编写一个决策树算法代码
时间: 2024-05-10 08:14:12 浏览: 17
好的,下面是一个基本的决策树算法代码:
```python
import numpy as np
class DecisionTree:
def __init__(self, max_depth=5, min_samples_split=2):
self.max_depth = max_depth
self.min_samples_split = min_samples_split
def fit(self, X, y):
self.n_features_ = X.shape[1]
self.tree_ = self._grow_tree(X, y)
def predict(self, X):
return [self._predict(inputs) for inputs in X]
def _best_split(self, X, y):
m = y.size
if m <= 1:
return None, None
num_parent = [np.sum(y == c) for c in range(self.n_classes_)]
best_gini = 1.0 - sum((n / m) ** 2 for n in num_parent)
best_idx, best_thr = None, None
for idx in range(self.n_features_):
thresholds, classes = zip(*sorted(zip(X[:, idx], y)))
num_left = [0] * self.n_classes_
num_right = num_parent.copy()
for i in range(1, m):
c = classes[i - 1]
num_left[c] += 1
num_right[c] -= 1
gini_left = 1.0 - sum(
(num_left[x] / i) ** 2 for x in range(self.n_classes_)
)
gini_right = 1.0 - sum(
(num_right[x] / (m - i)) ** 2 for x in range(self.n_classes_)
)
gini = (i * gini_left + (m - i) * gini_right) / m
if thresholds[i] == thresholds[i - 1]:
continue
if gini < best_gini:
best_gini = gini
best_idx = idx
best_thr = (thresholds[i] + thresholds[i - 1]) / 2
return best_idx, best_thr
def _grow_tree(self, X, y, depth=0):
num_samples_per_class = [np.sum(y == i) for i in range(self.n_classes_)]
predicted_class = np.argmax(num_samples_per_class)
node = Node(
gini=1.0 - sum((np.sum(y == c) / y.size) ** 2 for c in range(self.n_classes_)),
num_samples=y.size,
num_samples_per_class=num_samples_per_class,
predicted_class=predicted_class,
)
if depth < self.max_depth and y.size >= self.min_samples_split:
idx, thr = self._best_split(X, y)
if idx is not None:
indices_left = X[:, idx] < thr
X_left, y_left = X[indices_left], y[indices_left]
X_right, y_right = X[~indices_left], y[~indices_left]
node.feature_index = idx
node.threshold = thr
node.left = self._grow_tree(X_left, y_left, depth + 1)
node.right = self._grow_tree(X_right, y_right, depth + 1)
return node
def _predict(self, inputs):
node = self.tree_
while node.left:
if inputs[node.feature_index] < node.threshold:
node = node.left
else:
node = node.right
return node.predicted_class
class Node:
def __init__(self, *, gini, num_samples, num_samples_per_class, predicted_class):
self.gini = gini
self.num_samples = num_samples
self.num_samples_per_class = num_samples_per_class
self.predicted_class = predicted_class
self.feature_index = 0
self.threshold = 0
self.left = None
self.right = None
```
这个代码实现了一个二叉决策树分类器,使用基尼不纯度作为分裂标准。您可以根据需要进行修改和扩展,例如使用其他不纯度度量或者实现回归决策树。