def __init__(self, output):
assert output in SUPPORTED_FORMATS, f"supported formats are {SUPPORTED_FORMATS}"
self.read_encoding = "utf-8"
self.write_encoding = "utf-8"
self.format = output
if self.format == "pdf":
pdf = PDFExporter()
pdf.exclude_output_prompt = True
pdf.exclude_input = True
self.exporter = pdf
elif self.format == "rst":
self.exporter = RSTExporter()
else:
self.exporter = MarkdownExporter()
def __init__(self, output_format, destination_mode):
assert output_format in SUPPORTED_FORMATS, f"supported formats are {SUPPORTED_FORMATS}"
assert (
destination_mode in SUPPORTED_DESTINATIONS_MODES
), f"supported destination modes are {SUPPORTED_DESTINATIONS_MODES}"
self.read_encoding = "utf-8"
self.write_encoding = "utf-8"
self.format = output_format
self.destination_mode = destination_mode
if self.format == "pdf":
pdf = PDFExporter()
pdf.exclude_output_prompt = True
pdf.exclude_input = True
self.exporter = pdf
elif self.format == "rst":
self.exporter = RSTExporter()
else:
self.exporter = MarkdownExporter()
def generate_report_notebook(config, job_type, data_dir, processed_data_dir,
genome_dirpath, filenames, report_filename):
file_loader = FileSystemLoader(os.path.join(ROOT_DIR, 'IDSort/src'))
env = Environment(loader=file_loader)
report_template = env.get_template('genome_report_template.ipynb')
if job_type == 'sort':
# convert given genomes to h5 files, and convert given inp files to
# genomes and then to h5 files
inp_to_genome_config = {
'analysis': False,
'readable': False,
'create_genome': True,
'id_filename': config['process_genome']['id_filename'],
'magnets_filename': config['process_genome']['magnets_filename'],
'id_template': config['process_genome']['id_template']
}
genome_to_h5_config = {
'analysis': True,
'readable': True,
'create_genome': False,
'id_filename': config['process_genome']['id_filename'],
'magnets_filename': config['process_genome']['magnets_filename'],
'id_template': config['process_genome']['id_template']
}
genome_h5_filepaths = []
for filename in filenames:
if filename.endswith('.genome'):
filepath = os.path.join(genome_dirpath, filename)
run_process_genome(genome_to_h5_config, filepath,
processed_data_dir)
genome_h5_filepaths.append(
os.path.join(processed_data_dir, filename + '.h5'))
elif filename.endswith('.inp'):
filepath = os.path.join(processed_data_dir, filename)
run_process_genome(inp_to_genome_config, filepath,
genome_dirpath)
new_genome_filename = filename + '.genome'
new_genome_filepath = os.path.join(genome_dirpath,
new_genome_filename)
run_process_genome(genome_to_h5_config, new_genome_filepath,
processed_data_dir)
genome_h5_filepaths.append(
os.path.join(processed_data_dir,
new_genome_filename + '.h5'))
elif job_type == 'shim':
genome_h5_filepaths = [
os.path.join(genome_dirpath, filename) for filename in filenames
]
report_output = report_template.render(
job_type=job_type, genome_h5_filepaths=genome_h5_filepaths)
notebook_name = 'genome_report.ipynb'
notebook_path = os.path.join(data_dir, notebook_name)
with open(notebook_path, 'w') as notebook:
notebook.write(report_output)
# create dir for genome reports
genome_report_dir = 'genome_reports/'
genome_report_dirpath = os.path.join(data_dir, genome_report_dir)
if not os.path.exists(genome_report_dirpath):
os.makedirs(genome_report_dirpath)
# execute notebook
with open(notebook_path, 'r') as notebook:
nb = nbformat.read(notebook, as_version=4)
ep = ExecutePreprocessor()
ep.preprocess(nb, {'metadata': {'path': data_dir}})
pdf_exporter = PDFExporter()
pdf_exporter.exclude_output_prompt = True
pdf_exporter.exclude_input = True
pdf_data, resources = pdf_exporter.from_notebook_node(nb)
# check the name of the report to see if a specific name has been given or
# not
if report_filename == 'genome_report.pdf':
# concatenate all genome/inp files using "_" as a separator to form the
# filename
report_filename = '_'.join(filenames) + '.pdf'
report_filepath = os.path.join(genome_report_dirpath, report_filename)
with open(report_filepath, 'wb') as report:
report.write(pdf_data)