3.5 tensorflow逻辑回归算法 Logistic Regression

逻辑回归算法通过 y = sigmoid(Ax + b)将线性回归的输出缩放到0到1.

import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
import requests
from tensorflow.python.framework import ops
import os.path
import csv
ops.reset_default_graph()
sess = tf.Session()

# Download data by requests module
birth_weight_file = 'birth_weight.csv' # Set name of data file
# Download data and create data file if file does not exist in current directory
if not os.path.exists(birth_weight_file):
    birthdata_url = 'https://github.com/nfmcclure/tensorflow_cookbook/raw/master/01_Introduction/07_Working_with_Data_Sources/birthweight_data/birthweight.dat'
    birth_file = requests.get(birthdata_url)
    birth_data = birth_file.text.split('rn')
    birth_header = birth_data[0].split('t')
    birth_data = [[float(x) for x in y.split('t') if len(x)>=1] for y in birth_data[1:] if len(y)>=1]
    with open(birth_weight_file, 'w', newline='') as f:
        writer = csv.writer(f)
        writer.writerow(birth_header)
        writer.writerows(birth_data)
        f.close()
# Read birth weight data into memory
birth_data = []
with open(birth_weight_file, newline='') as csvfile:
     csv_reader = csv.reader(csvfile)
     birth_header = next(csv_reader)
     for row in csv_reader:
         birth_data.append(row)
birth_data = [[float(x) for x in row] for row in birth_data]
# Pull out target variable
y_vals = np.array([x[0] for x in birth_data])
# Pull out predictor variables (not id, not target, and not birthweight)
x_vals = np.array([x[1:8] for x in birth_data])
# Set for reproducible results
seed = 99
np.random.seed(seed)
tf.set_random_seed(seed)

# Split data into train/test = 80%/20%将数据拆分为训练/测试
train_indices = np.random.choice(len(x_vals), round(len(x_vals)*0.8), replace=False)
test_indices = np.array(list(set(range(len(x_vals))) - set(train_indices)))
x_vals_train = x_vals[train_indices]
x_vals_test = x_vals[test_indices]
y_vals_train = y_vals[train_indices]
y_vals_test = y_vals[test_indices]

# Normalize by column (min-max norm)将特征归一化
def normalize_cols(m):
    col_max = m.max(axis=0)
    col_min = m.min(axis=0)
    return (m-col_min) / (col_max - col_min)
    
x_vals_train = np.nan_to_num(normalize_cols(x_vals_train))
x_vals_test = np.nan_to_num(normalize_cols(x_vals_test))
batch_size = 25
x_data = tf.placeholder(shape=[None, 7], dtype=tf.float32)
y_target = tf.placeholder(shape=[None, 1], dtype=tf.float32)
A = tf.Variable(tf.random_normal(shape=[7,1]))
b = tf.Variable(tf.random_normal(shape=[1,1]))
model_output = tf.add(tf.matmul(x_data, A), b)

# Declare loss function (Cross Entropy loss)
loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=model_output, labels=y_target))

my_opt = tf.train.GradientDescentOptimizer(0.01)
train_step = my_opt.minimize(loss)
init = tf.global_variables_initializer()
sess.run(init)
# Actual Prediction
prediction = tf.round(tf.sigmoid(model_output))
predictions_correct = tf.cast(tf.equal(prediction, y_target), tf.float32)
accuracy = tf.reduce_mean(predictions_correct)

# Training loop
loss_vec = []
train_acc = []
test_acc = []
for i in range(1500):
    rand_index = np.random.choice(len(x_vals_train), size=batch_size)
    rand_x = x_vals_train[rand_index]
    rand_y = np.transpose([y_vals_train[rand_index]])
    sess.run(train_step, feed_dict={x_data: rand_x, y_target: rand_y})

    temp_loss = sess.run(loss, feed_dict={x_data: rand_x, y_target: rand_y})
    loss_vec.append(temp_loss)
    temp_acc_train = sess.run(accuracy, feed_dict={x_data: x_vals_train, y_target: np.transpose([y_vals_train])})
    train_acc.append(temp_acc_train)
    temp_acc_test = sess.run(accuracy, feed_dict={x_data: x_vals_test, y_target: np.transpose([y_vals_test])})
    test_acc.append(temp_acc_test)
    if (i+1)%300==0:
        print('Loss = ' + str(temp_loss))      

最后

以上就是跳跃御姐为你收集整理的3.5 tensorflow逻辑回归算法 Logistic Regression的全部内容，希望文章能够帮你解决3.5 tensorflow逻辑回归算法 Logistic Regression所遇到的程序开发问题。

如果觉得靠谱客网站的内容还不错，欢迎将靠谱客网站推荐给程序员好友。