P3D = Pep3Dparser(pep3d)
P3D.get_all_tag_counts()
del P3D
le = P3D.LE
he = P3D.HE
le['ADCResponse'] = 10000
P3D.LE = le
he['ADCResponse'] = 10000
P3D.HE = he
P3D.write(pep3d.parent/(pep3d.stem + "_ADCResponse10000.xml"))
# compare outputs: with check sums:
from syncFiles.syncFiles import check_sum
from waters.parsers import iaDBsXMLparser
ia_workflows = list(data_f.glob('*_IA_Workflow*.xml'))
for iw in ia_workflows:
print(check_sum(iw))
# check sums do differ: what about the data?
orig = ia_workflows[0]
mod = ia_workflows[1]
parsed = [iaDBsXMLparser(i) for i in ia_workflows]
prots = [i.proteins() for i in parsed]
prods = [i.products() for i in parsed]
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
plt.style.use('dark_background')
data_f = Path('~/Projects/WatersData').expanduser()
apexPaths = list(data_f.glob('*/*_Apex3D.xml'))
apex3d = next(data_f.glob('*/*_Apex3D.xml'))
pep3d = next(data_f.glob('*/*_Pep3D_Spectrum.xml'))
iaDBs = next(data_f.glob('*/*_IA_workflow.xml'))
A = Apex3Dparser(apex3d)
A.LE
A.HE
A.to_hdf()
A.data_path
A.LE.to_hdf(apex3d.with_suffix('.hd5'), 'LE', complevel=9)
P = Pep3Dparser(pep3d)
P.LE
P.HE
IA = iaDBsXMLparser(iaDBs)
IA.parameters()
IA.count_proteins_per_hit()
IA.info()
)
args = p.parse_args()
try:
print('Parsing iaDBs outputs to csvs.')
from fs_ops.paths import find_suffixed_files
from waters.parsers import iaDBsXMLparser
xmls = list(
find_suffixed_files(args.paths, ['**/*_IA_workflow.xml'], ['.xml']))
print('Supplied paths:')
pprint(xmls)
for xml in xmls:
XML = iaDBsXMLparser(xml)
info = XML.info()
pprint(info)
print('dumping to csv')
XML.query_masses().to_csv(xml.parent / 'query_masses.csv')
XML.proteins().to_csv(xml.parent / 'proteins.csv')
XML.products().to_csv(xml.parent / 'products.csv')
except Exception as e:
print(e)
print()
print('Avoid tricks of Loki.')
print('And have a nice day..')
input('press ENTER')
%load_ext autoreload
%autoreload 2
from collections import Counter
from pathlib import Path
import pandas as pd
pd.set_option('display.max_columns', 100)
pd.set_option('display.max_rows', 5)
import numpy as np
from pprint import pprint
from waters.parsers import iaDBsXMLparser
data_f = Path(r"/home/matteo/Projects/WatersData/ADCResppnse")
files = list(data_f.glob('*IA*.xml'))
I0 = iaDBsXMLparser(files[0])
I1 = iaDBsXMLparser(files[1])
I2 = iaDBsXMLparser(files[2])
diff = lambda d0, d1: (d1 != d0).any(1)
I0.get_all_tag_counts()
I0.parameters()
PR0 = I0.products()
PR1 = I1.products()
sum(diff(PR0, PR1))
PR0[diff(PR0, PR1)]
sum(diff(PR0.iloc[:,:14], PR1.iloc[:,:14]))
Counter(PR0.LOSS_TYPE)
Counter(PR1.LOSS_TYPE) # dass siehst gut aus.
%load_ext autoreload
%autoreload 2
from pathlib import Path
from pprint import pprint
from collections import Counter
import pandas as pd
import csv
import json
import numpy as np
import xml.etree.cElementTree as ET
from plotnine import *
import sklearn
from sklearn.linear_model import LinearRegression
from statsmodels.api import OLS
import matplotlib.pyplot as plt
import statsmodels.api as sm
import statsmodels.formula.api as smf
from fs_ops.csv import rows2csv
from waters.parsers import XMLparser, iaDBsXMLparser, Pep3Dparser, Apex3Dparser
data_f = Path('~/Projects/WatersData/O190303_78').expanduser()
apex3d = next(data_f.glob('*_Apex3D.xml'))
pep3d = next(data_f.glob('*_Pep3D_Spectrum.xml'))
iadbs = next(data_f.glob('*_IA_workflow.xml'))
I = iaDBsXMLparser(iadbs)
A = Apex3Dparser(apex3d)
A.LE()
A.HE()
from pprint import pprint
from collections import Counter
import pandas as pd
import csv
import json
import numpy as np
import xml.etree.cElementTree as ET
from fs_ops.csv import rows2csv
from waters.parsers import XMLparser, iaDBsXMLparser
# data_path = Path("~/Projects/waters/data/T181207_07/T181207_07_IA_workflow.xml").expanduser()
data_path = Path("~/Projects/WatersData/O190303_78/O190303_78_IA_workflow.xml").expanduser()
assert data_path.exists()
iaDBsXML = iaDBsXMLparser(data_path)
prots = iaDBsXML.prot_ids()
iaDBsXML.get_tag_counts()
iaDBsXML.proteins()
iaDBsXML.products()
iaDBsXML.get_tag_counts()
iaDBsXML.parameters()
iaDBsXML.query_masses()
iaDBsXML.count_proteins_per_hit()
info = iaDBsXML.info()
rows2csv(Path("~/Projects/waters/data/info.csv").expanduser(),
[list(info), list(info.values())])