def make_columns():
user_id = fc.embedding_column(fc.categorical_column_with_vocabulary_file(
'user_id', vocabulary_file='user_id', dtype=tf.string, num_oov_buckets=4), dimension=6)
partner_ids = fc.categorical_column_with_vocabulary_file(
'reserve_partner_car_type_id', vocabulary_file='partner_car_type_id', dtype=tf.string, num_oov_buckets=1)
partner_ids_embedding = fc.embedding_column(partner_ids, dimension=3)
# partner_ids_embedding = fc.indicator_column(partner_ids)
dayofweek = fc.embedding_column(fc.categorical_column_with_vocabulary_list(
'dayofweek', [str(d) for d in range(0, 8)], dtype=tf.string, num_oov_buckets=1), dimension=3)
timeSlice = fc.embedding_column(fc.categorical_column_with_vocabulary_file(
'timeSlice', vocabulary_file='timeSlice', dtype=tf.string, num_oov_buckets=1), dimension=3)
sHexID = fc.embedding_column(fc.categorical_column_with_vocabulary_file(
'sHexID', vocabulary_file='sHexID', num_oov_buckets=1), dimension=6)
eHexID = fc.embedding_column(fc.categorical_column_with_vocabulary_file(
'eHexID', vocabulary_file='eHexID', num_oov_buckets=1), dimension=6)
order_columns = [
fc.numeric_column('dist')
]
user_columns = [fc.numeric_column(c) for c in user_null_columns + user_float32_columns]
spacetime_columns = [fc.numeric_column(c) for c in int64_columns + float32_columns]
embedding_columns = [user_id, partner_ids_embedding, dayofweek, timeSlice, sHexID]
# embedding_columns = [dayofweek]
# return embedding_columns + order_columns, embedding_columns + order_columns + spacetime_columns
return embedding_columns, order_columns, spacetime_columns, user_columns
def _base():
education_num=fc.numeric_column('education_num')
capital_gain=fc.numeric_column('capital_gain')
capital_loss=fc.numeric_column('capital_loss')
hours_per_week=fc.numeric_column('hours_per_week')
#categorical,embedding_column
relationship=fc.categorical_column_with_vocabulary_file('relationship',vocabulary_file='data/relationship')
relationship=fc.indicator_column(relationship)
education=fc.categorical_column_with_vocabulary_file('education',vocabulary_file='data/education')
education=fc.indicator_column(education)
race=fc.categorical_column_with_vocabulary_file('race',vocabulary_file='data/race')
race=fc.indicator_column(race)
occupation=fc.indicator_column(fc.categorical_column_with_hash_bucket('occupation',20))
return [education_num,capital_gain,capital_loss,hours_per_week,relationship,education,race,occupation]
def categorical_column(key, vocabulary_size=None,
vocabulary_list=None,
vocabulary_file=None,
num_oov_buckets=0):
if vocabulary_size:
categorical_col = feature_column.categorical_column_with_identity(key, vocabulary_size)
return categorical_col
elif vocabulary_list:
assert isinstance(vocabulary_list[0], six.string_types), "Vocabulary must be sequence of string"
categorical_col = feature_column.categorical_column_with_vocabulary_list(key, vocabulary_list, num_oov_buckets)
return categorical_col
elif vocabulary_file:
categorical_col = feature_column.categorical_column_with_vocabulary_file(key, vocabulary_file, num_oov_buckets)
return categorical_col
def make_columns_with_normalizer_with_file():
with open('summary.json') as fp:
import pandas as pd
summary = pd.DataFrame(json.load(fp)).T
# categorical_column_with_vocabulary_list
user_id = fc.embedding_column(fc.categorical_column_with_vocabulary_file(
'user_id', vocabulary_file='user_id', dtype=tf.string, num_oov_buckets=4), dimension=6)
partner_ids = fc.categorical_column_with_vocabulary_file(
'reserve_partner_car_type_id', vocabulary_file='partner_car_type_id', dtype=tf.string, num_oov_buckets=1)
partner_ids_embedding = fc.embedding_column(partner_ids, dimension=3)
# partner_ids_embedding = fc.indicator_column(partner_ids)
dayofweek = fc.embedding_column(fc.categorical_column_with_vocabulary_list(
'dayofweek', [str(d) for d in range(0, 8)], dtype=tf.string, num_oov_buckets=1), dimension=3)
timeSlice = fc.embedding_column(fc.categorical_column_with_vocabulary_file(
'timeSlice', vocabulary_file='timeSlice', dtype=tf.string, num_oov_buckets=1), dimension=3)
sHexID = fc.embedding_column(fc.categorical_column_with_vocabulary_file(
'sHexID', vocabulary_file='sHexID', num_oov_buckets=1), dimension=6)
eHexID = fc.embedding_column(fc.categorical_column_with_vocabulary_file(
'eHexID', vocabulary_file='eHexID', num_oov_buckets=1), dimension=6)
order_columns = [
fc.numeric_column('dist', normalizer_fn=lambda v: normalizer_fn(v, float(summary['dist']['min']), float(summary['dist']['max'])))
]
user_columns = [fc.numeric_column(c) for c in user_null_columns + user_float32_columns]
# TODO: summary info
spacetime_columns = [fc.numeric_column(c) for c in int64_columns]
spacetime_columns += [fc.numeric_column(c, normalizer_fn=lambda v: normalizer_fn(v, float(summary[c]['min']), float(summary[c]['max']))) for c in float32_columns]
embedding_columns = [user_id, partner_ids_embedding, dayofweek, timeSlice, sHexID]
# embedding_columns = [dayofweek]
# return embedding_columns + order_columns, embedding_columns + order_columns + spacetime_columns
return embedding_columns, order_columns, spacetime_columns, user_columns
def create_tf_categorical_feature_cols(categorical_col_list,
vocab_dir='./diabetes_vocab/'):
'''
categorical_col_list: list, categorical field list that will be transformed with TF feature column
vocab_dir: string, the path where the vocabulary text files are located
return:
output_tf_list: list of TF feature columns
'''
output_tf_list = []
for c in categorical_col_list:
vocab_file_path = os.path.join(vocab_dir, c + "_vocab.txt")
'''
Which TF function allows you to read from a text file and create a categorical feature
You can use a pattern like this below...
tf_categorical_feature_column = tf.feature_column.......
'''
cat = feature_column.categorical_column_with_vocabulary_file(
c, vocab_file_path)
col = feature_column.indicator_column(cat)
output_tf_list.append(col)
return output_tf_list
feature_columns.append(resStatus_one_hot)
arrivalMonth = feature_column.categorical_column_with_vocabulary_list(
'ArrivalDateMonth', [
'January', 'February', 'March', 'April', 'May', 'June', 'July',
'August', 'September', 'October', 'November', 'December'
])
arrivalMonth_one_hot = feature_column.indicator_column(arrivalMonth)
feature_columns.append(arrivalMonth_one_hot)
countryNames = feature_column.categorical_column_with_vocabulary_file(
'Country',
sys.argv[3],
vocabulary_size=None,
dtype=tf.dtypes.string,
default_value=None,
num_oov_buckets=0)
countryNames_one_hot = feature_column.indicator_column(countryNames)
feature_columns.append(countryNames_one_hot)
for header in [
'LeadTime', 'ArrivalDateWeekNumber', 'StaysInWeekendNights',
'StaysInWeekNights', 'Adults', 'Children', 'Babies',
'PreviousCancellations', 'PreviousBookingsNotCanceled',
'BookingChanges', 'DaysInWaitingList', 'RequiredCarParkingSpaces',
'TotalOfSpecialRequests', 'ADR', 'ArrivalDateDayOfMonth',
'ArrivalDateYear', 'Agent', 'Company'
#-*- coding:utf-8 -*-
#定义feature_columns
import tensorflow as tf
from tensorflow import feature_column as fc
#-----------------------用户特征列-----------------------------
province = fc.indicator_column(
fc.categorical_column_with_vocabulary_file('province',
'resource/province'))
region = fc.indicator_column(
fc.categorical_column_with_vocabulary_list(
'region', ['东北', '华中', '华东', '华北', '西北', '华南', '西南']))
city = fc.indicator_column(
fc.categorical_column_with_vocabulary_file('city', 'resource/city'))
city_level = fc.indicator_column(
fc.categorical_column_with_vocabulary_list(
'city_level', ['一线城市', '新一线城市', '二线城市', '三线城市', '四线城市', '五线城市']))
browser = fc.indicator_column(
fc.categorical_column_with_vocabulary_list('browser', [0, 1]))
os = fc.indicator_column(
fc.categorical_column_with_vocabulary_list(
'os', ['Android', 'android', 'devtools', 'unknown', 'iPhone', 'ios']))
ipv_7d_type = fc.indicator_column(
fc.categorical_column_with_vocabulary_list('ipv_7d_type', [1, 2, 3, 4]))
ipv_15d_type = fc.indicator_column(
fc.categorical_column_with_vocabulary_list('ipv_15d_type', [1, 2, 3, 4]))
ipv_30d_type = fc.indicator_column(
fc.categorical_column_with_vocabulary_list('ipv_30d_type', [1, 2, 3, 4]))
ipv_60d_type = fc.indicator_column(
fc.categorical_column_with_vocabulary_list('ipv_60d_type', [1, 2, 3, 4]))
feature_columns.append(resStatus_one_hot)
arrivalMonth = feature_column.categorical_column_with_vocabulary_list(
'ArrivalDateMonth', [
'January', 'February', 'March', 'April', 'May', 'June', 'July',
'August', 'September', 'October', 'November', 'December'
])
arrivalMonth_one_hot = feature_column.indicator_column(arrivalMonth)
feature_columns.append(arrivalMonth_one_hot)
countryNames = feature_column.categorical_column_with_vocabulary_file(
'Country',
'E:/stech/Documents/Uni/4thYear/Honours/CountryNames.csv',
vocabulary_size=None,
dtype=tf.dtypes.string,
default_value=None,
num_oov_buckets=0)
countryNames_one_hot = feature_column.indicator_column(countryNames)
feature_columns.append(countryNames_one_hot)
for header in [
'LeadTime', 'ArrivalDateWeekNumber', 'StaysInWeekendNights',
'StaysInWeekNights', 'Adults', 'Children', 'Babies',
'PreviousCancellations', 'PreviousBookingsNotCanceled',
'BookingChanges', 'DaysInWaitingList', 'RequiredCarParkingSpaces',
'TotalOfSpecialRequests', 'ADR', 'ArrivalDateDayOfMonth',
'ArrivalDateYear', 'Agent', 'Company'
