Country, custom events and mixed features

match ← All flat growth benchmarks

96 days with US country holidays, custom events, conditional weekly seasonality and a promotion regressor. Holiday effects are multiplicative.

Input

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

Output

Largest difference: 3.0e-5 (0.00062% of the input's range).

Every forecast row from both libraries.

Date	Effect Prophet	Python Prophet	Difference
2024-12-25	21.7611	21.7611	3.0e-5
2025-01-01	23.0406	23.0407	1.1e-5
2025-01-02	20.6095	20.6095	9.9e-6
2025-01-05	20.7451	20.7450	3.0e-5

Timing

Median of all measured repetitions.

Step	Effect Prophet	Python Prophet	Effect Prophet is
Convert input rows	46 µs	499 µs	11× faster
Fit	17.8 ms	54.9 ms	3.1× faster
Predict	222 µs	6.23 ms	28× faster
Fit and predict	17.1 ms	61.4 ms	3.6× faster
Convert, fit and predict	18.3 ms	61.6 ms	3.4× faster
First forecast in a new process	196 ms	1.65 s	8.4× faster
Save model to JSON	108 µs	704 µs	6.5× faster
Load model from JSON	810 µs	4.30 ms	5.3× faster
Load and predict in a new process	167 ms	1.60 s	9.6× faster

Settings

The case declaration both libraries ran.

{
  "kind": "map",
  "comparison": {
    "kind": "equivalent-objective",
    "evidenceId": "country-calendar-public-v1"
  },
  "configuration": {
    "growth": "flat",
    "countryHolidays": {
      "country": "US",
      "coverage": "reject-known-gaps",
      "priorScale": 10
    },
    "scaling": "absmax",
    "seasonalityMode": "additive",
    "holidaysMode": "multiplicative",
    "changepoints": {
      "mode": "auto",
      "count": 25,
      "range": 0.8
    },
    "changepointPriorScale": 0.05,
    "seasonalities": [
      {
        "name": "weekly-active",
        "periodDays": 7,
        "fourierOrder": 1,
        "priorScale": 10,
        "conditionName": "active"
      }
    ],
    "events": [
      {
        "name": "launch",
        "date": "2024-01-01",
        "lowerWindowDays": 0,
        "upperWindowDays": 0,
        "priorScale": 10
      },
      {
        "name": "launch",
        "date": "2024-01-05",
        "lowerWindowDays": 0,
        "upperWindowDays": 0,
        "priorScale": 10
      },
      {
        "name": "launch",
        "date": "2025-01-01",
        "lowerWindowDays": 0,
        "upperWindowDays": 0,
        "priorScale": 10
      },
      {
        "name": "launch",
        "date": "2025-01-05",
        "lowerWindowDays": 0,
        "upperWindowDays": 0,
        "priorScale": 10
      }
    ],
    "regressors": [
      {
        "name": "promotion",
        "priorScale": 10,
        "standardization": "never"
      }
    ]
  },
  "pythonOptimizer": {
    "algorithm": "Auto",
    "maxIterations": 10000,
    "newtonFallback": true,
    "sigFigs": 12
  }
}