Advanced Prophet Usage

You can scan through fbprophet docs and find many options how to tweak your model. Some of that functionality is moved to initialization stage to be compatible with Sklearn API. We will showcase the parts that were moved to initialization, but you can also look for other model parameters that could help fine-tuning your model

[1]:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
plt.style.use('seaborn')
plt.rcParams['figure.figsize'] = [12, 6]

[2]:

from hcrystalball.utils import generate_tsdata
X, y = generate_tsdata(n_dates=365*2)

[3]:

from hcrystalball.wrappers import ProphetWrapper

[4]:

ProphetWrapper?

Advanced Holidays

For holidays, we are able to define instead of single boolean attribute distribution around given day. We define lower_window, upper_window and prior_scales

[5]:

extra_holidays = {
    'Christmas Day':{'lower_window': -2, 'upper_window':2, 'prior_scale': 20},
#     'Good Friday':{'lower_window': -1, 'upper_window':1, 'prior_scale': 30}
}

Unusual Seasonalities

[6]:

extra_seasonalities = [
    {
        'name':'bi-weekly',
        'period': 14.,
        'fourier_order': 5,
        'prior_scale': 10.0,
        'mode': None
    },
    {
        'name':'bi-yearly',
        'period': 365*2.,
        'fourier_order': 5,
        'prior_scale': 5.0,
        'mode': None
    },
]

Exogenous Variables

[7]:

from sklearn.pipeline import Pipeline
from hcrystalball.feature_extraction import HolidayTransformer

[8]:

extra_regressors = ['trend_line']
X['trend_line'] = np.arange(len(X))

[9]:

prophet = ProphetWrapper(
    name='prophet',
)
prophet_extra = ProphetWrapper(
    extra_holidays=extra_holidays,
    extra_seasonalities=extra_seasonalities,
    extra_regressors=extra_regressors,
    name='prophet_extra',
)

[10]:

pipeline = Pipeline([
    ('holidays_de', HolidayTransformer(country_code = 'DE')),
    ('model', prophet)
])
pipeline_extra = Pipeline([
    ('holidays_de', HolidayTransformer(country_code = 'DE')),
    ('model', prophet_extra)
])

[11]:

prds = (pipeline.fit(X[:-10], y[:-10])
         .predict(X[-10:])
         .merge(y, left_index=True, right_index=True, how='outer')
         .tail(50))

prds.plot(title=f"MAE:{(prds['target']-prds['prophet']).abs().mean()}");

[11]:

<matplotlib.axes._subplots.AxesSubplot at 0x7fedcda1c750>
../../../_images/examples_tutorial_wrappers_06_advanced_prophet_14_1.png 
[12]:

prds_extra = (pipeline_extra.fit(X[:-10], y[:-10])
         .predict(X[-10:])
         .merge(y, left_index=True, right_index=True, how='outer')
         .tail(50))

prds_extra.plot(title=f"MAE:{(prds_extra['target']-prds_extra['prophet_extra']).abs().mean()}");

[12]:

<matplotlib.axes._subplots.AxesSubplot at 0x7fedcd477610>
../../../_images/examples_tutorial_wrappers_06_advanced_prophet_15_1.png

Compared to non-tweaked model, we are able to better catch the series dynamics, but don’t win against roughly average predictions

[13]:

prds = (ProphetWrapper().fit(X[:-10], y[:-10])
                 .predict(X[-10:])
                 .merge(y, left_index=True, right_index=True, how='outer')
                 .tail(50)
)
prds.plot(title=f"MAE:{(prds['target']-prds['prophet']).abs().mean()}");

[13]:

<matplotlib.axes._subplots.AxesSubplot at 0x7fedcd5f9d10>
../../../_images/examples_tutorial_wrappers_06_advanced_prophet_17_1.png

Full Prophet Output

If you need, you can also pass full_prophet_output and get rich predict output

[14]:

(ProphetWrapper(full_prophet_output=True, conf_int=True)
     .fit(X[:-10], y[:-10])
     .predict(X[-10:])
)

[14]:
trend prophet_lower prophet_upper trend_lower trend_upper additive_terms additive_terms_lower additive_terms_upper weekly weekly_lower weekly_upper multiplicative_terms multiplicative_terms_lower multiplicative_terms_upper prophet
2018-12-22 6.145564 0.483204 11.670660 6.145564 6.145564 -0.035994 -0.035994 -0.035994 -0.035994 -0.035994 -0.035994 0.0 0.0 0.0 6.109570
2018-12-23 6.143086 0.614726 11.691283 6.143086 6.143086 -0.058399 -0.058399 -0.058399 -0.058399 -0.058399 -0.058399 0.0 0.0 0.0 6.084687
2018-12-24 6.140608 1.059746 11.340479 6.140608 6.140608 -0.041247 -0.041247 -0.041247 -0.041247 -0.041247 -0.041247 0.0 0.0 0.0 6.099361
2018-12-25 6.138130 0.767389 11.599384 6.138130 6.138130 0.037883 0.037883 0.037883 0.037883 0.037883 0.037883 0.0 0.0 0.0 6.176013
2018-12-26 6.135652 0.777419 11.332295 6.135652 6.135652 0.038383 0.038383 0.038383 0.038383 0.038383 0.038383 0.0 0.0 0.0 6.174035
2018-12-27 6.133174 0.925499 11.286894 6.133174 6.133174 0.029158 0.029158 0.029158 0.029158 0.029158 0.029158 0.0 0.0 0.0 6.162332
2018-12-28 6.130696 0.655649 11.243649 6.130696 6.130725 0.030216 0.030216 0.030216 0.030216 0.030216 0.030216 0.0 0.0 0.0 6.160911
2018-12-29 6.128218 0.750822 11.166342 6.128178 6.128301 -0.035994 -0.035994 -0.035994 -0.035994 -0.035994 -0.035994 0.0 0.0 0.0 6.092224
2018-12-30 6.125740 0.763003 11.347704 6.125656 6.125901 -0.058399 -0.058399 -0.058399 -0.058399 -0.058399 -0.058399 0.0 0.0 0.0 6.067340
2018-12-31 6.123262 0.761844 11.239557 6.123104 6.123500 -0.041247 -0.041247 -0.041247 -0.041247 -0.041247 -0.041247 0.0 0.0 0.0 6.082015