forked from mlflow/mlflow
-
Notifications
You must be signed in to change notification settings - Fork 0
/
prophet.py
301 lines (251 loc) · 12.1 KB
/
prophet.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
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
"""
The ``mlflow.prophet`` module provides and API for logging and loading Prophet models.
This module exports univariate Prophet models in the following flavors:
Prophet (native) format
This is the main flavor that can be accessed with Prophet APIs.
:py:mod:`mlflow.pyfunc`
Produced for use by generic pyfunc-based deployment tools and for batch auditing
of historical forecasts.
.. _Prophet:
https://facebook.github.io/prophet/docs/quick_start.html#python-api
"""
import os
import yaml
import json
import mlflow
from mlflow import pyfunc
from mlflow.utils.requirements_utils import _get_pinned_requirement
from mlflow.utils.environment import (
_mlflow_conda_env,
_validate_env_arguments,
_process_pip_requirements,
_process_conda_env,
_CONDA_ENV_FILE_NAME,
_REQUIREMENTS_FILE_NAME,
_CONSTRAINTS_FILE_NAME,
)
from mlflow.utils.file_utils import write_to
from mlflow.utils.docstring_utils import format_docstring, LOG_MODEL_PARAM_DOCS
from mlflow.models.signature import ModelSignature
from mlflow.models.utils import _save_example
from mlflow.models import Model, ModelInputExample
from mlflow.tracking.artifact_utils import _download_artifact_from_uri
from mlflow.utils.model_utils import _get_flavor_configuration
from mlflow.models.model import MLMODEL_FILE_NAME
from mlflow.exceptions import MlflowException
from mlflow.tracking._model_registry import DEFAULT_AWAIT_MAX_SLEEP_SECONDS
FLAVOR_NAME = "prophet"
_MODEL_BINARY_KEY = "data"
_MODEL_BINARY_FILE_NAME = "model.pr"
_MODEL_TYPE_KEY = "model_type"
def get_default_pip_requirements():
"""
:return: A list of default pip requirements for MLflow Models produced by this flavor.
Calls to :func:`save_model()` and :func:`log_model()` produce a pip environment
that, at a minimum, contains these requirements.
"""
# Note: Prophet's whl build process will fail due to missing dependencies, defaulting
# to setup.py installation process.
# If a pystan installation error occurs, ensure gcc>=8 is installed in your environment.
# See: https://gcc.gnu.org/install/
return [_get_pinned_requirement("prophet")]
def get_default_conda_env():
"""
:return: The default Conda environment for MLflow Models produced by calls to
:func:`save_model()` and :func:`log_model()`.
"""
return _mlflow_conda_env(additional_pip_deps=get_default_pip_requirements())
@format_docstring(LOG_MODEL_PARAM_DOCS.format(package_name=FLAVOR_NAME))
def save_model(
pr_model,
path,
conda_env=None,
mlflow_model=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
pip_requirements=None,
extra_pip_requirements=None,
):
"""
Save a Prophet model to a path on the local file system.
:param pr_model: Prophet model (an instance of Prophet() forecaster that has been fit
on a temporal series.
:param path: Local path where the serialized model (as JSON) is to be saved.
:param conda_env: {{ conda_env }}
:param mlflow_model: :py:mod:`mlflow.models.Model` this flavor is being added to.
:param signature: :py:class:`ModelSignature <mlflow.models.ModelSignature>`
describes model input and output :py:class:`Schema <mlflow.types.Schema>`.
The model signature can be :py:func:`inferred <mlflow.models.infer_signature>`
from datasets with valid model input (e.g. the training dataset with target
column omitted) and valid model output (e.g. model predictions generated on
the training dataset), for example:
.. code-block:: python
from mlflow.models.signature import infer_signature
model = Prophet().fit(df)
train = model.history
predictions = model.predict(model.make_future_dataframe(30))
signature = infer_signature(train, predictions)
:param input_example: Input example provides one or several instances of valid
model input. The example can be used as a hint of what data to feed the
model. The given example will be converted to a Pandas DataFrame and then
serialized to json using the Pandas split-oriented format. Bytes are
base64-encoded.
:param pip_requirements: {{ pip_requirements }}
:param extra_pip_requirements: {{ extra_pip_requirements }}
"""
import prophet
_validate_env_arguments(conda_env, pip_requirements, extra_pip_requirements)
path = os.path.abspath(path)
if os.path.exists(path):
raise MlflowException(f"Path '{path}' already exists")
os.makedirs(path)
if mlflow_model is None:
mlflow_model = Model()
if signature is not None:
mlflow_model.signature = signature
if input_example is not None:
_save_example(mlflow_model, input_example, path)
model_data_path = os.path.join(path, _MODEL_BINARY_FILE_NAME)
_save_model(pr_model, model_data_path)
model_bin_kwargs = {_MODEL_BINARY_KEY: _MODEL_BINARY_FILE_NAME}
pyfunc.add_to_model(
mlflow_model, loader_module="mlflow.prophet", env=_CONDA_ENV_FILE_NAME, **model_bin_kwargs
)
flavor_conf = {
_MODEL_TYPE_KEY: pr_model.__class__.__name__,
**model_bin_kwargs,
}
mlflow_model.add_flavor(
FLAVOR_NAME,
prophet_version=prophet.__version__,
**flavor_conf,
)
mlflow_model.save(os.path.join(path, MLMODEL_FILE_NAME))
if conda_env is None:
if pip_requirements is None:
# cannot use inferred requirements due to prophet's build process
# as the package installation of pystan requires Cython to be present
# in the path. Prophet's installation itself requires imports of
# existing libraries, preventing the execution of a batched pip install
# and instead using a a strictly defined list of dependencies.
# NOTE: if Prophet .whl build architecture is changed, this should be
# modified to a standard inferred approach.
default_reqs = get_default_pip_requirements()
else:
default_reqs = None
conda_env, pip_requirements, pip_constraints = _process_pip_requirements(
default_reqs,
pip_requirements,
extra_pip_requirements,
)
else:
conda_env, pip_requirements, pip_constraints = _process_conda_env(conda_env)
with open(os.path.join(path, _CONDA_ENV_FILE_NAME), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
if pip_constraints:
write_to(os.path.join(path, _CONSTRAINTS_FILE_NAME), "\n".join(pip_constraints))
write_to(os.path.join(path, _REQUIREMENTS_FILE_NAME), "\n".join(pip_requirements))
@format_docstring(LOG_MODEL_PARAM_DOCS.format(package_name=FLAVOR_NAME))
def log_model(
pr_model,
artifact_path,
conda_env=None,
registered_model_name=None,
signature: ModelSignature = None,
input_example: ModelInputExample = None,
await_registration_for=DEFAULT_AWAIT_MAX_SLEEP_SECONDS,
pip_requirements=None,
extra_pip_requirements=None,
):
"""
Log a Prophet model as an MLflow artifact for the current run.
:param pr_model: Prophet model to be saved.
:param artifact_path: Run-relative artifact path.
:param conda_env: {{ conda_env }}
:param registered_model_name: This argument may change or be removed in a
future release without warning. If given, create a model
version under ``registered_model_name``, also creating a
registered model if one with the given name does not exist.
:param signature: :py:class:`ModelSignature <mlflow.models.ModelSignature>`
describes model input and output
:py:class:`Schema <mlflow.types.Schema>`.
The model signature can be :py:func:`inferred
<mlflow.models.infer_signature>` from datasets with valid model input
(e.g. the training dataset with target column omitted) and valid model
output (e.g. model predictions generated on the training dataset),
for example:
.. code-block:: python
from mlflow.models.signature import infer_signature
model = Prophet().fit(df)
train = model.history
predictions = model.predict(model.make_future_dataframe(30))
signature = infer_signature(train, predictions)
:param input_example: Input example provides one or several instances of valid
model input. The example can be used as a hint of what data to
feed the model. The given example will be converted to a
Pandas DataFrame and then serialized to json using the
Pandas split-oriented format. Bytes are base64-encoded.
:param await_registration_for: Number of seconds to wait for the model version
to finish being created and is in ``READY`` status.
By default, the function waits for five minutes.
Specify 0 or None to skip waiting.
:param pip_requirements: {{ pip_requirements }}
:param extra_pip_requirements: {{ extra_pip_requirements }}
:return: A :py:class:`ModelInfo <mlflow.models.model.ModelInfo>` instance that contains the
metadata of the logged model.
"""
return Model.log(
artifact_path=artifact_path,
flavor=mlflow.prophet,
registered_model_name=registered_model_name,
pr_model=pr_model,
conda_env=conda_env,
signature=signature,
input_example=input_example,
await_registration_for=await_registration_for,
pip_requirements=pip_requirements,
extra_pip_requirements=extra_pip_requirements,
)
def _save_model(model, path):
from prophet.serialize import model_to_json
model_ser = model_to_json(model)
with open(path, "w") as f:
json.dump(model_ser, f)
def _load_model(path):
from prophet.serialize import model_from_json
with open(path, "r") as f:
model = json.load(f)
return model_from_json(model)
def _load_pyfunc(path):
"""
Load PyFunc implementation for Prophet. Called by ``pyfunc.load_pyfunc``.
:param path: Local filesystem path to the MLflow Model with the ``prophet`` flavor.
"""
return _ProphetModelWrapper(_load_model(path))
def load_model(model_uri, dst_path=None):
"""
Load a Prophet model from a local file or a run.
:param model_uri: The location, in URI format, of the MLflow model. For example:
- ``/Users/me/path/to/local/model``
- ``relative/path/to/local/model``
- ``s3://my_bucket/path/to/model``
- ``runs:/<mlflow_run_id>/run-relative/path/to/model``
For more information about supported URI schemes, see
`Referencing Artifacts <https://www.mlflow.org/docs/latest/tracking.html#
artifact-locations>`_.
:param dst_path: The local filesystem path to which to download the model artifact.
This directory must already exist. If unspecified, a local output
path will be created.
:return: A Prophet model instance
"""
local_model_path = _download_artifact_from_uri(artifact_uri=model_uri, output_path=dst_path)
flavor_conf = _get_flavor_configuration(model_path=local_model_path, flavor_name=FLAVOR_NAME)
pr_model_path = os.path.join(
local_model_path, flavor_conf.get(_MODEL_BINARY_KEY, _MODEL_BINARY_FILE_NAME)
)
return _load_model(pr_model_path)
class _ProphetModelWrapper:
def __init__(self, pr_model):
self.pr_model = pr_model
def predict(self, dataframe):
return self.pr_model.predict(dataframe)