Qlik Py Tools Versions Save

Data Science algorithms for Qlik implemented as a Python Server Side Extension (SSE).

8.1

3 years ago

Maintenance Release

qlik-py-tools-8.1.zip

This zip archive only contains the files needed to deploy the SSE. You can get sample Qlik Sense apps from the docs or download the full source code below.

Tips for updating on Windows If you're on PyTools v.8.0, you can simply copy the files from the zip file above under the core folder and overwrite the files at qlik-py-tools\qlik-py-env\core. Then just restart the SSE.

For older releases, you'll need to download the zip file above, extract it and run Qilk-Py-Init as an administrator. Any model's trained previously will need to be re-trained.

Change Log v.8.1

  • Bug fix for calling REST based models from the load script.
  • Docker image v.8.1 released.

Change Log v.8.0

  • Ability to call pre-trained models that provide a REST API from the load script and chart expressions.
  • Removed dependency on skater. Upgraded to scikit-learn 0.23.1 which now provides the capability to calculate feature importances.
  • Updated HDBSCAN to version 0.8.26
  • Updated spaCy to version 2.2.4
  • Docker image v.8.0 released.

Change Log v.7.0

  • Ability to call externally trained scikit-learn and Keras models for predictions.
  • Sample app and documentation added here.
  • Additional sample app for forecasting with scikit-learn using existing capabilities.

Recent Updates

This release adds the capability to use pre-trained scikit-learn, Keras and REST API based models with Qlik. Read more here.

For more information refer to the Usage section.

Capabilities

  • Supervised Machine Learning : Implemented using scikit-learn, the go-to machine learning library for Python. This SSE implements the full machine learning flow from data preparation, model training and evaluation, to making predictions in Qlik.
  • Unsupervised Machine Learning : Also implemented using scikit-learn. This provides capabilities for dimensionality reduction and clustering.
  • Deep Learning : Implemented using Keras and TensorFlow. This SSE implements the full flow of setting up a neural network, training and evaluating it, and using it to make predictions. Deep Learning models can be used for sequence predictions and complex timeseries forecasting.
  • Use of pretrained ML models in Qlik : Pre-trained scikit-learn, Keras and REST API based models can be called from this SSE, allowing predictions to be exposed within the broader analysis and business context of a Qlik app. The implementation also allows for What-if analysis using the models.
  • Named Entity Recognition : Implemented using spaCy, an excellent Natural Language Processing library that comes with pre-trained neural networks. This SSE allows you to use spaCy's models for Named Entity Recognition or retrain them with your data for even better results.
  • Association rules : Implemented using Efficient-Apriori. Association Rules Analysis is a data mining technique to uncover how items are associated to each other. This technique is best known for Market Basket Analysis, but can be used more generally for finding interesting associations between sets of items that occur together, for example, in a transaction, a paragraph, or a diagnosis.
  • Clustering : Implemented using HDBSCAN, a high performance algorithm that is great for exploratory data analysis.
  • Time series forecasting : Implemented using Facebook Prophet, a modern library for easily generating good quality forecasts. Now with the ability to use multiple regressors as input.
  • Seasonality and holiday analysis : Also using Facebook Prophet.
  • Linear correlations : Implemented using Pandas.

For more information refer to the Usage section.

8.0

3 years ago

Feature Release

qlik-py-tools-8.0.zip

This zip archive only contains the files needed to deploy the SSE. You can get sample Qlik Sense apps from the docs or download the full source code below.

Tips for updating on Windows You'll need to download the zip file above, extract it and run Qilk-Py-Init as an administrator. Any model's trained previously will need to be re-trained.

Change Log v.8.0

  • Ability to call pre-trained models that provide a REST API from the load script and chart expressions.
  • Removed dependency on skater. Upgraded to scikit-learn 0.23.1 which now provides the capability to calculate feature importances.
  • Updated HDBSCAN to version 0.8.26
  • Updated spaCy to version 2.2.4
  • Docker image v.8.0 released.

Change Log v.7.0

  • Ability to call externally trained scikit-learn and Keras models for predictions.
  • Sample app and documentation added here.
  • Additional sample app for forecasting with scikit-learn using existing capabilities.

Recent Updates

This release adds the capability to use pre-trained scikit-learn, Keras and REST API based models with Qlik. Read more here.

With version 6, Deep Learning capabilities were added through integration with Keras and Tensorflow. This offers powerful capabilities for sequence predictions and complex timeseries forecasting.

PyTools now also includes the ability to use Additional Regressors with Prophet, allowing you to model more complex timeseries.

For more information refer to the Usage section.

Capabilities

  • Supervised Machine Learning : Implemented using scikit-learn, the go-to machine learning library for Python. This SSE implements the full machine learning flow from data preparation, model training and evaluation, to making predictions in Qlik.
  • Unsupervised Machine Learning : Also implemented using scikit-learn. This provides capabilities for dimensionality reduction and clustering.
  • Deep Learning : Implemented using Keras and TensorFlow. This SSE implements the full flow of setting up a neural network, training and evaluating it, and using it to make predictions. Deep Learning models can be used for sequence predictions and complex timeseries forecasting.
  • Use of pretrained ML models in Qlik : Pre-trained scikit-learn, Keras and REST API based models can be called from this SSE, allowing predictions to be exposed within the broader analysis and business context of a Qlik app. The implementation also allows for What-if analysis using the models.
  • Named Entity Recognition : Implemented using spaCy, an excellent Natural Language Processing library that comes with pre-trained neural networks. This SSE allows you to use spaCy's models for Named Entity Recognition or retrain them with your data for even better results.
  • Association rules : Implemented using Efficient-Apriori. Association Rules Analysis is a data mining technique to uncover how items are associated to each other. This technique is best known for Market Basket Analysis, but can be used more generally for finding interesting associations between sets of items that occur together, for example, in a transaction, a paragraph, or a diagnosis.
  • Clustering : Implemented using HDBSCAN, a high performance algorithm that is great for exploratory data analysis.
  • Time series forecasting : Implemented using Facebook Prophet, a modern library for easily generating good quality forecasts. Now with the ability to use multiple regressors as input.
  • Seasonality and holiday analysis : Also using Facebook Prophet.
  • Linear correlations : Implemented using Pandas.

For more information refer to the Usage section.

7.2

4 years ago

Maintenance Release

qlik-py-tools-7.2.zip

This zip archive only contains the files needed to deploy the SSE. You can get sample Qlik Sense apps from the docs or download the full source code below.

Tips for updating on Windows If you're on PyTools v.7.0 or above, you can simply copy the files from the zip file above under the core folder and overwrite the files at qlik-py-tools\qlik-py-env\core. Then just restart the SSE.

If you're on a release older than 7.0, you'll need to download the zip file above, extract it and run Qilk-Py-Init as an administrator. Any model's trained previously will need to be re-trained.

Change Log v.7.2

  • Fixed the initialization script which was broken by pip release 20.1.

Change Log v.7.1

  • Keras and scikit-learn fixes for transforming targets. Targets can be scaled and made stationary using log or differencing.
  • Docker image v.7.1 released.

Change Log v.7.0

  • Ability to call externally trained scikit-learn and Keras models for predictions.
  • Sample app and documentation added here.
  • Additional sample app for forecasting with scikit-learn using existing capabilities.
  • Docker image v.7.0 released.

Recent Updates

This release adds the capability to use pre-trained scikit-learn and Keras models with Qlik. Read more here.

With version 6, Deep Learning capabilities were added through integration with Keras and Tensorflow. This offers powerful capabilities for sequence predictions and complex timeseries forecasting.

PyTools now also includes the ability to use Additional Regressors with Prophet, allowing you to model more complex timeseries.

For more information refer to the Usage section.

Capabilities

  • Supervised Machine Learning : Implemented using scikit-learn, the go-to machine learning library for Python. This SSE implements the full machine learning flow from data preparation, model training and evaluation, to making predictions in Qlik. In addition, models can be interpreted using Skater.
  • Unsupervised Machine Learning : Also implemented using scikit-learn. This provides capabilities for dimensionality reduction and clustering.
  • Deep Learning : Implemented using Keras and TensorFlow. This SSE implements the full flow of setting up a neural network, training and evaluating it, and using it to make predictions. Deep Learning models can be used for sequence predictions and complex timeseries forecasting.
  • Use of pretrained ML models in Qlik : Pre-trained scikit-learn and Keras models can be called from this SSE, allowing predictions to be exposed within the broader analysis and business context of a Qlik app. The implementation also allows for What-if analysis using the models.
  • Named Entity Recognition : Implemented using spaCy, an excellent Natural Language Processing library that comes with pre-trained neural networks. This SSE allows you to use spaCy's models for Named Entity Recognition or retrain them with your data for even better results.
  • Association rules : Implemented using Efficient-Apriori. Association Rules Analysis is a data mining technique to uncover how items are associated to each other. This technique is best known for Market Basket Analysis, but can be used more generally for finding interesting associations between sets of items that occur together, for example, in a transaction, a paragraph, or a diagnosis.
  • Clustering : Implemented using HDBSCAN, a high performance algorithm that is great for exploratory data analysis.
  • Time series forecasting : Implemented using Facebook Prophet, a modern library for easily generating good quality forecasts. Now with the ability to use multiple regressors as input.
  • Seasonality and holiday analysis : Also using Facebook Prophet.
  • Linear correlations : Implemented using Pandas.

For more information refer to the Usage section.

7.1

4 years ago

Maintenance Release

qlik-py-tools-7.1.zip

This zip archive only contains the files needed to deploy the SSE. You can get sample Qlik Sense apps from the docs or download the full source code below.

Tips for updating on Windows If you're on PyTools v.7.0 or above, you can simply copy the files from the zip file above under the core folder and overwrite the files at qlik-py-tools\qlik-py-env\core. Then just restart the SSE.

If you're on a release older than 7.0, you'll need to download the zip file above, extract it and run Qilk-Py-Init as an administrator. Any model's trained previously will need to be re-trained.

Change Log v.7.1

  • Keras and scikit-learn fixes for transforming targets. Targets can be scaled and made stationary using log or differencing.
  • Docker image v.7.1 released.

Change Log v.7.0

  • Ability to call externally trained scikit-learn and Keras models for predictions.
  • Sample app and documentation added here.
  • Additional sample app for forecasting with scikit-learn using existing capabilities.
  • Docker image v.7.0 released.

Recent Updates

This release adds the capability to use pre-trained scikit-learn and Keras models with Qlik. Read more here.

With version 6, Deep Learning capabilities were added through integration with Keras and Tensorflow. This offers powerful capabilities for sequence predictions and complex timeseries forecasting.

PyTools now also includes the ability to use Additional Regressors with Prophet, allowing you to model more complex timeseries.

For more information refer to the Usage section.

Capabilities

  • Supervised Machine Learning : Implemented using scikit-learn, the go-to machine learning library for Python. This SSE implements the full machine learning flow from data preparation, model training and evaluation, to making predictions in Qlik. In addition, models can be interpreted using Skater.
  • Unsupervised Machine Learning : Also implemented using scikit-learn. This provides capabilities for dimensionality reduction and clustering.
  • Deep Learning : Implemented using Keras and TensorFlow. This SSE implements the full flow of setting up a neural network, training and evaluating it, and using it to make predictions. Deep Learning models can be used for sequence predictions and complex timeseries forecasting.
  • Use of pretrained ML models in Qlik : Pre-trained scikit-learn and Keras models can be called from this SSE, allowing predictions to be exposed within the broader analysis and business context of a Qlik app. The implementation also allows for What-if analysis using the models.
  • Named Entity Recognition : Implemented using spaCy, an excellent Natural Language Processing library that comes with pre-trained neural networks. This SSE allows you to use spaCy's models for Named Entity Recognition or retrain them with your data for even better results.
  • Association rules : Implemented using Efficient-Apriori. Association Rules Analysis is a data mining technique to uncover how items are associated to each other. This technique is best known for Market Basket Analysis, but can be used more generally for finding interesting associations between sets of items that occur together, for example, in a transaction, a paragraph, or a diagnosis.
  • Clustering : Implemented using HDBSCAN, a high performance algorithm that is great for exploratory data analysis.
  • Time series forecasting : Implemented using Facebook Prophet, a modern library for easily generating good quality forecasts. Now with the ability to use multiple regressors as input.
  • Seasonality and holiday analysis : Also using Facebook Prophet.
  • Linear correlations : Implemented using Pandas.

For more information refer to the Usage section.

7.0

4 years ago

Feature Release

qlik-py-tools-7.0.zip

This zip archive only contains the files needed to deploy the SSE. You can get sample Qlik Sense apps from the docs or download the full source code below.

Tips for updating on Windows This release includes new Python packages so you can't simply replace the core files. You'll need to download the zip file above, extract it and run Qilk-Py-Init as an administrator. Any model's trained previously may need to be re-trained.

Change Log v.7.0

  • Ability to call externally trained scikit-learn and Keras models for predictions.
  • Sample app and documentation added here.
  • Additional sample app for forecasting with scikit-learn using existing capabilities.
  • Docker image v.7.0 released.

Recent Updates

This release adds the capability to use pre-trained scikit-learn and Keras models with Qlik. Read more here.

With version 6, Deep Learning capabilities were added through integration with Keras and Tensorflow. This offers powerful capabilities for sequence predictions and complex timeseries forecasting.

PyTools now also includes the ability to use Additional Regressors with Prophet, allowing you to model more complex timeseries.

For more information refer to the Usage section.

Capabilities

  • Supervised Machine Learning : Implemented using scikit-learn, the go-to machine learning library for Python. This SSE implements the full machine learning flow from data preparation, model training and evaluation, to making predictions in Qlik. In addition, models can be interpreted using Skater.
  • Unsupervised Machine Learning : Also implemented using scikit-learn. This provides capabilities for dimensionality reduction and clustering.
  • Deep Learning : Implemented using Keras and TensorFlow. This SSE implements the full flow of setting up a neural network, training and evaluating it, and using it to make predictions. Deep Learning models can be used for sequence predictions and complex timeseries forecasting.
  • Use of pretrained ML models in Qlik : Pre-trained scikit-learn and Keras models can be called from this SSE, allowing predictions to be exposed within the broader analysis and business context of a Qlik app. The implementation also allows for What-if analysis using the models.
  • Named Entity Recognition : Implemented using spaCy, an excellent Natural Language Processing library that comes with pre-trained neural networks. This SSE allows you to use spaCy's models for Named Entity Recognition or retrain them with your data for even better results.
  • Association rules : Implemented using Efficient-Apriori. Association Rules Analysis is a data mining technique to uncover how items are associated to each other. This technique is best known for Market Basket Analysis, but can be used more generally for finding interesting associations between sets of items that occur together, for example, in a transaction, a paragraph, or a diagnosis.
  • Clustering : Implemented using HDBSCAN, a high performance algorithm that is great for exploratory data analysis.
  • Time series forecasting : Implemented using Facebook Prophet, a modern library for easily generating good quality forecasts. Now with the ability to use multiple regressors as input.
  • Seasonality and holiday analysis : Also using Facebook Prophet.
  • Linear correlations : Implemented using Pandas.

For more information refer to the Usage section.

6.5

4 years ago

Maintenance Release

qlik-py-tools-6.5.zip

This zip archive only contains the files needed to deploy the SSE. You can get sample Qlik Sense apps from the docs or download the full source code below.

Tips for a quick update on Windows If you're on PyTools v.6.0 or above, you can simply copy the files from the zip file above under the core folder and overwrite the files at qlik-py-tools\qlik-py-env\core. Then just restart the SSE.

Change Log v.6.5

  • Fix for Prophet incompatibility with new holidays package release (Issue #89).
  • Docker image v.6.5 released which includes updates from the previous release.

Recent Updates

Exciting new capabilities for Deep Learning with Keras and Tensorflow. You can now train and use neural networks for sequence predictions and complex timeseries forecasting.

This release also includes the ability to use Additional Regressors with Prophet, allowing you to model more complex timeseries.

For more information refer to the Usage section.

Capabilities

  • Supervised Machine Learning : Implemented using scikit-learn, the go-to machine learning library for Python. This SSE implements the full machine learning flow from data preparation, model training and evaluation, to making predictions in Qlik. In addition, models can be interpreted using Skater.
  • Unsupervised Machine Learning : Also implemented using scikit-learn. This provides capabilities for dimensionality reduction and clustering.
  • Deep Learning : Implemented using Keras and TensorFlow. This SSE implements the full flow of setting up a neural network, training and evaluating it, and using it to make predictions. Deep Learning models can be used for sequence predictions and complex timeseries forecasting.
  • Named Entity Recognition : Implemented using spaCy, an excellent Natural Language Processing library that comes with pre-trained neural networks. This SSE allows you to use spaCy's models for Named Entity Recognition or retrain them with your data for even better results.
  • Association rules : Implemented using Efficient-Apriori. Association Rules Analysis is a data mining technique to uncover how items are associated to each other. This technique is best known for Market Basket Analysis, but can be used more generally for finding interesting associations between sets of items that occur together, for example, in a transaction, a paragraph, or a diagnosis.
  • Clustering : Implemented using HDBSCAN, a high performance algorithm that is great for exploratory data analysis.
  • Time series forecasting : Implemented using Facebook Prophet, a modern library for easily generating good quality forecasts. Now with the ability to use multiple regressors as input.
  • Seasonality and holiday analysis : Also using Facebook Prophet.
  • Linear correlations : Implemented using Pandas.

For more information refer to the Usage section.

6.4

4 years ago

Maintenance Release

qlik-py-tools-6.4.zip

This zip archive only contains the files needed to deploy the SSE. You can get sample Qlik Sense apps from the docs or download the full source code below.

Tips for a quick update on Windows If you're on PyTools v.6.0 or above, you can simply copy the files from the zip file above under the core folder and overwrite the files at qlik-py-tools\qlik-py-env\core. Then just restart the SSE.

Change Log v.6.4

  • Ability to return residuals for historical data with Prophet (Issue #87). Simply pass return=residual in the parameters.
  • Updates for issue #86

Recent Updates

Exciting new capabilities for Deep Learning with Keras and Tensorflow. You can now train and use neural networks for sequence predictions and complex timeseries forecasting.

This release also includes the ability to use Additional Regressors with Prophet, allowing you to model more complex timeseries.

For more information refer to the Usage section.

Capabilities

  • Supervised Machine Learning : Implemented using scikit-learn, the go-to machine learning library for Python. This SSE implements the full machine learning flow from data preparation, model training and evaluation, to making predictions in Qlik. In addition, models can be interpreted using Skater.
  • Unsupervised Machine Learning : Also implemented using scikit-learn. This provides capabilities for dimensionality reduction and clustering.
  • Deep Learning : Implemented using Keras and TensorFlow. This SSE implements the full flow of setting up a neural network, training and evaluating it, and using it to make predictions. Deep Learning models can be used for sequence predictions and complex timeseries forecasting.
  • Named Entity Recognition : Implemented using spaCy, an excellent Natural Language Processing library that comes with pre-trained neural networks. This SSE allows you to use spaCy's models for Named Entity Recognition or retrain them with your data for even better results.
  • Association rules : Implemented using Efficient-Apriori. Association Rules Analysis is a data mining technique to uncover how items are associated to each other. This technique is best known for Market Basket Analysis, but can be used more generally for finding interesting associations between sets of items that occur together, for example, in a transaction, a paragraph, or a diagnosis.
  • Clustering : Implemented using HDBSCAN, a high performance algorithm that is great for exploratory data analysis.
  • Time series forecasting : Implemented using Facebook Prophet, a modern library for easily generating good quality forecasts. Now with the ability to use multiple regressors as input.
  • Seasonality and holiday analysis : Also using Facebook Prophet.
  • Linear correlations : Implemented using Pandas.

For more information refer to the Usage section.

6.3

4 years ago

Maintenance Release

qlik-py-tools-6.3.zip

This zip archive only contains the files needed to deploy the SSE. You can get sample Qlik Sense apps from the docs or download the full source code below.

Tips for a quick update on Windows If you're on PyTools v.6.0 or above, you can simply copy the files from the zip file above under the core folder and overwrite the files at qlik-py-tools\qlik-py-env\core. Then just restart the SSE.

Change Log v.6.3

  • Ability to provide parameters for Keras optimizers
  • Updates for issues #78 #79
  • Docker image v.6.3 published

Recent Updates

Exciting new capabilities for Deep Learning with Keras and Tensorflow. You can now train and use neural networks for sequence predictions and complex timeseries forecasting.

This release also includes the ability to use Additional Regressors with Prophet, allowing you to model more complex timeseries.

For more information refer to the Usage section.

Capabilities

  • Supervised Machine Learning : Implemented using scikit-learn, the go-to machine learning library for Python. This SSE implements the full machine learning flow from data preparation, model training and evaluation, to making predictions in Qlik. In addition, models can be interpreted using Skater.
  • Unsupervised Machine Learning : Also implemented using scikit-learn. This provides capabilities for dimensionality reduction and clustering.
  • Deep Learning : Implemented using Keras and TensorFlow. This SSE implements the full flow of setting up a neural network, training and evaluating it, and using it to make predictions. Deep Learning models can be used for sequence predictions and complex timeseries forecasting.
  • Named Entity Recognition : Implemented using spaCy, an excellent Natural Language Processing library that comes with pre-trained neural networks. This SSE allows you to use spaCy's models for Named Entity Recognition or retrain them with your data for even better results.
  • Association rules : Implemented using Efficient-Apriori. Association Rules Analysis is a data mining technique to uncover how items are associated to each other. This technique is best known for Market Basket Analysis, but can be used more generally for finding interesting associations between sets of items that occur together, for example, in a transaction, a paragraph, or a diagnosis.
  • Clustering : Implemented using HDBSCAN, a high performance algorithm that is great for exploratory data analysis.
  • Time series forecasting : Implemented using Facebook Prophet, a modern library for easily generating good quality forecasts. Now with the ability to use multiple regressors as input.
  • Seasonality and holiday analysis : Also using Facebook Prophet.
  • Linear correlations : Implemented using Pandas.

For more information refer to the Usage section.

6.2

4 years ago

Maintenance Release

qlik-py-tools-6.2.zip

This zip archive only contains the files needed to deploy the SSE. You can get sample Qlik Sense apps from the docs or download the full source code below.

Change Log v.6.2

  • Fix when using hold-out testing strategy with scikit-learn (issue #65)
  • Docker image v.6.2 published

Recent Updates

Exciting new capabilities for Deep Learning with Keras and Tensorflow. You can now train and use neural networks for sequence predictions and complex timeseries forecasting.

This release also includes the ability to use Additional Regressors with Prophet, allowing you to model more complex timeseries.

For more information refer to the Usage section.

Capabilities

  • Supervised Machine Learning : Implemented using scikit-learn, the go-to machine learning library for Python. This SSE implements the full machine learning flow from data preparation, model training and evaluation, to making predictions in Qlik. In addition, models can be interpreted using Skater.
  • Unsupervised Machine Learning : Also implemented using scikit-learn. This provides capabilities for dimensionality reduction and clustering.
  • Deep Learning : Implemented using Keras and TensorFlow. This SSE implements the full flow of setting up a neural network, training and evaluating it, and using it to make predictions. Deep Learning models can be used for sequence predictions and complex timeseries forecasting.
  • Named Entity Recognition : Implemented using spaCy, an excellent Natural Language Processing library that comes with pre-trained neural networks. This SSE allows you to use spaCy's models for Named Entity Recognition or retrain them with your data for even better results.
  • Association rules : Implemented using Efficient-Apriori. Association Rules Analysis is a data mining technique to uncover how items are associated to each other. This technique is best known for Market Basket Analysis, but can be used more generally for finding interesting associations between sets of items that occur together, for example, in a transaction, a paragraph, or a diagnosis.
  • Clustering : Implemented using HDBSCAN, a high performance algorithm that is great for exploratory data analysis.
  • Time series forecasting : Implemented using Facebook Prophet, a modern library for easily generating good quality forecasts. Now with the ability to use multiple regressors as input.
  • Seasonality and holiday analysis : Also using Facebook Prophet.
  • Linear correlations : Implemented using Pandas.

For more information refer to the Usage section.

6.1

4 years ago

Maintenance Release

qlik-py-tools-6.1.zip

This zip archive only contains the files needed to deploy the SSE. You can get sample Qlik Sense apps from the docs or download the full source code below.

Change Log v.6.1

  • Fix for using Grid Search with Scikit-Learn estimators (issue #58)

New Features

Exciting new capabilities for Deep Learning with Keras and Tensorflow. You can now train and use neural networks for sequence predictions and complex timeseries forecasting.

This release also includes the ability to use Additional Regressors with Prophet, allowing you to model more complex timeseries.

For more information refer to the Usage section.

Capabilities

  • Supervised Machine Learning : Implemented using scikit-learn, the go-to machine learning library for Python. This SSE implements the full machine learning flow from data preparation, model training and evaluation, to making predictions in Qlik. In addition, models can be interpreted using Skater.
  • Unsupervised Machine Learning : Also implemented using scikit-learn. This provides capabilities for dimensionality reduction and clustering.
  • Deep Learning : Implemented using Keras and TensorFlow. This SSE implements the full flow of setting up a neural network, training and evaluating it, and using it to make predictions. Deep Learning models can be used for sequence predictions and complex timeseries forecasting.
  • Named Entity Recognition : Implemented using spaCy, an excellent Natural Language Processing library that comes with pre-trained neural networks. This SSE allows you to use spaCy's models for Named Entity Recognition or retrain them with your data for even better results.
  • Association rules : Implemented using Efficient-Apriori. Association Rules Analysis is a data mining technique to uncover how items are associated to each other. This technique is best known for Market Basket Analysis, but can be used more generally for finding interesting associations between sets of items that occur together, for example, in a transaction, a paragraph, or a diagnosis.
  • Clustering : Implemented using HDBSCAN, a high performance algorithm that is great for exploratory data analysis.
  • Time series forecasting : Implemented using Facebook Prophet, a modern library for easily generating good quality forecasts. Now with the ability to use multiple regressors as input.
  • Seasonality and holiday analysis : Also using Facebook Prophet.
  • Linear correlations : Implemented using Pandas.

For more information refer to the Usage section.