Created
August 19, 2017 03:07
-
-
Save regonn/3433b32158b48cc481d61add5069b2e5 to your computer and use it in GitHub Desktop.
random forest
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from sklearn.base import ClassifierMixin | |
from collections import Counter | |
import numpy as np | |
class RandomForest(): | |
def __init__(self, n_trees=10): | |
self._n_trees = n_trees | |
self._forest = [None] * self._n_trees | |
self._using_data = [None] * self._n_trees | |
def _bootstrap_sample(self, X, y): | |
n_data = X.shape[1] | |
n_data_forest = np.floor(np.sqrt(n_data)) | |
bootstrapped_X = list() | |
bootstrapped_y = list() | |
for i in range(self._n_trees): | |
index = np.random.choice(len(y), size=len(y)) | |
col = np.random.choice(n_data, size=n_data_forest, replace=False) | |
bootstrapped_X.append(X[np.ix_(index, col)]) | |
bootstrapped_y.append(y[index]) | |
self._using_data[i] = col | |
return bootstrapped_X, bootstrapped_y | |
def create_forest(self, X, y): | |
self._targets = np.unique(y) | |
bootstrap_X, bootstrapped_y = self._bootstrap_sample(X, y) | |
for i, (i_bootstrapped_X, i_bootstrapped_y) in enumerate(zip(bootstrapped_X, bootstrapped_y)): | |
tree = DecisionTree() | |
tree.create_tree(i_bootstrapped_X, i_bootstrapped_y) | |
self._forest[i] = tree | |
def predict(self, X): | |
proba = self._predict_proba(X) | |
return self._targets[np.argmax(proba, axis=1)] | |
def _predict_proba(self, X): | |
if self._forest[0] is None: | |
raise ValueError('fitしてね') | |
votes = [tree.predict(X[:, using_data]) for tree, using_data in zip(self._forest, self._using_features)] | |
counts = [Counter(row) for row in np.array(votes).transpose()] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment