tensorflow knn 预测房价 注意有 Min-Max Scaling

示例数据：

0.00632  18.00   2.310  0  0.5380  6.5750  65.20  4.0900   1  296.0  15.30 396.90   4.98  24.00
 0.02731   0.00   7.070  0  0.4690  6.4210  78.90  4.9671   2  242.0  17.80 396.90   9.14  21.60
 0.02729   0.00   7.070  0  0.4690  7.1850  61.10  4.9671   2  242.0  17.80 392.83   4.03  34.70
 0.03237   0.00   2.180  0  0.4580  6.9980  45.80  6.0622   3  222.0  18.70 394.63   2.94  33.40
 0.06905   0.00   2.180  0  0.4580  7.1470  54.20  6.0622   3  222.0  18.70 396.90   5.33  36.20
 0.02985   0.00   2.180  0  0.4580  6.4300  58.70  6.0622   3  222.0  18.70 394.12   5.21  28.70
 0.08829  12.50   7.870  0  0.5240  6.0120  66.60  5.5605   5  311.0  15.20 395.60  12.43  22.90
 0.14455  12.50   7.870  0  0.5240  6.1720  96.10  5.9505   5  311.0  15.20 396.90  19.15  27.10
 0.21124  12.50   7.870  0  0.5240  5.6310 100.00  6.0821   5  311.0  15.20 386.63  29.93  16.50
 0.17004  12.50   7.870  0  0.5240  6.0040  85.90  6.5921   5  311.0  15.20 386.71  17.10  18.90
 0.22489  12.50   7.870  0  0.5240  6.3770  94.30  6.3467   5  311.0  15.20 392.52  20.45  15.00
 0.11747  12.50   7.870  0  0.5240  6.0090  82.90  6.2267   5  311.0  15.20 396.90  13.27  18.90
 0.09378  12.50   7.870  0  0.5240  5.8890  39.00  5.4509   5  311.0  15.20 390.50  15.71  21.70
 0.62976   0.00   8.140  0  0.5380  5.9490  61.80  4.7075   4  307.0  21.00 396.90   8.26  20.40
 0.63796   0.00   8.140  0  0.5380  6.0960  84.50  4.4619   4  307.0  21.00 380.02  10.26  18.20
 0.62739   0.00   8.140  0  0.5380  5.8340  56.50  4.4986   4  307.0  21.00 395.62   8.47  19.90
 1.05393   0.00   8.140  0  0.5380  5.9350  29.30  4.4986   4  307.0  21.00 386.85   6.58  23.10

代码：最大值与最小值之差：ptp()

# k-Nearest Neighbor
#----------------------------------
#
# This function illustrates how to use
# k-nearest neighbors in tensorflow
#
# We will use the 1970s Boston housing dataset
# which is available through the UCI
# ML data repository.
#
# Data:
#----------x-values-----------
# CRIM   : per capita crime rate by town
# ZN     : prop. of res. land zones
# INDUS  : prop. of non-retail business acres
# CHAS   : Charles river dummy variable
# NOX    : nitrix oxides concentration / 10 M
# RM     : Avg. # of rooms per building
# AGE    : prop. of buildings built prior to 1940
# DIS    : Weighted distances to employment centers
# RAD    : Index of radian highway access
# TAX    : Full tax rate value per $10k
# PTRATIO: Pupil/Teacher ratio by town
# B      : 1000*(Bk-0.63)^2, Bk=prop. of blacks
# LSTAT  : % lower status of pop
#------------y-value-----------
# MEDV   : Median Value of homes in $1,000's

import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
import requests
from tensorflow.python.framework import ops
ops.reset_default_graph()

# Create graph
sess = tf.Session()

# Load the data
housing_url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/housing/housing.data'
housing_header = ['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT', 'MEDV']
cols_used = ['CRIM', 'INDUS', 'NOX', 'RM', 'AGE', 'DIS', 'TAX', 'PTRATIO', 'B', 'LSTAT']
num_features = len(cols_used)
housing_file = requests.get(housing_url)
housing_data = [[float(x) for x in y.split(' ') if len(x)>=1] for y in housing_file.text.split('\n') if len(y)>=1]

y_vals = np.transpose([np.array([y[13] for y in housing_data])])
x_vals = np.array([[x for i,x in enumerate(y) if housing_header[i] in cols_used] for y in housing_data])

## Min-Max Scaling
x_vals = (x_vals - x_vals.min(0)) / x_vals.ptp(0)

# Split the data into train and test sets
np.random.seed(13)  #make results reproducible
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]

# Declare k-value and batch size
k = 4
batch_size=len(x_vals_test)

# Placeholders
x_data_train = tf.placeholder(shape=[None, num_features], dtype=tf.float32)
x_data_test = tf.placeholder(shape=[None, num_features], dtype=tf.float32)
y_target_train = tf.placeholder(shape=[None, 1], dtype=tf.float32)
y_target_test = tf.placeholder(shape=[None, 1], dtype=tf.float32)

# Declare distance metric
# L1
distance = tf.reduce_sum(tf.abs(tf.subtract(x_data_train, tf.expand_dims(x_data_test,1))), axis=2)

# L2
#distance = tf.sqrt(tf.reduce_sum(tf.square(tf.subtract(x_data_train, tf.expand_dims(x_data_test,1))), reduction_indices=1))

# Predict: Get min distance index (Nearest neighbor)
#prediction = tf.arg_min(distance, 0)
top_k_xvals, top_k_indices = tf.nn.top_k(tf.negative(distance), k=k)
x_sums = tf.expand_dims(tf.reduce_sum(top_k_xvals, 1),1)
x_sums_repeated = tf.matmul(x_sums,tf.ones([1, k], tf.float32))
x_val_weights = tf.expand_dims(tf.div(top_k_xvals,x_sums_repeated), 1)

top_k_yvals = tf.gather(y_target_train, top_k_indices)
prediction = tf.squeeze(tf.matmul(x_val_weights,top_k_yvals), axis=[1])

# Calculate MSE
mse = tf.div(tf.reduce_sum(tf.square(tf.subtract(prediction, y_target_test))), batch_size)

# Calculate how many loops over training data
num_loops = int(np.ceil(len(x_vals_test)/batch_size))

for i in range(num_loops):
    min_index = i*batch_size
    max_index = min((i+1)*batch_size,len(x_vals_train))
    x_batch = x_vals_test[min_index:max_index]
    y_batch = y_vals_test[min_index:max_index]
    predictions = sess.run(prediction, feed_dict={x_data_train: x_vals_train, x_data_test: x_batch,
                                         y_target_train: y_vals_train, y_target_test: y_batch})
    batch_mse = sess.run(mse, feed_dict={x_data_train: x_vals_train, x_data_test: x_batch,
                                         y_target_train: y_vals_train, y_target_test: y_batch})

    print('Batch #' + str(i+1) + ' MSE: ' + str(np.round(batch_mse,3)))

# Plot prediction and actual distribution
bins = np.linspace(5, 50, 45)

plt.hist(predictions, bins, alpha=0.5, label='Prediction')
plt.hist(y_batch, bins, alpha=0.5, label='Actual')
plt.title('Histogram of Predicted and Actual Values')
plt.xlabel('Med Home Value in $1,000s')
plt.ylabel('Frequency')
plt.legend(loc='upper right')
plt.show()