这篇文章主要讲解了“python怎么实现AdaBoost算法”，文中的讲解内容简单清晰，易于学习与理解，下面请大家跟着小编的思路慢慢深入，一起来研究和学习“python怎么实现AdaBoost算法”吧！
计算
安全
数据库
网络和加速
企业服务
import numpy as np
import pandas as pd
import math
from math import log
from math import exp
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
def create_data():
iris = load_iris()
df = pd.DataFrame(iris.data, columns=iris.feature_names)
df['label'] = iris.target
df.columns = ['sepal length', 'sepal width', 'petal length', 'petal width', 'label']
data = np.array(df.iloc[:100, [0, 1, -1]])
for i in range(len(data)):
if data[i, -1] == 0:
data[i, -1] = -1
return data[:, :2], data[:, -1]
class AdaBoost:
def __init__(self, n_estimators=50, learning_rate=1.0):
self.clf_num = n_estimators
self.learning_rate = learning_rate
def init_args(self, datasets, labels):
self.X = datasets
self.Y = labels
self.M, self.N = datasets.shape
# 弱分类器数目和集合
self.clf_sets = []
# 初始化weights
self.weights = [1.0 / self.M] * self.M
# G(x)系数 alpha
self.alpha = []
def _G(self, features, labels, weights):
m = len(features)
error = 100000.0 # 无穷大
best_v = 0.0
# 单维features
features_min = min(features)
features_max = max(features)
n_step = (features_max - features_min +
self.learning_rate) // self.learning_rate
# print('n_step:{}'.format(n_step))
direct, compare_array = None, None
for i in range(1, int(n_step)):
v = features_min + self.learning_rate * i
if v not in features:
# 误分类计算
compare_array_positive = np.array(
[1 if features[k] > v else -1 for k in range(m)])
weight_error_positive = sum([
weights[k] for k in range(m)
if compare_array_positive[k] != labels[k]
])
compare_array_nagetive = np.array(
[-1 if features[k] > v else 1 for k in range(m)])
weight_error_nagetive = sum([
weights[k] for k in range(m)
if compare_array_nagetive[k] != labels[k]
])
if weight_error_positive < weight_error_nagetive:
weight_error = weight_error_positive
_compare_array = compare_array_positive
direct = 'positive'
else:
weight_error = weight_error_nagetive
_compare_array = compare_array_nagetive
direct = 'nagetive'
# print('v:{} error:{}'.format(v, weight_error))
if weight_error < error:
error = weight_error
compare_array = _compare_array
best_v = v
return best_v, direct, error, compare_array
# 计算alpha
def _alpha(self, error):
return 0.5 * np.log((1 - error) / error)
# 规范化因子
def _Z(self, weights, a, clf):
return sum([
weights[i] * np.exp(-1 * a * self.Y[i] * clf[i])
for i in range(self.M)
])
# 权值更新
def _w(self, a, clf, Z):
for i in range(self.M):
self.weights[i] = self.weights[i] * np.exp(
-1 * a * self.Y[i] * clf[i]) / Z
# G(x)的线性组合
def _f(self, alpha, clf_sets):
pass
def G(self, x, v, direct):
if direct == 'positive':
return 1 if x > v else -1
else:
return -1 if x > v else 1
def fit(self, X, y):
self.init_args(X, y)
for epoch in range(self.clf_num):
axis = 0
final_direct = 'null'
best_clf_error, best_v, clf_result = 100000, None, None
# 根据特征维度, 选择误差最小的
for j in range(self.N):
features = self.X[:, j]
# 分类阈值，分类误差，分类结果
v, direct, error, compare_array = self._G(
features, self.Y, self.weights)
if error < best_clf_error:
best_clf_error = error
best_v = v
final_direct = direct
clf_result = compare_array
axis = j # axis数字代表第几个属性列
# print('epoch:{}/{} feature:{} error:{} v:{}'.format(epoch, self.clf_num, j, error, best_v))
if best_clf_error == 0:
break
# 计算G(x)系数a
a = self._alpha(best_clf_error)
self.alpha.append(a)
# 记录分类器
self.clf_sets.append((axis, best_v, final_direct))
# 规范化因子
Z = self._Z(self.weights, a, clf_result)
# 权值更新
self._w(a, clf_result, Z)
def predict(self, feature):
result = 0.0
for i in range(len(self.clf_sets)):
axis, clf_v, direct = self.clf_sets[i]
f_input = feature[axis]
result += self.alpha[i] * self.G(f_input, clf_v, direct)
# sign
return 1 if result > 0 else -1
def score(self, X_test, y_test):
right_count = 0
for i in range(len(X_test)):
feature = X_test[i]
if self.predict(feature) == y_test[i]:
right_count += 1
return right_count / len(X_test)
X, y = create_data()
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
clf = AdaBoost(n_estimators=3, learning_rate=0.5)
clf.fit(X_train, y_train)
print("评分：{}".format(clf.score(X_test, y_test)))结果：有时1.0有时0.75有时0.6有时0.4注意，这个程序计算规范化因子的时候可能报错：TypeError: 'NoneType' object is not subscriptable。原因是由于划分数据的时候，v选择的时候恰好造成了一边为空，另一边为满的。由于有一边是空的，所以，计算规范化因子的时候，参数clf为none。这时候我们在用clf[i]，肯定是不行的，也就报了这个错误。
import numpy as np
import pandas as pd
import math
from math import log
from math import exp
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.ensemble import AdaBoostClassifier
def create_data():
iris = load_iris()
df = pd.DataFrame(iris.data, columns=iris.feature_names)
df['label'] = iris.target
df.columns = ['sepal length', 'sepal width', 'petal length', 'petal width', 'label']
data = np.array(df.iloc[:100, [0, 1, -1]])
for i in range(len(data)):
if data[i, -1] == 0:
data[i, -1] = -1
return data[:, :2], data[:, -1]
X, y = create_data()
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
clf = AdaBoostClassifier(n_estimators=100, learning_rate=0.5)
clf.fit(X_train, y_train)
print("评分：{}".format(clf.score(X_test, y_test)))感谢各位的阅读，以上就是“python怎么实现AdaBoost算法”的内容了，经过本文的学习后，相信大家对python怎么实现AdaBoost算法这一问题有了更深刻的体会，具体使用情况还需要大家实践验证。这里是亿速云，小编将为大家推送更多相关知识点的文章，欢迎关注！
亿速云「云服务器」，即开即用、新一代英特尔至强铂金CPU、三副本存储NVMe SSD云盘，价格低至29元/月。点击查看>>
免责声明：本站发布的内容（图片、视频和文字）以原创、转载和分享为主，文章观点不代表本网站立场，如果涉及侵权请联系站长邮箱：is@yisu.com进行举报，并提供相关证据，一经查实，将立刻删除涉嫌侵权内容。
原文链接：https://my.oschina.net/LevideGrowthHistory/blog/4742755
