Shulou(Shulou.com)06/02 Report--

This article mainly introduces "how to use python machine learning tool pyCaret". In daily operation, I believe many people have doubts about how to use python machine learning tool pyCaret. The editor consulted all kinds of materials and sorted out simple and easy-to-use operation methods. I hope it will be helpful to answer the doubts about "how to use python machine learning tool pyCaret". Next, please follow the editor to study!

PyCaret is an open source, low-code Python machine learning library that automates machine learning workflows. It is an end-to-end machine learning and model management tool that can exponentially speed up the lab cycle and improve your productivity. Welcome to collect and learn, like to give likes and support, and provide technical exchange groups at the end of the article.

Compared to other open source machine learning libraries, PyCaret is an alternative low-code library that can be used to replace hundreds of lines of code with just a few lines of code. This makes the speed and efficiency of the experiment increase exponentially. PyCaret is essentially an Python wrapper around multiple machine learning libraries and frameworks, such as scikit-learn, XGBoost, LightGBM, CatBoost, spaCy, Optuna, Hyperopt, Ray, etc.

PyCaret's design and simplicity are inspired by the emerging role of data scientist to perform simple and moderately complex analytical tasks that previously required more technical expertise.

PyCaret time series module

A beta version of PyCaret's new time series module is now available. Adhering to the simplicity of PyCaret, it is consistent with the existing API and has many features. Statistical testing, model training and selection (more than 30 algorithms), model analysis, automatic hyperparameter tuning, experimental recording, cloud deployment, etc., all require only a few lines of code (just like other modules in pycaret). If you want to give it a try, please check the official Quick start notebook.

You can install this library using pip. If you install PyCaret in the same environment, you must create a separate environment for pycaret-ts-alpha due to dependency conflicts.

Pip install pycaret-ts-alpha

The next arrangement is as follows

The workflow in PyCaret's time series module is very simple. It starts with the setup function, where you can define the prediction range fh and the number of collapses. You can also define fold_strategy as expanding or sliding.

After setting up, the famous compare_models function trains and evaluates more than 30 algorithms from ARIMA to XGboost (TBATS, FBProphet, ETS, etc.).

The plot_model function can be used before or after training. When used before training, it collects a large number of time series EDA diagrams using the plotly interface. When used with a model, plot_model handles model residuals and can be used to access model fitting.

Finally, predict_model is used to generate predictions.

Load data import pandas as pdfrom pycaret.datasets import get_datadata = get_data ('pycaret_downloads') data [' Date'] = pd.to_datetime (data ['Date']) data = data.groupby (' Date'). Sum () data = data.asfreq ('D') data.head ()

# plot the datadata.plot ()

This time series is the number of times the PyCaret library is downloaded from pip per day.

Initialization setting # with functional APIfrom pycaret.time_series import * setup (data, fh = 7, fold = 3, session_id = 123) # with new object-oriented APIfrom pycaret.internal.pycaret_experiment import TimeSeriesExperimentexp = TimeSeriesExperiment () exp.setup (data, fh = 7, fold = 3, session_id = 123)

Statistical Test check_stats ()

Exploratory data analysis # functional APIplot_model (plot = 'ts') # object-oriented APIexp.plot_model (plot =' ts')

# cross-validation plotplot_model (plot = 'cv')

# ACF plotplot_model (plot = 'acf')

# Diagnostics plotplot_model (plot = 'diagnostics')

# Decomposition plotplot_model (plot = 'decomp_stl')

Model training and selection # functional APIbest = compare_models () # object-oriented APIbest = exp.compare_models ()

The create_model in the time series module is the same as in other modules.

# create fbprophet modelprophet = create_model ('prophet') print (prophet)

Tune_model is not much different.

Tuned_prophet = tune_model (prophet) print (tuned_prophet)

Plot_model (best, plot = 'forecast')

# forecast in unknown futureplot_model (best, plot = 'forecast', data_kwargs = {' fh': 30})

# in-sample plotplot_model (best, plot = 'insample')

# residuals plotplot_model (best, plot = 'residuals')

# diagnostics plotplot_model (best, plot = 'diagnostics')

Save the model # finalize modelfinal_best = finalize_model (best) # generate predictionspredict_model (final_best, fh = 90)

# save the modelsave_model (final_best, 'my_best_model')

At this point, the study on "how to use the python machine learning tool pyCaret" is over. I hope to be able to solve your doubts. The collocation of theory and practice can better help you learn, go and try it! If you want to continue to learn more related knowledge, please continue to follow the website, the editor will continue to work hard to bring you more practical articles!

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.