def main(args):
# Need to take each arg and turn into data frame and add to new list
flagDataFrameList = []
logger.info("Importing data")
# Check for commas, commas are used in galaxy. If there are commas separate
# the list by commas
if ',' in args.flagFiles[0]:
args.flagFiles = args.flagFiles[0].split(',')
# If args.filename is provided then use it to add its name to column names
# This paramether will should be used only on galaxy
if args.filename:
# Cleaning weird characters on file names and replacing them with '_'.
filenames = [cleanStr(x=fname) for fname in args.filename]
# Convert files into dataframes and populate into new list
for flagFile,filename in zip(args.flagFiles,filenames):
# Read table
dataFrame = pd.read_table(flagFile)
# Flag uniqID
if args.flagUniqID:
try:
dataFrame.set_index(args.flagUniqID, inplace=True)
except:
logger.error("Index {0} does not exist on file.".format(args.flagUniqID))
dataFrame.columns=[name+"_"+filename for name in dataFrame.columns]
# List of frame
flagDataFrameList.append(dataFrame)
#logger.info("Checking all indexes are the same")
# Merge flags using Flags class
mergedFlags = Flags.merge(flagDataFrameList)
# Export merged flags
# NOTE: Pandas cannot store NANs as an int. If there are NANs from the
# merge, then the column becomes a float. Here I change the float output to
# look like an int.
mergedFlags.to_csv(args.mergedFile, float_format='%.0f', sep='\t')
logger.info("Script Complete!")
def main(args):
# Import data
dat = wideToDesign(args.input,
args.design,
args.uniqID,
args.group,
logger=logger)
# Get a list of samples to process, if processOnly is specified only
# analyze specified group.
if args.processOnly:
dat.design = dat.design[dat.design[args.group].isin(args.processOnly)]
toProcess = dat.design.index
dat.sampleIDs = toProcess.tolist()
# Create dataframe with sampleIDs that are to be analyzed.
dat.keep_sample(dat.sampleIDs)
# Get list of pairwise combinations. If group is specified, only do
# within group combinations.
combos = list()
if args.group:
# If group is given, only do within group pairwise combinations
logger.info('Only doing within group, pairwise comparisons.')
for groupName, dfGroup in dat.design.groupby(dat.group):
combos.extend(list(combinations(dfGroup.index, 2)))
else:
logger.info('Doing all pairwise comparisons. This could take a while!')
# Get all pairwise combinations for all samples
combos.extend(list(combinations(dat.sampleIDs, 2)))
# Open a multiple page PDF for plots
ppBA = PdfPages(args.baName)
# Loop over combinations and generate plots and return a list of flags.
logger.info('Generating flags and plots.')
flags = map(lambda combo: iterateCombo(dat, combo, ppBA), combos)
# Close PDF with plots
ppBA.close()
# Merge flags
logger.info('Merging outlier flags.')
merged = Flags.merge(flags)
# Summarize flags
logger.info('Summarizing outlier flags.')
propSample, propFeature, propSample_p, propFeature_p, propSample_c, propFeature_c, propSample_d, propFeature_d = summarizeFlags(
dat, merged, combos)
plotFlagDist(propSample, propFeature, args.distName)
# Create sample level flags
flag_sample = Flags(index=dat.sampleIDs)
flag_sample.addColumn(column='flag_sample_BA_outlier',
mask=(propSample >= args.sampleCutoff))
flag_sample.addColumn(column='flag_sample_BA_pearson',
mask=(propSample_p >= args.sampleCutoff))
flag_sample.addColumn(column='flag_sample_BA_cooks',
mask=(propSample_c >= args.sampleCutoff))
flag_sample.addColumn(column='flag_sample_BA_dffits',
mask=(propSample_d >= args.sampleCutoff))
flag_sample.df_flags.index.name = "sampleID"
flag_sample.df_flags.to_csv(args.flagSample, sep='\t')
# Create metabolite level flags
flag_metabolite = Flags(dat.wide.index)
flag_metabolite.addColumn(column='flag_feature_BA_outlier',
mask=(propFeature >= args.featureCutoff))
flag_metabolite.addColumn(column='flag_feature_BA_pearson',
mask=(propFeature_p >= args.featureCutoff))
flag_metabolite.addColumn(column='flag_feature_BA_cooks',
mask=(propFeature_c >= args.featureCutoff))
flag_metabolite.addColumn(column='flag_feature_BA_dffits',
mask=(propFeature_d >= args.featureCutoff))
flag_metabolite.df_flags.to_csv(args.flagFeature, sep='\t')
# Finish Script
logger.info("Script Complete!")