手写决策树算法，实现准确率、精度、召回率、F度量值

好的，以下是手写决策树算法的实现及评估指标的计算： ``` import pandas as pd import numpy as np class DecisionTree(): def __init__(self, criterion='gini', max_depth=None): self.criterion = criterion self.max_depth = max_depth def fit(self, X, y): self.classes = np.unique(y) self.tree = self._grow_tree(X, y) def predict(self, X): return np.array([self._predict(inputs, self.tree) 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 self.classes] best_gini = float('inf') best_idx, best_thr = None, None for idx in range(X.shape[1]): thresholds, classes = zip(*sorted(zip(X[:, idx], y))) num_left = [0] * len(self.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(len(self.classes))) gini_right = 1.0 - sum((num_right[x] / (m - i)) ** 2 for x in range(len(self.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 self.classes] predicted_class = np.argmax(num_samples_per_class) node = Node(predicted_class=predicted_class) if depth < self.max_depth: 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): if node.left is None and node.right is None: return node.predicted_class if inputs[node.feature_index] < node.threshold: return self._predict(inputs, node.left) return self._predict(inputs, node.right) class Node(): def __init__(self, feature_index=None, threshold=None, predicted_class=None): self.feature_index = feature_index self.threshold = threshold self.predicted_class = predicted_class self.left = None self.right = None def accuracy(y_true, y_pred): return np.mean(y_true == y_pred) def precision(y_true, y_pred): tp = np.sum((y_true == 1) & (y_pred == 1)) fp = np.sum((y_true == 0) & (y_pred == 1)) return tp / (tp + fp) def recall(y_true, y_pred): tp = np.sum((y_true == 1) & (y_pred == 1)) fn = np.sum((y_true == 1) & (y_pred == 0)) return tp / (tp + fn) def f1_score(y_true, y_pred): p = precision(y_true, y_pred) r = recall(y_true, y_pred) return 2 * p * r / (p + r) # 测试代码 data = pd.read_csv('data.csv') X = data.iloc[:, :-1].values y = data.iloc[:, -1].values tree = DecisionTree() tree.fit(X, y) y_pred = tree.predict(X) print('Accuracy: ', accuracy(y, y_pred)) print('Precision: ', precision(y, y_pred)) print('Recall: ', recall(y, y_pred)) print('F1 score: ', f1_score(y, y_pred)) ``` 其中，`DecisionTree` 类为决策树模型的实现，`Node` 类为树结点的实现，`accuracy`、`precision`、`recall`、`f1_score` 分别为准确率、精度、召回率、F度量值的计算函数。 运行代码后即可得到相应的评估指标结果。