Classification

Linear Models

Linear SVC

svm.LinearSVC([name, overwrite_model])

Creates an LinearSVC object using scikit-learn for training and the scalability of VAST DataBase for the inferences.

Methods:

LinearSVC.classification_report([metrics, ...])	Computes a classification report using multiple model evaluation metrics (auc, accuracy, f1...).
LinearSVC.confusion_matrix([cutoff])	Computes the model confusion matrix.
LinearSVC.contour([nbins, chart])	Draws the model's contour plot.
LinearSVC.cutoff_curve([nbins, show, chart])	Draws the model Cutoff curve.
LinearSVC.deploySQL([X, cutoff])	Returns the SQL code needed to deploy the model.
LinearSVC.drop()	Drops the model from the VAST DataBase.
LinearSVC.export_models(name, path[, kind])	Exports machine learning models.
LinearSVC.features_importance([show, chart])	Computes the model's features importance.
LinearSVC.fit(input_relation, X, y[, ...])	Trains the model.
LinearSVC.get_attributes([attr_name])	Returns the model attributes.
LinearSVC.get_match_index(x, col_list[, ...])	Returns the matching index.
LinearSVC.get_params()	Returns the parameters of the model.
LinearSVC.get_plotting_lib([class_name, ...])	Returns the first available library (Plotly, Matplotlib) to draw a specific graphic.
LinearSVC.import_models(path[, schema, kind])	Imports machine learning models.
LinearSVC.lift_chart([nbins, show, chart])	Draws the model Lift Chart.
LinearSVC.plot([max_nb_points, chart])	Draws the model.
LinearSVC.prc_curve([nbins, show, chart])	Draws the model PRC curve.
LinearSVC.predict(vdf[, X, name, cutoff, ...])	Makes predictions on the input relation.
LinearSVC.predict_proba(vdf[, X, name, ...])	Returns the model's probabilities using the input relation.
LinearSVC.report([metrics, cutoff, nbins])	Computes a classification report using multiple model evaluation metrics (auc, accuracy, f1...).
LinearSVC.roc_curve([nbins, show, chart])	Draws the model ROC curve.
LinearSVC.score([metric, cutoff, nbins])	Computes the model score.
LinearSVC.set_params([parameters])	Sets the parameters of the model.
LinearSVC.summarize()	Summarizes the model.
LinearSVC.to_binary(path)	Exports the model to the VAST Binary format.
LinearSVC.to_memmodel()	Converts the model to an InMemory object that can be used for different types of predictions.
LinearSVC.to_python([return_proba, ...])	Returns the Python function needed for in-memory scoring without using built-in VAST functions.
LinearSVC.to_sql([X, return_proba, ...])	Returns the SQL code needed to deploy the model without using built-in VAST functions.

Attributes:

LinearSVC.object_type
LinearSVC.classes_

Logistic Regression

linear_model.LogisticRegression([name, ...])

Creates a LogisticRegression object using scikit-learn for training and the scalability of VAST DataBase for the inferences.

Methods:

LogisticRegression.classification_report([...])	Computes a classification report using multiple model evaluation metrics (auc, accuracy, f1...).
LogisticRegression.confusion_matrix([cutoff])	Computes the model confusion matrix.
LogisticRegression.contour([nbins, chart])	Draws the model's contour plot.
LogisticRegression.cutoff_curve([nbins, ...])	Draws the model Cutoff curve.
LogisticRegression.deploySQL([X, cutoff])	Returns the SQL code needed to deploy the model.
LogisticRegression.drop()	Drops the model from the VAST DataBase.
LogisticRegression.export_models(name, path)	Exports machine learning models.
LogisticRegression.features_importance([...])	Computes the model's features importance.
LogisticRegression.fit(input_relation, X, y)	Trains the model.
LogisticRegression.get_attributes([attr_name])	Returns the model attributes.
LogisticRegression.get_match_index(x, col_list)	Returns the matching index.
LogisticRegression.get_params()	Returns the parameters of the model.
LogisticRegression.get_plotting_lib([...])	Returns the first available library (Plotly, Matplotlib) to draw a specific graphic.
LogisticRegression.import_models(path[, ...])	Imports machine learning models.
LogisticRegression.lift_chart([nbins, show, ...])	Draws the model Lift Chart.
LogisticRegression.plot([max_nb_points, chart])	Draws the model.
LogisticRegression.prc_curve([nbins, show, ...])	Draws the model PRC curve.
LogisticRegression.predict(vdf[, X, name, ...])	Makes predictions on the input relation.
LogisticRegression.predict_proba(vdf[, X, ...])	Returns the model's probabilities using the input relation.
LogisticRegression.report([metrics, cutoff, ...])	Computes a classification report using multiple model evaluation metrics (auc, accuracy, f1...).
LogisticRegression.roc_curve([nbins, show, ...])	Draws the model ROC curve.
LogisticRegression.score([metric, cutoff, nbins])	Computes the model score.
LogisticRegression.set_params([parameters])	Sets the parameters of the model.
LogisticRegression.summarize()	Summarizes the model.
LogisticRegression.to_binary(path)	Exports the model to the VAST Binary format.
LogisticRegression.to_memmodel()	Converts the model to an InMemory object that can be used for different types of predictions.
LogisticRegression.to_python([return_proba, ...])	Returns the Python function needed for in-memory scoring without using built-in VAST functions.
LogisticRegression.to_sql([X, return_proba, ...])	Returns the SQL code needed to deploy the model without using built-in VAST functions.

Attributes:

LogisticRegression.object_type
LogisticRegression.classes_

---

Tree-based algorithms

Random Forest Classifier

ensemble.RandomForestClassifier([name, ...])

Creates an RandomForestClassifier object using scikit-learn for training and the scalability of VAST DataBase for the inferences.

Methods:

RandomForestClassifier.classification_report([...])	Computes a classification report using multiple model evaluation metrics (auc, accuracy, f1...).
RandomForestClassifier.confusion_matrix([...])	Computes the model confusion matrix.
RandomForestClassifier.contour([pos_label, ...])	Draws the model's contour plot.
RandomForestClassifier.cutoff_curve([...])	Draws the model Cutoff curve.
RandomForestClassifier.deploySQL([X, ...])	Returns the SQL code needed to deploy the model.
RandomForestClassifier.drop()	Drops the model from the VAST DataBase.
RandomForestClassifier.export_models(name, path)	Exports machine learning models.
RandomForestClassifier.features_importance([...])	Computes the model's features importance.
RandomForestClassifier.fit(input_relation, X, y)	Trains the model.
RandomForestClassifier.get_attributes([...])	Returns the model attributes.
RandomForestClassifier.get_match_index(x, ...)	Returns the matching index.
RandomForestClassifier.get_params()	Returns the parameters of the model.
RandomForestClassifier.get_plotting_lib([...])	Returns the first available library (Plotly, Matplotlib) to draw a specific graphic.
RandomForestClassifier.get_tree([tree_id])	Returns a table with all the input tree information.
RandomForestClassifier.import_models(path[, ...])	Imports machine learning models.
RandomForestClassifier.lift_chart([...])	Draws the model Lift Chart.
RandomForestClassifier.plot([max_nb_points, ...])	Draws the model.
RandomForestClassifier.plot_tree([tree_id, ...])	Draws the input tree.
RandomForestClassifier.prc_curve([...])	Draws the model PRC curve.
RandomForestClassifier.predict(vdf[, X, ...])	Predicts using the input relation.
RandomForestClassifier.predict_proba(vdf[, ...])	Returns the model's probabilities using the input relation.
RandomForestClassifier.report([metrics, ...])	Computes a classification report using multiple model evaluation metrics (auc, accuracy, f1...).
RandomForestClassifier.roc_curve([...])	Draws the model ROC curve.
RandomForestClassifier.score([metric, ...])	Computes the model score.
RandomForestClassifier.set_params([parameters])	Sets the parameters of the model.
RandomForestClassifier.summarize()	Summarizes the model.
RandomForestClassifier.to_binary(path)	Exports the model to the VAST Binary format.
RandomForestClassifier.to_graphviz([...])	Returns the code for a Graphviz tree.
RandomForestClassifier.to_memmodel()	Converts the model to an InMemory object that can be used for different types of predictions.
RandomForestClassifier.to_python([...])	Returns the Python function needed for in-memory scoring without using built-in VAST functions.
RandomForestClassifier.to_sql([X, ...])	Returns the SQL code needed to deploy the model without using built-in VAST functions.

Attributes:

RandomForestClassifier.object_type

GradientBoosting Classifier

ensemble.GradientBoostingClassifier([name, ...])

Creates an GradientBoostingClassifier object using scikit-learn for training and the scalability of VAST DataBase for the inferences.

Methods:

GradientBoostingClassifier.classification_report([...])	Computes a classification report using multiple model evaluation metrics (auc, accuracy, f1...).
GradientBoostingClassifier.confusion_matrix([...])	Computes the model confusion matrix.
GradientBoostingClassifier.contour([...])	Draws the model's contour plot.
GradientBoostingClassifier.cutoff_curve([...])	Draws the model Cutoff curve.
GradientBoostingClassifier.deploySQL([X, ...])	Returns the SQL code needed to deploy the model.
GradientBoostingClassifier.drop()	Drops the model from the VAST DataBase.
GradientBoostingClassifier.export_models(...)	Exports machine learning models.
GradientBoostingClassifier.features_importance([...])	Computes the model's features importance.
GradientBoostingClassifier.fit(...[, ...])	Trains the model.
GradientBoostingClassifier.get_attributes([...])	Returns the model attributes.
GradientBoostingClassifier.get_match_index(x, ...)	Returns the matching index.
GradientBoostingClassifier.get_params()	Returns the parameters of the model.
GradientBoostingClassifier.get_plotting_lib([...])	Returns the first available library (Plotly, Matplotlib) to draw a specific graphic.
GradientBoostingClassifier.get_tree([tree_id])	Returns a table with all the input tree information.
GradientBoostingClassifier.import_models(path)	Imports machine learning models.
GradientBoostingClassifier.lift_chart([...])	Draws the model Lift Chart.
GradientBoostingClassifier.plot([...])	Draws the model.
GradientBoostingClassifier.plot_tree([...])	Draws the input tree.
GradientBoostingClassifier.prc_curve([...])	Draws the model PRC curve.
GradientBoostingClassifier.predict(vdf[, X, ...])	Predicts using the input relation.
GradientBoostingClassifier.predict_proba(vdf)	Returns the model's probabilities using the input relation.
GradientBoostingClassifier.report([metrics, ...])	Computes a classification report using multiple model evaluation metrics (auc, accuracy, f1...).
GradientBoostingClassifier.roc_curve([...])	Draws the model ROC curve.
GradientBoostingClassifier.score([metric, ...])	Computes the model score.
GradientBoostingClassifier.set_params([...])	Sets the parameters of the model.
GradientBoostingClassifier.summarize()	Summarizes the model.
GradientBoostingClassifier.to_binary(path)	Exports the model to the VAST Binary format.
GradientBoostingClassifier.to_graphviz([...])	Returns the code for a Graphviz tree.
GradientBoostingClassifier.to_json([path])	Creates a Python GradientBoosting JSON file that can be imported into the Python GradientBoosting API.
GradientBoostingClassifier.to_memmodel()	Converts the model to an InMemory object that can be used for different types of predictions.
GradientBoostingClassifier.to_python([...])	Returns the Python function needed for in-memory scoring without using built-in VAST functions.
GradientBoostingClassifier.to_sql([X, ...])	Returns the SQL code needed to deploy the model without using built-in VAST functions.

Attributes:

GradientBoostingClassifier.object_type

---

Naive Bayes

Naive Bayes

naive_bayes.NaiveBayes([name, ...])

Creates an NaiveBayes object using scikit-learn for training and the scalability of VAST DataBase for the inferences.

Methods:

NaiveBayes.classification_report([metrics, ...])	Computes a classification report using multiple model evaluation metrics (auc, accuracy, f1...).
NaiveBayes.confusion_matrix([pos_label, cutoff])	Computes the model confusion matrix.
NaiveBayes.contour([pos_label, nbins, chart])	Draws the model's contour plot.
NaiveBayes.cutoff_curve([pos_label, nbins, ...])	Draws the model Cutoff curve.
NaiveBayes.deploySQL([X, pos_label, cutoff, ...])	Returns the SQL code needed to deploy the model.
NaiveBayes.drop()	Drops the model from the VAST DataBase.
NaiveBayes.export_models(name, path[, kind])	Exports machine learning models.
NaiveBayes.fit(input_relation, X, y[, ...])	Trains the model.
NaiveBayes.get_attributes([attr_name])	Returns the model attributes.
NaiveBayes.get_match_index(x, col_list[, ...])	Returns the matching index.
NaiveBayes.get_params()	Returns the parameters of the model.
NaiveBayes.get_plotting_lib([class_name, ...])	Returns the first available library (Plotly, Matplotlib) to draw a specific graphic.
NaiveBayes.import_models(path[, schema, kind])	Imports machine learning models.
NaiveBayes.lift_chart([pos_label, nbins, ...])	Draws the model Lift Chart.
NaiveBayes.prc_curve([pos_label, nbins, ...])	Draws the model PRC curve.
NaiveBayes.predict(vdf[, X, name, cutoff, ...])	Predicts using the input relation.
NaiveBayes.predict_proba(vdf[, X, name, ...])	Returns the model's probabilities using the input relation.
NaiveBayes.report([metrics, cutoff, labels, ...])	Computes a classification report using multiple model evaluation metrics (auc, accuracy, f1...).
NaiveBayes.roc_curve([pos_label, nbins, ...])	Draws the model ROC curve.
NaiveBayes.score([metric, average, ...])	Computes the model score.
NaiveBayes.set_params([parameters])	Sets the parameters of the model.
NaiveBayes.summarize()	Summarizes the model.
NaiveBayes.to_binary(path)	Exports the model to the VAST Binary format.
NaiveBayes.to_memmodel()	Converts the model to an InMemory object that can be used for different types of predictions.
NaiveBayes.to_python([return_proba, ...])	Returns the Python function needed for in-memory scoring without using built-in VAST functions.
NaiveBayes.to_sql([X, return_proba, ...])	Returns the SQL code needed to deploy the model without using built-in VAST functions.

Attributes:

NaiveBayes.object_type

---

Neighbors

K-Nearest Neighbors Classifier (Beta)

neighbors.KNeighborsClassifier([name, ...])

[Beta Version] Creates a KNeighborsClassifier object using the k-nearest neighbors algorithm.

Methods:

KNeighborsClassifier.classification_report([...])	Computes a classification report using multiple model evaluation metrics (auc, accuracy, f1...).
KNeighborsClassifier.confusion_matrix([...])	Computes the model confusion matrix.
KNeighborsClassifier.contour([pos_label, ...])	Draws the model's contour plot.
KNeighborsClassifier.cutoff_curve([...])	Draws the model Cutoff curve.
KNeighborsClassifier.deploySQL([X, ...])	Returns the SQL code needed to deploy the model.
KNeighborsClassifier.drop()	KNeighborsClassifier models are not stored in the VAST DataBase.
KNeighborsClassifier.export_models(name, path)	Exports machine learning models.
KNeighborsClassifier.fit(input_relation, X, y)	Trains the model.
KNeighborsClassifier.get_attributes([attr_name])	Returns the model attributes.
KNeighborsClassifier.get_match_index(x, col_list)	Returns the matching index.
KNeighborsClassifier.get_params()	Returns the parameters of the model.
KNeighborsClassifier.get_plotting_lib([...])	Returns the first available library (Plotly, Matplotlib) to draw a specific graphic.
KNeighborsClassifier.import_models(path[, ...])	Imports machine learning models.
KNeighborsClassifier.lift_chart([pos_label, ...])	Draws the model Lift Chart.
KNeighborsClassifier.prc_curve([pos_label, ...])	Draws the model PRC curve.
KNeighborsClassifier.predict(vdf[, X, name, ...])	Predicts using the input relation.
KNeighborsClassifier.predict_proba(vdf[, X, ...])	Returns the model's probabilities using the input relation.
KNeighborsClassifier.report([metrics, ...])	Computes a classification report using multiple model evaluation metrics (auc, accuracy, f1...).
KNeighborsClassifier.roc_curve([pos_label, ...])	Draws the model ROC curve.
KNeighborsClassifier.score([metric, ...])	Computes the model score.
KNeighborsClassifier.set_params([parameters])	Sets the parameters of the model.
KNeighborsClassifier.summarize()	Summarizes the model.
KNeighborsClassifier.to_binary(path)	Exports the model to the VAST Binary format.
KNeighborsClassifier.to_python([...])	Returns the Python function needed for in-memory scoring without using built-in VAST functions.
KNeighborsClassifier.to_sql([X, ...])	Returns the SQL code needed to deploy the model without using built-in VAST functions.

Attributes:

KNeighborsClassifier.object_type

Nearest Centroid (Beta)

cluster.NearestCentroid([name, ...])

Creates a NearestCentroid object using the k-nearest centroid algorithm.

Methods:

NearestCentroid.classification_report([...])	Computes a classification report using multiple model evaluation metrics (auc, accuracy, f1...).
NearestCentroid.confusion_matrix([...])	Computes the model confusion matrix.
NearestCentroid.contour([pos_label, nbins, ...])	Draws the model's contour plot.
NearestCentroid.cutoff_curve([pos_label, ...])	Draws the model Cutoff curve.
NearestCentroid.deploySQL([X, pos_label, ...])	Returns the SQL code needed to deploy the model.
NearestCentroid.drop()	NearestCentroid models are not stored in the VAST DataBase.
NearestCentroid.export_models(name, path[, kind])	Exports machine learning models.
NearestCentroid.fit(input_relation, X, y[, ...])	Trains the model.
NearestCentroid.get_attributes([attr_name])	Returns the model attributes.
NearestCentroid.get_match_index(x, col_list)	Returns the matching index.
NearestCentroid.get_params()	Returns the parameters of the model.
NearestCentroid.get_plotting_lib([...])	Returns the first available library (Plotly, Matplotlib) to draw a specific graphic.
NearestCentroid.import_models(path[, ...])	Imports machine learning models.
NearestCentroid.lift_chart([pos_label, ...])	Draws the model Lift Chart.
NearestCentroid.prc_curve([pos_label, ...])	Draws the model PRC curve.
NearestCentroid.predict(vdf[, X, name, ...])	Predicts using the input relation.
NearestCentroid.predict_proba(vdf[, X, ...])	Returns the model's probabilities using the input relation.
NearestCentroid.report([metrics, cutoff, ...])	Computes a classification report using multiple model evaluation metrics (auc, accuracy, f1...).
NearestCentroid.roc_curve([pos_label, ...])	Draws the model ROC curve.
NearestCentroid.score([metric, average, ...])	Computes the model score.
NearestCentroid.set_params([parameters])	Sets the parameters of the model.
NearestCentroid.summarize()	Summarizes the model.
NearestCentroid.to_binary(path)	Exports the model to the VAST Binary format.
NearestCentroid.to_memmodel()	Converts the model to an InMemory object that can be used for different types of predictions.
NearestCentroid.to_python([return_proba, ...])	Returns the Python function needed for in-memory scoring without using built-in VAST functions.
NearestCentroid.to_sql([X, return_proba, ...])	Returns the SQL code needed to deploy the model without using built-in VAST functions.

Attributes:

NearestCentroid.object_type