SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2111.15397 · 2021

NeuralProphet: Explainable Forecasting at Scale

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2111.15397.json · badge: /api/ran/2111.15397.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
ourownstory/neural_prophet canonical (classifier label)
classifier basis not recorded on the link
5 ran · 2 no recorded run
FunctionStatusWhere it lives
check_multiple_series_id Ran
ran on a synthesized input
ourownstory/neural_prophet/neuralprophet/df_utils.py
code served (permissive licence) · get_code("55e6b51a2099a219")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import pandas as pd
import logging

logging.basicConfig(level=logging.DEBUG)

# Test case 1: DataFrame without ID column (single time series)
df_single = pd.DataFrame({
    'value': [1.0, 2.0, 3.0, 4.0],
    'timestamp': [1, 2, 3, 4]
})

# Test case 2: DataFrame with ID column (multiple time series)
df_multiple = pd.DataFrame({
    'ID': ['series_1', 'series_1', 'series_2', 'series_2'],
    'value': [1.0, 2.0, 3.0, 4.0],
    'timestamp': [1, 2, 3, 4]
})

ARGS = {
    'df': df_single
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_dynamic_axis_range Ran
ran on a synthesized input
ourownstory/neural_prophet/neuralprophet/plot_model_parameters_plotly.py
code served (permissive licence) · get_code("d5206169f97f06b2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a numpy array of numeric values for testing
numeric_range = np.array([1.0, 2.5, 3.8, 5.2, 7.1, 9.3, 12.0, 15.5])

# Create a numpy array of datetime-like values (using numeric representation)
dt_range = np.array([1000.0, 2000.0, 3000.0, 4000.0, 5000.0, 6000.0, 7000.0, 8000.0])

ARGS = {
    "df_range": numeric_range,
    "type": "numeric",
    "pad": 0.05,
    "inverse": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
merge_dataframes Ran
ran on a synthesized input
ourownstory/neural_prophet/neuralprophet/df_utils.py
code served (permissive licence) · get_code("39145a33caa43e9b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned DataFrame. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import pandas as pd
import numpy as np

# Create a sample DataFrame with required columns: 'ds', 'y', and 'ID'
df = pd.DataFrame({
    'ds': pd.date_range('2023-01-01', periods=6, freq='D').tolist() + 
          pd.date_range('2023-01-01', periods=6, freq='D').tolist(),
    'y': [1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 1.5, 2.5, 3.5, 4.5, 5.5, 6.5],
    'ID': ['series_1'] * 6 + ['series_2'] * 6
})

# Add some duplicates to test duplicate removal
df = pd.concat([df, df.iloc[:2]], ignore_index=True)

ARGS = {
    'df': df
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
plot_components Ran
ran on a synthesized input
ourownstory/neural_prophet/neuralprophet/torch_prophet.py
code served (permissive licence) · get_code("2974b74148d37c5d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Figure. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import pandas as pd
import numpy as np
from unittest.mock import Mock, MagicMock
import matplotlib.pyplot as plt

torch.manual_seed(0)

# Create a minimal NeuralProphet-like model mock
class MockNeuralProphet:
    def __init__(self):
        self.name = "NeuralProphet"
        self.fitted = True
    
    def plot_components(self, fcst, **kwargs):
        """Mock plot_components that returns a matplotlib figure."""
        fig, ax = plt.subplots(figsize=kwargs.get('figsize', (10, 6)))
        ax.set_title("Mock NeuralProphet Components")
        return fig

# Create the mock model
m = MockNeuralProphet()

# Create a mock forecast DataFrame
# NeuralProphet's predict typically returns a DataFrame with:
# - ds (datetime)
# - yhat (prediction)
# - trend, yearly, weekly, etc. components
dates = pd.date_range('2023-01-01', periods=10, freq='D')
fcst = pd.DataFrame({
    'ds': dates,
    'yhat': np.random.randn(10),
    'trend': np.random.randn(10),
    'yearly': np.random.randn(10),
    'weekly': np.random.randn(10),
})

# Construct ARGS dict with all parameters
ARGS = {
    'm': m,
    'fcst': fcst,
    'uncertainty': True,
    'plot_cap': True,
    'weekly_start': 0,
    'yearly_start': 0,
    'figsize': (12, 8),
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy, pandas, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Figure — a Figure output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Figure output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
return_df_in_original_format Ran
ran on a synthesized input
ourownstory/neural_prophet/neuralprophet/df_utils.py
code served (permissive licence) · get_code("5294cedc2a2b165a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned DataFrame. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import pandas as pd
import logging

log = logging.getLogger('NP.df_utils')

# Create a sample dataframe with an ID column and some time series data
df = pd.DataFrame({
    'ID': [1, 1, 1, 1],
    'value1': [10.0, 20.0, 30.0, 40.0],
    'value2': [100.0, 200.0, 300.0, 400.0]
})

ARGS = {
    'df': df,
    'received_ID_col': False,
    'received_single_time_series': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
plot_trend Not yet run
unverified (harvested, no recorded run)
ourownstory/neural_prophet/neuralprophet/plot_model_parameters_matplotlib.py
code served (permissive licence) · get_code("7092508fed578b4b")
How it ran

no invocation recorded.

plot_trend_change Not yet run
unverified (harvested, no recorded run)
ourownstory/neural_prophet/neuralprophet/plot_model_parameters_matplotlib.py
code served (permissive licence) · get_code("d2efabb8afef33ab")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We introduce NeuralProphet, a successor to Facebook Prophet, which set an industry standard for explainable, scalable, and user-friendly forecasting frameworks. With the proliferation of time series data, explainable forecasting remains a challenging task for business and operational decision making. Hybrid solutions are needed to bridge the gap between interpretable classical methods and scalable deep learning models. We view Prophet as a precursor to such a solution. However, Prophet lacks local context, which is essential for forecasting the near-term future and is challenging to extend due to its Stan backend. NeuralProphet is a hybrid forecasting framework based on PyTorch and trained with standard deep learning methods, making it easy for developers to extend the framework. Local context is introduced with auto-regression and covariate modules, which can be configured as classical linear regression or as Neural Networks. Otherwise, NeuralProphet retains the design philosophy of Prophet and provides the same basic model components. Our results demonstrate that NeuralProphet produces interpretable forecast components of equivalent or superior quality to Prophet on a set of generated time series. NeuralProphet outperforms Prophet on a diverse collection of real-world datasets. For short to medium-term forecasts, NeuralProphet improves forecast accuracy by 55 to 92 percent.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2111.15397")
get_code_for_paper("2111.15397")
have("2111.15397")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2111.15397.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2111.15397.svg)](https://syntology.ai/paper/2111.15397)

Connect an agent — have() is free.