matclassification.methods.similarity package

Submodules

matclassification.methods.similarity.TDT module

MAT-Tools: Python Framework for Multiple Aspect Trajectory Data Mining

The present package offers a tool, to support the user in the task of data analysis of multiple aspect trajectories. It integrates into a unique framework for multiple aspects trajectories and in general for multidimensional sequence data mining methods. Copyright (C) 2022, MIT license (this portion of code is subject to licensing from source project distribution)

Created on Dec, 2021 Copyright (C) 2022, License GPL Version 3 or superior (this portion of code is subject to licensing from source project distribution)

Authors:

• Tarlis Portela

class matclassification.methods.similarity.TDT.TDT(save_results=False, n_jobs=1, verbose=0, random_state=42, filterwarnings='ignore')

Bases: SimilarityClassifier

A similarity-based classifier using Decision Trees.

This class extends the SimilarityClassifier to implement a similarity-based classifier utilizing Decision Trees. It enables classification of trajectory data by learning decision boundaries in feature space.

Parameters:

save_results (bool):

Flag indicating whether to save results (default is False).

n_jobsint, optional (default=-1)

The number of parallel jobs to run for computation. -1 means using all processors.

verboseint, optional (default=2)

Verbosity level. Higher values enable more detailed output during training and model creation.

random_stateint, optional (default=42)

Random seed used for reproducibility.

filterwarningsstr, optional (default=’ignore’)

Controls the filter for output warnings.

Methods:

fit(X, y):

Fit the SVC model to the training data.

predict(X):

Predict class labels for the provided data.

predict_proba(X):

Predict class probabilities for the provided data.

evaluate(X_test, y_test):

Evaluate the model performance on the test data.

tree():

Generates and returns a graphical representation of the decision tree.

create(config)

tree()

matclassification.methods.similarity.TKNN module

MAT-Tools: Python Framework for Multiple Aspect Trajectory Data Mining

The present package offers a tool, to support the user in the task of data analysis of multiple aspect trajectories. It integrates into a unique framework for multiple aspects trajectories and in general for multidimensional sequence data mining methods. Copyright (C) 2022, MIT license (this portion of code is subject to licensing from source project distribution)

Created on Dec, 2021 Copyright (C) 2022, License GPL Version 3 or superior (this portion of code is subject to licensing from source project distribution)

Authors:

• Tarlis Portela

class matclassification.methods.similarity.TKNN.TKNN(k=[1, 3, 5], weights='distance', save_results=False, n_jobs=1, verbose=0, random_state=42, filterwarnings='ignore')

Bases: SimilarityClassifier

A similarity-based classifier using k-Nearest Neighbors (KNN).

This class extends the SimilarityClassifier to implement a similarity-based classifier utilizing the k-Nearest Neighbors algorithm. It allows for classification of trajectory data based on the distance between samples.

Parameters:

k (list):

Number of neighbors to consider (default is [1, 3, 5]).

weights (str):

Weight function used in prediction (default is ‘distance’).

save_results (bool):

Flag indicating whether to save results (default is False).

n_jobsint, optional (default=-1)

The number of parallel jobs to run for computation. -1 means using all processors.

verboseint, optional (default=2)

Verbosity level. Higher values enable more detailed output during training and model creation.

random_stateint, optional (default=42)

Random seed used for reproducibility.

filterwarningsstr, optional (default=’ignore’)

Controls the filter for output warnings.

Methods:

fit(X, y):

Fit the SVC model to the training data.

predict(X):

Predict class labels for the provided data.

predict_proba(X):

Predict class probabilities for the provided data.

evaluate(X_test, y_test):

Evaluate the model performance on the test data.

create(config)

matclassification.methods.similarity.TSVC module

MAT-Tools: Python Framework for Multiple Aspect Trajectory Data Mining

The present package offers a tool, to support the user in the task of data analysis of multiple aspect trajectories. It integrates into a unique framework for multiple aspects trajectories and in general for multidimensional sequence data mining methods. Copyright (C) 2022, MIT license (this portion of code is subject to licensing from source project distribution)

Created on Dec, 2021 Copyright (C) 2022, License GPL Version 3 or superior (this portion of code is subject to licensing from source project distribution)

Authors:

• Tarlis Portela

class matclassification.methods.similarity.TSVC.TSVC(save_results=False, n_jobs=1, verbose=0, random_state=42, filterwarnings='ignore')

Bases: SimilarityClassifier

A similarity-based classifier using Support Vector Classification (SVC).

This class extends the SimilarityClassifier to implement a similarity-based classifier utilizing Support Vector Machines. It allows for classification of trajectory data based on customizable parameters of the SVC model.

Parameters:

save_results (bool):

Flag indicating whether to save results (default is False).

n_jobsint, optional (default=-1)

The number of parallel jobs to run for computation. -1 means using all processors.

verboseint, optional (default=2)

Verbosity level. Higher values enable more detailed output during training and model creation.

random_stateint, optional (default=42)

Random seed used for reproducibility.

filterwarningsstr, optional (default=’ignore’)

Controls the filter for output warnings.

Methods:

fit(X, y):

Fit the SVC model to the training data.

predict(X):

Predict class labels for the provided data.

predict_proba(X):

Predict class probabilities for the provided data.

evaluate(X_test, y_test):

Evaluate the model performance on the test data.

create(config)

Module contents