Model | The parameter settings |
---|---|
Decision Tree (DT) | criterion = “gini” # The function to measure the quality of a split, supported criteria # are “gini” for the Gini impurity splitter = “best” # The strategy used to choose the split at each node max_depth = None # The maximum depth of the tree min_samples_split = 2 # The minimum number of samples required to split an # internal node min_samples_leaf = 1 # The minimum number of samples required to be at a leaf # node min_weight_fraction_leaf = 0.0 # The minimum weighted fraction of the sum total # of weights required to be at a leaf node max_features = None # The number of features to consider when looking for the # best split random_state = None # It is the seed used by the random number generator max_leaf_nodes = None # Grow trees with max_leaf_nodes in best-first fashion, # if None then unlimited number of leaf nodes class_weight = None # Weights associated with classes, if not given, all classes are # supposed to have weight one presort = False # The data is not presorted |
support vector machine (SVM) | kernel = “rbf” # Specifies the kernel type to be used in the algorithm # “rbf” is Gaussian kernel function gamma = “auto” # Kernel coefficient for ‘rbf’ probability = True # Whether to enable probability estimates |
logistic regression (LR) | solver = “lbfgs” # The optimized algorithm is “lbfgs” multi_class = “auto” # Determines the multi-class strategy if y contains more than # two classes penalty = “l2” # Specifies the norm used in the penalization, the ‘l2’ penalty is the # standard used in SVC |
Random forest (RF) | n_estimators = 100 # The number of trees in the forest |