Observed spillovers and unseen future names

match ← All linear growth benchmarks

96 daily rows from 2010; sparse prediction years 2021 and 2060. December 31's observed New Year's Day is retained while unseen Juneteenth names are ignored.

Input

benchmark/inputs/v5/country-boundary-96.json: 96 history rows and 4 forecast rows.

Output

Largest difference: 1.9e-9 (< 0.0001% of the input's range).

Every forecast row from both libraries.

Date	Effect Prophet	Python Prophet	Difference
2021-06-18	22.4917	22.4917	4.2e-10
2021-06-19	22.4923	22.4923	4.2e-10
2021-12-31	22.6104	22.6104	4.4e-10
2060-01-01	33.9385	33.9385	1.9e-9

Timing

Median of all measured repetitions.

Step	Effect Prophet	Python Prophet	Effect Prophet is
Convert input rows	14 µs	474 µs	34× faster
Fit	6.44 ms	20.7 ms	3.2× faster
Predict	217 µs	5.31 ms	24× faster
Fit and predict	5.50 ms	27.2 ms	4.9× faster
Convert, fit and predict	5.13 ms	28.4 ms	5.5× faster
First forecast in a new process	173 ms	1.62 s	9.4× faster
Save model to JSON	81 µs	537 µs	6.7× faster
Load model from JSON	956 µs	3.37 ms	3.5× faster
Load and predict in a new process	159 ms	1.58 s	9.9× faster

Settings

The case declaration both libraries ran.

{
  "kind": "map",
  "comparison": {
    "kind": "equivalent-objective",
    "evidenceId": "country-calendar-public-v1"
  },
  "configuration": {
    "growth": "linear",
    "countryHolidays": {
      "country": "US",
      "coverage": "reject-known-gaps",
      "priorScale": 10
    },
    "scaling": "absmax",
    "seasonalityMode": "additive",
    "holidaysMode": "additive",
    "changepoints": {
      "mode": "auto",
      "count": 2,
      "range": 0.8
    },
    "changepointPriorScale": 0.05,
    "seasonalities": [],
    "events": [],
    "regressors": []
  },
  "effectOptimizer": {
    "algorithm": "auto",
    "maxIterations": 10000,
    "fallback": "newton",
    "lbfgs": {
      "historySize": 5,
      "initAlpha": 0.001,
      "tolObj": 1e-12,
      "tolRelObj": 10000,
      "tolGrad": 1e-8,
      "tolRelGrad": 10000000,
      "tolParam": 1e-8
    }
  },
  "pythonOptimizer": {
    "algorithm": "Auto",
    "maxIterations": 10000,
    "newtonFallback": true,
    "sigFigs": 12
  }
}