LSHTM_analysis/scripts/ml/running_ml_scripts.txt

138 lines
5.2 KiB
Text

==================================
# UQ run: same as ORIGINAL except
# Features NOT including AA index, but includes active site annotations
# Date: 30/05/2022, but reran with from my desktop on 19/05/2022 to capture log and include active_site indication column
# captures error: 2>$1
=================================
./pnca_config.py 2>&1 | tee log_pnca_config.txt
./embb_config.py 2>&1 | tee log_embb_config.txt
./gid_config.py 2>&1 | tee log_gid_config.txt
./katg_config.py 2>&1 | tee log_katg_config.txt
./rpob_config.py 2>&1 | tee log_rpob_config.txt
./alr_config.py 2>&1 | tee log_alr_config.txt
# ERROR, as expected, too few values!
########################################################################
=================================
# Split: ORIGINAL
# actual values: training set
# imputed values: blind set
# All features including AA index
# Date: 18/05/2022 # reran with minor formatting and log capture
# captures error: 2>$1
=================================
./pnca_orig.py 2>&1 | tee log_pnca_orig.txt
./embb_orig.py 2>&1 | tee log_embb_orig.txt
./gid_orig.py 2>&1 | tee log_gid_orig.txt
./katg_orig.py 2>&1 | tee log_katg_orig.txt
./rpob_orig.py 2>&1 | tee log_rpob_orig.txt
./alr_orig.py 2>&1 | tee log_alr_orig.txt # ERROR, as expected, too few values!
########################################################################
=================================
# Split: 70/30
# All features including AA index
# Date: 17/05/2022 and 18/05/2022, reran with minor foramtting and log capture
# captures error: 2>$1
=================================
./pnca_7030.py 2>&1 | tee log_pnca_7030.txt
./embb_7030.py 2>&1 | tee log_embb_7030.txt
./gid_7030.py 2>&1 | tee log_gid_7030.txt
./katg_7030.py 2>&1 | tee log_katg_7030.txt
./rpob_7030.py 2>&1 | tee log_rpob_7030.txt
./alr_7030.py 2>&1 | tee log_alr_7030.txt # ERROR, as expected, too few values!
problems, CT values are non existing except for rouC
########################################################################
=================================
# Split: 80/20
# All features including AA index
# Date: 17/05/2022, 18:48
# captures error: 2>$1
=================================
./pnca_8020.py 2>&1 | tee log_pnca_8020.txt
./embb_8020.py 2>&1 | tee log_embb_8020.txt
./gid_8020.py 2>&1 | tee log_gid_8020.txt
./katg_8020.py 2>&1 | tee log_katg_8020.txt
./rpob_8020.py 2>&1 | tee log_rpob_8020.txt
./alr_8020.py 2>&1 | tee log_alr_8020.txt # ERROR, as expected, too few values!
########################################################################
=================================
# Split: scaling law
# All features including AA index
# Date: 17/05/2022, 18:48
# captures error: 2>$1
=================================
./pnca_sl.py 2>&1 | tee log_pnca_sl.txt
./embb_sl.py 2>&1 | tee log_embb_sl.txt
./gid_sl.py 2>&1 | tee log_gid_sl.txt
./katg_sl.py 2>&1 | tee log_katg_sl.txt
./rpob_sl.py 2>&1 | tee log_rpob_sl.txt
./alr_sl.py 2>&1 | tee log_alr_sl.txt # ERROR, as expected, too few values!
########################################################################
=================================
# Split: REVERSE training
# imputed values: training set
# actual values: blind set
# All features including AA index
# Date: 18/05/2022
# captures error: 2>$1
=================================
./pnca_rt.py 2>&1 | tee log_pnca_rt.txt
./embb_rt.py 2>&1 | tee log_embb_rt.txt
./gid_rt.py 2>&1 | tee log_gid_rt.txt
./katg_rt.py 2>&1 | tee log_katg_rt.txt
./rpob_rt.py 2>&1 | tee log_rpob_rt.txt
./alr_rt.py 2>&1 | tee log_alr_rt.txt # ERROR, as expected, too few values!
########################################################################
# COMPLETE Data: actual + na i.e imputed
########################################################################
=================================
# Split: 70/30 [COMPLETE DATA]
# All features including AA index
# Date: 18/05/2022
# captures error: 2>$1
=================================
./pnca_cd_7030.py 2>&1 | tee log_pnca_cd_7030.txt
./embb_cd_7030.py 2>&1 | tee log_embb_cd_7030.txt
./gid_cd_7030.py 2>&1 | tee log_gid_cd_7030.txt
./katg_cd_7030.py 2>&1 | tee log_katg_cd_7030.txt
./rpob_cd_7030.py 2>&1 | tee log_rpob_cd_7030.txt
./alr_cd_7030.py 2>&1 | tee log_alr_cd_7030.txt # ERROR, as expected, too few values!
########################################################################
=================================
# Split: 80/20 [COMPLETE DATA]
# All features including AA index
# Date: 18/05/2022
# captures error: 2>$1
=================================
./pnca_cd_8020.py 2>&1 | tee log_pnca_cd_8020.txt
./embb_cd_8020.py 2>&1 | tee log_embb_cd_8020.txt
./gid_cd_8020.py 2>&1 | tee log_gid_cd_8020.txt
./katg_cd_8020.py 2>&1 | tee log_katg_cd_8020.txt
./rpob_cd_8020.py 2>&1 | tee log_rpob_cd_8020.txt
./alr_cd_8020.py 2>&1 | tee log_alr_cd_8020.txt # ERROR, as expected, too few values!
=================================
# Split: scaling law [COMPLETE DATA]
# All features including AA index
# Date: 18/05/2022
# captures error: 2>$1
=================================
./pnca_cd_sl.py 2>&1 | tee log_pnca_cd_sl.txt
./embb_cd_sl.py 2>&1 | tee log_embb_cd_sl.txt
./gid_cd_sl.py 2>&1 | tee log_gid_cd_sl.txt
./katg_cd_sl.py 2>&1 | tee log_katg_cd_sl.txt
./rpob_cd_sl.py 2>&1 | tee log_rpob_cd_sl.txt
./alr_cd_sl.py 2>&1 | tee log_alr_cd_sl.txt # ERROR, as expected, too few values!