jubakit

jubakit: Jubatus Toolkit

jubakit is a Python module to access Jubatus features easily. jubakit can be used in conjunction with scikit-learn so that you can use powerful features like cross validation and model evaluation. See the Jubakit Documentation for the detailed description.

Currently jubakit supports Classifier, Regression, Anomaly, Recommender, NearestNeighbor, Clustering, Burst, Bandit and Weight engines.

Install

pip install jubakit

Requirements

Python 2.7, 3.3, 3.4 or 3.5.
Jubatus needs to be installed.
Although not mandatory, installing scikit-learn is required to use some features like K-fold cross validation.

Quick Start

The following example shows how to perform train/classify using CSV dataset.

from jubakit.classifier import Classifier, Schema, Dataset, Config
from jubakit.loader.csv import CSVLoader

# Load a CSV file.
loader = CSVLoader('iris.csv')

# Define types for each column in the CSV file.
schema = Schema({
  'Species': Schema.LABEL,
}, Schema.NUMBER)

# Get the shuffled dataset.
dataset = Dataset(loader, schema).shuffle()

# Run the classifier service (`jubaclassifier` process).
classifier = Classifier.run(Config())

# Train the classifier.
for _ in classifier.train(dataset): pass

# Classify using the trained classifier.
for (idx, label, result) in classifier.classify(dataset):
  print("true label: {0}, estimated label: {1}".format(label, result[0][0]))

Examples by Topics

See the example directory for working examples.

Example	Topics	Requires scikit-learn
classifier_csv.py	Handling CSV file and numeric features
classifier_shogun.py	Handling CSV file and string features
classifier_digits.py	Handling toy dataset (digits)	✓
classifier_libsvm.py	Handling LIBSVM file	✓
classifier_kfold.py	K-fold cross validation and metrics	✓
classifier_parameter.py	Finding best hyper parameter	✓
classifier_hyperopt_tuning.py	Finding best hyper parameter using hyperopt	✓
classifier_bulk.py	Bulk Train-Test Classifier
classifier_twitter.py	Handling Twitter Streams
classifier_model_extract.py	Extract contents of Classfier model file
classifier_sklearn_wrapper.py	Classification using scikit-learn wrapper	✓
classifier_sklearn_grid_search.py	Grid Search example using scikit-learn wrapper	✓
classifier_tensorboard.py	Visualize a training process using TensorBoard	✓
regression_boston.py	Regression with toy dataset (boston)	✓
regression_csv.py	Regression with CSV file
regression_sklearn_wrapper.py	Regression using scikit-learn wrapper	✓
anomaly_auc.py	Anomaly detection and metrics
recommender_npb.py	Recommend similar items
nearest_neighbor_aaai.py	Search neighbor items
clustering_2d.py	Clustering 2-dimensional dataset
burst_dummy_stream.py	Burst detection with stream data
bandit_slot.py	Multi-armed bandit with slot machine example
weight_shogun.py	Tracing fv_converter behavior using Weight
weight_model_extract.py	Extract contents of Weight model file

License

MIT License

Metadata

Release files for jubakit 0.6.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for jubakit 0.6.2
File	Size	Uploaded
jubakit-0.6.2.tar.gz	57.0 kB	Jan 28, 2019	Details

Release files / jubakit-0.6.2.tar.gz

Download URL	jubakit-0.6.2.tar.gz
Size	57.0 kB
Tags	Source
SHA-256 checksum How to use checksums	`c88c8a71b7ce0cf829acf9c6690aeef77150f9982f6f52b7238772803c3f85a9`
BLAKE2b-256 checksum How to use checksums	`7454ca9bc2f9a637d53097d8da5607f0a4a56c6073a3b51d7f002b9bcc9d5219`
Upload date	Jan 28, 2019
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`Python-urllib/3.6`