【学习笔记】合成特征与离群值

1
2
3
4
5
6
df = pd.read_csv('california_housing_train.csv')
df['median_house_value'] /=1000
df['rooms_per_person'] = df['total_rooms']/df['population'].astype('float32')
df = df.reindex(np.random.permutation(df.index))
x1 = df[['rooms_per_person']]
y1 = df[['median_house_value']].astype('float32')

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
import pandas as pd
import tensorflow as tf
import numpy as np


def add_layer(inputs, input_size, output_size, activation_function=None):
    weights = tf.Variable(tf.random_normal([input_size, output_size]))
    biases = tf.Variable(tf.zeros(output_size)+0.1)
    wx_b = tf.matmul(inputs, weights) + biases
    if activation_function is None:
        outputs = wx_b
    else:
        outputs = activation_function(wx_b)
    return outputs


df = pd.read_csv('california_housing_train.csv')
df['median_house_value'] /= 1000
df['rooms_per_person'] = df['total_rooms']/df['population'].astype('float32')
df = df.reindex(np.random.permutation(df.index))
x1 = df[['rooms_per_person']]
y1 = df[['median_house_value']].astype('float32')


xs = tf.placeholder(tf.float32, [None, 1])
ys = tf.placeholder(tf.float32, [None, 1])

l1 = add_layer(xs, 1, 1)

loss = tf.sqrt(tf.reduce_mean(tf.square(l1 - ys)))

train_step = tf.train.AdamOptimizer(0.1).minimize(loss)

sess = tf.Session()
init = tf.global_variables_initializer()
sess.run(init)
for i in range(1000):
    sess.run(train_step, feed_dict={xs: x1, ys: y1})
    if i % 50 == 0:
        print(sess.run(loss, feed_dict={xs: x1, ys: y1}))

1
df['rooms_per_person'] = df['rooms_per_person'].apply(lambda x:min(x, 5))

1
df['rooms_per_person'] = np.clip(df['rooms_per_person'], 0, 5)