mirror of
https://github.com/saymrwulf/prophet.git
synced 2026-11-21 09:15:36 +00:00
Replaced pystan with cmdstanpy (#1083)
* changes * added actual tests for fit method * precision * syntax * sampling not working * sampling seems to work * sampling not working again * sampling works, tests to be removed * replaced data with rmse * replace pystan with cmdstanpy * cleanup * cleanup * test for newton * added support for multiple backends * minor fixes * fixed comment * added support for --test-slow flag * fixed import * reverted style change * specify backend based on env variable * fixes * PR fixes
This commit is contained in:
parent
496facb152
commit
1d18adc0ba
7 changed files with 391 additions and 92 deletions
|
|
@ -1,7 +1,6 @@
|
||||||
dist: xenial
|
dist: xenial
|
||||||
language: python
|
language: python
|
||||||
python:
|
python:
|
||||||
- "2.7"
|
|
||||||
- "3.7"
|
- "3.7"
|
||||||
|
|
||||||
install:
|
install:
|
||||||
|
|
@ -10,3 +9,8 @@ install:
|
||||||
|
|
||||||
script:
|
script:
|
||||||
- cd python && python setup.py develop test
|
- cd python && python setup.py develop test
|
||||||
|
- python setup.py clean
|
||||||
|
- wget https://github.com/stan-dev/cmdstan/releases/download/v2.22.1/cmdstan-2.22.1.tar.gz -O /tmp/cmdstan.tar.gz > /dev/null
|
||||||
|
- tar -xvf /tmp/cmdstan.tar.gz -C /tmp > /dev/null
|
||||||
|
- make -C /tmp/cmdstan-2.22.1/ build > /dev/null
|
||||||
|
- CMDSTAN=/tmp/cmdstan-2.22.1 STAN_BACKEND=CMDSTANPY python setup.py develop test
|
||||||
|
|
|
||||||
|
|
@ -185,6 +185,7 @@ def prophet_copy(m, cutoff=None):
|
||||||
mcmc_samples=m.mcmc_samples,
|
mcmc_samples=m.mcmc_samples,
|
||||||
interval_width=m.interval_width,
|
interval_width=m.interval_width,
|
||||||
uncertainty_samples=m.uncertainty_samples,
|
uncertainty_samples=m.uncertainty_samples,
|
||||||
|
stan_backend=m.stan_backend.get_type()
|
||||||
)
|
)
|
||||||
m2.extra_regressors = deepcopy(m.extra_regressors)
|
m2.extra_regressors = deepcopy(m.extra_regressors)
|
||||||
m2.seasonalities = deepcopy(m.seasonalities)
|
m2.seasonalities = deepcopy(m.seasonalities)
|
||||||
|
|
|
||||||
|
|
@ -13,14 +13,10 @@ from datetime import timedelta, datetime
|
||||||
|
|
||||||
import numpy as np
|
import numpy as np
|
||||||
import pandas as pd
|
import pandas as pd
|
||||||
import pystan # noqa F401
|
|
||||||
|
|
||||||
from fbprophet.diagnostics import prophet_copy
|
|
||||||
from fbprophet.make_holidays import get_holiday_names, make_holidays_df
|
from fbprophet.make_holidays import get_holiday_names, make_holidays_df
|
||||||
from fbprophet.models import prophet_stan_model
|
from fbprophet.models import StanBackendEnum
|
||||||
from fbprophet.plot import (plot, plot_components, plot_forecast_component,
|
from fbprophet.plot import (plot, plot_components)
|
||||||
plot_seasonality, plot_weekly, plot_yearly,
|
|
||||||
seasonality_plot_df)
|
|
||||||
|
|
||||||
logger = logging.getLogger('fbprophet')
|
logger = logging.getLogger('fbprophet')
|
||||||
logger.addHandler(logging.NullHandler())
|
logger.addHandler(logging.NullHandler())
|
||||||
|
|
@ -77,6 +73,9 @@ class Prophet(object):
|
||||||
uncertainty_samples: Number of simulated draws used to estimate
|
uncertainty_samples: Number of simulated draws used to estimate
|
||||||
uncertainty intervals. Settings this value to 0 or False will disable
|
uncertainty intervals. Settings this value to 0 or False will disable
|
||||||
uncertainty estimation and speed up the calculation.
|
uncertainty estimation and speed up the calculation.
|
||||||
|
uncertainty intervals.
|
||||||
|
stan_backend: str as defined in StanBackendEnum default: None - will try to
|
||||||
|
iterate over all available backends and find the working one
|
||||||
"""
|
"""
|
||||||
|
|
||||||
def __init__(
|
def __init__(
|
||||||
|
|
@ -96,6 +95,7 @@ class Prophet(object):
|
||||||
mcmc_samples=0,
|
mcmc_samples=0,
|
||||||
interval_width=0.80,
|
interval_width=0.80,
|
||||||
uncertainty_samples=1000,
|
uncertainty_samples=1000,
|
||||||
|
stan_backend=None
|
||||||
):
|
):
|
||||||
self.growth = growth
|
self.growth = growth
|
||||||
|
|
||||||
|
|
@ -140,6 +140,20 @@ class Prophet(object):
|
||||||
self.train_holiday_names = None
|
self.train_holiday_names = None
|
||||||
self.fit_kwargs = {}
|
self.fit_kwargs = {}
|
||||||
self.validate_inputs()
|
self.validate_inputs()
|
||||||
|
self._load_stan_backend(stan_backend)
|
||||||
|
|
||||||
|
def _load_stan_backend(self, stan_backend):
|
||||||
|
if stan_backend is None:
|
||||||
|
for i in StanBackendEnum:
|
||||||
|
try:
|
||||||
|
logger.debug("Trying to load backend: %s", i.name)
|
||||||
|
return self._load_stan_backend(i.name)
|
||||||
|
except Exception as e:
|
||||||
|
logger.info("Unable to load backend %s (%s), trying the next one", i.name, e)
|
||||||
|
else:
|
||||||
|
self.stan_backend = StanBackendEnum.get_backend_class(stan_backend)(logger)
|
||||||
|
|
||||||
|
logger.info("Loaded stan backend: %s", self.stan_backend.get_type())
|
||||||
|
|
||||||
def validate_inputs(self):
|
def validate_inputs(self):
|
||||||
"""Validates the inputs to Prophet."""
|
"""Validates the inputs to Prophet."""
|
||||||
|
|
@ -1108,10 +1122,7 @@ class Prophet(object):
|
||||||
dat['cap'] = history['cap_scaled']
|
dat['cap'] = history['cap_scaled']
|
||||||
kinit = self.logistic_growth_init(history)
|
kinit = self.logistic_growth_init(history)
|
||||||
|
|
||||||
model = prophet_stan_model
|
stan_init = {
|
||||||
|
|
||||||
def stan_init():
|
|
||||||
return {
|
|
||||||
'k': kinit[0],
|
'k': kinit[0],
|
||||||
'm': kinit[1],
|
'm': kinit[1],
|
||||||
'delta': np.zeros(len(self.changepoints_t)),
|
'delta': np.zeros(len(self.changepoints_t)),
|
||||||
|
|
@ -1122,44 +1133,14 @@ class Prophet(object):
|
||||||
if (history['y'].min() == history['y'].max()
|
if (history['y'].min() == history['y'].max()
|
||||||
and self.growth == 'linear'):
|
and self.growth == 'linear'):
|
||||||
# Nothing to fit.
|
# Nothing to fit.
|
||||||
self.params = stan_init()
|
self.params = stan_init
|
||||||
self.params['sigma_obs'] = 1e-9
|
self.params['sigma_obs'] = 1e-9
|
||||||
for par in self.params:
|
for par in self.params:
|
||||||
self.params[par] = np.array([self.params[par]])
|
self.params[par] = np.array([self.params[par]])
|
||||||
elif self.mcmc_samples > 0:
|
elif self.mcmc_samples > 0:
|
||||||
args = dict(
|
self.params = self.stan_backend.sampling(stan_init, dat, self.mcmc_samples, **kwargs)
|
||||||
data=dat,
|
|
||||||
init=stan_init,
|
|
||||||
iter=self.mcmc_samples,
|
|
||||||
)
|
|
||||||
args.update(kwargs)
|
|
||||||
self.stan_fit = model.sampling(**args)
|
|
||||||
for par in self.stan_fit.model_pars:
|
|
||||||
self.params[par] = self.stan_fit[par]
|
|
||||||
# Shape vector parameters
|
|
||||||
if (par in ['delta', 'beta']
|
|
||||||
and len(self.params[par].shape) < 2):
|
|
||||||
self.params[par] = self.params[par].reshape((-1, 1))
|
|
||||||
else:
|
else:
|
||||||
args = dict(
|
self.params = self.stan_backend.fit(stan_init, dat, **kwargs)
|
||||||
data=dat,
|
|
||||||
init=stan_init,
|
|
||||||
algorithm='Newton' if dat['T'] < 100 else 'LBFGS',
|
|
||||||
iter=1e4,
|
|
||||||
)
|
|
||||||
args.update(kwargs)
|
|
||||||
try:
|
|
||||||
self.stan_fit = model.optimizing(**args)
|
|
||||||
except RuntimeError:
|
|
||||||
logger.warning(
|
|
||||||
'Optimization terminated abnormally. '
|
|
||||||
'Falling back to Newton.'
|
|
||||||
)
|
|
||||||
args['algorithm'] = 'Newton'
|
|
||||||
self.stan_fit = model.optimizing(**args)
|
|
||||||
|
|
||||||
for par in self.stan_fit:
|
|
||||||
self.params[par] = self.stan_fit[par].reshape((1, -1))
|
|
||||||
|
|
||||||
# If no changepoints were requested, replace delta with 0s
|
# If no changepoints were requested, replace delta with 0s
|
||||||
if len(self.changepoints) == 0:
|
if len(self.changepoints) == 0:
|
||||||
|
|
|
||||||
|
|
@ -5,13 +5,253 @@
|
||||||
# LICENSE file in the root directory of this source tree.
|
# LICENSE file in the root directory of this source tree.
|
||||||
|
|
||||||
from __future__ import absolute_import, division, print_function
|
from __future__ import absolute_import, division, print_function
|
||||||
|
from abc import abstractmethod, ABC
|
||||||
|
from typing import Tuple
|
||||||
|
from collections import OrderedDict
|
||||||
|
from enum import Enum
|
||||||
import pickle
|
import pickle
|
||||||
|
|
||||||
import pkg_resources
|
import pkg_resources
|
||||||
|
import numpy as np
|
||||||
|
import os
|
||||||
|
|
||||||
|
|
||||||
def get_prophet_stan_model():
|
class IStanBackend(ABC):
|
||||||
|
def __init__(self, logger):
|
||||||
|
self.model = self.load_model()
|
||||||
|
self.logger = logger
|
||||||
|
|
||||||
|
@staticmethod
|
||||||
|
@abstractmethod
|
||||||
|
def get_type():
|
||||||
|
pass
|
||||||
|
|
||||||
|
@abstractmethod
|
||||||
|
def load_model(self):
|
||||||
|
pass
|
||||||
|
|
||||||
|
@abstractmethod
|
||||||
|
def fit(self, stan_init, stan_data, **kwargs) -> dict:
|
||||||
|
pass
|
||||||
|
|
||||||
|
@abstractmethod
|
||||||
|
def sampling(self, stan_init, stan_data, samples, **kwargs) -> dict:
|
||||||
|
pass
|
||||||
|
|
||||||
|
@staticmethod
|
||||||
|
@abstractmethod
|
||||||
|
def build_model(target_dir, model_dir):
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
|
class CmdStanPyBackend(IStanBackend):
|
||||||
|
|
||||||
|
@staticmethod
|
||||||
|
def get_type():
|
||||||
|
return StanBackendEnum.CMDSTANPY.name
|
||||||
|
|
||||||
|
@staticmethod
|
||||||
|
def build_model(target_dir, model_dir):
|
||||||
|
from shutil import copy
|
||||||
|
import cmdstanpy
|
||||||
|
model_name = 'prophet.stan'
|
||||||
|
target_name = 'prophet_model.bin'
|
||||||
|
|
||||||
|
sm = cmdstanpy.Model(stan_file=os.path.join(model_dir, model_name))
|
||||||
|
sm.compile()
|
||||||
|
copy(sm.exe_file, os.path.join(target_dir, target_name))
|
||||||
|
|
||||||
|
def load_model(self):
|
||||||
|
import cmdstanpy
|
||||||
|
model_file = pkg_resources.resource_filename(
|
||||||
|
'fbprophet',
|
||||||
|
'stan_model/prophet_model.bin',
|
||||||
|
)
|
||||||
|
return cmdstanpy.Model(exe_file=model_file)
|
||||||
|
|
||||||
|
def fit(self, stan_init, stan_data, **kwargs):
|
||||||
|
(stan_init, stan_data) = self.prepare_data(stan_init, stan_data)
|
||||||
|
if 'algorithm' not in kwargs:
|
||||||
|
kwargs['algorithm'] = 'Newton' if stan_data['T'] < 100 else 'LBFGS'
|
||||||
|
iterations = int(1e4)
|
||||||
|
try:
|
||||||
|
stan_fit = self.model.optimize(data=stan_data,
|
||||||
|
inits=stan_init,
|
||||||
|
iter=iterations,
|
||||||
|
**kwargs)
|
||||||
|
except RuntimeError as e:
|
||||||
|
# Fall back on Newton
|
||||||
|
if kwargs['algorithm'] != 'Newton':
|
||||||
|
self.logger.warning(
|
||||||
|
'Optimization terminated abnormally. Falling back to Newton.'
|
||||||
|
)
|
||||||
|
kwargs['algorithm'] = 'Newton'
|
||||||
|
stan_fit = self.model.optimize(data=stan_data,
|
||||||
|
inits=stan_init,
|
||||||
|
iter=iterations,
|
||||||
|
**kwargs)
|
||||||
|
else:
|
||||||
|
raise e
|
||||||
|
|
||||||
|
params = self.stan_to_dict_numpy(stan_fit.column_names, stan_fit.optimized_params_np)
|
||||||
|
for par in params:
|
||||||
|
params[par] = params[par].reshape((1, -1))
|
||||||
|
return params
|
||||||
|
|
||||||
|
def sampling(self, stan_init, stan_data, samples, **kwargs) -> dict:
|
||||||
|
(stan_init, stan_data) = self.prepare_data(stan_init, stan_data)
|
||||||
|
|
||||||
|
if 'chains' not in kwargs:
|
||||||
|
kwargs['chains'] = 4
|
||||||
|
if 'warmup_iters' not in kwargs:
|
||||||
|
kwargs['warmup_iters'] = samples // 2
|
||||||
|
|
||||||
|
stan_fit = self.model.sample(data=stan_data,
|
||||||
|
inits=stan_init,
|
||||||
|
sampling_iters=samples,
|
||||||
|
**kwargs)
|
||||||
|
res = stan_fit.sample
|
||||||
|
(samples, c, columns) = res.shape
|
||||||
|
res = res.reshape((samples * c, columns))
|
||||||
|
params = self.stan_to_dict_numpy(stan_fit.column_names, res)
|
||||||
|
|
||||||
|
for par in params:
|
||||||
|
s = params[par].shape
|
||||||
|
if s[1] == 1:
|
||||||
|
params[par] = params[par].reshape((s[0],))
|
||||||
|
|
||||||
|
if par in ['delta', 'beta'] and len(s) < 2:
|
||||||
|
params[par] = params[par].reshape((-1, 1))
|
||||||
|
|
||||||
|
return params
|
||||||
|
|
||||||
|
@staticmethod
|
||||||
|
def prepare_data(init, data) -> Tuple[dict, dict]:
|
||||||
|
cmdstanpy_data = {
|
||||||
|
'T': data['T'],
|
||||||
|
'S': data['S'],
|
||||||
|
'K': data['K'],
|
||||||
|
'tau': data['tau'],
|
||||||
|
'trend_indicator': data['trend_indicator'],
|
||||||
|
'y': data['y'].tolist(),
|
||||||
|
't': data['t'].tolist(),
|
||||||
|
'cap': data['cap'].tolist(),
|
||||||
|
't_change': data['t_change'].tolist(),
|
||||||
|
's_a': data['s_a'].tolist(),
|
||||||
|
's_m': data['s_m'].tolist(),
|
||||||
|
'X': data['X'].to_numpy().tolist(),
|
||||||
|
'sigmas': data['sigmas']
|
||||||
|
}
|
||||||
|
|
||||||
|
cmdstanpy_init = {
|
||||||
|
'k': init['k'],
|
||||||
|
'm': init['m'],
|
||||||
|
'delta': init['delta'].tolist(),
|
||||||
|
'beta': init['beta'].tolist(),
|
||||||
|
'sigma_obs': 1
|
||||||
|
}
|
||||||
|
return (cmdstanpy_init, cmdstanpy_data)
|
||||||
|
|
||||||
|
@staticmethod
|
||||||
|
def stan_to_dict_numpy(column_names: Tuple[str, ...], data: np.array):
|
||||||
|
output = OrderedDict()
|
||||||
|
|
||||||
|
prev = None
|
||||||
|
|
||||||
|
start = 0
|
||||||
|
end = 0
|
||||||
|
two_dims = True if len(data.shape) > 1 else False
|
||||||
|
for cname in column_names:
|
||||||
|
parsed = cname.split(".")
|
||||||
|
|
||||||
|
curr = parsed[0]
|
||||||
|
if prev is None:
|
||||||
|
prev = curr
|
||||||
|
|
||||||
|
if curr != prev:
|
||||||
|
if prev in output:
|
||||||
|
raise RuntimeError(
|
||||||
|
"Found repeated column name"
|
||||||
|
)
|
||||||
|
if two_dims:
|
||||||
|
output[prev] = np.array(data[:, start:end])
|
||||||
|
else:
|
||||||
|
output[prev] = np.array(data[start:end])
|
||||||
|
prev = curr
|
||||||
|
start = end
|
||||||
|
end += 1
|
||||||
|
else:
|
||||||
|
end += 1
|
||||||
|
|
||||||
|
if prev in output:
|
||||||
|
raise RuntimeError(
|
||||||
|
"Found repeated column name"
|
||||||
|
)
|
||||||
|
if two_dims:
|
||||||
|
output[prev] = np.array(data[:, start:end])
|
||||||
|
else:
|
||||||
|
output[prev] = np.array(data[start:end])
|
||||||
|
return output
|
||||||
|
|
||||||
|
|
||||||
|
class PyStanBackend(IStanBackend):
|
||||||
|
|
||||||
|
@staticmethod
|
||||||
|
def get_type():
|
||||||
|
return StanBackendEnum.PYSTAN.name
|
||||||
|
|
||||||
|
@staticmethod
|
||||||
|
def build_model(target_dir, model_dir):
|
||||||
|
import pystan
|
||||||
|
model_name = 'prophet.stan'
|
||||||
|
target_name = 'prophet_model.pkl'
|
||||||
|
with open(os.path.join(model_dir, model_name)) as f:
|
||||||
|
model_code = f.read()
|
||||||
|
sm = pystan.StanModel(model_code=model_code)
|
||||||
|
with open(os.path.join(target_dir, target_name), 'wb') as f:
|
||||||
|
pickle.dump(sm, f, protocol=pickle.HIGHEST_PROTOCOL)
|
||||||
|
|
||||||
|
def sampling(self, stan_init, stan_data, samples, **kwargs) -> dict:
|
||||||
|
|
||||||
|
args = dict(
|
||||||
|
data=stan_data,
|
||||||
|
init=lambda: stan_init,
|
||||||
|
iter=samples,
|
||||||
|
)
|
||||||
|
args.update(kwargs)
|
||||||
|
stan_fit = self.model.sampling(**args)
|
||||||
|
out = dict()
|
||||||
|
for par in stan_fit.model_pars:
|
||||||
|
out[par] = stan_fit[par]
|
||||||
|
# Shape vector parameters
|
||||||
|
if par in ['delta', 'beta'] and len(out[par].shape) < 2:
|
||||||
|
out[par] = out[par].reshape((-1, 1))
|
||||||
|
return out
|
||||||
|
|
||||||
|
def fit(self, stan_init, stan_data, **kwargs) -> dict:
|
||||||
|
|
||||||
|
args = dict(
|
||||||
|
data=stan_data,
|
||||||
|
init=lambda: stan_init,
|
||||||
|
algorithm='Newton' if stan_data['T'] < 100 else 'LBFGS',
|
||||||
|
iter=1e4,
|
||||||
|
)
|
||||||
|
args.update(kwargs)
|
||||||
|
try:
|
||||||
|
params = self.model.optimizing(**args)
|
||||||
|
except RuntimeError:
|
||||||
|
# Fall back on Newton
|
||||||
|
self.logger.warning(
|
||||||
|
'Optimization terminated abnormally. Falling back to Newton.'
|
||||||
|
)
|
||||||
|
args['algorithm'] = 'Newton'
|
||||||
|
params = self.model.optimizing(**args)
|
||||||
|
|
||||||
|
for par in params:
|
||||||
|
params[par] = params[par].reshape((1, -1))
|
||||||
|
|
||||||
|
return params
|
||||||
|
|
||||||
|
def load_model(self):
|
||||||
"""Load compiled Stan model"""
|
"""Load compiled Stan model"""
|
||||||
model_file = pkg_resources.resource_filename(
|
model_file = pkg_resources.resource_filename(
|
||||||
'fbprophet',
|
'fbprophet',
|
||||||
|
|
@ -21,4 +261,13 @@ def get_prophet_stan_model():
|
||||||
return pickle.load(f)
|
return pickle.load(f)
|
||||||
|
|
||||||
|
|
||||||
prophet_stan_model = get_prophet_stan_model()
|
class StanBackendEnum(Enum):
|
||||||
|
PYSTAN = PyStanBackend
|
||||||
|
CMDSTANPY = CmdStanPyBackend
|
||||||
|
|
||||||
|
@staticmethod
|
||||||
|
def get_backend_class(name: str) -> IStanBackend:
|
||||||
|
try:
|
||||||
|
return StanBackendEnum[name].value
|
||||||
|
except KeyError:
|
||||||
|
raise ValueError("Unknown stan backend: {}".format(name))
|
||||||
|
|
|
||||||
|
|
@ -9,13 +9,14 @@ from __future__ import print_function
|
||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
import os
|
import os
|
||||||
from unittest import TestCase
|
import sys
|
||||||
|
from unittest import TestCase, skipUnless
|
||||||
|
|
||||||
import numpy as np
|
import numpy as np
|
||||||
import pandas as pd
|
import pandas as pd
|
||||||
|
|
||||||
from fbprophet import Prophet
|
from fbprophet import Prophet
|
||||||
|
|
||||||
|
|
||||||
DATA = pd.read_csv(
|
DATA = pd.read_csv(
|
||||||
os.path.join(os.path.dirname(__file__), 'data.csv'),
|
os.path.join(os.path.dirname(__file__), 'data.csv'),
|
||||||
parse_dates=['ds'],
|
parse_dates=['ds'],
|
||||||
|
|
@ -28,14 +29,59 @@ DATA2 = pd.read_csv(
|
||||||
|
|
||||||
class TestProphet(TestCase):
|
class TestProphet(TestCase):
|
||||||
|
|
||||||
|
@staticmethod
|
||||||
|
def rmse(predictions, targets):
|
||||||
|
return np.sqrt(np.mean((predictions - targets) ** 2))
|
||||||
|
|
||||||
def test_fit_predict(self):
|
def test_fit_predict(self):
|
||||||
|
days = 30
|
||||||
N = DATA.shape[0]
|
N = DATA.shape[0]
|
||||||
train = DATA.head(N // 2)
|
train = DATA.head(N - days)
|
||||||
future = DATA.tail(N // 2)
|
test = DATA.tail(days)
|
||||||
|
test.reset_index(inplace=True)
|
||||||
|
|
||||||
forecaster = Prophet()
|
forecaster = Prophet()
|
||||||
forecaster.fit(train)
|
forecaster.fit(train, seed=1237861298)
|
||||||
forecaster.predict(future)
|
np.random.seed(876543987)
|
||||||
|
future = forecaster.make_future_dataframe(days, include_history=False)
|
||||||
|
future = forecaster.predict(future)
|
||||||
|
# this gives ~ 10.64
|
||||||
|
res = self.rmse(future['yhat'], test['y'])
|
||||||
|
self.assertTrue(15 > res > 5, msg="backend: {}".format(forecaster.stan_backend))
|
||||||
|
|
||||||
|
def test_fit_predict_newton(self):
|
||||||
|
days = 30
|
||||||
|
N = DATA.shape[0]
|
||||||
|
train = DATA.head(N - days)
|
||||||
|
test = DATA.tail(days)
|
||||||
|
test.reset_index(inplace=True)
|
||||||
|
|
||||||
|
forecaster = Prophet()
|
||||||
|
forecaster.fit(train, seed=1237861298, algorithm='Newton')
|
||||||
|
np.random.seed(876543987)
|
||||||
|
future = forecaster.make_future_dataframe(days, include_history=False)
|
||||||
|
future = forecaster.predict(future)
|
||||||
|
# this gives ~ 10.64
|
||||||
|
res = self.rmse(future['yhat'], test['y'])
|
||||||
|
self.assertAlmostEqual(res, 23.44, places=2, msg="backend: {}".format(forecaster.stan_backend))
|
||||||
|
|
||||||
|
@skipUnless("--test-slow" in sys.argv, "Skipped due to the lack of '--test-slow' argument")
|
||||||
|
def test_fit_sampling_predict(self):
|
||||||
|
days = 30
|
||||||
|
N = DATA.shape[0]
|
||||||
|
train = DATA.head(N - days)
|
||||||
|
test = DATA.tail(days)
|
||||||
|
test.reset_index(inplace=True)
|
||||||
|
|
||||||
|
forecaster = Prophet(mcmc_samples=500)
|
||||||
|
|
||||||
|
forecaster.fit(train, seed=1237861298, chains=4)
|
||||||
|
np.random.seed(876543987)
|
||||||
|
future = forecaster.make_future_dataframe(days, include_history=False)
|
||||||
|
future = forecaster.predict(future)
|
||||||
|
# this gives ~ 215.77
|
||||||
|
res = self.rmse(future['yhat'], test['y'])
|
||||||
|
self.assertTrue(236 > res > 193, msg="backend: {}".format(forecaster.stan_backend))
|
||||||
|
|
||||||
def test_fit_predict_no_seasons(self):
|
def test_fit_predict_no_seasons(self):
|
||||||
N = DATA.shape[0]
|
N = DATA.shape[0]
|
||||||
|
|
@ -63,7 +109,8 @@ class TestProphet(TestCase):
|
||||||
def test_fit_changepoint_not_in_history(self):
|
def test_fit_changepoint_not_in_history(self):
|
||||||
train = DATA[(DATA['ds'] < '2013-01-01') | (DATA['ds'] > '2014-01-01')]
|
train = DATA[(DATA['ds'] < '2013-01-01') | (DATA['ds'] > '2014-01-01')]
|
||||||
future = pd.DataFrame({'ds': DATA['ds']})
|
future = pd.DataFrame({'ds': DATA['ds']})
|
||||||
forecaster = Prophet(changepoints=['2013-06-06'])
|
prophet = Prophet(changepoints=['2013-06-06'])
|
||||||
|
forecaster = prophet
|
||||||
forecaster.fit(train)
|
forecaster.fit(train)
|
||||||
forecaster.predict(future)
|
forecaster.predict(future)
|
||||||
|
|
||||||
|
|
@ -228,7 +275,7 @@ class TestProphet(TestCase):
|
||||||
true_values = np.array([
|
true_values = np.array([
|
||||||
0.7818315, 0.6234898, 0.9749279, -0.2225209, 0.4338837, -0.9009689
|
0.7818315, 0.6234898, 0.9749279, -0.2225209, 0.4338837, -0.9009689
|
||||||
])
|
])
|
||||||
self.assertAlmostEqual(np.sum((mat[0] - true_values)**2), 0.0)
|
self.assertAlmostEqual(np.sum((mat[0] - true_values) ** 2), 0.0)
|
||||||
|
|
||||||
def test_fourier_series_yearly(self):
|
def test_fourier_series_yearly(self):
|
||||||
mat = Prophet.fourier_series(DATA['ds'], 365.25, 3)
|
mat = Prophet.fourier_series(DATA['ds'], 365.25, 3)
|
||||||
|
|
@ -236,7 +283,7 @@ class TestProphet(TestCase):
|
||||||
true_values = np.array([
|
true_values = np.array([
|
||||||
0.7006152, -0.7135393, -0.9998330, 0.01827656, 0.7262249, 0.6874572
|
0.7006152, -0.7135393, -0.9998330, 0.01827656, 0.7262249, 0.6874572
|
||||||
])
|
])
|
||||||
self.assertAlmostEqual(np.sum((mat[0] - true_values)**2), 0.0)
|
self.assertAlmostEqual(np.sum((mat[0] - true_values) ** 2), 0.0)
|
||||||
|
|
||||||
def test_growth_init(self):
|
def test_growth_init(self):
|
||||||
model = Prophet(growth='logistic')
|
model = Prophet(growth='logistic')
|
||||||
|
|
@ -593,7 +640,7 @@ class TestProphet(TestCase):
|
||||||
# Test priors
|
# Test priors
|
||||||
m = Prophet(
|
m = Prophet(
|
||||||
holidays=holidays, yearly_seasonality=False,
|
holidays=holidays, yearly_seasonality=False,
|
||||||
seasonality_mode='multiplicative',
|
seasonality_mode='multiplicative'
|
||||||
)
|
)
|
||||||
m.add_seasonality(name='monthly', period=30, fourier_order=5,
|
m.add_seasonality(name='monthly', period=30, fourier_order=5,
|
||||||
prior_scale=2., mode='additive')
|
prior_scale=2., mode='additive')
|
||||||
|
|
@ -654,7 +701,6 @@ class TestProphet(TestCase):
|
||||||
self.assertTrue(np.array_equal((seasonal_features[conditional_weekly_columns] != 0).any(axis=1).values,
|
self.assertTrue(np.array_equal((seasonal_features[conditional_weekly_columns] != 0).any(axis=1).values,
|
||||||
df['is_conditional_week'].values))
|
df['is_conditional_week'].values))
|
||||||
|
|
||||||
|
|
||||||
def test_added_regressors(self):
|
def test_added_regressors(self):
|
||||||
m = Prophet()
|
m = Prophet()
|
||||||
m.add_regressor('binary_feature', prior_scale=0.2)
|
m.add_regressor('binary_feature', prior_scale=0.2)
|
||||||
|
|
|
||||||
|
|
@ -1,4 +1,5 @@
|
||||||
Cython>=0.22
|
Cython>=0.22
|
||||||
|
cmdstanpy==0.4
|
||||||
pystan>=2.14
|
pystan>=2.14
|
||||||
numpy>=1.10.0
|
numpy>=1.10.0
|
||||||
pandas>=0.23.4
|
pandas>=0.23.4
|
||||||
|
|
|
||||||
|
|
@ -4,10 +4,9 @@
|
||||||
# LICENSE file in the root directory of this source tree.
|
# LICENSE file in the root directory of this source tree.
|
||||||
|
|
||||||
import os.path
|
import os.path
|
||||||
import pickle
|
|
||||||
import platform
|
import platform
|
||||||
import sys
|
import sys
|
||||||
|
import os
|
||||||
from pkg_resources import (
|
from pkg_resources import (
|
||||||
normalize_path,
|
normalize_path,
|
||||||
working_set,
|
working_set,
|
||||||
|
|
@ -18,7 +17,8 @@ from setuptools import setup, find_packages
|
||||||
from setuptools.command.build_py import build_py
|
from setuptools.command.build_py import build_py
|
||||||
from setuptools.command.develop import develop
|
from setuptools.command.develop import develop
|
||||||
from setuptools.command.test import test as test_command
|
from setuptools.command.test import test as test_command
|
||||||
|
from fbprophet.models import StanBackendEnum
|
||||||
|
from typing import List
|
||||||
|
|
||||||
PLATFORM = 'unix'
|
PLATFORM = 'unix'
|
||||||
if platform.platform().startswith('Win'):
|
if platform.platform().startswith('Win'):
|
||||||
|
|
@ -28,15 +28,14 @@ MODEL_DIR = os.path.join('stan', PLATFORM)
|
||||||
MODEL_TARGET_DIR = os.path.join('fbprophet', 'stan_model')
|
MODEL_TARGET_DIR = os.path.join('fbprophet', 'stan_model')
|
||||||
|
|
||||||
|
|
||||||
def build_stan_model(target_dir, model_dir=MODEL_DIR):
|
def get_backends_from_env() -> List[str]:
|
||||||
from pystan import StanModel
|
import os
|
||||||
model_name = 'prophet.stan'
|
return os.environ.get("STAN_BACKEND", StanBackendEnum.PYSTAN.name).split(",")
|
||||||
target_name = 'prophet_model.pkl'
|
|
||||||
with open(os.path.join(model_dir, model_name)) as f:
|
|
||||||
model_code = f.read()
|
def build_models(target_dir):
|
||||||
sm = StanModel(model_code=model_code)
|
for backend in get_backends_from_env():
|
||||||
with open(os.path.join(target_dir, target_name), 'wb') as f:
|
StanBackendEnum.get_backend_class(backend).build_model(target_dir, MODEL_DIR)
|
||||||
pickle.dump(sm, f, protocol=pickle.HIGHEST_PROTOCOL)
|
|
||||||
|
|
||||||
|
|
||||||
class BuildPyCommand(build_py):
|
class BuildPyCommand(build_py):
|
||||||
|
|
@ -46,7 +45,7 @@ class BuildPyCommand(build_py):
|
||||||
if not self.dry_run:
|
if not self.dry_run:
|
||||||
target_dir = os.path.join(self.build_lib, MODEL_TARGET_DIR)
|
target_dir = os.path.join(self.build_lib, MODEL_TARGET_DIR)
|
||||||
self.mkpath(target_dir)
|
self.mkpath(target_dir)
|
||||||
build_stan_model(target_dir)
|
build_models(target_dir)
|
||||||
|
|
||||||
build_py.run(self)
|
build_py.run(self)
|
||||||
|
|
||||||
|
|
@ -58,12 +57,29 @@ class DevelopCommand(develop):
|
||||||
if not self.dry_run:
|
if not self.dry_run:
|
||||||
target_dir = os.path.join(self.setup_path, MODEL_TARGET_DIR)
|
target_dir = os.path.join(self.setup_path, MODEL_TARGET_DIR)
|
||||||
self.mkpath(target_dir)
|
self.mkpath(target_dir)
|
||||||
build_stan_model(target_dir)
|
build_models(target_dir)
|
||||||
|
|
||||||
develop.run(self)
|
develop.run(self)
|
||||||
|
|
||||||
|
|
||||||
class TestCommand(test_command):
|
class TestCommand(test_command):
|
||||||
|
user_options = [
|
||||||
|
('test-module=', 'm', "Run 'test_suite' in specified module"),
|
||||||
|
('test-suite=', 's',
|
||||||
|
"Run single test, case or suite (e.g. 'module.test_suite')"),
|
||||||
|
('test-runner=', 'r', "Test runner to use"),
|
||||||
|
('test-slow', 'w', "Test slow suites (default off)"),
|
||||||
|
]
|
||||||
|
|
||||||
|
def initialize_options(self):
|
||||||
|
super(TestCommand, self).initialize_options()
|
||||||
|
self.test_slow = False
|
||||||
|
|
||||||
|
def finalize_options(self):
|
||||||
|
super(TestCommand, self).finalize_options()
|
||||||
|
if self.test_slow is None:
|
||||||
|
self.test_slow = getattr(self.distribution, 'test_slow', False)
|
||||||
|
|
||||||
"""We must run tests on the build directory, not source."""
|
"""We must run tests on the build directory, not source."""
|
||||||
|
|
||||||
def with_project_on_sys_path(self, func):
|
def with_project_on_sys_path(self, func):
|
||||||
|
|
@ -97,6 +113,7 @@ class TestCommand(test_command):
|
||||||
sys.modules.update(old_modules)
|
sys.modules.update(old_modules)
|
||||||
working_set.__init__()
|
working_set.__init__()
|
||||||
|
|
||||||
|
|
||||||
with open('requirements.txt', 'r') as f:
|
with open('requirements.txt', 'r') as f:
|
||||||
install_requires = f.read().splitlines()
|
install_requires = f.read().splitlines()
|
||||||
|
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue