Meteos/DatasetsandModels

Meteos Dataset

Dataset is a data to create a prediction model.

DataSet Format

Meteos currently supports following data format.

Supported dataset format differs depending on prediction models.

Model/Dataset Format	CSV data format	LibSVM data format	Text data format
Logistic Regression Model	YES	YES	NO
Naive Bayes Model Model	YES	NO	YES
Linear Regression Model	YES	YES	NO
Ridge Regression Model	YES	YES	NO
Decision Tree Classification Model	YES	YES	NO
Decision Tree Regression Model	YES	YES	NO
Random Forest Classification Model	YES	YES	NO
Random Forest Regression Model	YES	YES	NO
Kmeans Model	YES	NO	YES
Recommendation Model	YES	NO	NO
Word2Vec Model	NO	NO	YES
FP-growth Model	NO	NO	YES

Most of models support cvs dataset format, however libsvm dataset format is only supported by LinearRegression Model, LogisticRegression Model and DecisionTree Mode.

CSV data format

<label>,<value1>,<value2>, ... <valueN>

LibSVM data format

<label> <index1>:<value1> <index2>:<value2> ... <indexN>:<valueN>

Text data format is only supported Word2Vec and FP-growth Model. Any other Model can not handle text data.

Text data format

This is a text data format

DataSet URL

When creating a prediction model, user specify a "source_dataset_url" parameter which show the place where dataset is located.

A Source_dataset_url has two url types as follows:

Swift URL

Swift URL is used when creating a model from dataset in swift.

If it is no neccesary to parse a dataset, user can create a model from dataset in swift directly by specify source_data_url as below.

swift://<container_name>/<object_name>

Internal HDFS URL

Internal HDFS URL is used when creating a model from internal hdfs of meteos experiment.

"Internal" is meaning that dataset has been already downloaded or parsed by Meteos.

When creating a model from dataset in hdfs, user have to specify a url as below.

internal://<dataset_id>

Meteos Prediction Model

Currently Meteos supports these following prediction models of Apache Spark.

Apache Spark has two machine learning libraries (MLlib and Ml).

MLlib and ML has multiple prediction models by data mining and machine learning algorithms.

MLlib

Supervised learning

Classification

Logistic Regression Model

Naive Bayes Model

Regression

Linear Regression Model

Ridge Regression Model

Tree

Decision Tree Classification Model

Decision Tree Regression Model

Random Forest Classification Model

Random Forest Regression Model

ML

Not Supported.