tensorflow feature_column 讲解

官网写的很清楚

• 我自己跑了一遍，贴个代码

import numpy as np
import pandas as pd

import tensorflow as tf

from tensorflow import feature_column
from tensorflow.keras import layers
from sklearn.model_selection import train_test_split

import pathlib

dataset_url = 'http://storage.googleapis.com/download.tensorflow.org/data/petfinder-mini.zip'
csv_file = 'datasets/petfinder-mini/petfinder-mini.csv'

tf.keras.utils.get_file('petfinder_mini.zip', dataset_url,
                        extract=True, cache_dir='.')
dataframe = pd.read_csv(csv_file)

print(dataframe.head())

dataframe['target'] = np.where(dataframe['AdoptionSpeed']==4, 0, 1)

# Drop un-used columns.
dataframe = dataframe.drop(columns=['AdoptionSpeed', 'Description'])

train, test = train_test_split(dataframe, test_size=0.2)
train, val = train_test_split(train, test_size=0.2)
print(len(train), 'train examples')
print(len(val), 'validation examples')
print(len(test), 'test examples')


def df_to_dataset(dataframe, shuffle=True, batch_size=32):
  dataframe = dataframe.copy()
  labels = dataframe.pop('target')
  ds = tf.data.Dataset.from_tensor_slices((dict(dataframe), labels))
  if shuffle:
    ds = ds.shuffle(buffer_size=len(dataframe))
  ds = ds.batch(batch_size)
  return ds




batch_size = 5 # A small batch sized is used for demonstration purposes
train_ds = df_to_dataset(train, batch_size=batch_size)
val_ds = df_to_dataset(val, shuffle=False, batch_size=batch_size)
test_ds = df_to_dataset(test, shuffle=False, batch_size=batch_size)


for feature_batch, label_batch in train_ds.take(1):
  print('Every feature:', list(feature_batch.keys()))
  print('A batch of ages:', feature_batch['Age'])
  print('A batch of targets:', label_batch )


# We will use this batch to demonstrate several types of feature columns
example_batch = next(iter(train_ds))[0]


# A utility method to create a feature column
# and to transform a batch of data
def demo(feature_column):
  feature_layer = layers.DenseFeatures(feature_column)
  print(feature_layer(example_batch).numpy())



photo_count = feature_column.numeric_column('PhotoAmt')
demo(photo_count)


age = feature_column.numeric_column('Age')
age_buckets = feature_column.bucketized_column(age, boundaries=[1, 3, 5])
demo(age_buckets)

animal_type = feature_column.categorical_column_with_vocabulary_list(
      'Type', ['Cat', 'Dog'])

animal_type_one_hot = feature_column.indicator_column(animal_type)
demo(animal_type_one_hot)


breed1 = feature_column.categorical_column_with_vocabulary_list(
      'Breed1', dataframe.Breed1.unique())
breed1_embedding = feature_column.embedding_column(breed1, dimension=8)
demo(breed1_embedding)

print(dataframe.Breed1.unique())
breed1_hashed = feature_column.categorical_column_with_hash_bucket(
      'Breed1', hash_bucket_size=20)
demo(feature_column.indicator_column(breed1_hashed))



'''
Crossed feature columns
Combining features into a single feature, better known as feature crosses,
 enables a model to learn separate weights for each combination of features. 
 Here, we will create a new feature that is the cross of Age and Type. 
 Note that crossed_column does not build the full table of all possible combinations (which could be very large). 
Instead, it is backed by a hashed_column, so you can choose how large the table is.
'''

crossed_feature = feature_column.crossed_column([age_buckets, animal_type], hash_bucket_size=10)
demo(feature_column.indicator_column(crossed_feature))
'''
tensorflow 官网的demo 运行出错  我也是佛了  
[[1. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
 [0. 1. 0. 0. 0. 0. 0. 0. 0. 0.]
 [0. 0. 0. 0. 0. 0. 0. 0. 1. 0.]
 [0. 1. 0. 0. 0. 0. 0. 0. 0. 0.]
 [0. 0. 0. 0. 0. 0. 1. 0. 0. 0.]]
'''

参考：https://tensorflow.google.cn/tutorials/structured_data/feature_columns
https://blog.csdn.net/u014021893/article/details/80423112