逻辑回归Logistic regression
这个脚本展示如何用TensorFlow求解逻辑回归。 =(×+)y=sigmoid(A×x+b)
我们使用低出生重量数据,特别地:
```
y = 0 or 1 = low birth weight
x = demographic and medical history data
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()
#tf.set_random_seed(42)
np.random.seed(42)
# name of data file
birth_weight_file = 'birth_weight1.csv'
# 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('\r\n')
#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%
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)
def normalize_cols(m, col_min=np.array([None]), col_max=np.array([None])):
if not col_min[0]:
col_min = m.min(axis=0)
if not col_max[0]:
col_max = m.max(axis=0)
return (m-col_min) / (col_max - col_min), col_min, col_max
x_vals_train, train_min, train_max = np.nan_to_num(normalize_cols(x_vals_train))
x_vals_test, _, _ = np.nan_to_num(normalize_cols(x_vals_test, train_min, train_max))
def model(x,w,b):
# Declare model operations
model_output = tf.add(tf.matmul(x, w), b)
return model_output
def loss1(x,y,w,b):
# Declare Deming loss function
loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=model(x,w,b), labels=y))
return loss
def grad1(x,y,w,b):
with tf.GradientTape() as tape:
loss_1 = loss1(x,y,w,b)
return tape.gradient(loss_1,[w,b])
# Declare batch size
# Declare batch size
batch_size = 25
learning_rate = 0.25 # Will not converge with learning rate at 0.4
iterations = 50
# Create variables for linear regression
w1 = tf.Variable(tf.random.normal(shape=[7,1]),tf.float32)
b1 = tf.Variable(tf.random.normal(shape=[1,1]),tf.float32)
optimizer = tf.optimizers.Adam(learning_rate)
# Training loop
# Training loop
loss_vec = []
train_acc = []
test_acc = []
for i in range(5000):
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]])
x=tf.cast(rand_x,tf.float32)
y=tf.cast(rand_y,tf.float32)
grads1=grad1(x,y,w1,b1)
optimizer.apply_gradients(zip(grads1,[w1,b1]))
#sess.run(train_step, feed_dict={x_data: rand_x, y_target: rand_y})
temp_loss1 = loss1(x, y,w1,b1).numpy()
#sess.run(loss, feed_dict={x_data: rand_x, y_target: rand_y})
loss_vec.append(temp_loss1)
# 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)
prediction1 = tf.round(tf.sigmoid(model(tf.cast(x_vals_train,tf.float32),w1,b1)))
predictions_correct1 = tf.cast(tf.equal(prediction1, tf.cast(np.transpose([y_vals_train]),tf.float32)), tf.float32)
temp_acc_train = tf.reduce_mean(predictions_correct1)
train_acc.append(temp_acc_train)
prediction2 = tf.round(tf.sigmoid(model(tf.cast(x_vals_test,tf.float32),w1,b1)))
predictions_correct2 = tf.cast(tf.equal(prediction2, tf.cast(np.transpose([y_vals_test]),tf.float32)), tf.float32)
temp_acc_test=tf.reduce_mean(predictions_correct2)
test_acc.append(temp_acc_test)
if (i+1)%25==0:
print('Step #' + str(i+1) + ' A = ' + str(w1.numpy()) + ' b = ' + str(b1.numpy()))
print('Loss = ' + str(temp_loss1))
%matplotlib inline
# Plot loss over time
plt.plot(loss_vec, 'k-')
plt.title('Cross Entropy Loss per Generation')
plt.xlabel('Generation')
plt.ylabel('Cross Entropy Loss')
plt.show()
# Plot train and test accuracy
plt.plot(train_acc, 'k-', label='Train Set Accuracy')
plt.plot(test_acc, 'r--', label='Test Set Accuracy')
plt.title('Train and Test Accuracy')
plt.xlabel('Generation')
plt.ylabel('Accuracy')
plt.legend(loc='lower right')
plt.show()
