Icon

13_​DocumentVector_​Hashing

Streaming Sentiment Analysis of Documents using Document Vector Hashing

This workflows shows an alternative way to execute the Sentiment Analysis example with streaming enabled using the Document Vector Hashing node. The node creates document vectors with a fixed number of dimensions using various hashing methods.

It reads textual data from a csv file and converts the strings into documents, which are then preprocessed, i.e. filtered and stemmed and transformed into numerical/binary document vectors in a streaming fashion. All the preprocessing steps take place in the Streaming text preprocessing meta node. After the document vectors have been created the sentiment class is extracted and a predictive model is built and scored.

This workflow demonstrates how to use the Document Vector Hashing node to execute the Sentiment Analysis example in a streaming fashion. Extract sentimentlabelColor by sentimentlabelTraining / test setApply decisiontree modelScore decisiontree modelScore decisiontree modelRead IMDb reviewsfrom CSV fileBuild predictive modelPreprocess documents andconvert todocument vectors Category To Class Color Manager Partitioning Decision TreePredictor Scorer ROC Curve (local) File Reader DecisionTree Learner Streaming textpreprocessing This workflow demonstrates how to use the Document Vector Hashing node to execute the Sentiment Analysis example in a streaming fashion. Extract sentimentlabelColor by sentimentlabelTraining / test setApply decisiontree modelScore decisiontree modelScore decisiontree modelRead IMDb reviewsfrom CSV fileBuild predictive modelPreprocess documents andconvert todocument vectorsCategory To Class Color Manager Partitioning Decision TreePredictor Scorer ROC Curve (local) File Reader DecisionTree Learner Streaming textpreprocessing

Nodes

Extensions

Links