First 70 days, minmax scaling

match ← All flat growth benchmarks

The 96-day mixed-feature history cut to its first 70 days: the training window of one cross-validation fold.

Input

benchmark/inputs/v1/flat-mixed-components-prefix-70.json: 70 history rows and 7 forecast rows.

Output

Largest difference: 4.1e-7 (< 0.0001% of the input's range).

Every forecast row from both libraries.

Date	Effect Prophet	Python Prophet	Difference
2020-03-11	35.0021	35.0021	1.4e-7
2020-03-12	62.8710	62.8710	4.1e-7
2020-03-13	69.8466	69.8466	2.8e-7
2020-03-14	50.4778	50.4778	4.9e-8
2020-03-15	20.6352	20.6352	1.1e-7
2020-03-16	35.0021	35.0021	1.4e-7
2020-03-17	7.1718	7.1718	1.0e-7

Timing

Median of all measured repetitions.

Step	Effect Prophet	Python Prophet	Effect Prophet is
Fit	2.04 ms	7.85 ms	3.9× faster
Predict	166 µs	4.69 ms	28× faster
Save model to JSON	21 µs	618 µs	30× faster
Load model from JSON	208 µs	3.59 ms	17× faster
Load and predict in a new process	157 ms	1.43 s	9.1× faster

Settings

The case declaration both libraries ran.

{
  "kind": "map",
  "comparison": {
    "kind": "equivalent-objective",
    "evidenceId": "flat-growth-mixed-scaling-v1"
  },
  "configuration": {
    "growth": "flat",
    "scaling": "minmax",
    "seasonalityMode": "additive",
    "holidaysMode": "additive",
    "changepoints": {
      "mode": "auto",
      "count": 25,
      "range": 0.8
    },
    "changepointPriorScale": 0.05,
    "seasonalities": [
      {
        "name": "weekly-custom",
        "periodDays": 7,
        "fourierOrder": 2,
        "priorScale": 10,
        "conditionName": "active",
        "mode": "multiplicative"
      }
    ],
    "events": [
      {
        "name": "campaign",
        "date": "2020-01-22",
        "lowerWindowDays": 0,
        "upperWindowDays": 0,
        "priorScale": 10
      }
    ],
    "regressors": [
      {
        "name": "promotion",
        "priorScale": 10,
        "standardization": "never"
      }
    ]
  },
  "effectOptimizer": {
    "algorithm": "lbfgs",
    "maxIterations": 10000,
    "fallback": "none",
    "lbfgs": {
      "historySize": 5,
      "initAlpha": 0.001,
      "tolObj": 1e-12,
      "tolRelObj": 10000,
      "tolGrad": 1e-8,
      "tolRelGrad": 10000000,
      "tolParam": 1e-8
    }
  },
  "pythonOptimizer": {
    "algorithm": "LBFGS",
    "maxIterations": 10000,
    "newtonFallback": false
  }
}