{"flow":{"id":"18870","uploader":"6691","name":"sklearn.linear_model.logistic.LogisticRegression","custom_name":"sklearn.LogisticRegression","class_name":"sklearn.linear_model.logistic.LogisticRegression","version":"36","external_version":"openml==0.12.2,sklearn==0.18.1","description":"Logistic Regression (aka logit, MaxEnt) classifier.\n\nIn the multiclass case, the training algorithm uses the one-vs-rest (OvR)\nscheme if the 'multi_class' option is set to 'ovr', and uses the cross-\nentropy loss if the 'multi_class' option is set to 'multinomial'.\n(Currently the 'multinomial' option is supported only by the 'lbfgs',\n'sag' and 'newton-cg' solvers.)\n\nThis class implements regularized logistic regression using the\n'liblinear' library, 'newton-cg', 'sag' and 'lbfgs' solvers. It can handle\nboth dense and sparse input. Use C-ordered arrays or CSR matrices\ncontaining 64-bit floats for optimal performance; any other input format\nwill be converted (and copied).\n\nThe 'newton-cg', 'sag', and 'lbfgs' solvers support only L2 regularization\nwith primal formulation. The 'liblinear' solver supports both L1 and L2\nregularization, with a dual formulation only for the L2 penalty.","upload_date":"2021-08-13T19:19:20","language":"English","dependencies":"sklearn==0.18.1\nnumpy>=1.6.1\nscipy>=0.9","parameter":[{"name":"C","data_type":"float","default_value":"1.0","description":"Inverse of regularization strength; must be a positive float\n Like in support vector machines, smaller values specify stronger\n regularization"},{"name":"class_weight","data_type":"dict or","default_value":"null","description":"Weights associated with classes in the form ``{class_label: weight}``\n If not given, all classes are supposed to have weight one\n\n The \"balanced\" mode uses the values of y to automatically adjust\n weights inversely proportional to class frequencies in the input data\n as ``n_samples \/ (n_classes * np.bincount(y))``\n\n Note that these weights will be multiplied with sample_weight (passed\n through the fit method) if sample_weight is specified\n\n .. versionadded:: 0.17\n *class_weight='balanced'* instead of deprecated\n *class_weight='auto'*"},{"name":"dual","data_type":"bool","default_value":"false","description":"Dual or primal formulation. Dual formulation is only implemented for\n l2 penalty with liblinear solver. Prefer dual=False when\n n_samples > n_features"},{"name":"fit_intercept","data_type":"bool","default_value":"true","description":"Specifies if a constant (a.k.a. bias or intercept) should be\n added to the decision function"},{"name":"intercept_scaling","data_type":"float","default_value":"1","description":"Useful only when the solver 'liblinear' is used\n and self.fit_intercept is set to True. In this case, x becomes\n [x, self.intercept_scaling],\n i.e. a \"synthetic\" feature with constant value equal to\n intercept_scaling is appended to the instance vector\n The intercept becomes ``intercept_scaling * synthetic_feature_weight``\n\n Note! the synthetic feature weight is subject to l1\/l2 regularization\n as all other features\n To lessen the effect of regularization on synthetic feature weight\n (and therefore on the intercept) intercept_scaling has to be increased"},{"name":"max_iter","data_type":"int","default_value":"100","description":"Useful only for the newton-cg, sag and lbfgs solvers\n Maximum number of iterations taken for the solvers to converge"},{"name":"multi_class","data_type":"str","default_value":"\"ovr\"","description":"Multiclass option can be either 'ovr' or 'multinomial'. If the option\n chosen is 'ovr', then a binary problem is fit for each label. Else\n the loss minimised is the multinomial loss fit across\n the entire probability distribution. Works only for the 'newton-cg',\n 'sag' and 'lbfgs' solver\n\n .. versionadded:: 0.18\n Stochastic Average Gradient descent solver for 'multinomial' case"},{"name":"n_jobs","data_type":"int","default_value":"1","description":"Number of CPU cores used during the cross-validation loop. If given\n a value of -1, all cores are used."},{"name":"penalty","data_type":"str","default_value":"\"l2\"","description":"Used to specify the norm used in the penalization. The 'newton-cg',\n 'sag' and 'lbfgs' solvers support only l2 penalties"},{"name":"random_state","data_type":"int seed","default_value":"null","description":"The seed of the pseudo random number generator to use when\n shuffling the data. Used only in solvers 'sag' and 'liblinear'\n\nsolver : {'newton-cg', 'lbfgs', 'liblinear', 'sag'}, default: 'liblinear'\n Algorithm to use in the optimization problem\n\n - For small datasets, 'liblinear' is a good choice, whereas 'sag' is\n faster for large ones\n - For multiclass problems, only 'newton-cg', 'sag' and 'lbfgs' handle\n multinomial loss; 'liblinear' is limited to one-versus-rest\n schemes\n - 'newton-cg', 'lbfgs' and 'sag' only handle L2 penalty\n\n Note that 'sag' fast convergence is only guaranteed on features with\n approximately the same scale. You can preprocess the data with a\n scaler from sklearn.preprocessing\n\n .. versionadded:: 0.17\n Stochastic Average Gradient descent solver"},{"name":"solver","data_type":[],"default_value":"\"liblinear\"","description":[]},{"name":"tol","data_type":"float","default_value":"0.0001","description":"Tolerance for stopping criteria"},{"name":"verbose","data_type":"int","default_value":"0","description":"For the liblinear and lbfgs solvers set verbose to any positive\n number for verbosity"},{"name":"warm_start","data_type":"bool","default_value":"false","description":"When set to True, reuse the solution of the previous call to fit as\n initialization, otherwise, just erase the previous solution\n Useless for liblinear solver\n\n .. versionadded:: 0.17\n *warm_start* to support *lbfgs*, *newton-cg*, *sag* solvers"}],"tag":["openml-python","python","scikit-learn","sklearn","sklearn_0.18.1"]}}