{
  "sklearn_version": "1.4.2",
  "models": {
    "logistic_regression": [
      {
        "name": "penalty",
        "label": "Penalty",
        "description": "Specify the norm of the penalty:",
        "kind": "mixed",
        "options": [
          {
            "value": "elasticnet",
            "label": "elasticnet"
          },
          {
            "value": "l1",
            "label": "l1"
          },
          {
            "value": "l2",
            "label": "l2"
          },
          {
            "value": null,
            "label": "None"
          }
        ],
        "default": "l2"
      },
      {
        "name": "dual",
        "label": "Dual",
        "description": "Dual (constrained) or primal (regularized, see also this equation) formulation.",
        "kind": "boolean",
        "default": false
      },
      {
        "name": "tol",
        "label": "Tol",
        "description": "Tolerance for stopping criteria.",
        "kind": "number",
        "min": 0,
        "default": 0.0001
      },
      {
        "name": "C",
        "label": "C",
        "description": "Inverse of regularization strength; must be a positive float.",
        "kind": "number",
        "min": 0,
        "minExclusive": true,
        "default": 1.0
      },
      {
        "name": "fit_intercept",
        "label": "Fit intercept",
        "description": "Specifies if a constant (a.k.a. bias or intercept) should be added to the decision function.",
        "kind": "boolean",
        "default": true
      },
      {
        "name": "intercept_scaling",
        "label": "Intercept scaling",
        "description": "Useful only when the solver 'liblinear' is used and self.fit_intercept is set to True.",
        "kind": "number",
        "min": 0,
        "minExclusive": true,
        "default": 1
      },
      {
        "name": "class_weight",
        "label": "Class weight",
        "description": "Weights associated with classes in the form {class_label: weight}.",
        "kind": "mixed",
        "options": [
          {
            "value": "balanced",
            "label": "balanced"
          },
          {
            "value": null,
            "label": "None"
          }
        ],
        "default": null
      },
      {
        "name": "random_state",
        "label": "Random state",
        "description": "Used when solver == 'sag', 'saga' or 'liblinear' to shuffle the data.",
        "kind": "integer",
        "min": 0,
        "max": 4294967295,
        "nullable": "None",
        "default": null
      },
      {
        "name": "solver",
        "label": "Solver",
        "description": "Algorithm to use in the optimization problem.",
        "kind": "choice",
        "options": [
          {
            "value": "lbfgs",
            "label": "lbfgs"
          },
          {
            "value": "liblinear",
            "label": "liblinear"
          },
          {
            "value": "newton-cg",
            "label": "newton-cg"
          },
          {
            "value": "newton-cholesky",
            "label": "newton-cholesky"
          },
          {
            "value": "sag",
            "label": "sag"
          },
          {
            "value": "saga",
            "label": "saga"
          }
        ],
        "default": "lbfgs"
      },
      {
        "name": "max_iter",
        "label": "Max iter",
        "description": "Maximum number of iterations taken for the solvers to converge.",
        "kind": "integer",
        "min": 0,
        "default": 100
      },
      {
        "name": "l1_ratio",
        "label": "L1 ratio",
        "description": "The Elastic-Net mixing parameter, with 0 <= l1_ratio <= 1.",
        "kind": "number",
        "min": 0,
        "max": 1,
        "nullable": "None",
        "default": null
      }
    ],
    "knn": [
      {
        "name": "n_neighbors",
        "label": "N neighbors",
        "description": "Number of neighbors to use by default for kneighbors queries.",
        "kind": "integer",
        "min": 1,
        "nullable": "None",
        "default": 5
      },
      {
        "name": "algorithm",
        "label": "Algorithm",
        "description": "Algorithm used to compute the nearest neighbors:",
        "kind": "choice",
        "options": [
          {
            "value": "auto",
            "label": "auto"
          },
          {
            "value": "ball_tree",
            "label": "ball_tree"
          },
          {
            "value": "brute",
            "label": "brute"
          },
          {
            "value": "kd_tree",
            "label": "kd_tree"
          }
        ],
        "default": "auto"
      },
      {
        "name": "leaf_size",
        "label": "Leaf size",
        "description": "Leaf size passed to BallTree or KDTree.",
        "kind": "integer",
        "min": 1,
        "default": 30
      },
      {
        "name": "p",
        "label": "p",
        "description": "Power parameter for the Minkowski metric.",
        "kind": "number",
        "min": 0,
        "minExclusive": true,
        "nullable": "None",
        "default": 2
      },
      {
        "name": "metric",
        "label": "Metric",
        "description": "Metric to use for distance computation.",
        "kind": "choice",
        "options": [
          {
            "value": "braycurtis",
            "label": "braycurtis"
          },
          {
            "value": "canberra",
            "label": "canberra"
          },
          {
            "value": "chebyshev",
            "label": "chebyshev"
          },
          {
            "value": "cityblock",
            "label": "cityblock"
          },
          {
            "value": "correlation",
            "label": "correlation"
          },
          {
            "value": "cosine",
            "label": "cosine"
          },
          {
            "value": "dice",
            "label": "dice"
          },
          {
            "value": "euclidean",
            "label": "euclidean"
          },
          {
            "value": "hamming",
            "label": "hamming"
          },
          {
            "value": "haversine",
            "label": "haversine"
          },
          {
            "value": "infinity",
            "label": "infinity"
          },
          {
            "value": "jaccard",
            "label": "jaccard"
          },
          {
            "value": "l1",
            "label": "l1"
          },
          {
            "value": "l2",
            "label": "l2"
          },
          {
            "value": "mahalanobis",
            "label": "mahalanobis"
          },
          {
            "value": "manhattan",
            "label": "manhattan"
          },
          {
            "value": "minkowski",
            "label": "minkowski"
          },
          {
            "value": "nan_euclidean",
            "label": "nan_euclidean"
          },
          {
            "value": "p",
            "label": "p"
          },
          {
            "value": "pyfunc",
            "label": "pyfunc"
          },
          {
            "value": "rogerstanimoto",
            "label": "rogerstanimoto"
          },
          {
            "value": "russellrao",
            "label": "russellrao"
          },
          {
            "value": "seuclidean",
            "label": "seuclidean"
          },
          {
            "value": "sokalmichener",
            "label": "sokalmichener"
          },
          {
            "value": "sokalsneath",
            "label": "sokalsneath"
          },
          {
            "value": "sqeuclidean",
            "label": "sqeuclidean"
          },
          {
            "value": "yule",
            "label": "yule"
          }
        ],
        "default": "minkowski"
      },
      {
        "name": "weights",
        "label": "Weights",
        "description": "Weight function used in prediction.",
        "kind": "mixed",
        "options": [
          {
            "value": "distance",
            "label": "distance"
          },
          {
            "value": "uniform",
            "label": "uniform"
          },
          {
            "value": null,
            "label": "None"
          }
        ],
        "default": "uniform"
      }
    ],
    "svm": [
      {
        "name": "kernel",
        "label": "Kernel",
        "description": "Specifies the kernel type to be used in the algorithm.",
        "kind": "choice",
        "options": [
          {
            "value": "linear",
            "label": "linear"
          },
          {
            "value": "poly",
            "label": "poly"
          },
          {
            "value": "rbf",
            "label": "rbf"
          },
          {
            "value": "sigmoid",
            "label": "sigmoid"
          }
        ],
        "default": "rbf"
      },
      {
        "name": "degree",
        "label": "Degree",
        "description": "Degree of the polynomial kernel function ('poly').",
        "kind": "integer",
        "min": 0,
        "default": 3
      },
      {
        "name": "gamma",
        "label": "Gamma",
        "description": "Kernel coefficient for 'rbf', 'poly' and 'sigmoid'.",
        "kind": "mixed",
        "options": [
          {
            "value": "auto",
            "label": "auto"
          },
          {
            "value": "scale",
            "label": "scale"
          }
        ],
        "number": {
          "integer": false,
          "min": 0.0
        },
        "default": "scale"
      },
      {
        "name": "coef0",
        "label": "Coef0",
        "description": "Independent term in kernel function.",
        "kind": "number",
        "default": 0.0
      },
      {
        "name": "tol",
        "label": "Tol",
        "description": "Tolerance for stopping criterion.",
        "kind": "number",
        "min": 0.0,
        "minExclusive": true,
        "default": 0.001
      },
      {
        "name": "C",
        "label": "C",
        "description": "Regularization parameter.",
        "kind": "number",
        "min": 0.0,
        "minExclusive": true,
        "default": 1.0
      },
      {
        "name": "shrinking",
        "label": "Shrinking",
        "description": "Whether to use the shrinking heuristic.",
        "kind": "boolean",
        "default": true
      },
      {
        "name": "probability",
        "label": "Probability",
        "description": "Whether to enable probability estimates.",
        "kind": "boolean",
        "default": false
      },
      {
        "name": "cache_size",
        "label": "Cache size",
        "description": "Specify the size of the kernel cache (in MB).",
        "kind": "number",
        "min": 0,
        "minExclusive": true,
        "default": 200
      },
      {
        "name": "class_weight",
        "label": "Class weight",
        "description": "Set the parameter C of class i to class_weight[i]*C for SVC.",
        "kind": "mixed",
        "options": [
          {
            "value": "balanced",
            "label": "balanced"
          },
          {
            "value": null,
            "label": "None"
          }
        ],
        "default": null
      },
      {
        "name": "max_iter",
        "label": "Max iter",
        "description": "Hard limit on iterations within solver, or -1 for no limit.",
        "kind": "integer",
        "min": -1,
        "default": -1
      },
      {
        "name": "random_state",
        "label": "Random state",
        "description": "Controls the pseudo random number generation for shuffling the data for probability estimates.",
        "kind": "integer",
        "min": 0,
        "max": 4294967295,
        "nullable": "None",
        "default": null
      },
      {
        "name": "decision_function_shape",
        "label": "Decision function shape",
        "description": "Whether to return a one-vs-rest ('ovr') decision function of shape (n_samples, n_classes) as all other classifiers, or the original one-vs-one ('ovo') decision function of libsvm which has shape (n_samples, n_classes * (n_classes - 1) / 2).",
        "kind": "choice",
        "options": [
          {
            "value": "ovo",
            "label": "ovo"
          },
          {
            "value": "ovr",
            "label": "ovr"
          }
        ],
        "default": "ovr"
      },
      {
        "name": "break_ties",
        "label": "Break ties",
        "description": "If true, decision_function_shape='ovr', and number of classes > 2, predict will break ties according to the confidence values of decision_function; otherwise the first class among the tied classes is returned.",
        "kind": "boolean",
        "default": false
      }
    ],
    "decision_tree": [
      {
        "name": "splitter",
        "label": "Splitter",
        "description": "The strategy used to choose the split at each node.",
        "kind": "choice",
        "options": [
          {
            "value": "best",
            "label": "best"
          },
          {
            "value": "random",
            "label": "random"
          }
        ],
        "default": "best"
      },
      {
        "name": "max_depth",
        "label": "Max depth",
        "description": "The maximum depth of the tree.",
        "kind": "integer",
        "min": 1,
        "nullable": "None",
        "default": null
      },
      {
        "name": "min_samples_split",
        "label": "Min samples split",
        "description": "The minimum number of samples required to split an internal node:",
        "kind": "number",
        "min": 0.0,
        "minExclusive": true,
        "default": 2
      },
      {
        "name": "min_samples_leaf",
        "label": "Min samples leaf",
        "description": "The minimum number of samples required to be at a leaf node.",
        "kind": "number",
        "min": 0.0,
        "minExclusive": true,
        "default": 1
      },
      {
        "name": "min_weight_fraction_leaf",
        "label": "Min weight fraction leaf",
        "description": "The minimum weighted fraction of the sum total of weights (of all the input samples) required to be at a leaf node.",
        "kind": "number",
        "min": 0.0,
        "max": 0.5,
        "default": 0.0
      },
      {
        "name": "max_features",
        "label": "Max features",
        "description": "The number of features to consider when looking for the best split:",
        "kind": "mixed",
        "options": [
          {
            "value": "log2",
            "label": "log2"
          },
          {
            "value": "sqrt",
            "label": "sqrt"
          },
          {
            "value": null,
            "label": "None"
          }
        ],
        "number": {
          "integer": false,
          "min": 0.0,
          "minExclusive": true
        },
        "default": null
      },
      {
        "name": "random_state",
        "label": "Random state",
        "description": "Controls the randomness of the estimator.",
        "kind": "integer",
        "min": 0,
        "max": 4294967295,
        "nullable": "None",
        "default": null
      },
      {
        "name": "max_leaf_nodes",
        "label": "Max leaf nodes",
        "description": "Grow a tree with max_leaf_nodes in best-first fashion.",
        "kind": "integer",
        "min": 2,
        "nullable": "None",
        "default": null
      },
      {
        "name": "min_impurity_decrease",
        "label": "Min impurity decrease",
        "description": "A node will be split if this split induces a decrease of the impurity greater than or equal to this value.",
        "kind": "number",
        "min": 0.0,
        "default": 0.0
      },
      {
        "name": "ccp_alpha",
        "label": "Ccp alpha",
        "description": "Complexity parameter used for Minimal Cost-Complexity Pruning.",
        "kind": "number",
        "min": 0.0,
        "default": 0.0
      },
      {
        "name": "criterion",
        "label": "Criterion",
        "description": "The function to measure the quality of a split.",
        "kind": "choice",
        "options": [
          {
            "value": "entropy",
            "label": "entropy"
          },
          {
            "value": "gini",
            "label": "gini"
          },
          {
            "value": "log_loss",
            "label": "log_loss"
          }
        ],
        "default": "gini"
      },
      {
        "name": "class_weight",
        "label": "Class weight",
        "description": "Weights associated with classes in the form {class_label: weight}.",
        "kind": "mixed",
        "options": [
          {
            "value": "balanced",
            "label": "balanced"
          },
          {
            "value": null,
            "label": "None"
          }
        ],
        "default": null
      }
    ],
    "random_forest": [
      {
        "name": "n_estimators",
        "label": "N estimators",
        "description": "The number of trees in the forest.",
        "kind": "integer",
        "min": 1,
        "default": 100
      },
      {
        "name": "bootstrap",
        "label": "Bootstrap",
        "description": "Whether bootstrap samples are used when building trees.",
        "kind": "boolean",
        "default": true
      },
      {
        "name": "oob_score",
        "label": "Oob score",
        "description": "Whether to use out-of-bag samples to estimate the generalization score.",
        "kind": "boolean",
        "default": false
      },
      {
        "name": "random_state",
        "label": "Random state",
        "description": "Controls both the randomness of the bootstrapping of the samples used when building trees (if bootstrap=True) and the sampling of the features to consider when looking for the best split at each node (if max_features < n_features).",
        "kind": "integer",
        "min": 0,
        "max": 4294967295,
        "nullable": "None",
        "default": null
      },
      {
        "name": "max_samples",
        "label": "Max samples",
        "description": "If bootstrap is True, the number of samples to draw from X to train each base estimator.",
        "kind": "number",
        "min": 0.0,
        "minExclusive": true,
        "nullable": "None",
        "default": null
      },
      {
        "name": "max_depth",
        "label": "Max depth",
        "description": "The maximum depth of the tree.",
        "kind": "integer",
        "min": 1,
        "nullable": "None",
        "default": null
      },
      {
        "name": "min_samples_split",
        "label": "Min samples split",
        "description": "The minimum number of samples required to split an internal node:",
        "kind": "number",
        "min": 0.0,
        "minExclusive": true,
        "default": 2
      },
      {
        "name": "min_samples_leaf",
        "label": "Min samples leaf",
        "description": "The minimum number of samples required to be at a leaf node.",
        "kind": "number",
        "min": 0.0,
        "minExclusive": true,
        "default": 1
      },
      {
        "name": "min_weight_fraction_leaf",
        "label": "Min weight fraction leaf",
        "description": "The minimum weighted fraction of the sum total of weights (of all the input samples) required to be at a leaf node.",
        "kind": "number",
        "min": 0.0,
        "max": 0.5,
        "default": 0.0
      },
      {
        "name": "max_features",
        "label": "Max features",
        "description": "The number of features to consider when looking for the best split:",
        "kind": "mixed",
        "options": [
          {
            "value": "log2",
            "label": "log2"
          },
          {
            "value": "sqrt",
            "label": "sqrt"
          },
          {
            "value": null,
            "label": "None"
          }
        ],
        "number": {
          "integer": false,
          "min": 0.0,
          "minExclusive": true
        },
        "default": "sqrt"
      },
      {
        "name": "max_leaf_nodes",
        "label": "Max leaf nodes",
        "description": "Grow trees with max_leaf_nodes in best-first fashion.",
        "kind": "integer",
        "min": 2,
        "nullable": "None",
        "default": null
      },
      {
        "name": "min_impurity_decrease",
        "label": "Min impurity decrease",
        "description": "A node will be split if this split induces a decrease of the impurity greater than or equal to this value.",
        "kind": "number",
        "min": 0.0,
        "default": 0.0
      },
      {
        "name": "ccp_alpha",
        "label": "Ccp alpha",
        "description": "Complexity parameter used for Minimal Cost-Complexity Pruning.",
        "kind": "number",
        "min": 0.0,
        "default": 0.0
      },
      {
        "name": "criterion",
        "label": "Criterion",
        "description": "The function to measure the quality of a split.",
        "kind": "choice",
        "options": [
          {
            "value": "entropy",
            "label": "entropy"
          },
          {
            "value": "gini",
            "label": "gini"
          },
          {
            "value": "log_loss",
            "label": "log_loss"
          }
        ],
        "default": "gini"
      },
      {
        "name": "class_weight",
        "label": "Class weight",
        "description": "Weights associated with classes in the form {class_label: weight}.",
        "kind": "mixed",
        "options": [
          {
            "value": "balanced",
            "label": "balanced"
          },
          {
            "value": "balanced_subsample",
            "label": "balanced_subsample"
          },
          {
            "value": null,
            "label": "None"
          }
        ],
        "default": null
      }
    ],
    "gradient_boosting": [
      {
        "name": "max_depth",
        "label": "Max depth",
        "description": "Maximum depth of the individual regression estimators.",
        "kind": "integer",
        "min": 1,
        "nullable": "None",
        "default": 3
      },
      {
        "name": "min_samples_split",
        "label": "Min samples split",
        "description": "The minimum number of samples required to split an internal node:",
        "kind": "number",
        "min": 0.0,
        "minExclusive": true,
        "default": 2
      },
      {
        "name": "min_samples_leaf",
        "label": "Min samples leaf",
        "description": "The minimum number of samples required to be at a leaf node.",
        "kind": "number",
        "min": 0.0,
        "minExclusive": true,
        "default": 1
      },
      {
        "name": "min_weight_fraction_leaf",
        "label": "Min weight fraction leaf",
        "description": "The minimum weighted fraction of the sum total of weights (of all the input samples) required to be at a leaf node.",
        "kind": "number",
        "min": 0.0,
        "max": 0.5,
        "default": 0.0
      },
      {
        "name": "max_features",
        "label": "Max features",
        "description": "The number of features to consider when looking for the best split:",
        "kind": "mixed",
        "options": [
          {
            "value": "log2",
            "label": "log2"
          },
          {
            "value": "sqrt",
            "label": "sqrt"
          },
          {
            "value": null,
            "label": "None"
          }
        ],
        "number": {
          "integer": false,
          "min": 0.0,
          "minExclusive": true
        },
        "default": null
      },
      {
        "name": "random_state",
        "label": "Random state",
        "description": "Controls the random seed given to each Tree estimator at each boosting iteration.",
        "kind": "integer",
        "min": 0,
        "max": 4294967295,
        "nullable": "None",
        "default": null
      },
      {
        "name": "max_leaf_nodes",
        "label": "Max leaf nodes",
        "description": "Grow trees with max_leaf_nodes in best-first fashion.",
        "kind": "integer",
        "min": 2,
        "nullable": "None",
        "default": null
      },
      {
        "name": "min_impurity_decrease",
        "label": "Min impurity decrease",
        "description": "A node will be split if this split induces a decrease of the impurity greater than or equal to this value.",
        "kind": "number",
        "min": 0.0,
        "default": 0.0
      },
      {
        "name": "ccp_alpha",
        "label": "Ccp alpha",
        "description": "Complexity parameter used for Minimal Cost-Complexity Pruning.",
        "kind": "number",
        "min": 0.0,
        "default": 0.0
      },
      {
        "name": "criterion",
        "label": "Criterion",
        "description": "The function to measure the quality of a split.",
        "kind": "choice",
        "options": [
          {
            "value": "friedman_mse",
            "label": "friedman_mse"
          },
          {
            "value": "squared_error",
            "label": "squared_error"
          }
        ],
        "default": "friedman_mse"
      },
      {
        "name": "learning_rate",
        "label": "Learning rate",
        "description": "Learning rate shrinks the contribution of each tree by learning_rate.",
        "kind": "number",
        "min": 0.0,
        "default": 0.1
      },
      {
        "name": "n_estimators",
        "label": "N estimators",
        "description": "The number of boosting stages to perform.",
        "kind": "integer",
        "min": 1,
        "default": 100
      },
      {
        "name": "subsample",
        "label": "Subsample",
        "description": "The fraction of samples to be used for fitting the individual base learners.",
        "kind": "number",
        "min": 0.0,
        "minExclusive": true,
        "max": 1.0,
        "default": 1.0
      },
      {
        "name": "validation_fraction",
        "label": "Validation fraction",
        "description": "The proportion of training data to set aside as validation set for early stopping.",
        "kind": "number",
        "min": 0.0,
        "minExclusive": true,
        "max": 1.0,
        "maxExclusive": true,
        "default": 0.1
      },
      {
        "name": "n_iter_no_change",
        "label": "N iter no change",
        "description": "n_iter_no_change is used to decide if early stopping will be used to terminate training when validation score is not improving.",
        "kind": "integer",
        "min": 1,
        "nullable": "None",
        "default": null
      },
      {
        "name": "tol",
        "label": "Tol",
        "description": "Tolerance for the early stopping.",
        "kind": "number",
        "min": 0.0,
        "default": 0.0001
      },
      {
        "name": "loss",
        "label": "Loss",
        "description": "The loss function to be optimized. 'log_loss' refers to binomial and multinomial deviance, the same as used in logistic regression.",
        "kind": "choice",
        "options": [
          {
            "value": "exponential",
            "label": "exponential"
          },
          {
            "value": "log_loss",
            "label": "log_loss"
          }
        ],
        "default": "log_loss"
      },
      {
        "name": "init",
        "label": "Init",
        "description": "An estimator object that is used to compute the initial predictions. init has to provide fit and predict_proba.",
        "kind": "mixed",
        "options": [
          {
            "value": "zero",
            "label": "zero"
          },
          {
            "value": null,
            "label": "None"
          }
        ],
        "default": null
      }
    ]
  }
}