def plots(l_populations):
for suffix in [
## samples (concatenate)
'imiss','het','sexcheck','genome',
## SNPs (paste/join)
## 'frq','hwe','SNPQC.lmiss',
'fam','sampleQC.samples',
## 'mds',
]:
bool_continue = False
for population in l_populations:
if not os.path.isfile('%s.%s' %(population,suffix,)):
bool_continue = True
break
continue
if bool_continue == True:
print 'skip', suffix
continue
else:
print 'concatenate', suffix
fd = open('agv.%s' %(suffix),'w')
fd.close()
if not suffix in ['fam','sampleQC.samples',]:
cmd = 'head -1 %s.%s > agv.%s' %(l_populations[0],suffix,suffix,)
os.system(cmd)
for population in l_populations:
## no header
if suffix in ['fam','sampleQC.samples',]:
cmd = "cat %s.%s >> agv.%s" %(population,suffix,suffix,)
## header
else:
cmd = "sed '1d' %s.%s >> agv.%s" %(population,suffix,suffix,)
os.system(cmd)
continue
continue
instanceQC = QC.main()
## instanceQC.plink_plots('agv',i_wait=0)
## samples
instanceQC.histogram_imiss('agv',)
instanceQC.histogram_het('agv',bool_with_stddev=False,)
instanceQC.histogram_genome('agv',)
instanceQC.scatter_het_call('agv',bool_with_stddev=False,)
if os.path.isfile('agv.mds'):
instanceQC.scatter_mds('agv')
## ## SNPs
## instanceQC.scatter_lmiss_frq('agv')
## instanceQC.histogram_lmiss('agv')
## instanceQC.histogram_frq('agv')
## instanceQC.histogram_hwe('agv')
return
def process_df(df, df_info):
df_info = df_info.set_index('info')
try:
lat, lon = float(
df_info.loc['Download Location (lat/long)', 'lat']), float(
df_info.loc['Download Location (lat/long)', 'lon'])
except:
print('Location is not given')
lat, lon = 0, 0
df['datetime'] = pd.to_datetime(df.Date + ' ' + df.Time,
format='%d/%m/%Y %H:%M:%S')
df.rename(columns={
'Temperature C': 'temperature',
'Depth Decibar': 'pressure',
'Depth M': 'pressure'
},
inplace=True)
df['temperature'] = pd.to_numeric(df['temperature'])
df['pressure'] = pd.to_numeric(df['pressure'])
df['temperature'] = df.apply(lambda x: round(x['temperature'], 4), axis=1)
df['pressure'] = df.apply(lambda x: round(x['pressure'], 3), axis=1)
df = df[['datetime', 'temperature', 'pressure']]
df.loc[:, 'latitude'] = lat
df.loc[:, 'longitude'] = lon
df.rename(columns={
'datetime': 'DATETIME',
'temperature': 'TEMPERATURE',
'pressure': 'PRESSURE',
'latitude': 'LATITUDE',
'longitude': 'LONGITUDE'
},
inplace=True)
df = QC.QC(df).df
df.rename(columns={
'DATETIME': 'datetime',
'TEMPERATURE': 'temperature',
'PRESSURE': 'pressure',
'LATITUDE': 'latitude',
'LONGITUDE': 'longitude'
},
inplace=True)
return df
#!/usr/bin/PYTHON import integrated_denovo_pipeline as pipeline import QC as qc import os import re # run the FASTX toolkit quality filters on Read 2 only (lots of data; will be slow) # get the degeneracy stats for the quality filtered Read 2 files pipeline.iterative_FASTQ_quality_filter(directory = '~/CWD_RADseq/', out_dir = '/qual_filtered_R2_for_DBR_distr/', out_name = 'qual_filtered_30.fastq.gz', q = 30, p = 50, read = 'R2') qc.degeneracy_r2(directory = '~/CWD_RADseq/', out_name = 'qual_filtered_30_degeneracy_check')
try:
import ttk
py3 = False
except ImportError:
import tkinter.ttk as ttk
py3 = True
def set_Tk_var():
global che53
che53 = StringVar()
def init(top, gui, *args, **kwargs):
global w, top_level, root
w = gui
top_level = top
root = top
def destroy_window():
# Function which closes the window.
global top_level
top_level.destroy()
top_level = None
if __name__ == '__main__':
import QC
QC.vp_start_gui()
def main(input_file_or_folder,
output_folder,
sampling_rate,
*,
swan=True,
muss=True,
qc=True,
parallel=False,
debug=False,
profiling=True):
"""Run SWaN, MUSS and QC on an actigraph csv file
Examples:
Run all models
>> pipenv run python main.py ABCRAW.csv ./outputs/ 80
Run only QC script
>> pipenv run python main.py ABCRAW.csv ./outputs/ 80 --swan=False --muss=False
Don't run QC script
>> pipenv run python main.py ABCRAW.csv ./outputs/ 80 --qc=False
:param input_file_or_folder: path of the input Actigraph raw csv file if a file, or an mhealth folder if a folder
:param output_folder: relative or absolute path of an output folder. All algorithm outputs will be placed in a subfolder (with the same name as the input actigraph files (no extension)) of this output folder. So if you have multiple input actigraph files, you can always set this output folder to be the same as the master folder storing outputs for all of the input files.
:param sampling_rate: sampling rate in Hz.
:param swan: Run SWaN model
:param muss: Run MUSS model
:param qc: Run Quality check script
:param parallel: if option is presented, muss will use multicore processing
:param debug: if option is presented, all intermediate files and converted mhealth data files will be preserved otherwise, they will be deleted in the end. If error occurs during running algorithms, intermediate files and converted mhealth data files will always be preserved regardless of this option. Converted mhealth data files will be stored in `.temp` folder in the script root folder, algorithm intermediate files will be stored in the output folder corresponding to each input actigraph csv.
:param profiling: Use profiling if available.
"""
if os.path.isfile(input_file_or_folder):
auto_id = os.path.basename(input_file_or_folder).split('.')[0]
intermediate_folder = './.temp/'
mhealth_folder = os.path.join(intermediate_folder, auto_id)
mhealth.convert_to_mhealth(input_file_or_folder, mhealth_folder)
output_path = create_output_folder(output_folder, auto_id)
else:
intermediate_folder = None
mhealth_folder = input_file_or_folder
output_path = output_folder
sampling_rate = float(sampling_rate)
if muss:
print('Running MUSS model...')
muss_intermediate_folder = os.path.join(output_path,
'muss_intermediate')
os.makedirs(muss_intermediate_folder, exist_ok=True)
muss_feature, muss_prediction = muss_model.main(
mhealth_folder,
sampling_rate=sampling_rate,
parallel=parallel,
profiling=profiling)
muss_feature.to_csv(
os.path.join(muss_intermediate_folder, 'muss_feature.csv'))
muss_prediction.to_csv(os.path.join(output_path, 'muss_output.csv'),
index=False,
header=True)
if swan:
print('Running SWaN model...')
SWaN.main(mhealth_folder, output_path, sampling_rate=sampling_rate)
if qc:
print('Running Quality check...')
qc_result = QC.main(mhealth_folder, output_path)
qc_result.to_csv(os.path.join(output_path, 'qc_output.csv'),
index=False,
header=True)
if not debug:
if intermediate_folder != None:
remove_intermediate(intermediate_folder)
remove_intermediate(os.path.join(output_path, 'intermediate'),
os.path.join(output_path, 'qc_intermediate'),
os.path.join(output_path, 'muss_intermediate'))
