Series de tiempo multivariadas

0 ×

This is a simple example workflow for multivariant time series analysis using an LSTM based recurrent neural network and implemented via the KNIME Deep Learning - Keras Integration.

It is based on the bike demand predition dataset from Kaggle and trains a model to predict the demand in the next hour based on the demand and the other features in the last 10 hours.

URL: Dataset on Kaggle https://www.kaggle.com/hmavrodiev/london-bike-sharing-dataset

Nodes

• CSV Reader1 ×
• Column Filter1 ×
• Create Collection Column1 ×
• Extract Date&Time Fields1 ×
• Keras Dense Layer1 ×
• Keras Input Layer1 ×
• Keras LSTM Layer1 ×
• Keras Network Executor1 ×
• Keras Network Learner1 ×
• Keras Network Writer1 ×
• Lag Column1 ×
• Missing Value1 ×
• String to Date&Time1 ×
• Partitioning1 ×

Extensions

• FeatureKNIME Base nodes
• FeatureKNIME Deep Learning - Keras Integration

Links

• No links available