Add CI and shadow calibration reporting

This commit is contained in:
2569718930@qq.com
2026-03-20 20:59:30 +08:00
parent 25ab512371
commit 1c84893bed
39 changed files with 149223 additions and 3277 deletions
@@ -0,0 +1,161 @@
{
"version": "emos-20260320123829",
"trained_at": "2026-03-20T12:38:29.985991+00:00",
"global": {
"mu": {
"intercept": -1.57406048,
"raw_mu_coef": 2.80583627,
"deb_coef": -0.06819634,
"ens_median_coef": -1.81560215,
"max_so_far_gap_coef": 0.0
},
"sigma": {
"intercept": 0.67509915,
"raw_sigma_coef": 0.14431833,
"spread_coef": 0.14431833,
"peak_flag_coef": 0.0,
"max_so_far_gap_coef": 0.0
}
},
"blending": {
"alpha_mu": 0.0,
"alpha_sigma": 1.0
},
"cities": {
"ankara": {
"samples": 7,
"mu_bias": 0.566273,
"sigma_scale": 2.0,
"confidence": 0.875
},
"london": {
"samples": 6,
"mu_bias": 0.489961,
"sigma_scale": 2.0,
"confidence": 0.75
},
"new york": {
"samples": 4,
"mu_bias": 1.852451,
"sigma_scale": 0.830444,
"confidence": 0.5
},
"paris": {
"samples": 7,
"mu_bias": 0.308599,
"sigma_scale": 2.0,
"confidence": 0.875
},
"seoul": {
"samples": 6,
"mu_bias": -1.486024,
"sigma_scale": 1.569585,
"confidence": 0.75
},
"toronto": {
"samples": 5,
"mu_bias": -0.734395,
"sigma_scale": 1.656751,
"confidence": 0.625
},
"buenos aires": {
"samples": 5,
"mu_bias": -1.753334,
"sigma_scale": 1.831739,
"confidence": 0.625
},
"wellington": {
"samples": 6,
"mu_bias": 0.350757,
"sigma_scale": 1.377974,
"confidence": 0.75
},
"chicago": {
"samples": 4,
"mu_bias": 3.01062,
"sigma_scale": 0.825575,
"confidence": 0.5
},
"sao paulo": {
"samples": 5,
"mu_bias": 1.632457,
"sigma_scale": 2.0,
"confidence": 0.625
},
"dallas": {
"samples": 4,
"mu_bias": 3.77714,
"sigma_scale": 0.796874,
"confidence": 0.5
},
"miami": {
"samples": 5,
"mu_bias": -4.868741,
"sigma_scale": 2.0,
"confidence": 0.625
},
"atlanta": {
"samples": 5,
"mu_bias": -7.648823,
"sigma_scale": 2.0,
"confidence": 0.625
},
"seattle": {
"samples": 4,
"mu_bias": 4.058619,
"sigma_scale": 2.0,
"confidence": 0.5
},
"lucknow": {
"samples": 4,
"mu_bias": 3.257609,
"sigma_scale": 2.0,
"confidence": 0.5
},
"munich": {
"samples": 6,
"mu_bias": -0.780811,
"sigma_scale": 2.0,
"confidence": 0.75
},
"hong kong": {
"samples": 3,
"mu_bias": -0.492675,
"sigma_scale": 2.0,
"confidence": 0.375
},
"taipei": {
"samples": 3,
"mu_bias": 1.462462,
"sigma_scale": 1.132834,
"confidence": 0.375
},
"milan": {
"samples": 3,
"mu_bias": -2.729203,
"sigma_scale": 2.0,
"confidence": 0.375
},
"warsaw": {
"samples": 3,
"mu_bias": 0.349319,
"sigma_scale": 1.337949,
"confidence": 0.375
}
},
"metrics": {
"sample_count": 105,
"mean_crps": 2.744961,
"legacy_mean_crps": 2.793938,
"legacy_mean_mae": 2.721143,
"legacy_bucket_hit_rate": 0.695238,
"selected_mean_crps": 2.747094,
"selected_mean_mae": 2.721143,
"selected_bucket_hit_rate": 0.704762,
"selected_score": 3.609685,
"legacy_score": 3.675576,
"filled_actual_from_history": 2,
"settlement_history_city_count": 30
},
"source": "artifacts\\probability_calibration\\default.json"
}
@@ -0,0 +1,248 @@
{
"summary": {
"sample_count": 105,
"filled_actual_from_history": 2,
"legacy": {
"mean_crps": 2.793938,
"mean_mae": 2.721143,
"bucket_hit_rate": 0.695238
},
"emos": {
"mean_crps": 2.747094,
"mean_mae": 2.721143,
"bucket_hit_rate": 0.685714
},
"delta": {
"crps": -0.046843,
"mae": 0.0,
"bucket_hit_rate": -0.009524
}
},
"by_city": {
"ankara": {
"samples": 7,
"legacy_mean_crps": 2.023242,
"emos_mean_crps": 2.259428,
"legacy_mean_mae": 1.984286,
"emos_mean_mae": 1.984286,
"legacy_bucket_hit_rate": 0.714286,
"emos_bucket_hit_rate": 0.714286
},
"atlanta": {
"samples": 5,
"legacy_mean_crps": 12.792034,
"emos_mean_crps": 12.537301,
"legacy_mean_mae": 12.806,
"emos_mean_mae": 12.806,
"legacy_bucket_hit_rate": 0.6,
"emos_bucket_hit_rate": 0.6
},
"buenos aires": {
"samples": 5,
"legacy_mean_crps": 3.846144,
"emos_mean_crps": 3.745234,
"legacy_mean_mae": 4.168,
"emos_mean_mae": 4.168,
"legacy_bucket_hit_rate": 0.6,
"emos_bucket_hit_rate": 0.6
},
"chicago": {
"samples": 4,
"legacy_mean_crps": 1.346667,
"emos_mean_crps": 0.66337,
"legacy_mean_mae": 0.0,
"emos_mean_mae": 0.0,
"legacy_bucket_hit_rate": 1.0,
"emos_bucket_hit_rate": 1.0
},
"dallas": {
"samples": 4,
"legacy_mean_crps": 1.256111,
"emos_mean_crps": 0.651563,
"legacy_mean_mae": 0.0,
"emos_mean_mae": 0.0,
"legacy_bucket_hit_rate": 1.0,
"emos_bucket_hit_rate": 1.0
},
"hong kong": {
"samples": 3,
"legacy_mean_crps": 0.261027,
"emos_mean_crps": 0.621432,
"legacy_mean_mae": 0.1,
"emos_mean_mae": 0.1,
"legacy_bucket_hit_rate": 1.0,
"emos_bucket_hit_rate": 0.666667
},
"london": {
"samples": 6,
"legacy_mean_crps": 2.079624,
"emos_mean_crps": 1.986319,
"legacy_mean_mae": 2.451667,
"emos_mean_mae": 2.451667,
"legacy_bucket_hit_rate": 0.166667,
"emos_bucket_hit_rate": 0.166667
},
"lucknow": {
"samples": 4,
"legacy_mean_crps": 1.468528,
"emos_mean_crps": 1.523689,
"legacy_mean_mae": 1.6025,
"emos_mean_mae": 1.6025,
"legacy_bucket_hit_rate": 0.5,
"emos_bucket_hit_rate": 0.5
},
"madrid": {
"samples": 2,
"legacy_mean_crps": 6.27726,
"emos_mean_crps": 6.028088,
"legacy_mean_mae": 7.33,
"emos_mean_mae": 7.33,
"legacy_bucket_hit_rate": 0.0,
"emos_bucket_hit_rate": 0.0
},
"miami": {
"samples": 5,
"legacy_mean_crps": 11.665378,
"emos_mean_crps": 11.614409,
"legacy_mean_mae": 12.07,
"emos_mean_mae": 12.07,
"legacy_bucket_hit_rate": 0.6,
"emos_bucket_hit_rate": 0.6
},
"milan": {
"samples": 3,
"legacy_mean_crps": 4.401392,
"emos_mean_crps": 3.905274,
"legacy_mean_mae": 4.06,
"emos_mean_mae": 4.06,
"legacy_bucket_hit_rate": 0.666667,
"emos_bucket_hit_rate": 0.666667
},
"munich": {
"samples": 6,
"legacy_mean_crps": 2.988583,
"emos_mean_crps": 2.892973,
"legacy_mean_mae": 3.143333,
"emos_mean_mae": 3.143333,
"legacy_bucket_hit_rate": 0.5,
"emos_bucket_hit_rate": 0.5
},
"new york": {
"samples": 4,
"legacy_mean_crps": 1.861101,
"emos_mean_crps": 1.420965,
"legacy_mean_mae": 1.3725,
"emos_mean_mae": 1.3725,
"legacy_bucket_hit_rate": 0.75,
"emos_bucket_hit_rate": 0.75
},
"paris": {
"samples": 7,
"legacy_mean_crps": 2.430082,
"emos_mean_crps": 2.23397,
"legacy_mean_mae": 2.518571,
"emos_mean_mae": 2.518571,
"legacy_bucket_hit_rate": 0.571429,
"emos_bucket_hit_rate": 0.571429
},
"sao paulo": {
"samples": 5,
"legacy_mean_crps": 2.454756,
"emos_mean_crps": 2.351014,
"legacy_mean_mae": 2.628,
"emos_mean_mae": 2.628,
"legacy_bucket_hit_rate": 0.6,
"emos_bucket_hit_rate": 0.6
},
"seattle": {
"samples": 4,
"legacy_mean_crps": 0.531656,
"emos_mean_crps": 0.850792,
"legacy_mean_mae": 0.0,
"emos_mean_mae": 0.0,
"legacy_bucket_hit_rate": 1.0,
"emos_bucket_hit_rate": 1.0
},
"seoul": {
"samples": 6,
"legacy_mean_crps": 0.328088,
"emos_mean_crps": 0.710725,
"legacy_mean_mae": 0.2,
"emos_mean_mae": 0.2,
"legacy_bucket_hit_rate": 1.0,
"emos_bucket_hit_rate": 1.0
},
"shanghai": {
"samples": 2,
"legacy_mean_crps": 0.250034,
"emos_mean_crps": 0.463888,
"legacy_mean_mae": 0.15,
"emos_mean_mae": 0.15,
"legacy_bucket_hit_rate": 1.0,
"emos_bucket_hit_rate": 1.0
},
"singapore": {
"samples": 2,
"legacy_mean_crps": 0.281993,
"emos_mean_crps": 0.484792,
"legacy_mean_mae": 0.15,
"emos_mean_mae": 0.15,
"legacy_bucket_hit_rate": 1.0,
"emos_bucket_hit_rate": 1.0
},
"taipei": {
"samples": 3,
"legacy_mean_crps": 0.356996,
"emos_mean_crps": 0.538714,
"legacy_mean_mae": 0.1,
"emos_mean_mae": 0.1,
"legacy_bucket_hit_rate": 1.0,
"emos_bucket_hit_rate": 0.666667
},
"tel aviv": {
"samples": 2,
"legacy_mean_crps": 0.446758,
"emos_mean_crps": 0.55971,
"legacy_mean_mae": 0.3,
"emos_mean_mae": 0.3,
"legacy_bucket_hit_rate": 1.0,
"emos_bucket_hit_rate": 1.0
},
"tokyo": {
"samples": 2,
"legacy_mean_crps": 0.450128,
"emos_mean_crps": 0.565212,
"legacy_mean_mae": 0.25,
"emos_mean_mae": 0.25,
"legacy_bucket_hit_rate": 0.5,
"emos_bucket_hit_rate": 1.0
},
"toronto": {
"samples": 5,
"legacy_mean_crps": 2.647861,
"emos_mean_crps": 2.402627,
"legacy_mean_mae": 2.532,
"emos_mean_mae": 2.532,
"legacy_bucket_hit_rate": 0.6,
"emos_bucket_hit_rate": 0.6
},
"warsaw": {
"samples": 3,
"legacy_mean_crps": 1.618875,
"emos_mean_crps": 1.601375,
"legacy_mean_mae": 2.056667,
"emos_mean_mae": 2.056667,
"legacy_bucket_hit_rate": 0.333333,
"emos_bucket_hit_rate": 0.333333
},
"wellington": {
"samples": 6,
"legacy_mean_crps": 0.266349,
"emos_mean_crps": 0.592134,
"legacy_mean_mae": 0.2,
"emos_mean_mae": 0.2,
"legacy_bucket_hit_rate": 1.0,
"emos_bucket_hit_rate": 1.0
}
}
}
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff