【学习笔记】特征组合编程练习

import numpy as np
import pandas as pd
import tensorflow as tf

df = pd.read_csv('california_housing_train.csv')

def z_score(features):
    df = (features - features.mean()) / features.std()
    return df


def log_score(features):
    df = np.log(features + 1)
    return df


def gets_onehot(inputs, features, buckets):
    _inputs = {features: inputs.values}
    df_fc = tf.feature_column.numeric_column(features)
    _range = np.linspace(inputs.min(), inputs.max(), buckets+2)
    _range = np.delete(_range, -1)
    _range = np.delete(_range, 0)
    _column = tf.feature_column.bucketized_column(df_fc, list(_range))
    _tensor = tf.feature_column.input_layer(_inputs, [_column])
    return _tensor


df['per_rooms'] = df['total_rooms'] / df['population']
df['per_bedrooms'] = df['total_bedrooms'] / df['population']

df['households'] = log_score(df['households'])
df['housing_median_age'] = log_score(df['housing_median_age'])
df['median_house_value'] = log_score(df['median_house_value'])
df['per_rooms'] = log_score(df['per_rooms'])
df['per_bedrooms'] = log_score(df['per_bedrooms'])
df['median_income'] = log_score(df['median_income'])

sess = tf.Session()

df1 = sess.run(gets_onehot(df['latitude'], 'latitude', 6)).copy()
df2 = sess.run(gets_onehot(df['longitude'], 'longitude', 6)).copy()
df1 = pd.DataFrame(df1, columns=['latitude1', 'latitude2', 'latitude3', 'latitude4', 'latitude5'
                                 , 'latitude6', 'latitude7'])
df2 = pd.DataFrame(df2, columns=['longitude1', 'longitude2