From 249284b7db13456f9f8ceb906c59c6080d9720d7 Mon Sep 17 00:00:00 2001
From: Venkat Malladi <venkat.malladi@utsouthwestern.edu>
Date: Thu, 26 Oct 2017 14:31:56 -0500
Subject: [PATCH] Refactor code to have consistent use of arguments and
referenceing pandas.
---
workflow/scripts/check_design.py | 21 ++++++++++++---------
workflow/scripts/experiment_design.py | 11 ++++++-----
workflow/scripts/experiment_qc.py | 13 +++++++------
workflow/scripts/trim_reads.py | 6 ++++--
4 files changed, 29 insertions(+), 22 deletions(-)
diff --git a/workflow/scripts/check_design.py b/workflow/scripts/check_design.py
index 6bd822f..a900c3b 100644
--- a/workflow/scripts/check_design.py
+++ b/workflow/scripts/check_design.py
@@ -21,7 +21,7 @@ logger.setLevel(logging.INFO)
def get_args():
'''Define arguments.'''
-
+
parser = argparse.ArgumentParser(
description=__doc__, epilog=EPILOG,
formatter_class=argparse.RawDescriptionHelpFormatter)
@@ -137,23 +137,26 @@ def check_files(design, fastq, paired):
def main():
args = get_args()
+ design = args.design
+ fastq = args.fastq
+ paired = args.paired
# Create a file handler
handler = logging.FileHandler('design.log')
logger.addHandler(handler)
- # Read files
- design_file = pd.read_csv(args.design, sep='\t')
- fastq_file = pd.read_csv(args.fastq, sep='\t', names=['name', 'path'])
+ # Read files as dataframes
+ design_df = pd.read_csv(args.design, sep='\t')
+ fastq_df = pd.read_csv(args.fastq, sep='\t', names=['name', 'path'])
# Check design file
- check_design_headers(design_file, args.paired)
- check_controls(design_file)
- check_replicates(design_file)
- new_design = check_files(design_file, fastq_file, args.paired)
+ check_design_headers(design_df, paired)
+ check_controls(design_df)
+ check_replicates(design_df)
+ new_design_df = check_files(design_file, fastq_df, paired)
# Write out new design file
- new_design.to_csv('design.tsv', header=True, sep='\t', index=False)
+ new_design_df.to_csv('design.tsv', header=True, sep='\t', index=False)
if __name__ == '__main__':
diff --git a/workflow/scripts/experiment_design.py b/workflow/scripts/experiment_design.py
index 3d6697a..f527b46 100644
--- a/workflow/scripts/experiment_design.py
+++ b/workflow/scripts/experiment_design.py
@@ -21,7 +21,7 @@ logger.setLevel(logging.INFO)
def get_args():
'''Define arguments.'''
-
+
parser = argparse.ArgumentParser(
description=__doc__, epilog=EPILOG,
formatter_class=argparse.RawDescriptionHelpFormatter)
@@ -64,19 +64,20 @@ def make_experiment_design(design):
def main():
args = get_args()
+ design = args.design
# Create a file handler
handler = logging.FileHandler('experiment_generation.log')
logger.addHandler(handler)
- # Read files
- design_file = pd.read_csv(args.design, sep='\t')
+ # Read files as dataframes
+ design_df = pd.read_csv(design, sep='\t')
# Update design file for check_controls
- new_design = update_controls(design_file)
+ new_design_df = update_controls(design_df)
# write out experiment design files
- make_experiment_design(new_design)
+ make_experiment_design(new_design_df)
if __name__ == '__main__':
diff --git a/workflow/scripts/experiment_qc.py b/workflow/scripts/experiment_qc.py
index 711da18..6f63b52 100644
--- a/workflow/scripts/experiment_qc.py
+++ b/workflow/scripts/experiment_qc.py
@@ -25,7 +25,7 @@ logger.setLevel(logging.INFO)
def get_args():
'''Define arguments.'''
-
+
parser = argparse.ArgumentParser(
description=__doc__, epilog=EPILOG,
formatter_class=argparse.RawDescriptionHelpFormatter)
@@ -146,6 +146,7 @@ def check_enrichment(sample_id, control_id, sample_reads, control_reads):
def main():
args = get_args()
+ design = args.design
# Create a file handler
handler = logging.FileHandler('experiment_qc.log')
@@ -155,18 +156,18 @@ def main():
check_tools()
# Read files
- design_file = pd.read_csv(args.design, sep='\t')
+ design_df = pd.read_csv(design, sep='\t')
# Run correlation
- mbs_filename = generate_read_summary(design_file)
+ mbs_filename = generate_read_summary(design_df)
check_correlation(mbs_filename)
# Run coverage
- check_coverage(design_file)
+ check_coverage(design_df)
# Run enrichment
- new_design = update_controls(design_file)
- for index, row in new_design.iterrows():
+ new_design_df = update_controls(design_df)
+ for index, row in new_design_df.iterrows():
check_enrichment(
row['sample_id'],
row['control_id'],
diff --git a/workflow/scripts/trim_reads.py b/workflow/scripts/trim_reads.py
index 2f7f3e5..036c5f7 100644
--- a/workflow/scripts/trim_reads.py
+++ b/workflow/scripts/trim_reads.py
@@ -22,7 +22,7 @@ logger.setLevel(logging.INFO)
def get_args():
'''Define arguments.'''
-
+
parser = argparse.ArgumentParser(
description=__doc__, epilog=EPILOG,
formatter_class=argparse.RawDescriptionHelpFormatter)
@@ -81,6 +81,8 @@ def trim_reads(fastq, paired):
def main():
args = get_args()
+ fastq = args.fastq
+ paired = args.paired
# Create a file handler
handler = logging.FileHandler('trim.log')
@@ -90,7 +92,7 @@ def main():
check_tools()
# Run trim_reads
- trim_reads(args.fastq, args.paired)
+ trim_reads(fastq, paired)
if __name__ == '__main__':
--
GitLab