diff --git a/.python-version b/.python-version new file mode 100644 index 0000000..56d91d3 --- /dev/null +++ b/.python-version @@ -0,0 +1 @@ +3.10.12 diff --git a/conf.yaml b/conf.yaml index d741d88..dfa4762 100644 --- a/conf.yaml +++ b/conf.yaml @@ -3,7 +3,8 @@ debug_conf: &debug_conf METRICS: - acc OUT_DIR_NAME: output/debug - DATASET_N_PREVS: 9 + DATASET_N_PREVS: 4 + # DATASET_PREVS: [[0.1, 0.1, 0.8]] COMP_ESTIMATORS: # - bin_sld_lr # - mul_sld_lr @@ -24,21 +25,25 @@ debug_conf: &debug_conf # - d_mul_kde_rbf # - d_m3w_kde_rbf # - mandoline - - bin_sld_lr_is - - mul_sld_lr_is - - m3w_sld_lr_is - - rca - - rca_star + # - bin_sld_lr_is + - bin_sld_lr_gs + - mul_sld_lr_gs + # - m3w_sld_lr_is + # - rca + # - rca_star - doc - atc_mc N_JOBS: -2 confs: - - DATASET_NAME: imdb - - DATASET_NAME: rcv1 - DATASET_TARGET: CCAT - other_confs: - DATASET_NAME: twitter_gasp + other_confs: + - DATASET_NAME: rcv1 + DATASET_TARGET: GCAT + - DATASET_NAME: rcv1 + DATASET_TARGET: MCAT + - DATASET_NAME: imdb + - DATASET_NAME: imdb - DATASET_NAME: rcv1 DATASET_TARGET: CCAT @@ -456,4 +461,4 @@ timing_gs_conf: &timing_gs_conf confs: *main_confs -exec: *d_sld_rbf_conf +exec: *debug_conf diff --git a/log b/log index b9948ff..e507128 100755 --- a/log +++ b/log @@ -6,5 +6,5 @@ if [[ "${1}" == "r" ]]; then elif [[ "${1}" == "d" ]]; then ssh andreaesuli@edge-nd1.isti.cnr.it tail -n 500 -f /home/andreaesuli/raid/lorenzo/quacc.log | bat -P --language=log else - tail -n 500 -f /home/lorev/tesi/quacc.log | bat --paging=never --language log + tail -n 500 -f /home/lorev/quacc/quacc.log | bat --paging=never --language log fi diff --git a/quacc.log b/quacc.log index 2b9742c..b858d43 100644 --- a/quacc.log +++ b/quacc.log @@ -17192,3 +17192,687 @@ LinearRegression does not accept missing values encoded as NaN natively. For sup 24/01/24 12:22:49| INFO mul_sld_lr_is finished [took 22.1600s] 24/01/24 12:22:56| INFO bin_sld_lr_is finished [took 29.8913s] 24/01/24 12:22:56| INFO Dataset sample [0.9 0.1] of dataset imdb finished [took 30.3839s] +---------------------------------------------------------------------------------------------------- +07/03/24 19:58:33| INFO dataset imdb [pool size: 10] +07/03/24 19:58:34| INFO Dataset sample [0.1 0.9] of dataset imdb started +07/03/24 19:58:44| INFO ref finished [took 8.8355s] +07/03/24 19:58:47| INFO atc_mc finished [took 12.2906s] +07/03/24 19:58:49| INFO doc finished [took 14.4880s] +07/03/24 19:59:02| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 1.0, 'quantifier__classifier__class_weight': None, 'quantifier__recalib': None, 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.01297) [took 12.3215s] +07/03/24 19:59:24| INFO bin_sld_lr_gs finished [took 34.5666s] +07/03/24 19:59:24| INFO Dataset sample [0.1 0.9] of dataset imdb finished [took 50.8695s] +07/03/24 19:59:24| INFO Dataset sample [0.2 0.8] of dataset imdb started +07/03/24 19:59:34| INFO ref finished [took 9.1637s] +07/03/24 19:59:37| INFO atc_mc finished [took 11.8823s] +07/03/24 19:59:40| INFO doc finished [took 14.8240s] +07/03/24 20:00:07| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 1000.0, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': 'bcts', 'confidence': ['max_conf', 'entropy']} (score=0.00805) [took 27.2140s] +---------------------------------------------------------------------------------------------------- +07/03/24 20:00:35| INFO dataset rcv1_GCAT [pool size: 10] +07/03/24 20:00:35| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +07/03/24 20:01:05| INFO ref finished [took 28.5818s] +07/03/24 20:01:08| INFO atc_mc finished [took 31.6592s] +07/03/24 20:01:11| INFO doc finished [took 33.9302s] +07/03/24 20:01:13| WARNING Method bin_sld_lr_gs failed. Exception: no combination of hyperparameters seem to work +07/03/24 20:01:13| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 38.0514s] +07/03/24 20:01:13| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT started +---------------------------------------------------------------------------------------------------- +07/03/24 20:06:41| INFO dataset rcv1_GCAT [pool size: 10] +07/03/24 20:06:41| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +07/03/24 20:07:11| INFO ref finished [took 28.1024s] +07/03/24 20:07:14| INFO atc_mc finished [took 31.6235s] +07/03/24 20:07:16| INFO doc finished [took 33.7466s] +07/03/24 20:07:19| WARNING Method bin_sld_lr_gs failed. Exception: no combination of hyperparameters seem to work +07/03/24 20:07:19| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 37.8741s] +---------------------------------------------------------------------------------------------------- +07/03/24 20:07:32| INFO dataset rcv1_GCAT [pool size: 10] +07/03/24 20:07:32| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +07/03/24 20:07:34| WARNING Method bin_sld_lr_is failed. Exception: This solver needs samples of at least 2 classes in the data, but the data contains only one class: 0 +07/03/24 20:08:03| INFO ref finished [took 28.6003s] +07/03/24 20:08:06| INFO atc_mc finished [took 31.9771s] +07/03/24 20:08:07| INFO doc finished [took 33.3084s] +07/03/24 20:08:10| WARNING Method bin_sld_lr_gs failed. Exception: no combination of hyperparameters seem to work +07/03/24 20:08:10| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 37.3895s] +---------------------------------------------------------------------------------------------------- +19/03/24 13:45:06| INFO dataset rcv1_GCAT [pool size: 10] +19/03/24 13:45:06| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +19/03/24 13:45:07| WARNING Method bin_sld_lr_is failed. Exception: This solver needs samples of at least 2 classes in the data, but the data contains only one class: 0 +19/03/24 13:45:35| INFO ref finished [took 27.7958s] +19/03/24 13:45:38| INFO atc_mc finished [took 31.0394s] +19/03/24 13:45:41| INFO doc finished [took 33.5261s] +19/03/24 13:45:43| WARNING Method bin_sld_lr_gs failed. Exception: no combination of hyperparameters seem to work +19/03/24 13:45:44| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 38.0286s] +---------------------------------------------------------------------------------------------------- +19/03/24 13:46:06| INFO dataset rcv1_GCAT [pool size: 10] +19/03/24 13:46:06| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +19/03/24 13:46:07| WARNING Method bin_sld_lr_is failed. Exception: This solver needs samples of at least 2 classes in the data, but the data contains only one class: 0 +19/03/24 13:46:35| INFO ref finished [took 27.7592s] +19/03/24 13:46:39| INFO atc_mc finished [took 31.2291s] +19/03/24 13:46:41| INFO doc finished [took 33.4684s] +19/03/24 13:46:41| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 35.3567s] +---------------------------------------------------------------------------------------------------- +19/03/24 13:48:21| INFO dataset rcv1_GCAT [pool size: 10] +19/03/24 13:48:21| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +19/03/24 13:48:22| WARNING Method bin_sld_lr_is failed. Exception: This solver needs samples of at least 2 classes in the data, but the data contains only one class: 0 +19/03/24 13:48:50| INFO ref finished [took 27.4811s] +19/03/24 13:48:54| INFO atc_mc finished [took 31.5975s] +19/03/24 13:48:56| INFO doc finished [took 33.6588s] +19/03/24 13:48:56| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 35.4838s] +---------------------------------------------------------------------------------------------------- +19/03/24 13:49:52| INFO dataset rcv1_GCAT [pool size: 10] +19/03/24 13:49:52| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +19/03/24 13:49:54| WARNING Method bin_sld_lr_is failed. Exception: This solver needs samples of at least 2 classes in the data, but the data contains only one class: 0 +19/03/24 13:50:22| INFO ref finished [took 27.8656s] +19/03/24 13:50:25| INFO atc_mc finished [took 30.5674s] +19/03/24 13:50:27| INFO doc finished [took 33.0146s] +19/03/24 13:50:27| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 34.9069s] +---------------------------------------------------------------------------------------------------- +19/03/24 18:16:33| INFO dataset rcv1_GCAT [pool size: 10] +19/03/24 18:16:34| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +19/03/24 18:16:35| WARNING Method bin_sld_lr_is failed. Exception: This solver needs samples of at least 2 classes in the data, but the data contains only one class: 0 +19/03/24 18:17:03| INFO ref finished [took 28.0456s] +19/03/24 18:17:07| INFO atc_mc finished [took 31.8627s] +19/03/24 18:17:09| INFO doc finished [took 33.9372s] +19/03/24 18:17:09| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 35.8737s] +---------------------------------------------------------------------------------------------------- +22/03/24 17:39:01| INFO dataset rcv1_GCAT [pool size: 10] +22/03/24 17:39:01| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +22/03/24 17:39:03| WARNING Method bin_sld_lr_is failed. Exception: This solver needs samples of at least 2 classes in the data, but the data contains only one class: 0 +22/03/24 17:39:32| INFO ref finished [took 28.5519s] +22/03/24 17:39:34| INFO atc_mc finished [took 31.3473s] +22/03/24 17:39:37| INFO doc finished [took 33.8775s] +22/03/24 17:39:37| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 35.7640s] +---------------------------------------------------------------------------------------------------- +22/03/24 17:40:03| INFO dataset rcv1_GCAT [pool size: 10] +22/03/24 17:40:03| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +22/03/24 17:40:05| WARNING Method bin_sld_lr_is failed. Exception: 'numpy.ndarray' object has no attribute 'Xy' +22/03/24 17:40:33| INFO ref finished [took 28.3034s] +22/03/24 17:40:37| INFO atc_mc finished [took 32.0578s] +22/03/24 17:40:38| INFO doc finished [took 33.4997s] +22/03/24 17:40:38| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 35.3824s] +---------------------------------------------------------------------------------------------------- +22/03/24 17:41:41| INFO dataset rcv1_GCAT [pool size: 10] +22/03/24 17:41:41| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +---------------------------------------------------------------------------------------------------- +22/03/24 17:45:54| INFO dataset rcv1_GCAT [pool size: 10] +22/03/24 17:45:54| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +22/03/24 17:46:24| INFO ref finished [took 28.5613s] +22/03/24 17:46:28| INFO atc_mc finished [took 32.3978s] +22/03/24 17:46:30| INFO doc finished [took 34.5604s] +22/03/24 17:46:33| INFO bin_sld_lr_is finished [took 37.7079s] +22/03/24 17:46:33| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 39.5748s] +---------------------------------------------------------------------------------------------------- +23/03/24 13:00:32| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 13:00:32| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 13:01:04| INFO ref finished [took 30.7154s] +23/03/24 13:01:08| INFO atc_mc finished [took 34.5902s] +23/03/24 13:01:10| INFO doc finished [took 36.6377s] +23/03/24 13:01:14| INFO bin_sld_lr_is finished [took 40.2864s] +23/03/24 13:01:14| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 42.3007s] +---------------------------------------------------------------------------------------------------- +23/03/24 13:01:54| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 13:01:54| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 13:02:26| INFO ref finished [took 30.4022s] +23/03/24 13:02:30| INFO atc_mc finished [took 34.2698s] +23/03/24 13:02:32| INFO doc finished [took 35.8748s] +23/03/24 13:02:34| INFO bin_sld_lr_is finished [took 38.3595s] +23/03/24 13:02:34| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 40.4090s] +---------------------------------------------------------------------------------------------------- +23/03/24 13:03:49| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 13:03:49| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 13:04:19| INFO ref finished [took 28.5940s] +23/03/24 13:04:22| INFO atc_mc finished [took 32.1501s] +23/03/24 13:04:25| INFO doc finished [took 34.3531s] +23/03/24 13:04:28| INFO bin_sld_lr_is finished [took 37.5110s] +23/03/24 13:04:28| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 39.3598s] +---------------------------------------------------------------------------------------------------- +23/03/24 13:05:25| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 13:05:25| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 13:05:55| INFO ref finished [took 28.5704s] +23/03/24 13:05:59| INFO atc_mc finished [took 32.0294s] +23/03/24 13:06:01| INFO doc finished [took 34.5325s] +23/03/24 13:06:05| INFO bin_sld_lr_is finished [took 37.9766s] +23/03/24 13:06:05| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 39.8671s] +---------------------------------------------------------------------------------------------------- +23/03/24 13:07:02| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 13:07:02| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 13:07:35| INFO ref finished [took 31.4744s] +23/03/24 13:07:39| INFO atc_mc finished [took 35.0584s] +23/03/24 13:07:41| INFO doc finished [took 37.2185s] +23/03/24 13:07:45| INFO bin_sld_lr_is finished [took 40.7480s] +23/03/24 13:07:45| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 42.7163s] +---------------------------------------------------------------------------------------------------- +23/03/24 13:24:27| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 13:24:27| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 13:24:59| INFO ref finished [took 30.9595s] +23/03/24 13:25:03| INFO atc_mc finished [took 34.8632s] +23/03/24 13:25:06| INFO doc finished [took 37.2251s] +23/03/24 13:25:08| INFO bin_sld_lr_is finished [took 40.1157s] +23/03/24 13:25:09| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 42.1099s] +---------------------------------------------------------------------------------------------------- +23/03/24 13:26:22| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 13:26:22| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 13:26:55| INFO ref finished [took 31.6397s] +23/03/24 13:26:58| INFO atc_mc finished [took 34.9376s] +23/03/24 13:27:01| INFO doc finished [took 37.2554s] +23/03/24 13:27:04| INFO bin_sld_lr_is finished [took 40.7601s] +23/03/24 13:27:05| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 42.7638s] +---------------------------------------------------------------------------------------------------- +23/03/24 13:28:54| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 13:28:54| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 13:29:26| INFO ref finished [took 30.7394s] +23/03/24 13:29:30| INFO atc_mc finished [took 34.5038s] +23/03/24 13:29:36| INFO doc finished [took 40.0651s] +23/03/24 13:29:36| INFO bin_sld_lr_is finished [took 40.2645s] +23/03/24 13:29:36| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 42.2545s] +---------------------------------------------------------------------------------------------------- +23/03/24 13:30:00| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 13:30:00| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 13:30:33| INFO ref finished [took 31.7178s] +23/03/24 13:30:36| INFO atc_mc finished [took 34.7653s] +23/03/24 13:30:38| INFO doc finished [took 36.7705s] +23/03/24 13:30:42| INFO bin_sld_lr_is finished [took 40.1862s] +23/03/24 13:30:42| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 42.2471s] +---------------------------------------------------------------------------------------------------- +23/03/24 13:35:15| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 13:35:15| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 13:35:49| INFO ref finished [took 31.5491s] +23/03/24 13:35:52| INFO atc_mc finished [took 35.1538s] +23/03/24 13:35:54| INFO doc finished [took 36.8684s] +23/03/24 13:35:56| INFO bin_sld_lr_is finished [took 38.4952s] +23/03/24 13:35:56| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 40.4850s] +---------------------------------------------------------------------------------------------------- +23/03/24 13:36:24| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 13:36:24| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 13:36:57| INFO ref finished [took 31.4153s] +23/03/24 13:37:00| INFO atc_mc finished [took 34.5550s] +23/03/24 13:37:03| INFO doc finished [took 37.0116s] +23/03/24 13:37:06| INFO bin_sld_lr_is finished [took 40.0674s] +23/03/24 13:37:06| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 42.0524s] +---------------------------------------------------------------------------------------------------- +23/03/24 13:37:34| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 13:37:34| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 13:38:07| INFO ref finished [took 30.9769s] +23/03/24 13:38:11| INFO atc_mc finished [took 34.5735s] +23/03/24 13:38:13| INFO doc finished [took 36.7363s] +23/03/24 13:38:16| INFO bin_sld_lr_is finished [took 40.1879s] +23/03/24 13:38:17| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 42.2425s] +---------------------------------------------------------------------------------------------------- +23/03/24 14:13:28| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 14:13:28| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 14:14:01| INFO ref finished [took 31.4967s] +23/03/24 14:14:04| INFO atc_mc finished [took 34.6677s] +23/03/24 14:14:06| INFO doc finished [took 36.7043s] +23/03/24 14:14:10| INFO bin_sld_lr_is finished [took 40.2211s] +23/03/24 14:14:10| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 42.2654s] +---------------------------------------------------------------------------------------------------- +23/03/24 14:16:10| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 14:16:10| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 14:16:43| INFO ref finished [took 31.1894s] +23/03/24 14:16:47| INFO atc_mc finished [took 34.8766s] +23/03/24 14:16:49| INFO doc finished [took 37.0967s] +23/03/24 14:16:53| INFO bin_sld_lr_is finished [took 41.1031s] +23/03/24 14:16:53| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 43.1300s] +---------------------------------------------------------------------------------------------------- +23/03/24 14:22:37| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 14:22:37| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 14:23:10| INFO ref finished [took 31.1393s] +23/03/24 14:23:14| INFO atc_mc finished [took 35.0549s] +23/03/24 14:23:17| INFO doc finished [took 37.5532s] +23/03/24 14:23:20| INFO bin_sld_lr_is finished [took 40.7132s] +23/03/24 14:23:20| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 42.7365s] +---------------------------------------------------------------------------------------------------- +23/03/24 14:27:10| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 14:27:10| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 14:27:43| INFO ref finished [took 31.1400s] +23/03/24 14:27:46| INFO atc_mc finished [took 34.6528s] +23/03/24 14:27:49| INFO doc finished [took 37.0410s] +23/03/24 14:27:52| INFO bin_sld_lr_is finished [took 40.2650s] +23/03/24 14:27:52| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 42.1148s] +---------------------------------------------------------------------------------------------------- +23/03/24 16:54:56| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 16:54:56| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 16:55:27| INFO ref finished [took 29.0701s] +23/03/24 16:55:29| INFO atc_mc finished [took 31.9601s] +23/03/24 16:55:32| INFO doc finished [took 34.4162s] +23/03/24 16:55:36| INFO bin_sld_lr_is finished [took 38.5255s] +23/03/24 16:55:36| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 40.3901s] +---------------------------------------------------------------------------------------------------- +23/03/24 17:26:57| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 17:26:57| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 17:26:59| WARNING Method bin_sld_lr_is failed. Exception: This solver needs samples of at least 2 classes in the data, but the data contains only one class: 0 +23/03/24 17:27:27| INFO ref finished [took 28.2144s] +23/03/24 17:27:31| INFO atc_mc finished [took 32.2246s] +23/03/24 17:27:33| INFO doc finished [took 34.0537s] +23/03/24 17:27:33| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 35.9403s] +---------------------------------------------------------------------------------------------------- +23/03/24 17:27:49| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 17:27:49| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT started +23/03/24 17:28:19| INFO ref finished [took 28.9425s] +23/03/24 17:28:23| INFO atc_mc finished [took 32.7912s] +23/03/24 17:28:25| INFO doc finished [took 34.3141s] +23/03/24 17:28:27| INFO bin_sld_lr_is finished [took 36.4641s] +23/03/24 17:28:27| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT finished [took 38.2816s] +---------------------------------------------------------------------------------------------------- +23/03/24 17:28:39| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 17:28:39| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT started +23/03/24 17:29:10| INFO ref finished [took 29.1823s] +23/03/24 17:29:14| INFO atc_mc finished [took 32.6478s] +23/03/24 17:29:16| INFO doc finished [took 34.7360s] +23/03/24 17:29:18| INFO bin_sld_lr_is finished [took 36.4193s] +23/03/24 17:29:18| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT finished [took 38.3387s] +---------------------------------------------------------------------------------------------------- +23/03/24 17:30:52| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 17:30:52| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT started +---------------------------------------------------------------------------------------------------- +23/03/24 17:32:15| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 17:32:15| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT started +23/03/24 17:32:45| INFO ref finished [took 29.1730s] +23/03/24 17:32:49| INFO atc_mc finished [took 32.2855s] +23/03/24 17:32:51| INFO doc finished [took 34.7664s] +23/03/24 17:32:58| INFO bin_sld_lr_is finished [took 41.7819s] +23/03/24 17:32:58| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT finished [took 43.7025s] +---------------------------------------------------------------------------------------------------- +23/03/24 17:34:24| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 17:34:24| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT started +23/03/24 17:34:55| INFO ref finished [took 29.2206s] +23/03/24 17:34:59| INFO atc_mc finished [took 32.8052s] +23/03/24 17:35:00| INFO doc finished [took 34.2601s] +23/03/24 17:35:06| INFO bin_sld_lr_is finished [took 40.7150s] +23/03/24 17:35:07| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT finished [took 42.6306s] +---------------------------------------------------------------------------------------------------- +23/03/24 17:36:08| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 17:36:08| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT started +23/03/24 17:36:39| INFO ref finished [took 29.4468s] +23/03/24 17:36:42| INFO atc_mc finished [took 32.4536s] +23/03/24 17:36:44| INFO doc finished [took 34.3966s] +23/03/24 17:36:52| INFO bin_sld_lr_is finished [took 42.2660s] +23/03/24 17:36:52| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT finished [took 44.2113s] +---------------------------------------------------------------------------------------------------- +23/03/24 17:37:09| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 17:37:09| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT started +23/03/24 17:37:11| INFO ref finished [took 0.3189s] +23/03/24 17:37:11| INFO atc_mc finished [took 0.3843s] +23/03/24 17:37:11| INFO bin_sld_lr_is finished [took 0.5766s] +23/03/24 17:37:16| INFO doc finished [took 5.0570s] +23/03/24 17:37:16| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT finished [took 6.9932s] +---------------------------------------------------------------------------------------------------- +23/03/24 17:38:05| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 17:38:05| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT started +23/03/24 17:38:07| INFO ref finished [took 0.3215s] +23/03/24 17:38:07| INFO atc_mc finished [took 0.3767s] +23/03/24 17:38:07| INFO bin_sld_lr_is finished [took 0.5589s] +23/03/24 17:38:12| INFO doc finished [took 5.1400s] +23/03/24 17:38:12| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT finished [took 7.0756s] +---------------------------------------------------------------------------------------------------- +23/03/24 17:38:19| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 17:38:19| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT started +23/03/24 17:38:21| INFO ref finished [took 0.3299s] +23/03/24 17:38:21| INFO atc_mc finished [took 0.3700s] +23/03/24 17:38:22| INFO bin_sld_lr_is finished [took 0.5536s] +23/03/24 17:38:26| INFO doc finished [took 5.1714s] +23/03/24 17:38:26| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT finished [took 7.1128s] +---------------------------------------------------------------------------------------------------- +23/03/24 17:38:33| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 17:38:33| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT started +23/03/24 17:39:04| INFO ref finished [took 29.4347s] +23/03/24 17:39:08| INFO atc_mc finished [took 32.6589s] +23/03/24 17:39:09| INFO doc finished [took 34.0316s] +23/03/24 17:39:15| INFO bin_sld_lr_is finished [took 40.3601s] +23/03/24 17:39:16| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT finished [took 42.2535s] +---------------------------------------------------------------------------------------------------- +23/03/24 17:40:25| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 17:40:25| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT started +23/03/24 17:40:56| INFO ref finished [took 29.4779s] +23/03/24 17:41:00| INFO atc_mc finished [took 33.2235s] +23/03/24 17:41:01| INFO doc finished [took 34.8981s] +23/03/24 17:41:08| INFO bin_sld_lr_is finished [took 41.0836s] +23/03/24 17:41:08| INFO mul_sld_lr_is finished [took 41.8461s] +23/03/24 17:41:09| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT finished [took 43.8091s] +---------------------------------------------------------------------------------------------------- +23/03/24 17:41:24| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 17:41:24| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 17:41:25| WARNING Method bin_sld_lr_is failed. Exception: This solver needs samples of at least 2 classes in the data, but the data contains only one class: 0 +23/03/24 17:41:55| INFO ref finished [took 29.4966s] +23/03/24 17:41:58| INFO atc_mc finished [took 33.0054s] +23/03/24 17:42:00| INFO doc finished [took 34.5157s] +23/03/24 17:42:05| INFO mul_sld_lr_is finished [took 39.2460s] +23/03/24 17:42:05| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 41.1783s] +23/03/24 17:42:05| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT started +23/03/24 17:42:36| INFO ref finished [took 29.9055s] +23/03/24 17:42:40| INFO atc_mc finished [took 33.0051s] +23/03/24 17:42:42| INFO doc finished [took 35.3254s] +23/03/24 17:42:48| INFO mul_sld_lr_is finished [took 41.1086s] +23/03/24 17:42:49| INFO bin_sld_lr_is finished [took 42.0787s] +23/03/24 17:42:49| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT finished [took 43.9374s] +23/03/24 17:42:49| INFO Dataset sample [0.3 0.7] of dataset rcv1_GCAT started +23/03/24 17:43:20| INFO ref finished [took 29.3024s] +23/03/24 17:43:22| INFO atc_mc finished [took 33.0082s] +23/03/24 17:43:25| INFO doc finished [took 35.1432s] +23/03/24 17:43:30| INFO bin_sld_lr_is finished [took 40.7482s] +23/03/24 17:43:32| INFO mul_sld_lr_is finished [took 42.1601s] +23/03/24 17:43:32| INFO Dataset sample [0.3 0.7] of dataset rcv1_GCAT finished [took 42.8091s] +23/03/24 17:43:32| INFO Dataset sample [0.4 0.6] of dataset rcv1_GCAT started +23/03/24 17:44:01| INFO ref finished [took 29.3167s] +23/03/24 17:44:05| INFO atc_mc finished [took 32.9997s] +23/03/24 17:44:08| INFO doc finished [took 35.4461s] +23/03/24 17:44:14| INFO bin_sld_lr_is finished [took 42.2606s] +23/03/24 17:44:15| INFO mul_sld_lr_is finished [took 43.0873s] +23/03/24 17:44:15| INFO Dataset sample [0.4 0.6] of dataset rcv1_GCAT finished [took 43.7627s] +23/03/24 17:44:15| INFO Dataset sample [0.5 0.5] of dataset rcv1_GCAT started +23/03/24 17:44:47| INFO ref finished [took 30.8422s] +23/03/24 17:44:50| INFO atc_mc finished [took 34.0480s] +23/03/24 17:44:51| INFO doc finished [took 35.5252s] +23/03/24 17:44:57| INFO bin_sld_lr_is finished [took 41.5550s] +23/03/24 17:44:59| INFO mul_sld_lr_is finished [took 42.7716s] +23/03/24 17:44:59| INFO Dataset sample [0.5 0.5] of dataset rcv1_GCAT finished [took 43.3850s] +23/03/24 17:44:59| INFO Dataset sample [0.6 0.4] of dataset rcv1_GCAT started +23/03/24 17:45:30| INFO ref finished [took 30.4643s] +23/03/24 17:45:34| INFO atc_mc finished [took 34.5937s] +23/03/24 17:45:36| INFO doc finished [took 36.4176s] +23/03/24 17:45:42| INFO bin_sld_lr_is finished [took 43.0109s] +23/03/24 17:45:44| INFO mul_sld_lr_is finished [took 44.2652s] +23/03/24 17:45:44| INFO Dataset sample [0.6 0.4] of dataset rcv1_GCAT finished [took 44.9128s] +23/03/24 17:45:44| INFO Dataset sample [0.7 0.3] of dataset rcv1_GCAT started +23/03/24 17:46:14| INFO ref finished [took 30.1696s] +23/03/24 17:46:19| INFO atc_mc finished [took 34.2701s] +23/03/24 17:46:20| INFO doc finished [took 35.4569s] +23/03/24 17:46:31| INFO mul_sld_lr_is finished [took 46.9930s] +23/03/24 17:46:34| INFO bin_sld_lr_is finished [took 49.7302s] +23/03/24 17:46:34| INFO Dataset sample [0.7 0.3] of dataset rcv1_GCAT finished [took 50.4071s] +23/03/24 17:46:34| INFO Dataset sample [0.8 0.2] of dataset rcv1_GCAT started +23/03/24 17:47:07| INFO ref finished [took 31.9256s] +23/03/24 17:47:09| INFO atc_mc finished [took 34.3939s] +23/03/24 17:47:11| INFO doc finished [took 36.7679s] +23/03/24 17:47:22| INFO bin_sld_lr_is finished [took 47.0653s] +23/03/24 17:47:31| INFO mul_sld_lr_is finished [took 56.3521s] +23/03/24 17:47:31| INFO Dataset sample [0.8 0.2] of dataset rcv1_GCAT finished [took 57.0191s] +23/03/24 17:47:31| INFO Dataset sample [0.9 0.1] of dataset rcv1_GCAT started +23/03/24 17:48:03| INFO ref finished [took 31.4172s] +23/03/24 17:48:07| INFO atc_mc finished [took 35.2173s] +23/03/24 17:48:09| INFO doc finished [took 37.7077s] +23/03/24 17:48:13| INFO bin_sld_lr_is finished [took 41.2463s] +23/03/24 17:48:19| INFO mul_sld_lr_is finished [took 47.2718s] +23/03/24 17:48:19| INFO Dataset sample [0.9 0.1] of dataset rcv1_GCAT finished [took 47.9285s] +---------------------------------------------------------------------------------------------------- +23/03/24 17:56:57| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 17:56:58| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 17:56:59| WARNING Method bin_sld_lr_is failed. Exception: TrivialQuantifier.fit() takes 1 positional argument but 2 were given +---------------------------------------------------------------------------------------------------- +23/03/24 17:58:28| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 17:58:28| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 17:58:59| INFO ref finished [took 29.4907s] +23/03/24 17:59:03| INFO atc_mc finished [took 33.1559s] +23/03/24 17:59:05| INFO doc finished [took 35.8358s] +---------------------------------------------------------------------------------------------------- +23/03/24 17:59:12| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 17:59:12| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 17:59:43| INFO ref finished [took 29.6093s] +23/03/24 17:59:47| INFO atc_mc finished [took 33.4002s] +23/03/24 17:59:49| INFO doc finished [took 35.3542s] +23/03/24 17:59:52| INFO bin_sld_lr_is finished [took 38.2598s] +23/03/24 17:59:54| INFO mul_sld_lr_is finished [took 39.7618s] +23/03/24 17:59:54| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 41.7033s] +---------------------------------------------------------------------------------------------------- +23/03/24 18:01:44| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 18:01:44| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 18:02:15| INFO ref finished [took 29.1981s] +23/03/24 18:02:19| INFO atc_mc finished [took 32.7179s] +23/03/24 18:02:21| INFO doc finished [took 35.2027s] +23/03/24 18:02:24| INFO bin_sld_lr_is finished [took 38.2967s] +23/03/24 18:02:32| INFO mul_sld_lr_is finished [took 45.5436s] +23/03/24 18:02:32| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 47.4588s] +23/03/24 18:02:32| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT started +23/03/24 18:03:03| INFO ref finished [took 29.3004s] +23/03/24 18:03:07| INFO atc_mc finished [took 33.1850s] +23/03/24 18:03:08| INFO doc finished [took 34.9167s] +23/03/24 18:03:12| INFO bin_sld_lr_is finished [took 39.0394s] +23/03/24 18:03:15| INFO mul_sld_lr_is finished [took 41.1164s] +23/03/24 18:03:15| INFO Dataset sample [0.2 0.8] of dataset rcv1_GCAT finished [took 42.9526s] +23/03/24 18:03:15| INFO Dataset sample [0.3 0.7] of dataset rcv1_GCAT started +23/03/24 18:03:46| INFO ref finished [took 29.5112s] +23/03/24 18:03:49| INFO atc_mc finished [took 33.5662s] +23/03/24 18:03:51| INFO doc finished [took 35.6094s] +23/03/24 18:03:56| INFO bin_sld_lr_is finished [took 40.6729s] +23/03/24 18:03:58| INFO mul_sld_lr_is finished [took 42.7415s] +23/03/24 18:03:58| INFO Dataset sample [0.3 0.7] of dataset rcv1_GCAT finished [took 43.4075s] +23/03/24 18:03:58| INFO Dataset sample [0.4 0.6] of dataset rcv1_GCAT started +23/03/24 18:04:29| INFO ref finished [took 29.9760s] +23/03/24 18:04:33| INFO atc_mc finished [took 33.9652s] +23/03/24 18:04:34| INFO doc finished [took 35.7287s] +---------------------------------------------------------------------------------------------------- +23/03/24 18:04:43| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 18:04:43| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +---------------------------------------------------------------------------------------------------- +23/03/24 18:05:31| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 18:05:31| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 18:06:01| INFO ref finished [took 28.6311s] +23/03/24 18:06:05| INFO atc_mc finished [took 32.6133s] +23/03/24 18:06:06| INFO doc finished [took 33.7780s] +23/03/24 18:06:10| INFO bin_sld_lr_is finished [took 37.3632s] +23/03/24 18:06:29| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 10.0, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': 'bcts', 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.00501) [took 18.4370s] +23/03/24 18:07:05| INFO bin_sld_lr_gs finished [took 54.8471s] +23/03/24 18:07:54| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 100.0, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': None} (score=0.00802) [took 48.9164s] +23/03/24 18:08:31| INFO mul_sld_lr_gs finished [took 86.2093s] +23/03/24 18:09:24| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 100.0, 'quantifier__classifier__class_weight': None, 'quantifier__recalib': 'bcts', 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.00627) [took 52.3243s] +23/03/24 18:09:58| INFO m3w_sld_lr_gs finished [took 86.1278s] +23/03/24 18:09:58| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 266.7565s] +23/03/24 18:09:58| INFO Dataset sample [0.9 0.1] of dataset rcv1_GCAT started +23/03/24 18:10:27| INFO ref finished [took 28.7630s] +23/03/24 18:10:30| INFO atc_mc finished [took 32.1853s] +23/03/24 18:10:34| INFO doc finished [took 35.4845s] +23/03/24 18:10:40| INFO bin_sld_lr_is finished [took 41.9813s] +23/03/24 18:10:56| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 1.0, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.15038) [took 15.1406s] +23/03/24 18:11:32| INFO bin_sld_lr_gs finished [took 51.8936s] +23/03/24 18:12:50| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 100.0, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': ['isoft']} (score=0.00994) [took 77.2499s] +23/03/24 18:13:27| INFO mul_sld_lr_gs finished [took 114.7003s] +23/03/24 18:14:21| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 1.0, 'quantifier__classifier__class_weight': None, 'quantifier__recalib': 'bcts', 'confidence': ['max_conf', 'entropy']} (score=0.00598) [took 53.4974s] +23/03/24 18:14:55| INFO m3w_sld_lr_gs finished [took 87.8074s] +23/03/24 18:14:55| INFO Dataset sample [0.9 0.1] of dataset rcv1_GCAT finished [took 297.3225s] +---------------------------------------------------------------------------------------------------- +23/03/24 18:15:00| INFO dataset rcv1_MCAT [pool size: 10] +23/03/24 18:15:00| INFO Dataset sample [0.1 0.9] of dataset rcv1_MCAT started +23/03/24 18:15:29| INFO ref finished [took 29.5145s] +23/03/24 18:15:33| INFO atc_mc finished [took 33.1925s] +23/03/24 18:15:35| INFO doc finished [took 35.2185s] +23/03/24 18:15:39| INFO bin_sld_lr_is finished [took 38.9318s] +23/03/24 18:15:48| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 100.0, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': None} (score=0.00499) [took 8.4072s] +23/03/24 18:16:25| INFO bin_sld_lr_gs finished [took 45.3163s] +23/03/24 18:17:37| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 1000.0, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': None} (score=0.00677) [took 72.8117s] +23/03/24 18:18:15| INFO mul_sld_lr_gs finished [took 110.2357s] +23/03/24 18:19:02| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 10.0, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': 'bcts', 'confidence': ['max_conf', 'entropy']} (score=0.00635) [took 46.9797s] +23/03/24 18:19:36| INFO m3w_sld_lr_gs finished [took 81.3292s] +23/03/24 18:19:36| INFO Dataset sample [0.1 0.9] of dataset rcv1_MCAT finished [took 276.7762s] +23/03/24 18:19:36| INFO Dataset sample [0.9 0.1] of dataset rcv1_MCAT started +23/03/24 18:20:06| INFO ref finished [took 29.4763s] +23/03/24 18:20:10| INFO atc_mc finished [took 32.8139s] +23/03/24 18:20:12| INFO doc finished [took 34.8111s] +23/03/24 18:20:22| INFO bin_sld_lr_is finished [took 45.3644s] +23/03/24 18:20:42| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 10.0, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': None} (score=0.13941) [took 19.8729s] +---------------------------------------------------------------------------------------------------- +23/03/24 18:21:29| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 18:21:29| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +---------------------------------------------------------------------------------------------------- +23/03/24 18:22:04| INFO dataset rcv1_GCAT [pool size: 10] +23/03/24 18:22:04| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT started +23/03/24 18:22:35| INFO ref finished [took 28.7281s] +23/03/24 18:22:38| INFO atc_mc finished [took 32.2898s] +23/03/24 18:22:40| INFO doc finished [took 34.0234s] +23/03/24 18:22:43| INFO bin_sld_lr_is finished [took 37.4724s] +23/03/24 18:23:02| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 10.0, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': 'bcts', 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.00501) [took 18.4731s] +23/03/24 18:23:39| INFO bin_sld_lr_gs finished [took 54.7945s] +23/03/24 18:23:39| INFO Dataset sample [0.1 0.9] of dataset rcv1_GCAT finished [took 94.3622s] +23/03/24 18:23:39| INFO Dataset sample [0.9 0.1] of dataset rcv1_GCAT started +23/03/24 18:24:09| INFO ref finished [took 29.6324s] +23/03/24 18:24:11| INFO atc_mc finished [took 32.3203s] +23/03/24 18:24:13| INFO doc finished [took 34.3130s] +23/03/24 18:24:18| INFO bin_sld_lr_is finished [took 39.1886s] +23/03/24 18:24:35| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 10.0, 'quantifier__classifier__class_weight': None, 'quantifier__recalib': None, 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.00589) [took 16.3871s] +23/03/24 18:25:12| INFO bin_sld_lr_gs finished [took 53.6400s] +23/03/24 18:25:12| INFO Dataset sample [0.9 0.1] of dataset rcv1_GCAT finished [took 93.6040s] +---------------------------------------------------------------------------------------------------- +23/03/24 18:28:02| INFO dataset twitter_gasp [pool size: 10] +23/03/24 18:28:02| INFO Dataset sample [0.1 0.1 0.8] of dataset twitter_gasp started +23/03/24 18:31:14| INFO ref finished [took 189.5881s] +23/03/24 18:31:50| INFO atc_mc finished [took 225.5500s] +23/03/24 18:33:11| INFO doc finished [took 306.3239s] +23/03/24 18:34:15| INFO bin_sld_lr_is finished [took 370.2931s] +23/03/24 18:34:15| INFO Dataset sample [0.1 0.1 0.8] of dataset twitter_gasp finished [took 373.0566s] +---------------------------------------------------------------------------------------------------- +23/03/24 18:35:12| INFO dataset twitter_gasp [pool size: 10] +23/03/24 18:35:12| INFO Dataset sample [0.1 0.1 0.8] of dataset twitter_gasp started +23/03/24 18:38:26| INFO ref finished [took 190.6336s] +23/03/24 18:39:00| INFO atc_mc finished [took 224.8782s] +23/03/24 18:40:22| INFO doc finished [took 307.1053s] +23/03/24 18:41:24| INFO bin_sld_lr_is finished [took 368.5114s] +23/03/24 18:42:39| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.001, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': ['isoft']} (score=0.31780) [took 74.0675s] +23/03/24 18:48:52| INFO bin_sld_lr_gs finished [took 447.3591s] +23/03/24 18:48:52| INFO Dataset sample [0.1 0.1 0.8] of dataset twitter_gasp finished [took 819.8403s] +---------------------------------------------------------------------------------------------------- +23/03/24 19:42:57| INFO dataset twitter_gasp [pool size: 10] +23/03/24 19:42:57| INFO Dataset sample [0.1 0.1 0.8] of dataset twitter_gasp started +23/03/24 19:45:47| INFO ref finished [took 167.4161s] +23/03/24 19:46:20| INFO atc_mc finished [took 200.6698s] +23/03/24 19:47:42| INFO doc finished [took 282.4151s] +23/03/24 19:48:55| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.001, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': ['isoft']} (score=0.31780) [took 71.2383s] +23/03/24 19:55:05| INFO bin_sld_lr_gs finished [took 441.6223s] +23/03/24 20:11:01| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.01, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.27695) [took 954.5342s] +23/03/24 20:16:29| INFO mul_sld_lr_gs finished [took 1282.8734s] +23/03/24 20:16:29| INFO Dataset sample [0.1 0.1 0.8] of dataset twitter_gasp finished [took 2012.0387s] +23/03/24 20:16:29| INFO Dataset sample [0.1 0.2 0.7] of dataset twitter_gasp started +23/03/24 20:19:25| INFO ref finished [took 171.3929s] +23/03/24 20:19:50| INFO atc_mc finished [took 196.6612s] +23/03/24 20:21:16| INFO doc finished [took 283.0184s] +23/03/24 20:23:37| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.01, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': ['isoft']} (score=0.20335) [took 137.0711s] +23/03/24 20:29:37| INFO bin_sld_lr_gs finished [took 496.6746s] +23/03/24 20:56:39| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.001, 'quantifier__classifier__class_weight': None, 'quantifier__recalib': None, 'confidence': ['isoft']} (score=0.18306) [took 1619.0936s] +23/03/24 21:02:55| INFO mul_sld_lr_gs finished [took 1994.9100s] +23/03/24 21:02:55| INFO Dataset sample [0.1 0.2 0.7] of dataset twitter_gasp finished [took 2785.7228s] +23/03/24 21:02:55| INFO Dataset sample [0.1 0.3 0.6] of dataset twitter_gasp started +23/03/24 21:05:45| INFO ref finished [took 165.7900s] +23/03/24 21:06:25| INFO atc_mc finished [took 205.3993s] +23/03/24 21:07:32| INFO doc finished [took 273.2106s] +23/03/24 21:10:11| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 1000.0, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': None} (score=0.45373) [took 154.4720s] +23/03/24 21:15:55| INFO bin_sld_lr_gs finished [took 498.7315s] +23/03/24 21:41:15| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 1.0, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': ['max_conf', 'entropy']} (score=0.34115) [took 1517.1957s] +23/03/24 21:47:01| INFO mul_sld_lr_gs finished [took 1863.1379s] +23/03/24 21:47:01| INFO Dataset sample [0.1 0.3 0.6] of dataset twitter_gasp finished [took 2646.2735s] +23/03/24 21:47:01| INFO Dataset sample [0.1 0.4 0.5] of dataset twitter_gasp started +23/03/24 21:49:53| INFO ref finished [took 169.4108s] +23/03/24 21:50:27| INFO atc_mc finished [took 203.1705s] +23/03/24 21:51:40| INFO doc finished [took 276.5127s] +23/03/24 21:57:52| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.01, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': None} (score=0.39790) [took 369.1918s] +23/03/24 22:03:49| INFO bin_sld_lr_gs finished [took 726.3554s] +23/03/24 22:33:27| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.01, 'quantifier__classifier__class_weight': None, 'quantifier__recalib': None, 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.29012) [took 1776.7620s] +23/03/24 22:39:12| INFO mul_sld_lr_gs finished [took 2121.1486s] +23/03/24 22:39:12| INFO Dataset sample [0.1 0.4 0.5] of dataset twitter_gasp finished [took 3130.6817s] +23/03/24 22:39:12| INFO Dataset sample [0.1 0.5 0.4] of dataset twitter_gasp started +23/03/24 22:42:05| INFO ref finished [took 168.4307s] +23/03/24 22:42:41| INFO atc_mc finished [took 204.3716s] +23/03/24 22:43:53| INFO doc finished [took 276.3731s] +23/03/24 22:49:15| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.01, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': None} (score=0.38753) [took 317.5081s] +23/03/24 22:55:16| INFO bin_sld_lr_gs finished [took 678.0761s] +23/03/24 23:21:31| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.01, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': ['max_conf', 'entropy']} (score=0.30605) [took 1569.6995s] +23/03/24 23:28:43| INFO mul_sld_lr_gs finished [took 2001.7825s] +23/03/24 23:28:43| INFO Dataset sample [0.1 0.5 0.4] of dataset twitter_gasp finished [took 2970.8333s] +23/03/24 23:28:43| INFO Dataset sample [0.1 0.6 0.3] of dataset twitter_gasp started +23/03/24 23:31:39| INFO ref finished [took 172.9644s] +23/03/24 23:31:59| INFO atc_mc finished [took 193.9490s] +23/03/24 23:33:28| INFO doc finished [took 282.4988s] +23/03/24 23:38:37| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.01, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.46894) [took 306.3956s] +23/03/24 23:45:15| INFO bin_sld_lr_gs finished [took 704.9389s] +24/03/24 00:13:34| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.01, 'quantifier__classifier__class_weight': None, 'quantifier__recalib': None, 'confidence': None} (score=0.28360) [took 1697.4398s] +24/03/24 00:19:45| INFO mul_sld_lr_gs finished [took 2068.7239s] +24/03/24 00:19:45| INFO Dataset sample [0.1 0.6 0.3] of dataset twitter_gasp finished [took 3062.8557s] +24/03/24 00:19:46| INFO Dataset sample [0.1 0.7 0.2] of dataset twitter_gasp started +24/03/24 00:22:39| INFO ref finished [took 171.2353s] +24/03/24 00:23:05| INFO atc_mc finished [took 197.1845s] +24/03/24 00:24:30| INFO doc finished [took 281.6584s] +24/03/24 00:26:04| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.001, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.45066) [took 92.5093s] +24/03/24 00:33:15| INFO bin_sld_lr_gs finished [took 523.9133s] +24/03/24 00:52:25| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.001, 'quantifier__classifier__class_weight': None, 'quantifier__recalib': None, 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.15728) [took 1148.3511s] +24/03/24 00:59:13| INFO mul_sld_lr_gs finished [took 1555.8012s] +24/03/24 00:59:13| INFO Dataset sample [0.1 0.7 0.2] of dataset twitter_gasp finished [took 2367.1019s] +24/03/24 00:59:13| INFO Dataset sample [0.1 0.8 0.1] of dataset twitter_gasp started +24/03/24 01:02:01| INFO ref finished [took 165.6138s] +24/03/24 01:02:38| INFO atc_mc finished [took 202.0159s] +24/03/24 01:03:48| INFO doc finished [took 272.3917s] +24/03/24 01:05:20| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.001, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.32780) [took 89.5332s] +24/03/24 01:14:01| INFO bin_sld_lr_gs finished [took 610.9926s] +24/03/24 01:34:15| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.01, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': ['max_conf', 'entropy']} (score=0.39650) [took 1212.0476s] +24/03/24 01:40:12| INFO mul_sld_lr_gs finished [took 1569.3225s] +24/03/24 01:40:12| INFO Dataset sample [0.1 0.8 0.1] of dataset twitter_gasp finished [took 2459.8550s] +24/03/24 01:40:13| INFO Dataset sample [0.2 0.1 0.7] of dataset twitter_gasp started +24/03/24 01:43:08| INFO ref finished [took 171.8125s] +24/03/24 01:43:41| INFO atc_mc finished [took 205.4032s] +24/03/24 01:44:50| INFO doc finished [took 274.7637s] +24/03/24 01:51:48| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.01, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.29861) [took 415.5057s] +24/03/24 01:57:37| INFO bin_sld_lr_gs finished [took 764.2145s] +24/03/24 02:24:40| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.01, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': ['isoft']} (score=0.08442) [took 1620.1289s] +24/03/24 02:32:04| INFO mul_sld_lr_gs finished [took 2064.8842s] +24/03/24 02:32:04| INFO Dataset sample [0.2 0.1 0.7] of dataset twitter_gasp finished [took 3111.7593s] +24/03/24 02:32:04| INFO Dataset sample [0.2 0.2 0.6] of dataset twitter_gasp started +24/03/24 02:34:59| INFO ref finished [took 171.7735s] +24/03/24 02:35:26| INFO atc_mc finished [took 198.4913s] +24/03/24 02:36:52| INFO doc finished [took 284.4719s] +24/03/24 02:55:15| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.001, 'quantifier__classifier__class_weight': None, 'quantifier__recalib': 'bcts', 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.10977) [took 1101.3241s] +24/03/24 03:06:36| INFO bin_sld_lr_gs finished [took 1782.1657s] +24/03/24 03:38:15| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.01, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': 'bcts', 'confidence': None} (score=0.10545) [took 1896.6195s] +24/03/24 03:44:22| INFO mul_sld_lr_gs finished [took 2263.4609s] +24/03/24 03:44:22| INFO Dataset sample [0.2 0.2 0.6] of dataset twitter_gasp finished [took 4337.6081s] +24/03/24 03:44:22| INFO Dataset sample [0.2 0.3 0.5] of dataset twitter_gasp started +24/03/24 03:47:16| INFO ref finished [took 169.1338s] +24/03/24 03:47:52| INFO atc_mc finished [took 205.8354s] +24/03/24 03:49:04| INFO doc finished [took 277.1275s] +24/03/24 04:06:25| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.001, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': 'bcts', 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.05928) [took 1036.7130s] +24/03/24 04:28:27| INFO bin_sld_lr_gs finished [took 2358.3194s] +24/03/24 04:56:30| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.01, 'quantifier__classifier__class_weight': None, 'quantifier__recalib': 'bcts', 'confidence': ['isoft']} (score=0.04820) [took 1678.8528s] +24/03/24 05:02:49| INFO mul_sld_lr_gs finished [took 2057.6758s] +24/03/24 05:02:49| INFO Dataset sample [0.2 0.3 0.5] of dataset twitter_gasp finished [took 4706.7902s] +24/03/24 05:02:49| INFO Dataset sample [0.2 0.4 0.4] of dataset twitter_gasp started +24/03/24 05:05:36| INFO ref finished [took 163.6101s] +24/03/24 05:06:16| INFO atc_mc finished [took 204.0339s] +24/03/24 05:07:38| INFO doc finished [took 285.2930s] +24/03/24 05:22:06| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 100.0, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': 'bcts', 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.06817) [took 865.6232s] +24/03/24 05:32:03| INFO bin_sld_lr_gs finished [took 1462.6470s] +24/03/24 05:55:34| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 1000.0, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': 'bcts', 'confidence': ['isoft']} (score=0.06590) [took 1408.2803s] +24/03/24 06:01:24| INFO mul_sld_lr_gs finished [took 1758.8460s] +24/03/24 06:01:24| INFO Dataset sample [0.2 0.4 0.4] of dataset twitter_gasp finished [took 3515.6718s] +24/03/24 06:01:24| INFO Dataset sample [0.2 0.5 0.3] of dataset twitter_gasp started +24/03/24 06:04:19| INFO ref finished [took 172.1190s] +24/03/24 06:04:45| INFO atc_mc finished [took 198.0125s] +24/03/24 06:06:11| INFO doc finished [took 283.3396s] +24/03/24 06:23:24| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 10.0, 'quantifier__classifier__class_weight': None, 'quantifier__recalib': 'bcts', 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.05915) [took 1031.1653s] +24/03/24 06:36:25| INFO bin_sld_lr_gs finished [took 1812.6412s] +24/03/24 07:09:17| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.01, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': ['max_conf', 'entropy']} (score=0.07436) [took 1969.4414s] +24/03/24 07:15:39| INFO mul_sld_lr_gs finished [took 2351.6924s] +24/03/24 07:15:39| INFO Dataset sample [0.2 0.5 0.3] of dataset twitter_gasp finished [took 4454.6974s] +24/03/24 07:15:39| INFO Dataset sample [0.2 0.6 0.2] of dataset twitter_gasp started +24/03/24 07:18:38| INFO ref finished [took 173.8867s] +24/03/24 07:18:59| INFO atc_mc finished [took 196.0171s] +24/03/24 07:20:28| INFO doc finished [took 283.8673s] +24/03/24 07:36:15| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.01, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.35023) [took 942.7367s] +24/03/24 07:42:39| INFO bin_sld_lr_gs finished [took 1326.8983s] +24/03/24 08:10:32| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.01, 'quantifier__classifier__class_weight': None, 'quantifier__recalib': None, 'confidence': ['isoft']} (score=0.14448) [took 1668.4160s] +24/03/24 08:16:54| INFO mul_sld_lr_gs finished [took 2050.4526s] +24/03/24 08:16:54| INFO Dataset sample [0.2 0.6 0.2] of dataset twitter_gasp finished [took 3675.1176s] +24/03/24 08:16:54| INFO Dataset sample [0.3 0.1 0.6] of dataset twitter_gasp started +24/03/24 08:19:45| INFO ref finished [took 167.6289s] +24/03/24 08:20:21| INFO atc_mc finished [took 203.5763s] +24/03/24 08:21:36| INFO doc finished [took 278.8141s] +24/03/24 08:29:33| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.01, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.43840) [took 474.1795s] +24/03/24 08:35:43| INFO bin_sld_lr_gs finished [took 844.4202s] +24/03/24 09:03:22| DEBUG [MultiClassAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.01, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': None, 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.33993) [took 1657.3825s] +24/03/24 09:09:38| INFO mul_sld_lr_gs finished [took 2033.2904s] +24/03/24 09:09:38| INFO Dataset sample [0.3 0.1 0.6] of dataset twitter_gasp finished [took 3163.8876s] +24/03/24 09:09:38| INFO Dataset sample [0.3 0.2 0.5] of dataset twitter_gasp started +24/03/24 09:12:28| INFO ref finished [took 166.0508s] +24/03/24 09:13:10| INFO atc_mc finished [took 207.8181s] +24/03/24 09:14:21| INFO doc finished [took 279.1057s] +24/03/24 09:33:22| DEBUG [BinaryQuantifierAccuracyEstimator] optimization finished: best params {'quantifier__classifier__C': 0.1, 'quantifier__classifier__class_weight': 'balanced', 'quantifier__recalib': 'bcts', 'confidence': ['max_conf', 'entropy', 'isoft']} (score=0.12476) [took 1138.0470s] +24/03/24 09:42:06| INFO bin_sld_lr_gs finished [took 1662.0260s] +---------------------------------------------------------------------------------------------------- +24/03/24 10:09:42| INFO dataset twitter_gasp_4prevs [pool size: 10] +24/03/24 10:09:42| INFO Dataset sample [0.2 0.2 0.6] of dataset twitter_gasp_4prevs started +24/03/24 10:12:41| INFO ref finished [took 173.8145s] +24/03/24 10:13:10| INFO atc_mc finished [took 203.0342s] +24/03/24 10:14:33| INFO doc finished [took 285.7280s] diff --git a/quacc/evaluation/method.py b/quacc/evaluation/method.py index 3b0af41..89430cb 100644 --- a/quacc/evaluation/method.py +++ b/quacc/evaluation/method.py @@ -17,6 +17,7 @@ from quacc.method.model_selection import ( SpiderSearchAE, ) from quacc.quantification import KDEy +import traceback def _param_grid(method, X_fit: np.ndarray): @@ -106,6 +107,7 @@ def evaluation_report( report.append_row(sample.prevalence(), **row) except Exception as e: print(f"sample prediction failed for method {method_name}: {e}") + traceback.print_exception(e) report.append_row( sample.prevalence(), acc_score=np.nan, diff --git a/quacc/method/base.py b/quacc/method/base.py index aa0999b..adb1286 100644 --- a/quacc/method/base.py +++ b/quacc/method/base.py @@ -166,11 +166,19 @@ class MultiClassAccuracyEstimator(ConfidenceBasedAccuracyEstimator): # def _get_pred_ext(self, pred_proba: np.ndarray): # return np.argmax(pred_proba, axis=1, keepdims=True) + def _get_multi_quant(self, quant, train: LabelledCollection): + _nz = np.nonzero(train.counts())[0] + if _nz.shape[0] == 1: + return TrivialQuantifier(train.n_classes, _nz[0]) + else: + return quant + def fit(self, train: LabelledCollection): pred_proba = self.classifier.predict_proba(train.X) self._fit_confidence(train.X, train.y, pred_proba) self.e_train = self.extend(train, pred_proba=pred_proba) + self.quantifier = self._get_multi_quant(self.quantifier, self.e_train) self.quantifier.fit(self.e_train) return self @@ -199,6 +207,64 @@ class MultiClassAccuracyEstimator(ConfidenceBasedAccuracyEstimator): return self.extpol.group_false +class TrivialQuantifier: + def __init__(self, n_classes, trivial_class): + self.trivial_class = trivial_class + + def fit(self, train: LabelledCollection): + pass + + def quantify(self, inst: LabelledCollection) -> np.ndarray: + return np.array([1.0]) + + @property + def classes_(self): + return np.array([self.trivial_class]) + + +class QuantifierProxy: + def __init__(self, train: LabelledCollection): + self.o_nclasses = train.n_classes + self.o_classes = train.classes_ + self.o_index = {c: i for i, c in enumerate(train.classes_)} + + self.mapping = {} + self.r_mapping = {} + _cnt = 0 + for cl, c in zip(train.classes_, train.counts()): + if c > 0: + self.mapping[cl] = _cnt + self.r_mapping[_cnt] = cl + _cnt += 1 + + self.n_nclasses = len(self.mapping) + + def apply_mapping(self, coll: LabelledCollection) -> LabelledCollection: + if not self.proxied: + return coll + + n_labels = np.copy(coll.labels) + for k in self.mapping: + n_labels[coll.labels == k] = self.mapping[k] + + return LabelledCollection(coll.X, n_labels, classes=np.arange(self.n_nclasses)) + + def apply_rmapping(self, prevs: np.ndarray, q_classes: np.ndarray) -> np.ndarray: + if not self.proxied: + return prevs, q_classes + + n_qclasses = np.array([self.r_mapping[qc] for qc in q_classes]) + + return prevs, n_qclasses + + def get_trivial(self): + return TrivialQuantifier(self.o_nclasses, self.n_nclasses) + + @property + def proxied(self): + return self.o_nclasses != self.n_nclasses + + class BinaryQuantifierAccuracyEstimator(ConfidenceBasedAccuracyEstimator): def __init__( self, @@ -219,6 +285,13 @@ class BinaryQuantifierAccuracyEstimator(ConfidenceBasedAccuracyEstimator): dense=dense, ) + def _get_binary_quant(self, quant, train: LabelledCollection): + _nz = np.nonzero(train.counts())[0] + if _nz.shape[0] == 1: + return TrivialQuantifier(train.n_classes, _nz[0]) + else: + return deepcopy(quant) + def fit(self, train: LabelledCollection | ExtendedCollection): pred_proba = self.classifier.predict_proba(train.X) self._fit_confidence(train.X, train.y, pred_proba) @@ -229,7 +302,7 @@ class BinaryQuantifierAccuracyEstimator(ConfidenceBasedAccuracyEstimator): self.quantifiers = [] for train in e_trains: - quant = deepcopy(self.quantifier) + quant = self._get_binary_quant(self.quantifier, train) quant.fit(train) self.quantifiers.append(quant) @@ -248,6 +321,7 @@ class BinaryQuantifierAccuracyEstimator(ConfidenceBasedAccuracyEstimator): # estim_prev = np.concatenate(estim_prevs.T) # return ExtendedPrev(estim_prev, e_inst.nbcl, extpol=self.extpol) + return ExtBinPrev( estim_prevs, e_inst.nbcl, @@ -263,7 +337,8 @@ class BinaryQuantifierAccuracyEstimator(ConfidenceBasedAccuracyEstimator): estim_prevs = [] for quant, inst, norm in zip(self.quantifiers, s_inst, norms): if inst.shape[0] > 0: - estim_prevs.append(quant.quantify(inst) * norm) + estim_prev = quant.quantify(inst) * norm + estim_prevs.append(estim_prev) else: estim_prevs.append(np.zeros((len(quant.classes_),)))