104 lines
4.5 KiB
Cython
104 lines
4.5 KiB
Cython
|
# Authors: Gilles Louppe <g.louppe@gmail.com>
|
||
|
|
# Peter Prettenhofer <peter.prettenhofer@gmail.com>
|
||
|
|
# Brian Holt <bdholt1@gmail.com>
|
||
|
|
# Joel Nothman <joel.nothman@gmail.com>
|
||
|
|
# Arnaud Joly <arnaud.v.joly@gmail.com>
|
||
|
|
# Jacob Schreiber <jmschreiber91@gmail.com>
|
||
|
|
# Nelson Liu <nelson@nelsonliu.me>
|
||
|
|
#
|
||
|
|
# License: BSD 3 clause
|
||
|
|
|
||
|
|
# See _tree.pyx for details.
|
||
|
|
|
||
|
|
import numpy as np
|
||
|
|
cimport numpy as cnp
|
||
|
|
|
||
|
|
ctypedef cnp.npy_float32 DTYPE_t # Type of X
|
||
|
|
ctypedef cnp.npy_float64 DOUBLE_t # Type of y, sample_weight
|
||
|
|
ctypedef cnp.npy_intp SIZE_t # Type for indices and counters
|
||
|
|
ctypedef cnp.npy_int32 INT32_t # Signed 32 bit integer
|
||
|
|
ctypedef cnp.npy_uint32 UINT32_t # Unsigned 32 bit integer
|
||
|
|
|
||
|
|
from ._splitter cimport Splitter
|
||
|
|
from ._splitter cimport SplitRecord
|
||
|
|
|
||
|
|
cdef struct Node:
|
||
|
|
# Base storage structure for the nodes in a Tree object
|
||
|
|
|
||
|
|
SIZE_t left_child # id of the left child of the node
|
||
|
|
SIZE_t right_child # id of the right child of the node
|
||
|
|
SIZE_t feature # Feature used for splitting the node
|
||
|
|
DOUBLE_t threshold # Threshold value at the node
|
||
|
|
DOUBLE_t impurity # Impurity of the node (i.e., the value of the criterion)
|
||
|
|
SIZE_t n_node_samples # Number of samples at the node
|
||
|
|
DOUBLE_t weighted_n_node_samples # Weighted number of samples at the node
|
||
|
|
|
||
|
|
|
||
|
|
cdef class Tree:
|
||
|
|
# The Tree object is a binary tree structure constructed by the
|
||
|
|
# TreeBuilder. The tree structure is used for predictions and
|
||
|
|
# feature importances.
|
||
|
|
|
||
|
|
# Input/Output layout
|
||
|
|
cdef public SIZE_t n_features # Number of features in X
|
||
|
|
cdef SIZE_t* n_classes # Number of classes in y[:, k]
|
||
|
|
cdef public SIZE_t n_outputs # Number of outputs in y
|
||
|
|
cdef public SIZE_t max_n_classes # max(n_classes)
|
||
|
|
|
||
|
|
# Inner structures: values are stored separately from node structure,
|
||
|
|
# since size is determined at runtime.
|
||
|
|
cdef public SIZE_t max_depth # Max depth of the tree
|
||
|
|
cdef public SIZE_t node_count # Counter for node IDs
|
||
|
|
cdef public SIZE_t capacity # Capacity of tree, in terms of nodes
|
||
|
|
cdef Node* nodes # Array of nodes
|
||
|
|
cdef double* value # (capacity, n_outputs, max_n_classes) array of values
|
||
|
|
cdef SIZE_t value_stride # = n_outputs * max_n_classes
|
||
|
|
|
||
|
|
# Methods
|
||
|
|
cdef SIZE_t _add_node(self, SIZE_t parent, bint is_left, bint is_leaf,
|
||
|
|
SIZE_t feature, double threshold, double impurity,
|
||
|
|
SIZE_t n_node_samples,
|
||
|
|
double weighted_n_node_samples) nogil except -1
|
||
|
|
cdef int _resize(self, SIZE_t capacity) nogil except -1
|
||
|
|
cdef int _resize_c(self, SIZE_t capacity=*) nogil except -1
|
||
|
|
|
||
|
|
cdef cnp.ndarray _get_value_ndarray(self)
|
||
|
|
cdef cnp.ndarray _get_node_ndarray(self)
|
||
|
|
|
||
|
|
cpdef cnp.ndarray predict(self, object X)
|
||
|
|
|
||
|
|
cpdef cnp.ndarray apply(self, object X)
|
||
|
|
cdef cnp.ndarray _apply_dense(self, object X)
|
||
|
|
cdef cnp.ndarray _apply_sparse_csr(self, object X)
|
||
|
|
|
||
|
|
cpdef object decision_path(self, object X)
|
||
|
|
cdef object _decision_path_dense(self, object X)
|
||
|
|
cdef object _decision_path_sparse_csr(self, object X)
|
||
|
|
|
||
|
|
cpdef compute_feature_importances(self, normalize=*)
|
||
|
|
|
||
|
|
|
||
|
|
# =============================================================================
|
||
|
|
# Tree builder
|
||
|
|
# =============================================================================
|
||
|
|
|
||
|
|
cdef class TreeBuilder:
|
||
|
|
# The TreeBuilder recursively builds a Tree object from training samples,
|
||
|
|
# using a Splitter object for splitting internal nodes and assigning
|
||
|
|
# values to leaves.
|
||
|
|
#
|
||
|
|
# This class controls the various stopping criteria and the node splitting
|
||
|
|
# evaluation order, e.g. depth-first or best-first.
|
||
|
|
|
||
|
|
cdef Splitter splitter # Splitting algorithm
|
||
|
|
|
||
|
|
cdef SIZE_t min_samples_split # Minimum number of samples in an internal node
|
||
|
|
cdef SIZE_t min_samples_leaf # Minimum number of samples in a leaf
|
||
|
|
cdef double min_weight_leaf # Minimum weight in a leaf
|
||
|
|
cdef SIZE_t max_depth # Maximal tree depth
|
||
|
|
cdef double min_impurity_decrease # Impurity threshold for early stopping
|
||
|
|
|
||
|
|
cpdef build(self, Tree tree, object X, cnp.ndarray y,
|
||
|
|
cnp.ndarray sample_weight=*)
|
||
|
|
cdef _check_input(self, object X, cnp.ndarray y, cnp.ndarray sample_weight)
|