def test_profile_ct_bincounts(self):
""" Test the ability of sortseq_tools.profile_ct to count frequencies
"""
print '\nIn test_profile_ct_bincounts...'
library_files = glob.glob(self.input_dir+'library_*.txt')
library_files += glob.glob(self.input_dir+'dataset_*.txt')
good_bin_num = 2
bad_bin_num = 5
for file_name in library_files:
print '\t%s ='%file_name,
description = file_name.split('_')[-1].split('.')[0]
executable = lambda:\
profile_ct.main(io.load_dataset(file_name),bin=good_bin_num)
print '(bin=%d)'%good_bin_num,
# If bad or library, then profile_ct.main should raise SortSeqError
if ('_bad' in file_name) or ('library' in file_name):
try:
self.assertRaises(SortSeqError,executable)
print 'badtype,',
except:
print 'good (ERROR).'
raise
# If good, then profile_ct.main should produce a valid df
elif ('_good' in file_name) or ('dataset' in file_name):
try:
df = executable()
qc.validate_profile_ct(df)
out_file = self.output_dir+\
'profile_ct_bin_%s.txt'%description
io.write(df,out_file)
io.load_profile_ct(out_file)
print 'good,',
except:
print 'bad (ERROR).'
raise
# There are no other options
else:
raise SortSeqError('Unrecognized class of file_name.')
# Should always raise an error if bin num is too large
executable = lambda:\
profile_ct.main(io.load_dataset(file_name),bin=bad_bin_num)
print '(bin=%d)'%bad_bin_num,
try:
self.assertRaises(SortSeqError,executable)
print 'badtype.'
except:
print 'good (ERROR).'
raise
def test_profile_ct_totalcounts(self):
""" Test the ability of sortseq_tools.profile_ct to count frequencies based on total count values
"""
print '\nIn test_profile_ct_totalcounts...'
library_files = glob.glob(self.input_dir+'library_*.txt')
library_files += glob.glob(self.input_dir+'dataset_*.txt')
for file_name in library_files:
print '\t%s ='%file_name,
description = file_name.split('_')[-1].split('.')[0]
executable = lambda: profile_ct.main(io.load_dataset(file_name))
# If good, then profile_ct.main should produce a valid df
if '_good' in file_name:
try:
df = executable()
qc.validate_profile_ct(df)
out_file = self.output_dir+\
'profile_ct_total_%s.txt'%description
io.write(df,out_file)
io.load_profile_ct(out_file)
print 'good.'
except:
print 'bad (ERROR).'
raise
# If bad, then profile_ct.main should raise SortSeqError
elif '_bad' in file_name:
try:
self.assertRaises(SortSeqError,executable)
print 'badtype.'
except:
print 'good (ERROR).'
raise
# There are no other options
else:
raise SortSeqError('Unrecognized class of file_name.')
def main(dataset_df, bin=None, start=0, end=None):
"""
Computes character counts at each position
Arguments:
dataset_df (pd.DataFrame): A dataframe containing a valid dataset.
bin (int): A bin number specifying which counts to use
start (int): An integer specifying the sequence start position
end (int): An integer specifying the sequence end position
Returns:
counts_df (pd.DataFrame): A dataframe containing counts for each nucleotide/amino acid character at each position.
"""
# Validate dataset_df
qc.validate_dataset(dataset_df)
# Retrieve type of sequence
seq_cols = [c for c in dataset_df.columns if qc.is_col_type(c,'seqs')]
if not len(seq_cols)==1:
raise SortSeqError('Dataset dataframe must have only one seq colum.')
colname = seq_cols[0]
seqtype = qc.colname_to_seqtype_dict[colname]
alphabet = qc.seqtype_to_alphabet_dict[seqtype]
num_chars = len(alphabet)
# Retrieve sequence length
if not dataset_df.shape[0] > 1:
raise SortSeqError('Dataset dataframe must have at least one row.')
total_seq_length = len(dataset_df[colname].iloc[0])
# Validate start and end
if start<0:
raise SortSeqError('start=%d is negative.'%start)
elif start>=total_seq_length:
raise SortSeqError('start=%d >= total_seq_length=%d'%\
(start,total_seq_length))
if end is None:
end=total_seq_length
elif end<=start:
raise SortSeqError('end=%d <= start=%d.'%(end,start))
elif end>total_seq_length:
raise SortSeqError('end=%d > total_seq_length=%d'%\
(start,total_seq_length))
# Set positions
poss = pd.Series(range(start,end),name='pos')
num_poss = len(poss)
# Retrieve counts
if bin is None:
ct_col = 'ct'
else:
ct_col = 'ct_%d'%bin
if not ct_col in dataset_df.columns:
raise SortSeqError('Column "%s" is not in columns=%s'%\
(ct_col,str(dataset_df.columns)))
counts = dataset_df[ct_col]
# Compute counts profile
counts_array = np.zeros([num_poss,num_chars])
counts_cols = ['ct_'+a for a in alphabet]
for i,pos in enumerate(range(start,end)):
char_list = dataset_df[colname].str.slice(pos,pos+1)
counts_array[i,:] = [np.sum(counts[char_list==a]) for a in alphabet]
temp_df = pd.DataFrame(counts_array,columns=counts_cols)
counts_df = pd.concat([poss,temp_df],axis=1)
# Validate as counts dataframe
counts_df = qc.validate_profile_ct(counts_df,fix=True)
return counts_df