对数几率回归

从kaggle下载的泰坦尼克数据集

import tensorflow as tf#对数几率回归参数和变量的初始化W = tf.Variable(tf.zeros([5, 1]), name="weights")b = tf.Variable(0.0, name="bias")#之前的推断现在用于值的合并def combine_inputs(X):    return tf.matmul(X, W) + b#新的推断是将sigmoid函数运用到前面的合并def inference(X):    return tf.sigmoid(combine_inputs(X))#对于sigmoid函数，标配的损失函数是 交叉熵def loss(X, Y):    return tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=combine_inputs(X), labels=Y))#预测与评价模型def evaluate(sess, X, Y):    predicted = tf.cast(inference(X) > 0.5, tf.float32)    print sess.run(tf.reduce_mean(tf.cast(tf.equal(predicted, Y), tf.float32)))#采用梯度下降优化器def train(tol_loss):    learning_rate = 0.01    return tf.train.GradientDescentOptimizer(learning_rate).minimize(tol_loss)#读取csv文件def read_csv(batch_size, file_name, record_defaults):    filename_queue = tf.train.string_input_producer([file_name])    reader = tf.TextLineReader(skip_header_lines=1)    key, value = reader.read(filename_queue)    decoded = tf.decode_csv(value, record_defaults=record_defaults)  # 字符串(文本行)转换到指定默认值张量列元组，为每列设置数据类型    return tf.train.shuffle_batch(decoded, batch_size=batch_size, capacity=batch_size * 50,                                  min_after_dequeue=batch_size)  # 读取文件，加载张量batch_size行def inputs():    passenger_id, survived, pclass, name, sex, age, sibsp, parch, ticket, fare,\    cabin, embarked = read_csv(100, "/home/hadoop/PycharmProjects/tens/train.csv",                                                                 [[0.0], [0.0], [0], [""], [""], [0.0], [0.0], [0.0],                                                                 [""], [0.0], [""], [""]])    is_first_class = tf.to_float(tf.equal(pclass, [1]))    is_second_class = tf.to_float(tf.equal(pclass, [2]))    is_third_class = tf.to_float(tf.equal(pclass, [3]))    gender = tf.to_float(tf.equal(sex, ["female"]))    features =  tf.transpose(tf.stack([is_first_class, is_second_class, is_third_class, gender, age]))    survived = tf.reshape(survived, [100,1])    return features, survivedwith tf.Session() as sess:    sess.run(tf.global_variables_initializer())    X, Y = inputs()    coord = tf.train.Coordinator()    threads = tf.train.start_queue_runners(coord=coord)    tol_loss = loss(X, Y)    train_op = train(tol_loss)    train_step = 1001    for step in range(train_step):        sess.run(train_op)        if step % 100 == 0:            print "%d loss" %step,  sess.run(tol_loss)    evaluate(sess, X, Y)    coord.request_stop()    coord.join(threads)

预测结果：

0 loss 0.660088100 loss 0.649859200 loss 0.678345300 loss 0.645126400 loss 0.6176500 loss 0.615742600 loss 0.562361700 loss 0.562884800 loss 0.500807900 loss 0.5987881000 loss 0.5640390.81