<em>Mac</em>Book项目 2009年学校开始实施<em>Mac</em>Book项目,所有师生配备一本<em>Mac</em>Book,并同步更新了校园无线网络。学校每周进行电脑技术更新,每月发送技术支持资料,极大改变了教学及学习方式。因此2011
2021-06-01 09:32:01
本文範例為大家分享了python實現梯度下降求解邏輯迴歸的具體程式碼,供大家參考,具體內容如下
對比線性迴歸理解邏輯迴歸,主要包含迴歸函數,似然函數,梯度下降求解及程式碼實現
似然函數的定義:給定聯合樣本值X下關於(未知)引數 的函數
似然函數:什麼樣的引數跟我們的資料組合後恰好是真實值
對數似然:
(誤差的表示式,我們的目的就是使得真實值與預測值之前的誤差最小)
(導數為0取得極值,得到函數的引數)
邏輯迴歸是線上性迴歸的結果外加一層Sigmoid函數
前提資料服從伯努利分佈
對數似然:
引入 轉變為梯度下降任務,邏輯迴歸目標函數
我的理解就是求導更新引數,達到一定條件後停止,得到近似最優解
Sigmoid函數
def sigmoid(z): return 1 / (1 + np.exp(-z))
預測函數
def model(X, theta): return sigmoid(np.dot(X, theta.T))
目標函數
def cost(X, y, theta): left = np.multiply(-y, np.log(model(X, theta))) right = np.multiply(1 - y, np.log(1 - model(X, theta))) return np.sum(left - right) / (len(X))
梯度
def gradient(X, y, theta): grad = np.zeros(theta.shape) error = (model(X, theta)- y).ravel() for j in range(len(theta.ravel())): #for each parmeter term = np.multiply(error, X[:,j]) grad[0, j] = np.sum(term) / len(X) return grad
梯度下降停止策略
STOP_ITER = 0 STOP_COST = 1 STOP_GRAD = 2 def stopCriterion(type, value, threshold): # 設定三種不同的停止策略 if type == STOP_ITER: # 設定迭代次數 return value > threshold elif type == STOP_COST: # 根據損失值停止 return abs(value[-1] - value[-2]) < threshold elif type == STOP_GRAD: # 根據梯度變化停止 return np.linalg.norm(value) < threshold
樣本重新洗牌
import numpy.random #洗牌 def shuffleData(data): np.random.shuffle(data) cols = data.shape[1] X = data[:, 0:cols-1] y = data[:, cols-1:] return X, y
梯度下降求解
def descent(data, theta, batchSize, stopType, thresh, alpha): # 梯度下降求解 init_time = time.time() i = 0 # 迭代次數 k = 0 # batch X, y = shuffleData(data) grad = np.zeros(theta.shape) # 計算的梯度 costs = [cost(X, y, theta)] # 損失值 while True: grad = gradient(X[k:k + batchSize], y[k:k + batchSize], theta) k += batchSize # 取batch數量個資料 if k >= n: k = 0 X, y = shuffleData(data) # 重新洗牌 theta = theta - alpha * grad # 引數更新 costs.append(cost(X, y, theta)) # 計算新的損失 i += 1 if stopType == STOP_ITER: value = i elif stopType == STOP_COST: value = costs elif stopType == STOP_GRAD: value = grad if stopCriterion(stopType, value, thresh): break return theta, i - 1, costs, grad, time.time() - init_time
import numpy as np import pandas as pd import matplotlib.pyplot as plt import os import numpy.random import time def sigmoid(z): return 1 / (1 + np.exp(-z)) def model(X, theta): return sigmoid(np.dot(X, theta.T)) def cost(X, y, theta): left = np.multiply(-y, np.log(model(X, theta))) right = np.multiply(1 - y, np.log(1 - model(X, theta))) return np.sum(left - right) / (len(X)) def gradient(X, y, theta): grad = np.zeros(theta.shape) error = (model(X, theta) - y).ravel() for j in range(len(theta.ravel())): # for each parmeter term = np.multiply(error, X[:, j]) grad[0, j] = np.sum(term) / len(X) return grad STOP_ITER = 0 STOP_COST = 1 STOP_GRAD = 2 def stopCriterion(type, value, threshold): # 設定三種不同的停止策略 if type == STOP_ITER: # 設定迭代次數 return value > threshold elif type == STOP_COST: # 根據損失值停止 return abs(value[-1] - value[-2]) < threshold elif type == STOP_GRAD: # 根據梯度變化停止 return np.linalg.norm(value) < threshold # 洗牌 def shuffleData(data): np.random.shuffle(data) cols = data.shape[1] X = data[:, 0:cols - 1] y = data[:, cols - 1:] return X, y def descent(data, theta, batchSize, stopType, thresh, alpha): # 梯度下降求解 init_time = time.time() i = 0 # 迭代次數 k = 0 # batch X, y = shuffleData(data) grad = np.zeros(theta.shape) # 計算的梯度 costs = [cost(X, y, theta)] # 損失值 while True: grad = gradient(X[k:k + batchSize], y[k:k + batchSize], theta) k += batchSize # 取batch數量個資料 if k >= n: k = 0 X, y = shuffleData(data) # 重新洗牌 theta = theta - alpha * grad # 引數更新 costs.append(cost(X, y, theta)) # 計算新的損失 i += 1 if stopType == STOP_ITER: value = i elif stopType == STOP_COST: value = costs elif stopType == STOP_GRAD: value = grad if stopCriterion(stopType, value, thresh): break return theta, i - 1, costs, grad, time.time() - init_time def runExpe(data, theta, batchSize, stopType, thresh, alpha): # import pdb # pdb.set_trace() theta, iter, costs, grad, dur = descent(data, theta, batchSize, stopType, thresh, alpha) name = "Original" if (data[:, 1] > 2).sum() > 1 else "Scaled" name += " data - learning rate: {} - ".format(alpha) if batchSize == n: strDescType = "Gradient" # 批次梯度下降 elif batchSize == 1: strDescType = "Stochastic" # 隨機梯度下降 else: strDescType = "Mini-batch ({})".format(batchSize) # 小批次梯度下降 name += strDescType + " descent - Stop: " if stopType == STOP_ITER: strStop = "{} iterations".format(thresh) elif stopType == STOP_COST: strStop = "costs change < {}".format(thresh) else: strStop = "gradient norm < {}".format(thresh) name += strStop print("***{}nTheta: {} - Iter: {} - Last cost: {:03.2f} - Duration: {:03.2f}s".format( name, theta, iter, costs[-1], dur)) fig, ax = plt.subplots(figsize=(12, 4)) ax.plot(np.arange(len(costs)), costs, 'r') ax.set_xlabel('Iterations') ax.set_ylabel('Cost') ax.set_title(name.upper() + ' - Error vs. Iteration') return theta path = 'data' + os.sep + 'LogiReg_data.txt' pdData = pd.read_csv(path, header=None, names=['Exam 1', 'Exam 2', 'Admitted']) positive = pdData[pdData['Admitted'] == 1] negative = pdData[pdData['Admitted'] == 0] # 畫圖觀察樣本情況 fig, ax = plt.subplots(figsize=(10, 5)) ax.scatter(positive['Exam 1'], positive['Exam 2'], s=30, c='b', marker='o', label='Admitted') ax.scatter(negative['Exam 1'], negative['Exam 2'], s=30, c='r', marker='x', label='Not Admitted') ax.legend() ax.set_xlabel('Exam 1 Score') ax.set_ylabel('Exam 2 Score') pdData.insert(0, 'Ones', 1) # 劃分訓練資料與標籤 orig_data = pdData.values cols = orig_data.shape[1] X = orig_data[:, 0:cols - 1] y = orig_data[:, cols - 1:cols] # 設定初始引數0 theta = np.zeros([1, 3]) # 選擇的梯度下降方法是基於所有樣本的 n = 100 runExpe(orig_data, theta, n, STOP_ITER, thresh=5000, alpha=0.000001) runExpe(orig_data, theta, n, STOP_COST, thresh=0.000001, alpha=0.001) runExpe(orig_data, theta, n, STOP_GRAD, thresh=0.05, alpha=0.001) runExpe(orig_data, theta, 1, STOP_ITER, thresh=5000, alpha=0.001) runExpe(orig_data, theta, 1, STOP_ITER, thresh=15000, alpha=0.000002) runExpe(orig_data, theta, 16, STOP_ITER, thresh=15000, alpha=0.001) from sklearn import preprocessing as pp # 資料預處理 scaled_data = orig_data.copy() scaled_data[:, 1:3] = pp.scale(orig_data[:, 1:3]) runExpe(scaled_data, theta, n, STOP_ITER, thresh=5000, alpha=0.001) runExpe(scaled_data, theta, n, STOP_GRAD, thresh=0.02, alpha=0.001) theta = runExpe(scaled_data, theta, 1, STOP_GRAD, thresh=0.002 / 5, alpha=0.001) runExpe(scaled_data, theta, 16, STOP_GRAD, thresh=0.002 * 2, alpha=0.001) # 設定閾值 def predict(X, theta): return [1 if x >= 0.5 else 0 for x in model(X, theta)] # 計算精度 scaled_X = scaled_data[:, :3] y = scaled_data[:, 3] predictions = predict(scaled_X, theta) correct = [1 if ((a == 1 and b == 1) or (a == 0 and b == 0)) else 0 for (a, b) in zip(predictions, y)] accuracy = (sum(map(int, correct)) % len(correct)) print('accuracy = {0}%'.format(accuracy))
以上就是本文的全部內容,希望對大家的學習有所幫助,也希望大家多多支援it145.com。
相關文章
<em>Mac</em>Book项目 2009年学校开始实施<em>Mac</em>Book项目,所有师生配备一本<em>Mac</em>Book,并同步更新了校园无线网络。学校每周进行电脑技术更新,每月发送技术支持资料,极大改变了教学及学习方式。因此2011
2021-06-01 09:32:01
综合看Anker超能充系列的性价比很高,并且与不仅和iPhone12/苹果<em>Mac</em>Book很配,而且适合多设备充电需求的日常使用或差旅场景,不管是安卓还是Switch同样也能用得上它,希望这次分享能给准备购入充电器的小伙伴们有所
2021-06-01 09:31:42
除了L4WUDU与吴亦凡已经多次共事,成为了明面上的厂牌成员,吴亦凡还曾带领20XXCLUB全队参加2020年的一场音乐节,这也是20XXCLUB首次全员合照,王嗣尧Turbo、陈彦希Regi、<em>Mac</em> Ova Seas、林渝植等人全部出场。然而让
2021-06-01 09:31:34
目前应用IPFS的机构:1 谷歌<em>浏览器</em>支持IPFS分布式协议 2 万维网 (历史档案博物馆)数据库 3 火狐<em>浏览器</em>支持 IPFS分布式协议 4 EOS 等数字货币数据存储 5 美国国会图书馆,历史资料永久保存在 IPFS 6 加
2021-06-01 09:31:24
开拓者的车机是兼容苹果和<em>安卓</em>,虽然我不怎么用,但确实兼顾了我家人的很多需求:副驾的门板还配有解锁开关,有的时候老婆开车,下车的时候偶尔会忘记解锁,我在副驾驶可以自己开门:第二排设计很好,不仅配置了一个很大的
2021-06-01 09:30:48
不仅是<em>安卓</em>手机,苹果手机的降价力度也是前所未有了,iPhone12也“跳水价”了,发布价是6799元,如今已经跌至5308元,降价幅度超过1400元,最新定价确认了。iPhone12是苹果首款5G手机,同时也是全球首款5nm芯片的智能机,它
2021-06-01 09:30:45