This repository has been archived by the owner on Apr 2, 2022. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 232
/
metadata.py
50 lines (43 loc) · 1.46 KB
/
metadata.py
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
45
46
47
48
49
50
# Copyright 2019 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Dataset metadata."""
# If the input CSV file has a header row, then set CSV_COLUMNS to None.
# Otherwise, set CSV_COLUMNS to a list of target and feature names:
CSV_COLUMNS = None
# Target name
TARGET_NAME = 'tip'
# The features to be used for training.
# If FEATURE_NAMES is None, then all the available columns will be
# used as features, except for the target column.
FEATURE_NAMES = [
'trip_miles',
'trip_seconds',
'fare',
'trip_start_month',
'trip_start_hour',
'trip_start_day',
]
# If the model is serialized using joblib
# then use 'model.joblib' for the model name
MODEL_FILE_NAME = 'model.joblib'
# Set to True if you want to tune some hyperparameters
HYPERPARAMTER_TUNING = True
# Used only if the dataset is to be read from BigQuery
BASE_QUERY = '''
SELECT
*
FROM
`{table}`
'''