geochemistrypi.data_mining.model package

Subpackages

Submodules

geochemistrypi.data_mining.model.classification module

class AdaBoostClassification(estimator: object | None = None, *, n_estimators: int = 50, learning_rate: float = 1.0, random_state: int | None = None, max_depth: int = 3)[source]

Bases: TreeWorkflowMixin, ClassificationWorkflowBase

The automation workflow of using AdaBoosting algorithm to make insightful products.

property customization: object

The customized AdaBoosting of FLAML framework

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'AdaBoost'
property settings: Dict

The configuration of AdaBoosting to implenment AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = ['Feature Importance Diagram', 'Single Tree Diagram']
class ClassificationWorkflowBase[source]

Bases: WorkflowBase

The base workflow class of classification algorithms.

property auto_model: object

Get AutoML trained model by FLAML framework.

common_components

Dispatch methods based on type signature

See also

Dispatcher

common_function = ['Model Score', 'Classification Report', 'Confusion Matrix', 'Cross Validation', 'Model Prediction', 'Model Persistence', 'Precision-Recall Curve', 'Precision-Recall vs. Threshold Diagram', 'ROC Curve', 'Two-dimensional Decision Boundary Diagram', 'Permutation Importance Diagram']
property customization: object

The customized model of FLAML framework.

static customize_label(y: DataFrame, y_train: DataFrame, y_test: DataFrame, name_column1: str, name_column2: str, name_column3: str, local_path: str, mlflow_path: str) → tuple[DataFrame, DataFrame, DataFrame][source]

Using this function to customize the label to which samples of each category belong.

fit

Dispatch methods based on type signature

See also

Dispatcher

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

predict

Dispatch methods based on type signature

See also

Dispatcher

static sample_balance(X_train: DataFrame, y_train: DataFrame, name_column: str, local_path: str, mlflow_path: str) → tuple[source]

Use this method when the sample size is unbalanced.

property settings: Dict

The configuration to implement AutoML by FLAML framework.

class DecisionTreeClassification(criterion: str = 'gini', splitter: str = 'best', max_depth: int | None = 3, min_samples_split: int | float = 2, min_samples_leaf: int | float = 1, min_weight_fraction_leaf: float = 0.0, max_features: int | float | str | None = None, random_state: int | None = None, max_leaf_nodes: int | None = None, min_impurity_decrease: float = 0.0, class_weight: dict | List[dict] | str | None = None, ccp_alpha: float = 0.0)[source]

Bases: TreeWorkflowMixin, ClassificationWorkflowBase

The automation workflow of using Decision Tree algorithm to make insightful products.

property customization: object

The customized Decision Tree of FLAML framework.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Decision Tree'
property settings: Dict

The configuration of Decision Tree to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = ['Feature Importance Diagram', 'Single Tree Diagram']
class ExtraTreesClassification(n_estimators: int = 100, criterion: str = 'gini', max_depth: int | None = None, min_samples_split: float | int = 2, min_samples_leaf: float | int = 1, min_weight_fraction_leaf: float = 0.0, max_features: str | float | int = 'sqrt', max_leaf_nodes: int | None = None, min_impurity_decrease: float = 0.0, bootstrap: bool = False, oob_score: bool = False, n_jobs: int | None = None, random_state: int | None = None, verbose: int = 0, warm_start: bool = False, class_weight: str | None = None, ccp_alpha: float = 0.0, max_samples: int | float | None = None)[source]

Bases: TreeWorkflowMixin, ClassificationWorkflowBase

The automation workflow of using Extra-Trees algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Extra-Trees'
property settings: Dict

The configuration to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = ['Feature Importance Diagram', 'Single Tree Diagram']
class GradientBoostingClassification(*, loss: str = 'log_loss', learning_rate: float = 0.1, n_estimators: int = 100, subsample: float = 1.0, criterion: str = 'squared_error', min_samples_split: int | float = 2, min_samples_leaf: int | float = 1, min_weight_fraction_leaf: float = 0.0, max_depth: float = 3, min_impurity_decrease: float = 0.0, init: object | None = None, random_state: int | None = None, max_features: str | int | float | None = None, verbose: int = 0, max_leaf_nodes: int | None = None, warm_start: bool = False, validation_fraction: float = 0.1, n_iter_no_change: int | None = None, tol: float = 0.0001, ccp_alpha: float = 0.0)[source]

Bases: TreeWorkflowMixin, ClassificationWorkflowBase

The automation workflow of using Gradient Boosting algorithm to make insightful products.

property customization: object

The customized Gradient Boosting of FLAML framework.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Gradient Boosting'
property settings: Dict

The configuration of Gradient Boosting to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = ['Feature Importance Diagram', 'Single Tree Diagram']
class KNNClassification(n_neighbors: int = 5, *, weights: str = 'uniform', algorithm: str = 'auto', leaf_size: int = 30, p: int = 2, metric: str = 'minkowski', metric_params: Dict | None = None, n_jobs: int | None = None)[source]

Bases: ClassificationWorkflowBase

The automation workflow of using KNN algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'K-Nearest Neighbors'
property settings: Dict

The configuration to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = []
class LogisticRegressionClassification(penalty: str = 'l2', dual: bool = False, tol: float = 0.0001, C: float = 1.0, fit_intercept: bool = True, intercept_scaling: float = 1, class_weight: Dict | str | None = None, random_state: int | None = None, solver: str = 'lbfgs', max_iter: int = 100, multi_class: str = 'auto', verbose: int = 0, warm_start: bool = False, n_jobs: int | None = None, l1_ratio: float | None = None)[source]

Bases: LinearWorkflowMixin, ClassificationWorkflowBase

The automation workflow of using Logistic Regression algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Logistic Regression'
property settings: Dict

The configuration to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = ['Logistic Regression Formula', 'Feature Importance Diagram']
class MLPClassification(hidden_layer_sizes: tuple = (100,), activation: str = 'relu', *, solver: str = 'adam', alpha: float = 0.0001, batch_size: int | str = 'auto', learning_rate: str = 'constant', learning_rate_init: float = 0.001, power_t: float = 0.5, max_iter: int = 200, shuffle: bool = True, random_state: int | None = None, tol: float = 0.0001, verbose: bool = False, warm_start: bool = False, momentum: float = 0.9, nesterovs_momentum: bool = True, early_stopping: bool = False, validation_fraction: float = 0.1, beta_1: float = 0.9, beta_2: float = 0.999, epsilon: float = 1e-08, n_iter_no_change: int = 10, max_fun: int = 15000)[source]

Bases: ClassificationWorkflowBase

The automation workflow of using Multi-layer Perceptron algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Multi-layer Perceptron'
ray_tune(X_train: DataFrame, X_test: DataFrame, y_train: DataFrame, y_test: DataFrame) → None[source]

The customized MLP of the combinations of Ray, FLAML and Scikit-learn framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = ['Loss Curve Diagram']
class RandomForestClassification(n_estimators: int = 100, criterion: str = 'gini', max_depth: int | None = 4, min_samples_split: int | float = 4, min_samples_leaf: int | float = 1, min_weight_fraction_leaf: float = 0.0, max_features: str | int | float = 'sqrt', max_leaf_nodes: int | None = 3, min_impurity_decrease: float = 0.0, bootstrap: bool = True, oob_score: bool = False, n_jobs: int | None = -1, random_state: int | None = None, verbose: int = 0, warm_start: bool = False, class_weight: str | dict | list[dict] | None = None, ccp_alpha: float = 0.0, max_samples: int | float = 10)[source]

Bases: TreeWorkflowMixin, ClassificationWorkflowBase

The automation workflow of using Random Forest algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Random Forest'
property settings: Dict

The configuration to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = ['Feature Importance Diagram', 'Single Tree Diagram']
class SGDClassification(loss: str = 'log_loss', penalty: str = 'l2', alpha: float = 0.0001, l1_ratio: float = 0.15, fit_intercept: bool = True, max_iter: int = 1000, tol: float | None = 0.001, shuffle: bool = True, verbose: int = 0, epsilon: float = 0.1, n_jobs: int | None = None, random_state: int | None = None, learning_rate: str = 'optimal', eta0: float = 0.0, power_t: float = 0.5, early_stopping: bool = False, validation_fraction: float = 0.1, n_iter_no_change: int = 5, class_weight: dict | str | None = None, warm_start: bool = False, average: bool | int = False)[source]

Bases: LinearWorkflowMixin, ClassificationWorkflowBase

The automation workflow of using Stochastic Gradient Descent - SGD algorithm to make insightful products.

property customization: object

The customized SGD of FLAML framework.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Stochastic Gradient Descent'
property settings: Dict

The configuration of SGD to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = ['SGD Classification Formula']
class SVMClassification(C: float = 1.0, kernel: str | Callable = 'rbf', degree: int = 3, gamma: str | float = 'scale', coef0: float = 0.0, shrinking: bool = True, probability: bool = True, tol: float = 0.001, cache_size: float = 200, class_weight: dict | str | None = None, verbose: bool = False, max_iter: int = -1, decision_function_shape: Literal['ovo', 'ovr'] = 'ovr', break_ties: bool = False, random_state: int | None = None)[source]

Bases: ClassificationWorkflowBase

The automation workflow of using SVC algorithm to make insightful products.

property customization: object

The customized SVC of FLAML framework.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Support Vector Machine'
property settings: Dict

The configuration of SVC to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = []
class XGBoostClassification(n_estimators: int = 100, max_depth: int | None = None, max_leaves: int | None = None, max_bin: int | None = None, grow_policy=1, learning_rate: float | None = None, verbosity: int | None = None, objective: str | Callable[[ndarray, ndarray], Tuple[ndarray, ndarray]] | None = None, booster: str | None = None, tree_method: str | None = None, n_jobs: int | None = None, gamma: float | None = None, min_child_weight: float | None = None, max_delta_step: float | None = None, subsample: float | None = None, colsample_bytree: float | None = None, colsample_bylevel: float | None = None, colsample_bynode: float | None = None, reg_alpha: float | None = None, reg_lambda: float | None = None, scale_pos_weight: float | None = None, base_score: float | None = None, random_state: RandomState | int | None = None, missing: float = nan, num_parallel_tree: int | None = None, monotone_constraints: Dict[str, int] | str | None = None, interaction_constraints: str | Sequence[Sequence[str]] | None = None, importance_type: str | None = 'weight', gpu_id: int | None = None, validate_parameters: bool | None = None, predictor: str | None = None, enable_categorical: bool = False, eval_metric: str | List[str] | Callable | None = None, early_stopping_rounds: int | None = None, **kwargs: Any)[source]

Bases: TreeWorkflowMixin, ClassificationWorkflowBase

The automation workflow of using XGBoost algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'XGBoost'
property settings: Dict

The configuration to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = ['Feature Importance Diagram']

geochemistrypi.data_mining.model.clustering module

class AffinityPropagationClustering(*, damping: float = 0.5, max_iter: int = 200, convergence_iter: int = 15, copy: bool = True, preference: Dict | None = None, affinity: str = 'euclidean', verbose: bool = False, random_state: Dict | None = None)[source]

Bases: ClusteringWorkflowBase

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'AffinityPropagation'
special_components(**kwargs: Dict | ndarray | int) → None[source]

Invoke all special application functions for this algorithms by Scikit-learn framework.

class Agglomerative(n_clusters: int = 2, *, affinity: str = 'euclidean', memory: str | None = None, connectivity: _SupportsArray[dtype] | _NestedSequence[_SupportsArray[dtype]] | bool | int | float | complex | str | bytes | _NestedSequence[bool | int | float | complex | str | bytes] | None = None, compute_full_tree: str = 'auto', linkage: str = 'ward', distance_threshold: float | None = None, compute_distances: bool = False)[source]

Bases: ClusteringWorkflowBase

The automation workflow of using Agglomerative Clustering to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Agglomerative'
special_components(**kwargs) → None[source]

Invoke all special application functions for this algorithms by Scikit-learn framework.

special_function = []
class BIRCHClusteringClustering[source]

Bases: ClusteringWorkflowBase

name = 'BIRCHClustering'
class BisectingKMeansClustering[source]

Bases: ClusteringWorkflowBase

name = 'BisectingKMeans'
class ClusteringWorkflowBase[source]

Bases: WorkflowBase

The base workflow class of clustering algorithms.

common_components() → None[source]

Invoke all common application functions for clustering algorithms.

common_function = ['Cluster Centers', 'Cluster Labels', 'Model Persistence', 'Model Score', 'Cluster Two-Dimensional Diagram', 'Cluster Three-Dimensional Diagram', 'Silhouette Diagram', 'Silhouette value Diagram']
fit(X: DataFrame, y: DataFrame | None = None) → None[source]

Fit the model according to the given training data.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

class DBSCANClustering(eps: float = 0.5, min_samples: int = 5, metric: str = 'euclidean', metric_params: Dict | None = None, algorithm: str = 'auto', leaf_size: int = 30, p: float | None = None, n_jobs: int | None = None)[source]

Bases: ClusteringMetricsMixin, ClusteringWorkflowBase

The automation workflow of using DBSCAN algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'DBSCAN'
special_components(**kwargs: Dict | ndarray | int) → None[source]

Invoke all special application functions for this algorithm by Scikit-learn framework.

special_function = ['Num of Clusters']
class GaussianMixturesClustering[source]

Bases: ClusteringWorkflowBase

name = 'GaussianMixtures'
class KMeansClustering(n_clusters: int = 8, init: str = 'k-means++', n_init: int = 10, max_iter: int = 300, tol: float = 0.0001, verbose: int = 0, random_state: int | None = None, copy_x: bool = True, algorithm: str = 'auto')[source]

Bases: ClusteringWorkflowBase

The automation workflow of using KMeans algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'KMeans'
special_components(**kwargs: Dict | ndarray | int) → None[source]

Invoke all special application functions for this algorithms by Scikit-learn framework.

special_function = ['Inertia Score']
class MeanShiftClustering(*, bandwidth: float | None = None, seeds: ndarray | list | None = None, bin_seeding: bool = False, min_bin_freq: int = 1, cluster_all: bool = True, n_jobs: int | None = None, max_iter: int = 300)[source]

Bases: ClusteringMetricsMixin, ClusteringWorkflowBase

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'MeanShift'
special_components(**kwargs: Dict | ndarray | int) → None[source]

Invoke all special application functions for this algorithm by Scikit-learn framework.

special_function = ['Num of Clusters']
class OPTICSClustering[source]

Bases: ClusteringWorkflowBase

name = 'OPTICS'
class SpectralClustering[source]

Bases: ClusteringWorkflowBase

name = 'Spectral'
class WardHierarchicalClustering[source]

Bases: ClusteringWorkflowBase

name = 'WardHierarchical'

geochemistrypi.data_mining.model.decomposition module

class DecompositionWorkflowBase[source]

Bases: WorkflowBase

The base workflow class of decomposition algorithms.

common_components() → None[source]

Invoke all common application functions for decomposition algorithms by Scikit-learn framework.

common_function = ['Model Persistence', 'Decomposition Two-Dimensional Diagram', 'Decomposition Heatmap', 'Dimensionality Reduction Contour Plot']
fit(X: DataFrame, y: DataFrame | None = None) → None[source]

Fit the model.

fit_transform(X: DataFrame, y: DataFrame | None = None) → DataFrame[source]

Fit the model with X and apply the dimensionality reduction on X.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

transform(X: DataFrame) → DataFrame[source]

Apply dimensionality reduction to X.

class MDSDecomposition(n_components: int = 2, *, metric: bool = True, n_init: int = 4, max_iter: int = 300, verbose: int = 0, eps: float = 0.001, n_jobs: int | None = None, random_state: int | None = None, dissimilarity: str = 'euclidean')[source]

Bases: DecompositionWorkflowBase

The automation workflow of using MDS algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'MDS'
special_components(**kwargs) → None[source]

Invoke all special application functions for this algorithms by Scikit-learn framework.

special_function = []
class PCADecomposition(n_components: int | None = None, copy: bool = True, whiten: bool = False, svd_solver: str = 'auto', tol: float = 0.0, iterated_power: int | str = 'auto', n_oversamples: int = 10, power_iteration_normalizer: str = 'auto', random_state: int | None = None)[source]

Bases: DecompositionWorkflowBase

The automation workflow of using PCA algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'PCA'
special_components(**kwargs: Dict | ndarray | int) → None[source]

Invoke all special application functions for this algorithms by Scikit-learn framework.

special_function = ['Principal Components', 'Explained Variance Ratio', 'Compositional Bi-plot', 'Compositional Tri-plot']
class TSNEDecomposition(n_components: int = 2, *, perplexity: float = 30.0, early_exaggeration: float = 12.0, learning_rate: float | str = 'auto', n_iter: int = 1000, n_iter_without_progress: int = 300, min_grad_norm: float = 1e-07, metric: str = 'euclidean', metric_params: Dict | None = None, init: str = 'pca', verbose: int = 0, random_state: int | None = None, method: str = 'exact', angle: float = 0.5, n_jobs: int | None = None, square_distances: bool | str = 'deprecated')[source]

Bases: DecompositionWorkflowBase

The automation workflow of using T-SNE algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'T-SNE'
special_components(**kwargs) → None[source]

Invoke all special application functions for this algorithms by Scikit-learn framework.

special_function = []

geochemistrypi.data_mining.model.detection module

class AnomalyDetectionWorkflowBase[source]

Bases: WorkflowBase

The base workflow class of anomaly detection algorithms.

common_components() → None[source]

Invoke all common application functions for anomaly detection algorithms by Scikit-learn framework.

common_function = ['Anomaly Detection Two-Dimensional Diagram', 'Anomaly Detection Three-Dimensional Diagram', 'Anomaly Detection Density Estimation']
fit(X: DataFrame, y: DataFrame | None = None) → None[source]

Fit the model by Scikit-learn framework.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

predict(X: DataFrame) → ndarray[source]

Perform Anomaly Detection on samples in X by Scikit-learn framework.

class IsolationForestAnomalyDetection(n_estimators: int = 100, max_samples: str | int | float = 'auto', contamination: str | float = 'auto', max_features: int | float = 1.0, bootstrap: bool = False, n_jobs: int | None = None, random_state: int | None = None, verbose: int = 0, warm_start: bool = False)[source]

Bases: AnomalyDetectionWorkflowBase

The automation workflow of using Isolation Forest algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Isolation Forest'
special_components(**kwargs) → None[source]

Invoke all special application functions for this algorithms by Scikit-learn framework.

special_function = []
class LocalOutlierFactorAnomalyDetection(n_neighbors: int = 20, algorithm: str = 'auto', leaf_size: int = 30, metric: str | callable = 'minkowski', p: float = 2.0, metric_params: dict | None = None, contamination: str | float = 'auto', novelty: bool = True, n_jobs: int | None = None)[source]

Bases: AnomalyDetectionWorkflowBase

The automation workflow of using Local Outlier Factor algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Local Outlier Factor'
special_components(**kwargs) → None[source]

Invoke all special application functions for this algorithms by Scikit-learn framework.

special_function = ['Lof Score Diagram']

geochemistrypi.data_mining.model.regression module

class BayesianRidgeRegression(tol: float = 0.001, alpha_1: float = 1e-06, alpha_2: float = 1e-06, lambda_1: float = 1e-06, lambda_2: float = 1e-06, alpha_init: float | None = None, lambda_init: float | None = None, compute_score: bool = False, fit_intercept: bool = True, copy_X: bool = True, verbose: bool = False)[source]

Bases: RegressionWorkflowBase

The automation workflow of using Bayesian ridge regression algorithm to make insightful products.

property customization: object

The customized BayesianRidge of FLAML framework.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'BayesianRidge Regression'
property settings: Dict

The configuration of BayesianRidge to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = []
class ClassicalLinearRegression(fit_intercept: bool = True, copy_X: bool = True, n_jobs: int | None = None, positive: bool = False)[source]

Bases: LinearWorkflowMixin, RegressionWorkflowBase

The automation workflow of using Linear Regression algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Linear Regression'
special_components(**kwargs) → None[source]

Invoke all special application functions for this algorithms by Scikit-learn framework.

special_function = ['Linear Regression Formula', '2D Scatter Diagram', '3D Scatter Diagram', '2D Line Diagram', '3D Surface Diagram']
class DecisionTreeRegression(criterion: str = 'squared_error', splitter: str = 'best', max_depth: int | None = None, min_samples_split: int | float = 2, min_samples_leaf: int | float = 1, min_weight_fraction_leaf: float = 0.0, max_features: int | float | str | None = None, random_state: int | None = None, max_leaf_nodes: int | None = None, min_impurity_decrease: float = 0.0, ccp_alpha: float = 0.0)[source]

Bases: TreeWorkflowMixin, RegressionWorkflowBase

The automation workflow of using Decision Tree algorithm to make insightful products.

property customization: object

The customized Decision Tree of FLAML framework.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Decision Tree'
property settings: Dict

The configuration of Decision Tree to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = ['Feature Importance Diagram', 'Single Tree Diagram']
class ElasticNetRegression(alpha: float = 1.0, l1_ratio: float = 0.5, fit_intercept: bool = True, precompute: bool = False, max_iter: int = 1000, copy_X: bool = True, tol: float = 0.0001, warm_start: bool = False, positive: bool = False, random_state: int | None = None, selection: str = 'cyclic')[source]

Bases: LinearWorkflowMixin, RegressionWorkflowBase

The automation workflow of using Elastic Net algorithm to make insightful products.

property customization: object

The customized Elastic Net of FLAML framework.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Elastic Net'
property settings: Dict

The configuration of Elastic Net to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = ['Elastic Net Formula', '2D Scatter Diagram', '3D Scatter Diagram', '2D Line Diagram', '3D Surface Diagram']
class ExtraTreesRegression(n_estimators: int = 100, criterion: str = 'mse', max_depth: int | None = None, min_samples_split: int | float = 2, min_samples_leaf: int | float = 1, min_weight_fraction_leaf: float = 0.0, max_features: int | float | str = 'auto', max_leaf_nodes: int | None = None, min_impurity_decrease: float = 0.0, bootstrap: bool = False, oob_score: bool = False, n_jobs: int | None = None, random_state: int | None = None, verbose: int = 0, warm_start: bool = False, ccp_alpha: float = 0.0, max_samples: int | float | None = None)[source]

Bases: TreeWorkflowMixin, RegressionWorkflowBase

The automation workflow of using Extra-Trees algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Extra-Trees'
property settings: Dict

The configuration to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = ['Feature Importance Diagram', 'Single Tree Diagram']
class GradientBoostingRegression(*, loss: str = 'squared_error', learning_rate: float = 0.1, n_estimators: int = 100, subsample: float = 1.0, criterion: str = 'friedman_mse', min_samples_split: int | float = 2, min_samples_leaf: int | float = 1, min_weight_fraction_leaf: float = 0.0, max_depth: float = 3, min_impurity_decrease: float = 0.0, init: object | None = None, random_state: int | None = None, max_features: str | int | float | None = None, alpha: float = 0.9, verbose: int = 0, max_leaf_nodes: int | None = None, warm_start: bool = False, validation_fraction: float = 0.1, n_iter_no_change: int | None = None, tol: float = 0.0001, ccp_alpha: float = 0.0)[source]

Bases: TreeWorkflowMixin, RegressionWorkflowBase

The automation workflow of using Gradient Boosting algorithm to make insightful products.

property customization: object

The customized Gradient Boosting of FLAML framework.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Gradient Boosting'
property settings: Dict

The configuration of Gradient Boosting to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = ['Feature Importance Diagram', 'Single Tree Diagram']
class KNNRegression(n_neighbors: int = 5, *, weights: str = 'uniform', algorithm: str = 'auto', leaf_size: int = 30, p: int = 2, metric: str = 'minkowski', metric_params: Dict | None = None, n_jobs: int | None = None)[source]

Bases: RegressionWorkflowBase

The automation workflow of using KNN algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'K-Nearest Neighbors'
property settings: Dict

The configuration to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = []
class LassoRegression(alpha: float = 1.0, *, fit_intercept: bool = True, precompute: bool = False, copy_X: bool = True, max_iter: int = 1000, tol: float = 0.0001, warm_start: bool = False, positive: bool = False, random_state: int | None = None, selection: str = 'cyclic')[source]

Bases: LinearWorkflowMixin, RegressionWorkflowBase

The automation workflow of using Lasso to make insightful products.

property customization: object

The customized Lasso of FLAML framework.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Lasso Regression'
property settings: Dict

The configuration of Lasso to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = ['Lasso Regression Formula', '2D Scatter Diagram', '3D Scatter Diagram', '2D Line Diagram', '3D Surface Diagram']
class MLPRegression(hidden_layer_sizes: tuple = (50, 25, 5), activation: str = 'relu', solver: str = 'adam', alpha: float = 0.0001, batch_size: int | str = 'auto', learning_rate: str = 'constant', learning_rate_init: float = 0.001, max_iter: int = 200, shuffle: bool = True, random_state: int | None = None, tol: float = 0.0001, verbose: bool = False, warm_start: bool = False, early_stopping: bool = False, validation_fraction: float = 0.1, beta_1: float = 0.9, beta_2: float = 0.999, epsilon: float = 1e-08, n_iter_no_change: int = 10)[source]

Bases: RegressionWorkflowBase

The automation workflow of using Multi-layer Perceptron algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Multi-layer Perceptron'
ray_tune(X_train: DataFrame, X_test: DataFrame, y_train: DataFrame, y_test: DataFrame) → None[source]

The customized MLP of the combinations of Ray, FLAML and Scikit-learn framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = ['Loss Curve Diagram']
class PolynomialRegression(degree: int = 2, interaction_only: bool = False, include_bias: bool = False, order: str = 'C', fit_intercept: bool = True, normalize: bool = False, copy_X: bool = True, n_jobs: int | None = None)[source]

Bases: LinearWorkflowMixin, RegressionWorkflowBase

The automation workflow of using Polynomial Regression algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Polynomial Regression'
poly(X_train: DataFrame, X_test: DataFrame) → Tuple[DataFrame, DataFrame][source]

Polynomial features.

special_components(**kwargs) → None[source]

Invoke all special application functions for this algorithms by Scikit-learn framework.

special_function = ['Polynomial Regression Formula']
class RandomForestRegression(n_estimators: int = 100, criterion: str = 'mse', max_depth: int | None = None, min_samples_split: int | float = 2, min_samples_leaf: int | float = 1, min_weight_fraction_leaf: float = 0.0, max_features: int | float = 'sqrt', max_leaf_nodes: int | None = None, min_impurity_decrease: float = 0.0, bootstrap: bool = True, oob_score: bool = False, n_jobs: int | None = None, random_state: int | None = None, verbose: int = 0, warm_start: bool = False, ccp_alpha: float = 0.0, max_samples: int | float | None = None)[source]

Bases: TreeWorkflowMixin, RegressionWorkflowBase

The automation workflow of using Random Forest algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Random Forest'
property settings: Dict

The configuration to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = ['Feature Importance Diagram', 'Single Tree Diagram']
class RegressionWorkflowBase[source]

Bases: WorkflowBase

The base workflow class of regression algorithms.

property auto_model: object

Get AutoML trained model by FLAML framework and RAY framework.

common_components

Dispatch methods based on type signature

See also

Dispatcher

common_function = ['Model Score', 'Cross Validation', 'Model Prediction', 'Model Persistence', 'Predicted vs. Actual Diagram', 'Residuals Diagram', 'Permutation Importance Diagram']
property customization: object

The customized model of FLAML framework.

fit

Dispatch methods based on type signature

See also

Dispatcher

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

predict

Dispatch methods based on type signature

See also

Dispatcher

ray_tune(X_train: DataFrame, X_test: DataFrame, y_train: DataFrame, y_test: DataFrame) → object[source]

The customized model of FLAML framework and RAY framework.

property settings: Dict

The configuration to implement AutoML by FLAML framework.

class RidgeRegression(alpha: float = 1.0, *, fit_intercept: bool = True, copy_X: bool = True, max_iter: int = 1000, tol: float = 0.0001, solver: str = 'auto', positive: bool = False, random_state: int | None = None)[source]

Bases: LinearWorkflowMixin, RegressionWorkflowBase

The automation workflow of using Lasso to make insightful products.

property customization: object

The customized Ridge of FLAML framework.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Ridge Regression'
property settings: Dict

The configuration of Ridge to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = ['Ridge Regression Formula', '2D Scatter Diagram', '3D Scatter Diagram', '2D Line Diagram', '3D Surface Diagram']
class SGDRegression(loss: str = 'squared_error', penalty: str = 'l2', alpha: float = 0.0001, l1_ratio: float = 0.15, fit_intercept: bool = True, max_iter: int = 1000, tol: float | None = 0.001, shuffle: bool = True, verbose: int = 0, epsilon: float = 0.1, random_state: int | None = None, learning_rate: str = 'invscaling', eta0: float = 0.01, power_t: float = 0.25, early_stopping: bool = False, validation_fraction: float = 0.1, n_iter_no_change: int = 5, warm_start: bool = False, average: bool | int = False)[source]

Bases: LinearWorkflowMixin, RegressionWorkflowBase

The automation workflow of using Stochastic Gradient Descent - SGD algorithm to make insightful products.

property customization: object

The customized SGD of FLAML framework.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'SGD Regression'
property settings: Dict

The configuration of SGD to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = ['SGD Regression Formula', '2D Scatter Diagram', '3D Scatter Diagram', '2D Line Diagram', '3D Surface Diagram']
class SVMRegression(kernel: str = 'rbf', degree: int = 3, gamma: str | float = 'scale', tol: float = 0.001, C: float = 1.0, epsilon: float = 0.1, shrinking: bool = True, cache_size: float = 200, verbose: bool = False, max_iter: int = -1)[source]

Bases: RegressionWorkflowBase

The automation workflow of using SVR algorithm to make insightful products.

property customization: object

The customized SVR of FLAML framework.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'Support Vector Machine'
property settings: Dict

The configuration of SVR to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = []
class XGBoostRegression(max_depth: int | None = 6, learning_rate: float | None = 0.3, n_estimators: int = 100, verbosity: int | None = 1, objective: str | Callable[[ndarray, ndarray], Tuple[ndarray, ndarray]] | None = None, booster: str | None = None, tree_method: str | None = 'auto', n_jobs: int | None = None, gamma: float | None = 0, min_child_weight: float | None = None, max_delta_step: float | None = 0, subsample: float | None = 1, colsample_bytree: float | None = 1, colsample_bylevel: float | None = 1, colsample_bynode: float | None = 1, reg_alpha: float | None = 0, reg_lambda: float | None = 1, scale_pos_weight: float | None = 1, base_score: float | None = None, random_state: RandomState | int | None = None, missing: float = nan, num_parallel_tree: int | None = 1, monotone_constraints: Dict[str, int] | str | None = None, interaction_constraints: str | Sequence[Sequence[str]] | None = None, importance_type: str | None = 'gain', gpu_id: int | None = None, validate_parameters: bool | None = None, predictor: str | None = None, eval_metric: str | List[str] | Callable | None = None, early_stopping_rounds: int | None = None, **kwargs: Any)[source]

Bases: TreeWorkflowMixin, RegressionWorkflowBase

The automation workflow of using XGBoost algorithm to make insightful products.

classmethod manual_hyper_parameters() → Dict[source]

Manual hyper-parameters specification.

name = 'XGBoost'
property settings: Dict

The configuration to implement AutoML by FLAML framework.

special_components

Dispatch methods based on type signature

See also

Dispatcher

special_function = ['Feature Importance Diagram']

Module contents

Geochemistrypy Wrapper interface for Scikit-Learn