Repeated timestamps with features

match ← All linear growth benchmarks

Repeated dates whose regressor and condition values differ from row to row.

Input

benchmark/inputs/v1/training-duplicate-features.json: 96 history rows and 8 forecast rows.

Output

Largest difference: 0.00093 (0.017% of the input's range).

Every forecast row from both libraries.

Date	Effect Prophet	Python Prophet	Difference
2020-01-25	17.0806	17.0808	0.00019
2020-01-26	16.4980	16.4981	0.00014
2020-01-27	16.0559	16.0562	0.00033
2020-01-28	16.4228	16.4231	0.00031
2020-01-29	17.7144	17.7148	0.00038
2020-01-30	17.4415	17.4421	0.00059
2020-01-31	18.3572	18.3579	0.00069
2020-02-01	18.2191	18.2200	0.00093

Timing

Median of all measured repetitions.

Step	Effect Prophet	Python Prophet	Effect Prophet is
Fit	32.6 ms	112 ms	3.4× faster
Predict	239 µs	3.49 ms	15× faster
Save model to JSON	24 µs	461 µs	19× faster
Load model from JSON	243 µs	2.75 ms	11× faster
Load and predict in a new process	158 ms	1.51 s	9.5× faster

Settings

The case declaration both libraries ran.

{
  "kind": "map",
  "comparison": {
    "kind": "equivalent-objective",
    "evidenceId": "linear-output-first-v4"
  },
  "configuration": {
    "growth": "linear",
    "scaling": "absmax",
    "seasonalityMode": "additive",
    "holidaysMode": "additive",
    "changepoints": {
      "mode": "auto",
      "count": 25,
      "range": 0.8
    },
    "changepointPriorScale": 0.05,
    "seasonalities": [
      {
        "name": "weekly-active",
        "periodDays": 7,
        "fourierOrder": 1,
        "priorScale": 10,
        "conditionName": "active"
      }
    ],
    "events": [],
    "regressors": [
      {
        "name": "promotion",
        "priorScale": 10,
        "standardization": "never"
      }
    ]
  },
  "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
  }
}