Logistic Regression
- class snapml.LogisticRegression(max_iter=1000, regularizer=1.0, device_ids=[], verbose=False, use_gpu=False, class_weight=None, dual=True, n_jobs=1, penalty='l2', tol=0.001, generate_training_history=None, privacy=False, eta=0.3, batch_size=100, privacy_epsilon=10, grad_clip=1, fit_intercept=False, intercept_scaling=1.0, normalize=False, kernel='linear', gamma=1.0, n_components=100, random_state=None)
Logistic Regression classifier
This class implements regularized logistic regression using the IBM Snap ML solver. It supports both local and distributed(MPI) methods of the Snap ML solver. It can be used for both binary and multi-class classification problems. For multi-class classification it predicts only classes (no probabilities). It handles both dense and sparse matrix inputs. Use csr, csc, ndarray, deviceNDArray or SnapML data partition format for training and csr, ndarray or SnapML data partition format for prediction. DeviceNDArray input data format is currently not supported for training with MPI implementation. We recommend the user to first normalize the input values.
- Parameters
- max_iterint, default=1000
Maximum number of iterations used by the solver to converge.
- regularizerfloat, default=1.0
Regularization strength. It must be a positive float. Larger regularization values imply stronger regularization.
- use_gpubool, default=False
Flag for indicating the hardware platform used for training. If True, the training is performed using the GPU. If False, the training is performed using the CPU.
- device_idsarray-like of int, default=[]
If use_gpu is True, it indicates the IDs of the GPUs used for training. For single-GPU training, set device_ids to the GPU ID to be used for training, e.g., [0]. For multi-GPU training, set device_ids to a list of GPU IDs to be used for training, e.g., [0, 1].
- class_weight{‘balanced’, None}, default=None
If set to ‘None’, all classes will have weight 1.
- dualbool, default=True
Dual or primal formulation. Recommendation: if n_samples > n_features use dual=True.
- verbosebool, default=False
If True, it prints the training cost, one per iteration. Warning: this will increase the training time. For performance evaluation, use verbose=False.
- n_jobsint, default=1
The number of threads used for running the training. The value of this parameter should be a multiple of 32 if the training is performed on GPU (use_gpu=True).
- penalty{‘l1’, ‘l2’}, default=’l2’
The regularization / penalty type. Possible values are “l2” for L2 regularization (LogisticRegression) or “l1” for L1 regularization (SparseLogisticRegression). L1 regularization is possible only for the primal optimization problem (dual=False).
- tolfloat, default=0.001
The tolerance parameter. Training will finish when maximum change in model coefficients is less than tol.
- generate_training_history{‘summary’, ‘full’, None}, default=None
Determines the level of summary statistics that are generated during training. By default no information is generated (None), but this parameter can be set to “summary”, to obtain summary statistics at the end of training, or “full” to obtain a complete set of statistics for the entire training procedure. Note, enabling either option will result in slower training. generate_training_history is not supported for DeviceNDArray input format.
- privacybool, default=False
Train the model using a differentially private algorithm. Currently not supported for MPI implementation.
- etafloat, default=0.3
Learning rate for the differentially private training algorithm. Currently not supported for MPI implementation.
- batch_sizeint, default=100
Mini-batch size for the differentially private training algorithm. Currently not supported for MPI implementation.
- privacy_epsilonfloat, default=10.0
Target privacy gaurantee. Learned model will be (privacy_epsilon, 0.01)-private. Currently not supported for MPI implementation.
- grad_clipfloat, default=1.0
Gradient clipping parameter for the differentially private training algorithm. Currently not supported for MPI implementation.
- fit_interceptbool, default=False
Add bias term – note, may affect speed of convergence, especially for sparse datasets.
- intercept_scalingfloat, default=1.0
Scaling of bias term. The inclusion of a bias term is implemented by appending an additional feature to the dataset. This feature has a constant value, that can be set using this parameter.
- normalizebool, default=False
Normalize rows of dataset (recommended for fast convergence).
- kernel{‘rbf’, ‘linear’}, default=’linear’
Approximate feature map of a specified kernel function.
- gammafloat, default=1.0
Parameter of RBF kernel: exp(-gamma * x^2)
- n_componentsint, default=100
Dimensionality of the feature space when approximating a kernel function.
- random_stateint, or None, default=None
If int, random_state is the seed used by the random number generator; If None, the random number generator is the RandomState instance used by np.random.
- Attributes
- coef_array-like, shape (n_features, 1) for binary classification or
(n_features, n_classes) for multi-class classification. Coefficients of the features in the trained model.
- intercept_: ndarray of shape (1,) or (n_classes,)
Intercept (bias) added to the decision function. If fit_intercept is False, the intercept is set to zero. intercept_ is of shape (1,) when the given problem is binary.
- support_array-like
Indices of the features that contribute to the decision. (only available for L1) Currently not supported for MPI implementation.
- model_sparsity_float
fraction of non-zeros in the model parameters. (only available for L1) Currently not supported for MPI implementation.
- training_history_dict
Training history statistics.
- fit(X_train, y_train=None)
Fit the model according to the given train dataset.
- Parameters
- X_trainTrain dataset. Supports the following input data-types :
Sparse matrix (csr_matrix, csc_matrix) or dense matrix (ndarray)
DeviceNDArray. Not supported for MPI execution.
SnapML data partition of type DensePartition, SparsePartition or ConstantValueSparsePartition
- y_trainThe target corresponding to X_train.
If X_train is sparse matrix or dense matrix, y_train should be array-like of shape = (n_samples,) In case of deviceNDArray, y_train should be array-like of shape = (n_samples, 1) If X_train is SnapML data partition type, then y_train is not required (i.e. None).
- Returns
- selfobject
- get_params(deep=True)
Get parameters for this estimator.
- Parameters
- deepbool, default=True
If True, will return the parameters for this estimator and contained subobjects that are estimators.
- Returns
- paramsdict
Parameter names mapped to their values.
- predict(X, n_jobs=None)
Class predictions
The returned class estimates.
- Parameters
- XDataset used for predicting estimates or class. Supports the following input data-types :
Sparse matrix (csr_matrix, csc_matrix) or dense matrix (ndarray)
SnapML data partition of type DensePartition, SparsePartition or ConstantValueSparsePartition
- n_jobsint, default=None
Number of threads used to run inference. By default the value of the class attribute is used.. This parameter is ignored for predict of a single observation.
- Returns
- pred: array-like, shape = (n_samples,)
Returns the predicted estimate/class of the sample.
- predict_proba(X, n_jobs=None)
Probability estimates
The returned probability estimates for the two classes. Only for binary classification.
- Parameters
- XDataset used for predicting probability estimates. Supports the following input data-types :
Sparse matrix (csr_matrix, csc_matrix) or dense matrix (ndarray)
SnapML data partition of type DensePartition, SparsePartition or ConstantValueSparsePartition
- n_jobsint, defaultNone
Number of threads used to run inference. By default the value of the class attribute is used.. This parameter is ignored for predict_proba of a single observation.
- Returns
- proba: array-like of shape (n_samples, 2) or (n_samples, 1)
Probability of the sample of each of the two classes for local implementation. Probability of the positive class only for the MPI implementation.
- score(X, y, sample_weight=None)
Return the mean accuracy on the given test data and labels.
In multi-label classification, this is the subset accuracy which is a harsh metric since you require for each sample that each label set be correctly predicted.
- Parameters
- Xarray-like of shape (n_samples, n_features)
Test samples.
- yarray-like of shape (n_samples,) or (n_samples, n_outputs)
True labels for X.
- sample_weightarray-like of shape (n_samples,), default=None
Sample weights.
- Returns
- scorefloat
Mean accuracy of
self.predict(X)
wrt. y.
- set_params(**params)
Set the parameters of this model.
Valid parameter keys can be listed with
get_params()
.- Returns
- self