Skip to content

Instantly share code, notes, and snippets.

View abojchevski's full-sized avatar
⚔️

Aleksandar Bojchevski abojchevski

⚔️
View GitHub Profile
REMOVING lysine residues at positions 147 and 151 ['lysine residues at positions 147', 'and', '151']
REMOVING Replacement of histidines 147 and 151 with tyrosine ['Replacement of histidines 147', 'and', '151 with tyrosine']
REMOVING inhibitors to histidine residues at positions 147 and 151 ['inhibitors to histidine residues at positions 147', 'and', '151']
REMOVING substitution in codon 14, coding for a histidine in GPT-1 and an asparagine in GPT-2 ['substitution in codon 14', ',', 'coding for a histidine in GPT-1', 'and', 'an asparagine in GPT-2']
REMOVING Mutation of both Ser(180) and Ser(181) to Ala ['Mutation of both Ser(180)', 'and', 'Ser(181) to Ala']
REMOVING cytosine-to-guanine transversion, a mutation that caused a single amino acid substitution (glutamine instead of glutamic acid) at position 22 ['cytosine-to-guanine transversion', ',', 'a mutation that caused a single amino acid substitution (glutamine instead of glutamic acid) at position 22']
REMOVING serine residues 367, 1893 ['serine residues 3
WITH
# class tp fp fn fp_ov fn_ov match P P_SE R R_SE F F_SE match P P_SE R R_SE F F_SE
0 319 56 82 36 39 e 0.8507 0.0023 0.7955 0.0025 0.8222 0.0022 o 0.9517 0.0014 0.9016 0.0018 0.9260 0.0013
1 69 191 194 151 124 e 0.2654 0.0023 0.2624 0.0023 0.2639 0.0022 o 0.8958 0.0013 0.8309 0.0019 0.8622 0.0013
2 17 42 43 23 25 e 0.2881 0.0054 0.2833 0.0057 0.2857 0.0046 o 0.7738 0.0057 0.7831 0.0055 0.7784 0.0045
405 289 319 210 188 e 0.5836 0.0024 0.5594 0.0023 0.5712 0.0023 o 0.9104 0.0010 0.8597 0.0012 0.8844 0.0009
WITHOUT
# class tp fp fn fp_ov fn_ov match P P_SE R R_SE F F_SE match P P_SE R R_SE F F_SE
/home/abojchevski/anaconda3/bin/python /home/abojchevski/projects/nala/scripts/train.py --test_corpus tmVar_test --model_path_1 /home/abojchevski/Downloads/nala_BIEO_del_None_466744.bin --we
SpacyLemmatizer: INIT START
SpacyLemmatizer: INIT END
word embddings loaded with vocab size: 519819
Running arguments:
crf_train_params = None
cv_fold = None
cv_n = None
delete_subclasses = []
do_train = False
/home/abojchevski/anaconda3/bin/python /home/abojchevski/projects/nala/scripts/train.py --test_corpus tmVar_test --model_path_1 /home/abojchevski/Downloads/nala_BIEO_del_None_466744.bin --we
SpacyLemmatizer: INIT START
SpacyLemmatizer: INIT END
Running arguments:
word embddings loaded with vocab size: 519819
crf_train_params = None
cv_fold = None
cv_n = None
delete_subclasses = []
do_train = False
/home/abojchevski/anaconda3/bin/python /home/abojchevski/projects/nala/scripts/train.py --test_corpus SETH --model_path_1 /home/abojchevski/Downloads/nala_BIEO_del_None_466744.bin --we
reading from cache /home/abojchevski/.nalaf/DownloadArticle_cache.json
writing the cache /home/abojchevski/.nalaf/DownloadArticle_cache.json
SpacyLemmatizer: INIT START
SpacyLemmatizer: INIT END
word embddings loaded with vocab size: 519819
Running arguments:
crf_train_params = None
cv_fold = None
cv_n = None
/home/abojchevski/anaconda3/bin/python /home/abojchevski/projects/nala/scripts/train.py --test_corpus IDP4 --model_path_1 /home/abojchevski/Downloads/nala_BIEO_del_None_466744.bin --we
Iteration: 0 : /home/abojchevski/projects/nala/resources/bootstrapping/iteration_0
Dataset(159 documents and 3337 annotations)
SpacyLemmatizer: INIT START
SpacyLemmatizer: INIT END
Running arguments:
word embddings loaded with vocab size: 519819
crf_train_params = None
cv_fold = None
cv_n = None
/home/abojchevski/anaconda3/bin/python /home/abojchevski/projects/nala/scripts/train.py --test_corpus IDP4 --model_path_1 /home/abojchevski/Downloads/nala_BIEO_del_None_466744.bin --we
Iteration: 0 : /home/abojchevski/projects/nala/resources/bootstrapping/iteration_0
Dataset(157 documents and 3337 annotations)
SpacyLemmatizer: INIT START
SpacyLemmatizer: INIT END
word embddings loaded with vocab size: 519819
Running arguments:
crf_train_params = None
cv_fold = None
8306: FP NOT OVERLAPPING A to G
8308: FP NOT OVERLAPPING In-frame single codon deletion
8310: FP NOT OVERLAPPING 1AT
8314: FP NOT OVERLAPPING 1AT
8316: FP NOT OVERLAPPING 1AT
8318: FP NOT OVERLAPPING IVS+6C
8321: FP NOT OVERLAPPING substitution of a basic residue arginine to a noncharged residue serine
8323: FP NOT OVERLAPPING amino acid sequence from positions 415 to 420
8324: FP NOT OVERLAPPING W221-I222-H223
8325: FP NOT OVERLAPPING 2-bp deletion
210-AAJV,Dell Precision T1700 MT CTO Basis
,Part Number,Description,Quantity
,6337P,"LABEL, SVC TAG/EXPRESS CODE, LATC",1
,JD509,"LABEL, REGULATORY, SIDE, UNIVERSAL, BLANK , V2",1
,T845M,"INSTRUCTION, TRIGGER, SVC TAG",1
328-BBBV,Dell Precision T1700 MT Verpackung
,Part Number,Description,Quantity
,G20NP,"SHIPPING MATERIAL, BOX, OPTION, KTSK, MNTW, EUROPE, MIDDLE EAST & AFRICA",1
,HK8G4,"CUSTOMER KIT, DVD+/-RW, 8X, TOSHIBA SAMSUNG STORAGE TECHNOLOGY, OPTIPLEX, 780",1
,VPD2H,"SHIPPING MATERIAL, CUSHION, SYSTEM, CMRS, MNTW",1
210-AAJV Dell Precision T1700 MT CTO Basis
Part Number Description Quantity
6337P LABEL, SVC TAG/EXPRESS CODE, LATC 1
JD509 LABEL, REGULATORY, SIDE, UNIVERSAL, BLANK , V2 1
T845M INSTRUCTION, TRIGGER, SVC TAG 1
328-BBBV Dell Precision T1700 MT Verpackung
Part Number Description Quantity
G20NP SHIPPING MATERIAL, BOX, OPTION, KTSK, MNTW, EUROPE, MIDDLE EAST & AFRICA 1
HK8G4 CUSTOMER KIT, DVD+/-RW, 8X, TOSHIBA SAMSUNG STORAGE TECHNOLOGY, OPTIPLEX, 780 1
VPD2H SHIPPING MATERIAL, CUSHION, SYSTEM, CMRS, MNTW 1