed by <a href="https://www.linkedin.com/in/ram-seshadri-nyc-nj/">Ram Seshadri</a> and was significantly expanded in functionality and scope and upgraded to its present status by <a href="https://github.com/ngupta23">Nikhil Gupta</a>.</p> -<p>auto-ts.Auto_TimeSeries is the main function that you will call with your train data. You can then choose what kind of models you want: stats, ml or Prophet based model. You can also tell it to automatically select the best model based on the scoring parameter you want it to be based on. It will return the best model and a dictionary containing predictions for the number of forecast_periods you mentioned (default=2).</p> -<h2 id="installation-instructions">INSTALLATION INSTRUCTIONS</h2> -<ol> -<li>Use “pip install auto-ts”</li> -<li>Use “pip3 install auto-ts” if the above doesn’t work</li> -<li>pip install git+git://github.com/AutoViML/Auto_TS</li> -</ol> -<h4>Note for Windows Users</h4> +### Installing on Windows <p>Windows users may experience difficulties with the Prophet and pystan dependency installations. Because of this, we recommend installing Prophet using instructions from the <a hreff="https://facebook.github.io/prophet/docs/installation.html"> Prophet documentation page</a> prior to installing auto-ts. For Anaconda users, this can be accomplished via: <ol> <li><p><code> conda install -c conda-forge prophet </code> </p></li> <li><p><code> pip install auto-ts </code> </p></li> </ol> -<h2 id="run">RUN</h2> -<p> First you need to import auto_timeseries from auto_ts library:<br> -<code> +<h2 id="usage">Usage</h2> + +### First you need to import auto_timeseries from auto_ts library:<br> + +``` from auto_ts import auto_timeseries -</code> -</p> -<p> -Second, Initialize an auto_timeseries model object which will hold all your parameters:</p> -<p><code> +``` + +### Second, Initialize an auto_timeseries model object which will hold all your parameters:</p> + +``` model = auto_timeseries( score_type='rmse', time_interval='Month', @@ -288,8 +321,9 @@ model = auto_timeseries( seasonal_period=12, model_type=['Prophet'], verbose=2) -</code></p> -Here are how the input parameters defined:<br> +``` + +#### Here are how the input parameters defined:<br> <ol> <li><b>score_type (default='rmse')</b>: The metric used for scoring the models. Type is string. Currently only the following two types are supported: @@ -348,8 +382,10 @@ Type can be either: [string, list] </li> <li><b>verbose (default=0)</b>: Indicates the verbosity of printing (Default = 0). Type is integer.</li> </ol> -The next step after defining the model object is to fit it with some real data: -<p><code><br> + +### The next step after defining the model object is to fit it with some real data: + +``` model.fit( traindata=train_data, ts_column=ts_column, @@ -357,8 +393,9 @@ model.fit( cv=5, sep="," ) -</code></p> -<br>Here are how the parameters defined: +``` + +Here are how the parameters defined: <ul> <li><b>traindata (required)</b>: It can be either a dataframe or a file. You must give the name of the file along with its data path in case if a file. It also accepts a pandas dataframe in case you already have a dataframe loaded in your notebook.</li> <li><b>ts_column (required)</b>: name of the datetime column in your dataset (it could be a name of column or index number in the columns index)</li> @@ -367,28 +404,29 @@ model.fit( </li> <li><b>sep (default=",")</b>: Sep is the separator in your traindata file. If your separator is ",", "\t", ";", make sure you enter it here. If not, it is ignored.</li> </ul> -The next step after training the model object is to make some predictions with test data:<br> -<p><code><br> + +### The next step after training the model object is to make some predictions with test data:<br> + +``` predictions = model.predict( testdata = can be either a dataframe or an integer standing for the forecast_period, model = 'best' or any other string that stands for the trained model ) -</code></p> +``` + Here are how the parameters are defined. You can choose to send either testdata in the form of a dataframe or send in an integer to decide how many periods you want to forecast. You need only <ul> <li><b>testdata (required)</b>: It can be either a dataframe containing test data or you can use an integer standing for the forecast_period (you want).</li> <li><b>model (optional, default = 'best')</b>: The name of the model you want to use among the many different models you have trained. Remember that the default is the best model. But you can choose any model that you want to forecast with. Type is String.</li> </ul> + <h2 id="requirements">Requirements</h2> -<p>dask</p> -<p>scikit-learn</p> -<p>Prophet</p> -<p>statsmodels</p> -<p>pmdarima</p> -<p>XGBoost</p> -<h1 id="license">License:</h1> +<p>dask, scikit-learn, prophet, statsmodels, pmdarima, XGBoost</p> + +<h2 id="license">License:</h2> <p>Apache License 2.0</p> -<h2 id="recommendations">Recommendations</h2> + +<h2 id="Tips">Tips</h2> <ul> <li>We recommend that you choose a small sample from your data set before attempting to run entire data. and the evaluation metric so it can select the best model. Currently models within “stats” are compared using AIC and BIC. However, models across different types are compared using RMSE. The results of models are shown using RMSE and Normalized RMSE (ratio of RMSE to the standard deviation of actuals).</li> <li>You must clean the data and not have any missing values. Make sure the target variable is numeric, otherwise, it won’t run. If there is more than one target variable in your data set, just specify only one for now, and if you know the time interval that is in your data, you can specify it. Otherwise it auto-ts will try to infer the time interval on its own.</li> @@ -401,12 +439,12 @@ Here are how the parameters are defined. You can choose to send either testdata <li>Optionally, you can give seasonal_period as any integer that measures the seasonality in the data. If not given, seasonal_period is assumed automatically as follows: Months = 12, Days = 30, Weeks = 52, Qtr = 4, Year = 1, Hours = 24, Minutes = 60 and Seconds = 60.</li> <li>If you want to give your own non-seasonal order, please input it as non_seasonal_pdq and for seasonal order, use seasonal_PDQ as the input. Use tuples. For example, seasonal_PDQ = (2,1,2) and non_seasonal_pdq = (0,0,3). It will accept only tuples. The default is None and Auto_Timeseries will automatically search for the best p,d,q (for Non Seasonal) and P, D, Q (for Seasonal) orders by searching for all parameters from 0 to 12 for each value of p,d,q and 0-3 for each P, Q and 0-1 for D.</li> </ul> + <h2 id="disclaimer">DISCLAIMER:</h2> <p>This is not an Officially supported Google project.</p> + <h2 id="copyright">Copyright</h2> <p>© Google</p> -</body> -</html> @@ -415,17 +453,51 @@ Here are how the parameters are defined. You can choose to send either testdata Summary: Development documents and examples for auto-ts Provides: python3-auto-ts-doc %description help -<!DOCTYPE html> -<html> -<head> -</head> -<body> +<h1 id="auto-ts">Auto_TS: Auto_TimeSeries</h1> +<p style="font-family:verdana">Automatically build multiple Time Series models using a Single Line of Code. Now updated with Dask. - + -<h1 id="mar-update">March 2023 Update:</h1> -<p style="font-family:verdana">We have now upgraded FB Prophet to the latest version which is simply called prophet. <br> -If you are using Colab or Kaggle kernel and want to install auto_ts, please use the following steps (otherwise error!): +`auto_timeseries` is a complex model building utility for time series data. Since it automates many +Tasks involved in a complex endeavor, it assumes many intelligent defaults. But you can change them. +Auto_Timeseries will rapidly build predictive models based on Statsmodels ARIMA, Seasonal ARIMA, Prophet +and Scikit-Learn ML. It will automatically select the best model which gives best score specified. + +# Table of Contents +<ul> +<li><a href="#Latest">Latest updates</a></li> +<li><a href="#introduction">What is auto_ts</a></li> +<li><a href="#install">How to install auto_ts</a></li> +<li><a href="#usage">Usage</a></li> +<li><a href="#requirements">Requirements</a></li> +<li><a href="#tips">Tips</a></li> +<li><a href="#license">License</a></li> +<li><a href="#copyright">Copyright</a></li> +<li><a href="#disclaimer">Disclaimer</a></li> +</ul> + +## Latest +To know about the latest updates and features added to Auto_TS please go to this [page](updates.md). + +<h2 id="introduction">Introduction</h2> +<p>Auto_TimeSeries enables you to build and select multiple time series models using techniques such as ARIMA, SARIMAX, VAR, decomposable (trend+seasonality+holidays) models, and ensemble machine learning models.</p> +<p>Auto_TimeSeries is an Automated ML library for time series data. Auto_TimeSeries was initially conceived and developed by <a href="https://www.linkedin.com/in/ram-seshadri-nyc-nj/">Ram Seshadri</a> and was significantly expanded in functionality and scope and upgraded to its present status by <a href="https://github.com/ngupta23">Nikhil Gupta</a>.</p> +<p>auto-ts.Auto_TimeSeries is the main function that you will call with your train data. You can then choose what kind of models you want: stats, ml or Prophet based model. You can also tell it to automatically select the best model based on the scoring parameter you want it to be based on. It will return the best model and a dictionary containing predictions for the number of forecast_periods you mentioned (default=2). + +## Install + +``` +pip install auto-ts +``` + +Use `pip3 install auto-ts` if the above doesn’t work + +``` +pip install git+https://github.com/AutoViML/Auto_TS.git +``` + +### Installing on Colab +If you are using Colab or Kaggle kernel and want to install auto_ts, please use the following steps (otherwise you will get an error!): ``` !pip install auto-ts --no-deps --ignore-installed @@ -434,46 +506,26 @@ If you are using Colab or Kaggle kernel and want to install auto_ts, please use !pip install pmdarima ``` -<h1 id="aug-update">Aug 2022 Update:</h1> -<p style="font-family:verdana">You can now add FB Prophet arguments directly into Auto_TimeSeries using the kwargs argument. See example below: - - + -<h1 id="auto-ts">Auto_TS: Auto_TimeSeries</h1> -<p style="font-family:verdana">Automatically build multiple Time Series models using a Single Line of Code. Now updated with Dask.</p> -<p>Auto_timeseries is a complex model building utility for time series data. Since it automates many -Tasks involved in a complex endeavor, it assumes many intelligent defaults. But you can change them. -Auto_Timeseries will rapidly build predictive models based on Statsmodels ARIMA, Seasonal ARIMA, Prophet -and Scikit-Learn ML. It will automatically select the best model which gives best score specified. -</p> -<p>New version 0.0.35 onwards has major updates: You can now load your file into Dask dataframes. Just provide the name of your file and if it is too large to fit into a pandas dataframe, Auto_TS will automatically detect and load it into a Dask dataframe. </p> -<p>Also, new since version 0.0.25 is the syntax of Auto_TimeSerie: It is now more like scikit-learn (with fit and predict). You will have to initialize an object and then call fit with your data and then predict again with data. Hope this makes it easier to remember and use.</p> -<h2 id="introduction">Introduction</h2> -<p>Auto_TimeSeries enables you to build and select multiple time series models using techniques such as ARIMA, SARIMAX, VAR, decomposable (trend+seasonality+holidays) models, and ensemble machine learning models.</p> -<p>Auto_TimeSeries is an Automated ML library for time series data. Auto_TimeSeries was initially conceived and developed by <a href="https://www.linkedin.com/in/ram-seshadri-nyc-nj/">Ram Seshadri</a> and was significantly expanded in functionality and scope and upgraded to its present status by <a href="https://github.com/ngupta23">Nikhil Gupta</a>.</p> -<p>auto-ts.Auto_TimeSeries is the main function that you will call with your train data. You can then choose what kind of models you want: stats, ml or Prophet based model. You can also tell it to automatically select the best model based on the scoring parameter you want it to be based on. It will return the best model and a dictionary containing predictions for the number of forecast_periods you mentioned (default=2).</p> -<h2 id="installation-instructions">INSTALLATION INSTRUCTIONS</h2> -<ol> -<li>Use “pip install auto-ts”</li> -<li>Use “pip3 install auto-ts” if the above doesn’t work</li> -<li>pip install git+git://github.com/AutoViML/Auto_TS</li> -</ol> -<h4>Note for Windows Users</h4> +### Installing on Windows <p>Windows users may experience difficulties with the Prophet and pystan dependency installations. Because of this, we recommend installing Prophet using instructions from the <a hreff="https://facebook.github.io/prophet/docs/installation.html"> Prophet documentation page</a> prior to installing auto-ts. For Anaconda users, this can be accomplished via: <ol> <li><p><code> conda install -c conda-forge prophet </code> </p></li> <li><p><code> pip install auto-ts </code> </p></li> </ol> -<h2 id="run">RUN</h2> -<p> First you need to import auto_timeseries from auto_ts library:<br> -<code> +<h2 id="usage">Usage</h2> + +### First you need to import auto_timeseries from auto_ts library:<br> + +``` from auto_ts import auto_timeseries -</code> -</p> -<p> -Second, Initialize an auto_timeseries model object which will hold all your parameters:</p> -<p><code> +``` + +### Second, Initialize an auto_timeseries model object which will hold all your parameters:</p> + +``` model = auto_timeseries( score_type='rmse', time_interval='Month', @@ -481,8 +533,9 @@ model = auto_timeseries( seasonal_period=12, model_type=['Prophet'], verbose=2) -</code></p> -Here are how the input parameters defined:<br> +``` + +#### Here are how the input parameters defined:<br> <ol> <li><b>score_type (default='rmse')</b>: The metric used for scoring the models. Type is string. Currently only the following two types are supported: @@ -541,8 +594,10 @@ Type can be either: [string, list] </li> <li><b>verbose (default=0)</b>: Indicates the verbosity of printing (Default = 0). Type is integer.</li> </ol> -The next step after defining the model object is to fit it with some real data: -<p><code><br> + +### The next step after defining the model object is to fit it with some real data: + +``` model.fit( traindata=train_data, ts_column=ts_column, @@ -550,8 +605,9 @@ model.fit( cv=5, sep="," ) -</code></p> -<br>Here are how the parameters defined: +``` + +Here are how the parameters defined: <ul> <li><b>traindata (required)</b>: It can be either a dataframe or a file. You must give the name of the file along with its data path in case if a file. It also accepts a pandas dataframe in case you already have a dataframe loaded in your notebook.</li> <li><b>ts_column (required)</b>: name of the datetime column in your dataset (it could be a name of column or index number in the columns index)</li> @@ -560,28 +616,29 @@ model.fit( </li> <li><b>sep (default=",")</b>: Sep is the separator in your traindata file. If your separator is ",", "\t", ";", make sure you enter it here. If not, it is ignored.</li> </ul> -The next step after training the model object is to make some predictions with test data:<br> -<p><code><br> + +### The next step after training the model object is to make some predictions with test data:<br> + +``` predictions = model.predict( testdata = can be either a dataframe or an integer standing for the forecast_period, model = 'best' or any other string that stands for the trained model ) -</code></p> +``` + Here are how the parameters are defined. You can choose to send either testdata in the form of a dataframe or send in an integer to decide how many periods you want to forecast. You need only <ul> <li><b>testdata (required)</b>: It can be either a dataframe containing test data or you can use an integer standing for the forecast_period (you want).</li> <li><b>model (optional, default = 'best')</b>: The name of the model you want to use among the many different models you have trained. Remember that the default is the best model. But you can choose any model that you want to forecast with. Type is String.</li> </ul> + <h2 id="requirements">Requirements</h2> -<p>dask</p> -<p>scikit-learn</p> -<p>Prophet</p> -<p>statsmodels</p> -<p>pmdarima</p> -<p>XGBoost</p> -<h1 id="license">License:</h1> +<p>dask, scikit-learn, prophet, statsmodels, pmdarima, XGBoost</p> + +<h2 id="license">License:</h2> <p>Apache License 2.0</p> -<h2 id="recommendations">Recommendations</h2> + +<h2 id="Tips">Tips</h2> <ul> <li>We recommend that you choose a small sample from your data set before attempting to run entire data. and the evaluation metric so it can select the best model. Currently models within “stats” are compared using AIC and BIC. However, models across different types are compared using RMSE. The results of models are shown using RMSE and Normalized RMSE (ratio of RMSE to the standard deviation of actuals).</li> <li>You must clean the data and not have any missing values. Make sure the target variable is numeric, otherwise, it won’t run. If there is more than one target variable in your data set, just specify only one for now, and if you know the time interval that is in your data, you can specify it. Otherwise it auto-ts will try to infer the time interval on its own.</li> @@ -594,18 +651,18 @@ Here are how the parameters are defined. You can choose to send either testdata <li>Optionally, you can give seasonal_period as any integer that measures the seasonality in the data. If not given, seasonal_period is assumed automatically as follows: Months = 12, Days = 30, Weeks = 52, Qtr = 4, Year = 1, Hours = 24, Minutes = 60 and Seconds = 60.</li> <li>If you want to give your own non-seasonal order, please input it as non_seasonal_pdq and for seasonal order, use seasonal_PDQ as the input. Use tuples. For example, seasonal_PDQ = (2,1,2) and non_seasonal_pdq = (0,0,3). It will accept only tuples. The default is None and Auto_Timeseries will automatically search for the best p,d,q (for Non Seasonal) and P, D, Q (for Seasonal) orders by searching for all parameters from 0 to 12 for each value of p,d,q and 0-3 for each P, Q and 0-1 for D.</li> </ul> + <h2 id="disclaimer">DISCLAIMER:</h2> <p>This is not an Officially supported Google project.</p> + <h2 id="copyright">Copyright</h2> <p>© Google</p> -</body> -</html> %prep -%autosetup -n auto-ts-0.0.70 +%autosetup -n auto_ts-0.0.71 %build %py3_build @@ -619,20 +676,20 @@ if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi pushd %{buildroot} if [ -d usr/lib ]; then - find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst + find usr/lib -type f -printf "\"/%h/%f\"\n" >> filelist.lst fi if [ -d usr/lib64 ]; then - find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst + find usr/lib64 -type f -printf "\"/%h/%f\"\n" >> filelist.lst fi if [ -d usr/bin ]; then - find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst + find usr/bin -type f -printf "\"/%h/%f\"\n" >> filelist.lst fi if [ -d usr/sbin ]; then - find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst + find usr/sbin -type f -printf "\"/%h/%f\"\n" >> filelist.lst fi touch doclist.lst if [ -d usr/share/man ]; then - find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst + find usr/share/man -type f -printf "\"/%h/%f.gz\"\n" >> doclist.lst fi popd mv %{buildroot}/filelist.lst . @@ -645,5 +702,5 @@ mv %{buildroot}/doclist.lst . %{_docdir}/* %changelog -* Wed May 10 2023 Python_Bot <Python_Bot@openeuler.org> - 0.0.70-1 +* Thu Jun 08 2023 Python_Bot <Python_Bot@openeuler.org> - 0.0.71-1 - Package Spec generated @@ -1 +1 @@ -9d5711cd1410dbad230f8e324de69e39 auto_ts-0.0.70.tar.gz +e0db8cd05a3da721bc21ccc645859d19 auto_ts-0.0.71.tar.gz |