# 飞桨 # paddlepaddle #李宏毅机器学习特训营
课程链接:https://aistudio.baidu.com/aistudio/course/introduce/1978
作业的题目要求:
项目描述:二元分类是机器学习中最基础的问题之一,在这份教学中,你将学会如何实作一个线性二元分类器,来根据人们的个人资料,判断其年收入是否高于50,000美元。我们将以两种方法:logistic regression与generative model,来达成以上目的,你可以尝试了解、分析两者的设计理念及差别。实现二分类任务:·个人收入是否超过50000元。
数据集介绍:这个数据集是由UCI Machine Learning Repository 的 Census-Income (KDD) Data Set 经过一些处理而得来,为了方便训练,我们移除了一些不必要的资讯,并且稍微平衡了正负两种标记的比例。事实上在训练过程中,只有X_train, Y_train, X_test这三个经过处理的档案会被用到,train.csv和test.csv这个两个原始资料则可以提供你一些额外的资讯。(1. 已去除不必要的属性。2. 已经平衡正标和负标数据之间的比例。)
特征格式:1. train.csv,test_no_label.csv。(·基于文本的原始数据 ·去掉不必要的属性,平衡正负比例)2. X_train, Y_train, X_test(测试) (·train.csv中的离散特征==>在X_train中onehot编码(学历、状态··· ···) ·train.csv中的连续特征==>在X_train中保持不变(年龄、资本损失··· ···) ·X_train, X_test: 每一行包括一个510-dim的特征,代表一个样本。 ·Y_train: label=0 表示"<50k"、label=1 表示">50k"。)
(声明:以下代码均为老师给的示例代码,我加入了一些注释和原理)
数据准备:下载资料,并且对每个属性做正规化,处理过后再将其切分为train_set 和 develop_set。
import numpy as np
np.random.seed(0)
X_train_fpath = 'work/data/X_train'
Y_train_fpath = 'work/data/Y_train'
X_test_fpath = 'work/data/X_test'
output_fpath = 'work/output_{}.csv'
# Parse csv files to numpy array
with open(X_train_fpath) as f:
next(f)
X_train = np.array([line.strip('\n').split(',')[1:] for line in f], dtype = float)
with open(Y_train_fpath) as f:
next(f)
Y_train = np.array([line.strip('\n').split(',')[1] for line in f], dtype = float)
with open(X_test_fpath) as f:
next(f)
X_test = np.array([line.strip('\n').split(',')[1:] for line in f], dtype = float)
def _normalize(X, train = True, specified_column = None, X_mean = None, X_std = None):
# This function normalizes specific columns of X.
# The mean and standard variance of training data will be reused when processing testing data.
#
# Arguments:
# X: data to be processed
# train: 'True' when processing training data, 'False' for testing data
# specific_column: indexes of the columns that will be normalized. If 'None', all columns
# will be normalized.
# X_mean: mean value of training data, used when train = 'False'
# X_std: standard deviation of training data, used when train = 'False'
# Outputs:
# X: normalized data
# X_mean: computed mean value of training data
# X_std: computed standard deviation of training data
if specified_column == None:
specified_column = np.arange(X.shape[1])
if train:
X_mean = np.mean(X[:, specified_column] ,0).reshape(1, -1)
X_std = np.std(X[:, specified_column], 0).reshape(1, -1)
X[:,specified_column] = (X[:, specified_column] - X_mean) / (X_std + 1e-8)
return X, X_mean, X_std
def _train_dev_split(X, Y, dev_ratio = 0.25):
# This function spilts data into training set and development set.
train_size = int(len(X) * (1 - dev_ratio))
return X[:train_size], Y[:train_size], X[train_size:], Y[train_size:]
# Normalize training and testing data
X_train, X_mean, X_std = _normalize(X_train, train = True)
X_test, _, _= _normalize(X_test, train = False, specified_column = None, X_mean = X_mean, X_std = X_std)
# Split data into training set and development set
dev_ratio = 0.1
X_train, Y_train, X_dev, Y_dev = _train_dev_split(X_train, Y_train, dev_ratio = dev_ratio)
train_size = X_train.shape[0]
dev_size = X_dev.shape[0]
test_size = X_test.shape[0]
data_dim = X_train.shape[1]
print('Size of training set: {}'.format(train_size))
print('Size of development set: {}'.format(dev_size))
print('Size of testing set: {}'.format(test_size))
print('Dimension of data: {}'.format(data_dim))
def _shuffle(X, Y):
# This function shuffles two equal-length list/array, X and Y, together.
randomize = np.arange(len(X))
np.random.shuffle(randomize)
return (X[randomize], Y[randomize])
# 用于将数组中的元素控制在一个给定的范围[1e-8, (1-(1e-8))]
def _sigmoid(z):
# Sigmoid function can be used to calculate probability.
# To avoid overflow, minimum/maximum output value is set.
return np.clip(1 / (1.0 + np.exp(-z)), 1e-8, 1 - (1e-8))
def _f(X, w, b):
# This is the logistic regression function, parameterized by w and b
#
# Arguements:
# X: input data, shape = [batch_size, data_dimension]
# w: weight vector, shape = [data_dimension, ]
# b: bias, scalar
# Output:
# predicted probability of each row of X being positively labeled, shape = [batch_size, ]
return _sigmoid(np.matmul(X, w) + b)
def _predict(X, w, b):
# This function returns a truth value prediction for each row of X
# by rounding the result of logistic regression function.
return np.round(_f(X, w, b)).astype(np.int)
def _accuracy(Y_pred, Y_label):
# This function calculates prediction accuracy
acc = 1 - np.mean(np.abs(Y_pred - Y_label))
return acc
def _cross_entropy_loss(y_pred, Y_label):
# This function computes the cross entropy.
#
# Arguements:
# y_pred: probabilistic predictions, float vector
# Y_label: ground truth labels, bool vector
# Output:
# cross entropy, scalar
cross_entropy = -np.dot(Y_label, np.log(y_pred)) - np.dot((1 - Y_label), np.log(1 - y_pred))
return cross_entropy
# X.T
def _gradient(X, Y_label, w, b):
# This function computes the gradient of cross entropy loss with respect to weight w and bias b.
y_pred = _f(X, w, b)
pred_error = Y_label - y_pred
w_grad = -np.sum(pred_error * X.T, 1)
b_grad = -np.sum(pred_error)
return w_grad, b_grad
# Zero initialization for weights ans bias
w = np.zeros((data_dim,))
b = np.zeros((1,))
# Some parameters for training
max_iter = 10
batch_size = 8
learning_rate = 0.2
# Keep the loss and accuracy at every iteration for plotting
train_loss = []
dev_loss = []
train_acc = []
dev_acc = []
# Calcuate the number of parameter updates
step = 1
# Iterative training
for epoch in range(max_iter):
# Random shuffle at the begging of each epoch
X_train, Y_train = _shuffle(X_train, Y_train)
# Mini-batch training
for idx in range(int(np.floor(train_size / batch_size))):
X = X_train[idx*batch_size:(idx+1)*batch_size]
Y = Y_train[idx*batch_size:(idx+1)*batch_size]
# Compute the gradient
w_grad, b_grad = _gradient(X, Y, w, b)
# gradient descent update
# learning rate decay with time
w = w - learning_rate/np.sqrt(step) * w_grad
b = b - learning_rate/np.sqrt(step) * b_grad
step = step + 1
# Compute loss and accuracy of training set and development set
y_train_pred = _f(X_train, w, b)
Y_train_pred = np.round(y_train_pred)
train_acc.append(_accuracy(Y_train_pred, Y_train))
train_loss.append(_cross_entropy_loss(y_train_pred, Y_train) / train_size)
y_dev_pred = _f(X_dev, w, b)
Y_dev_pred = np.round(y_dev_pred)
dev_acc.append(_accuracy(Y_dev_pred, Y_dev))
dev_loss.append(_cross_entropy_loss(y_dev_pred, Y_dev) / dev_size)
print('Training loss: {}'.format(train_loss[-1]))
print('Development loss: {}'.format(dev_loss[-1]))
print('Training accuracy: {}'.format(train_acc[-1]))
print('Development accuracy: {}'.format(dev_acc[-1]))
import matplotlib.pyplot as plt
# Loss curve
plt.plot(train_loss)
plt.plot(dev_loss)
plt.title('Loss')
plt.legend(['train', 'dev'])
plt.savefig('loss.png')
plt.show()
# Accuracy curve
plt.plot(train_acc)
plt.plot(dev_acc)
plt.title('Accuracy')
plt.legend(['train', 'dev'])
plt.savefig('acc.png')
plt.show()
多变量生成模型
# Parse csv files to numpy array
with open(X_train_fpath) as f:
next(f)
X_train = np.array([line.strip('\n').split(',')[1:] for line in f], dtype = float)
with open(Y_train_fpath) as f:
next(f)
Y_train = np.array([line.strip('\n').split(',')[1] for line in f], dtype = float)
with open(X_test_fpath) as f:
next(f)
X_test = np.array([line.strip('\n').split(',')[1:] for line in f], dtype = float)
# Normalize training and testing data
X_train, X_mean, X_std = _normalize(X_train, train = True)
X_test, _, _= _normalize(X_test, train = False, specified_column = None, X_mean = X_mean, X_std = X_std)
# Compute in-class mean
X_train_0 = np.array([x for x, y in zip(X_train, Y_train) if y == 0])
X_train_1 = np.array([x for x, y in zip(X_train, Y_train) if y == 1])
mean_0 = np.mean(X_train_0, axis = 0)
mean_1 = np.mean(X_train_1, axis = 0)
# Compute in-class covariance
cov_0 = np.zeros((data_dim, data_dim))
cov_1 = np.zeros((data_dim, data_dim))
for x in X_train_0:
cov_0 += np.dot(np.transpose([x - mean_0]), [x - mean_0]) / X_train_0.shape[0]
for x in X_train_1:
cov_1 += np.dot(np.transpose([x - mean_1]), [x - mean_1]) / X_train_1.shape[0]
# Shared covariance is taken as a weighted average of individual in-class covariance.
cov = (cov_0 * X_train_0.shape[0] + cov_1 * X_train_1.shape[0]) / (X_train_0.shape[0] + X_train_1.shape[0])
# Compute inverse of covariance matrix.
# Since covariance matrix may be nearly singular, np.linalg.inv() may give a large numerical error.
# Via SVD decomposition, one can get matrix inverse efficiently and accurately.
u, s, v = np.linalg.svd(cov, full_matrices=False)
inv = np.matmul(v.T * 1 / s, u.T)
# Directly compute weights and bias
w = np.dot(inv, mean_0 - mean_1)
b = (-0.5) * np.dot(mean_0, np.dot(inv, mean_0)) + 0.5 * np.dot(mean_1, np.dot(inv, mean_1))\
+ np.log(float(X_train_0.shape[0]) / X_train_1.shape[0])
# Compute accuracy on training set
Y_train_pred = 1 - _predict(X_train, w, b)
print('Training accuracy: {}'.format(_accuracy(Y_train_pred, Y_train)))
# Predict testing labels
predictions = 1 - _predict(X_test, w, b)
with open(output_fpath.format('generative'), 'w') as f:
f.write('id,label\n')
for i, label in enumerate(predictions):
f.write('{},{}\n'.format(i, label))
# Print out the most significant weights
ind = np.argsort(np.abs(w))[::-1]
with open(X_test_fpath) as f:
content = f.readline().strip('\n').split(',')
features = np.array(content)
for i in ind[0:10]:
print(features[i], w[i])