def to_csv(self, out_path, out_path_filtered, cutoff, sep, **kw):
# write first table with header
path = self.pathes[0]
table = read_csv(path, self.options.get("delim_in"))
df = self.scorer.score(table)
df.to_csv(out_path, sep, header=True, **kw)
self._update_scores(df)
df = df[df.d_score > cutoff]
df.to_csv(out_path_filtered, sep, header=True, **kw)
# now append and do not write headers again:
for path in self.pathes[1:]:
with open(out_path, "a") as fp, open(out_path_filtered, "a") as fp2:
table = read_csv(path, self.options.get("delim_in"))
df = self.scorer.score(table)
df.to_csv(fp, sep, header=True, **kw)
self._update_scores(df)
df = df[df.d_score > cutoff]
df.to_csv(fp2, sep, header=True, **kw)
def to_csv(self, out_path, out_path_filtered, cutoff, sep, **kw):
# write first table with header
path = self.pathes[0]
table = read_csv(path, self.options.get("delim_in"))
df = self.scorer.score(table)
df.to_csv(out_path, sep, header=True, **kw)
self._update_scores(df)
df = df[df.d_score > cutoff]
df.to_csv(out_path_filtered, sep, header=True, **kw)
# now append and do not write headers again:
for path in self.pathes[1:]:
with open(out_path, "a") as fp, open(out_path_filtered,
"a") as fp2:
table = read_csv(path, self.options.get("delim_in"))
df = self.scorer.score(table)
df.to_csv(fp, sep, header=True, **kw)
self._update_scores(df)
df = df[df.d_score > cutoff]
df.to_csv(fp2, sep, header=True, **kw)
def to_csv(self, out_path, out_path_filtered, cutoff, sep, **kw):
table = read_csv(self.path, self.options.get("delim_in"))
df = self.scorer.score(table)
df.to_csv(out_path, sep, **kw)
df = df[df.d_score > cutoff]
df.to_csv(out_path_filtered, sep, **kw)
self.decoys = df[df["decoy"] == 1]["d_score"].values
self.targets = df[df["decoy"] == 0]["d_score"].values
tops = df[df["peak_group_rank"] == 1]
self.top_decoys = tops[tops["decoy"] == 1]["d_score"].values
self.top_targets = tops[tops["decoy"] == 0]["d_score"].values
def to_csv(self, out_path, out_path_filtered, cutoff, sep, **kw):
table = read_csv(self.path, self.options.get("delim_in"))
df = self.scorer.score(table)
df.to_csv(out_path, sep, **kw)
df = df[df.d_score > cutoff]
df.to_csv(out_path_filtered, sep, **kw)
self.decoys = df[df["decoy"] == 1]["d_score"].values
self.targets = df[df["decoy"] == 0]["d_score"].values
tops = df[df["peak_group_rank"] == 1]
self.top_decoys = tops[tops["decoy"] == 1]["d_score"].values
self.top_targets = tops[tops["decoy"] == 0]["d_score"].values
def read_tables_iter(self, pathes, delim):
logging.info("process %s" % ", ".join(pathes))
for path in pathes:
part = read_csv(path, delim)
yield part
###################################
# temporary file for code testing #
###################################
# import python packages
import os
# import local files
import generators as gen
import data_handling as data
inputfile = 'data/random_subset_MainDiagonal.txt'
df = data.read_csv(inputfile, -1)
print('Input dataframe shape: ', df.shape)
df = df.loc[df['Json'] == True]
print('Input golden dataframe shape: ', df.shape)
(hist, runnbs, lsnbs) = data.get_hist_values(df)
print('Shape of histogram array: ' + str(hist.shape))
selhist = hist[102:103, :]
print('Shape of selected histogram array: ' + str(selhist.shape))
outfolder = 'testresults'
if not os.path.exists(outfolder):
os.makedirs(outfolder)
gen.fourier_noise_on_mean(hist,
outfilename=os.path.join(outfolder, 'fnom'),
figname=os.path.join(outfolder, 'fnom'),
nresamples=10,
nonnegative=True)
def read_tables_iter(self, pathes, delim):
logging.info("process %s" % ", ".join(pathes))
for path in pathes:
part = read_csv(path, delim)
yield part
