Numpy实现RandomForest

from __future__ import division, print_function
import numpy as np
import math
import progressbar

# Import helper functions
from mlfromscratch.utils import divide_on_feature, train_test_split, get_random_subsets, normalize
from mlfromscratch.utils import accuracy_score, calculate_entropy
from mlfromscratch.unsupervised_learning import PCA
from mlfromscratch.supervised_learning import ClassificationTree
from mlfromscratch.utils.misc import bar_widgets
from mlfromscratch.utils import Plot


class RandomForest():
    """Random Forest classifier. Uses a collection of classification trees that
    trains on random subsets of the data using a random subsets of the features.

    Parameters:
    -----------
    n_estimators: int
        The number of classification trees that are used.
    max_features: int
        The maximum number of features that the classification trees are allowed to
        use.
    min_samples_split: int
        The minimum number of samples needed to make a split when building a tree.
    min_gain: float
        The minimum impurity required to split the tree further. 
    max_depth: int
        The maximum depth of a tree.
    """
    def __init__(self, n_estimators=100, max_features=None, min_samples_split=2,
                 min_gain=0, max_depth=float("inf")):
        self.n_estimators = n_estimators    # Number of trees
        self.max_features = max_features    # Maxmimum number of features per tree
        self.min_samples_split = min_samples_split
        self.min_gain = min_gain            # Minimum information gain req. to continue
        self.max_depth = max_depth          # Maximum depth for tree
        self.progressbar = progressbar.ProgressBar(widgets=bar_widgets)

        # Initialize decision trees
        self.trees = []
        for _ in range(n_estimators):
            self.trees.append(
                ClassificationTree(
                    min_samples_split=self.min_samples_split,
                    min_impurity=min_gain,
                    max_depth=self.max_depth))

    def fit(self, X, y):
        n_features = np.shape(X)[1]
        # If max_features have not been defined => select it as
        # sqrt(n_features)
        if not self.max_features:
            self.max_features = int(math.sqrt(n_features))

        # Choose one random subset of the data for each tree
        subsets = get_random_subsets(X, y, self.n_estimators)

        for i in self.progressbar(range(self.n_estimators)):
            X_subset, y_subset = subsets[i]
            # Feature bagging (select random subsets of the features)
            idx = np.random.choice(range(n_features), size=self.max_features, replace=True)
            # Save the indices of the features for prediction
            self.trees[i].feature_indices = idx
            # Choose the features corresponding to the indices
            X_subset = X_subset[:, idx]
            # Fit the tree to the data
            self.trees[i].fit(X_subset, y_subset)

    def predict(self, X):
        y_preds = np.empty((X.shape[0], len(self.trees)))
        # Let each tree make a prediction on the data
        for i, tree in enumerate(self.trees):
            # Indices of the features that the tree has trained on
            idx = tree.feature_indices
            # Make a prediction based on those features
            prediction = tree.predict(X[:, idx])
            y_preds[:, i] = prediction
            
        y_pred = []
        # For each sample
        for sample_predictions in y_preds:
            # Select the most common class prediction
            y_pred.append(np.bincount(sample_predictions.astype('int')).argmax())
        return y_pred


  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
  
13
  
14
  
15
  
16
  
17
  
18
  
19
  
20
  
21
  
22
  
23
  
24
  
25
  
26
  
27
  
28
  
29
  
30
  
31
  
32
  
33
  
34
  
35
  
36
  
37
  
38
  
39
  
40
  
41
  
42
  
43
  
44
  
45
  
46
  
47
  
48
  
49
  
50
  
51
  
52
  
53
  
54
  
55
  
56
  
57
  
58
  
59
  
60
  
61
  
62
  
63
  
64
  
65
  
66
  
67
  
68
  
69
  
70
  
71
  
72
  
73
  
74
  
75
  
76
  
77
  
78
  
79
  
80
  
81
  
82
  
83
  
84
  
85
  
86
  
87
  
88
 

文章来源: wanghao.blog.csdn.net，作者：AI浩，版权归原作者所有，如需转载，请联系作者。

原文链接：wanghao.blog.csdn.net/article/details/121558431