update code documentation

pyrpipe/__diagnostic__.py

@@ -16,6 +16,14 @@
 
 
 def report():
+    """
+    Entry point for report subcommand
+
+    Returns
+    -------
+    None.
+
+    """
 
     parser = argparse.ArgumentParser(
 
@@ -66,7 +74,14 @@ def report():
 
 
 def shell():
-    print("Generating bash script")
+    """
+    Entry point for shell command
+
+    Returns
+    -------
+    None.
+
+    """
     parser = argparse.ArgumentParser(
 
             description='pyrpipe diagnostic utility\nGenerate shell script.',
@@ -101,7 +116,14 @@ def shell():
 
 
 def benchmark():
-    print("Generating benchmarks")
+    """
+    Entry point for benchmark subcommand
+
+    Returns
+    -------
+    None.
+
+    """
     parser = argparse.ArgumentParser(
 
             description='pyrpipe diagnostic utility\nGenerate benchmark report.',
@@ -147,7 +169,15 @@ def benchmark():
 
 
 def multiqc():
-    print("Generating html report with multiqc")
+    """
+    Entry point for multiqc subcommand
+
+    Returns
+    -------
+    None.
+
+    """
+
     parser = argparse.ArgumentParser(
 
             description='pyrpipe diagnostic utility\nGenerate report with multiqc.',

pyrpipe/__init__.py

@@ -150,6 +150,9 @@ def init_envlog(self):
 
 #read pyrpipe.conf in current dir
 class Conf:
+    """
+    Read and store pyrpipe configuration
+    """
     def __init__( self):
         #init default values to use
         self._dry = False
@@ -251,8 +254,8 @@ def init_sys_args(self):
 
 There are multiple ways to execute a python script containing pyrpipe code
 
-if infile is present implies invoked via pyrpipe command and control will go to the __main__ module
-If infile is absent, it was invoked using python script.py command. In this case all pyrpipe options are read
+if infile is present implies invoked via pyrpipe command, e.g. pyrpipe --in script.py, and control will go to the __main__ module
+If infile is absent, it was invoked using python script.py command, e.g python script.py. In this case all pyrpipe options are read
 and removed from the argv parameters so that passed argv  are available to the script.py
 """
 #if pyrpipe_diagnostic is invoked
@@ -316,6 +319,7 @@ def init_sys_args(self):
             if pu.check_files_exist(s):
                 _optsmd5[s]=pu.get_mdf(s)
 
+        #this will be executed at then end of script
         @atexit.register 
         def goodbye():
             logfile=os.path.join(_logs_dir,_log_name+'.log')

pyrpipe/assembly.py

@@ -41,6 +41,9 @@ class Stringtie(Assembly):
         
         threads: int
             number of threads
+        guide: str
+            Reference annotation gtf/gff to use as guide
+            
         """
     def __init__(self,*args,threads=None,guide=None,**kwargs):
         super().__init__(*args,**kwargs)
@@ -63,24 +66,12 @@ def perform_assembly(self,bam_file,out_dir=None,out_suffix="_stringtie",objectid
         
         bam_file: string
             path to the bam file
+        out_dir: string
+            Path to out file
         out_suffix: string
             Suffix for the output gtf file
-        reference_gtf: str
-            Path to the reference gtf used as guide
-        threads: int
-            Number of threads to use
-        overwrite: bool
-            Overwrite if output file already exists.
-        verbose: bool
-            Print stdout and std error
-        quiet: bool
-            Print nothing
-        logs: bool
-            Log this command to pyrpipe logs
         objectid: str
             Provide an id to attach with this command e.g. the SRR accession. This is useful for debugging, benchmarking and reports.
-        kwargs: dict
-            Options to pass to stringtie. 
         :return: Returns the path to output GTF file
         :rtype: string
         """
@@ -143,22 +134,8 @@ def perform_assembly(self,bam_file,out_dir=None,out_suffix="_cufflinks",objectid
             output directory
         out_suffix: string
             Suffix for the output gtf file
-        reference_gtf: str
-            Path to reference gtf 
-        threads: int
-            Number of threads to use
-        overwrite: bool
-            Overwrite if output file already exists.
-        verbose: bool
-            Print stdout and std error
-        quiet: bool
-            Print nothing
-        logs: bool
-            Log this command to pyrpipe logs
         objectid: str
             Provide an id to attach with this command e.g. the SRR accession.
-        kwargs: dict
-            Options to pass to cufflinks. 
             
         :return: Returns the path to output GTF file
         :rtype: string       

pyrpipe/mapping.py

@@ -71,7 +71,7 @@ def __init__(self,*args,index=None,genome=None,threads=None,**kwargs):
         Raises
         ------
         ValueError
-            Raises ValueError if hista index is not found and genome is not present to generate an index.
+            Raises ValueError if hisat index is not found and genome is not present to generate an index.
 
         Returns
         -------

pyrpipe/param_loader.py

@@ -16,12 +16,14 @@ def add_bool(self, node):
 SafeConstructor.add_constructor(u'tag:yaml.org,2002:bool', add_bool)
 
 class YAML_loader():
+    """
+    Load parameters from a yaml file
+    """
 
 
     def __init__(self,file):
         self.__params=None
         self.__kwargs=None
-        self.__args=None
 
         if not pu.check_files_exist(file):
             return
@@ -42,7 +44,7 @@ def get_kwargs(self):
 
     def parse_params(self):
         """
-        separate params into args and kwargs
+        store params as dict
         """
         #if file is empty
         if not self.__params:
@@ -62,10 +64,9 @@ def parse_params(self):
                 params[k]=str(v)
 
         for k in to_del:
-            del params[k]
-
+            del params[k]        
 
         self.__kwargs=params
-        #self.__args=tuple(args)
+
 
 

pyrpipe/pyrpipe_engine.py

@@ -42,7 +42,7 @@
 #a decorator to skip functions in safe mode
 def skippable(func):
     """
-    Skip a function execution
+    Skip a function execution in safemode
     """
     if not _safe:
         return func
@@ -83,7 +83,7 @@ def dried(cmd,*args,**kwargs):
 def parse_cmd(cmd):
     """This function converts a list to str.
     If a command is passed as list it is converted to str.
-    For pyrpipe v0.0.5 onwards the get_shell_output function uses shell=True
+    pyrpipe v0.0.5 onwards the get_shell_output function uses shell=True
     """
     if isinstance(cmd,list):
         return " ".join(cmd)
@@ -94,12 +94,15 @@ def parse_cmd(cmd):
 def get_shell_output(cmd,verbose=None):
     """Function to run a shell command and return returncode, stdout and stderr
     Currently (pyrpipe v 0.0.4) this function is called in 
-    getReturnStatus(), getProgramVersion(), find_files()
+    get_return_status(), get_program_version()
+    
+    pyrpipe v0.0.5 onwards the get_shell_output function uses shell=True
+    
     
     Parameters
     ----------
     
-    cdm: list
+    cdm: list or string
         command to run
     verbose: bool
         to print messages

pyrpipe/pyrpipe_session.py

@@ -8,9 +8,6 @@
 import dill
 import datetime as dt
 import os
-#importing pyrpipe_engine here causes issues and stalling of log
-#from pyrpipe import pyrpipe_engine as pre
-#import pyrpipe
 
 def getTimestamp(shorten=False):
     """Return timestamp YYYYMMDDHHMISE
@@ -40,17 +37,7 @@ def save_session(filename,add_timestamp=True,out_dir=""):
         outFile=outFile+"_"+timestamp+".pyrpipe"
     else:
         outFile=outFile+".pyrpipe"
-
-    """
-    Do not pickle logger. This causes problems when restoring session with python < 3.7
-    Delete all logger instances. 
-    del pre.pyrpipeLoggerObject
-    del pyrpipe.pyrpipe_engine.pyrpipeLoggerObject
-    """    
-    """
-    creating a logger class fixed this issue
-    """ 
-
+
 
     #save workspace
     try:

pyrpipe/pyrpipe_utils.py

@@ -516,6 +516,10 @@ def find_files(search_path,search_pattern,recursive=False,verbose=False):
     -------
     result : TYPE
         DESCRIPTION.
+    
+    Example
+    --------
+    find_files('path/to/directory','.*\.txt$',recursive=False,verbose=False)
 
     """
 
@@ -544,6 +548,20 @@ def find_files(search_path,search_pattern,recursive=False,verbose=False):
 
 
 def get_mdf(filename):
+    """
+    Compute and return md5checksum 
+
+    Parameters
+    ----------
+    filename : str
+        Path to input file
+
+    Returns
+    -------
+    md5 : str
+        MD5 checksum value
+
+    """
     if not check_files_exist(filename):
         #print_boldred('Error calculating MD5. File {} not found'.format(filename))
         return None

pyrpipe/qc.py

@@ -34,7 +34,10 @@ class Trimgalore(RNASeqQC):
     
     Parameters
     ----------
-        
+        args: tuple
+            arguments passed to trim_galore
+        threads: int
+            Num threads to use
         kwargs:
             trim_galore arguments.
     """
@@ -62,21 +65,11 @@ def perform_qc(self,sra_object,out_dir="",out_suffix="_trimgalore",objectid="NA"
             Path to output directory
         out_suffix: string
             Suffix for the output sam file
-        threads: int
-            Num threads to use
-        verbose: bool
-            Print stdout and std error
-        quiet: bool
-            Print nothing
-        logs: bool
-            Log this command to pyrpipe logs
         objectid: str
             Provide an id to attach with this command e.g. the SRR accession. This is useful for debugging, benchmarking and reports.
-        kwargs: dict
-            Options to pass to trimgalore. This will override the existing options 
-
-            :return: Returns the path of fastq files after QC. tuple has one item for single end files and two for paired.
-            :rtype: tuple
+            
+        :return: Returns the path of fastq files after QC. tuple has one item for single end files and two for paired.
+        :rtype: tuple
         """
         if not out_dir:
             out_dir=sra_object.directory
@@ -203,6 +196,15 @@ def __init__(self,*args,threads=None,memory=None,**kwargs):
     def perform_qc(self,sra_object,out_dir="",out_suffix="_bbduk",objectid="NA"):
         """Run bbduk on fastq files specified by the sra_object
        
+        sra_object: SRA
+            An SRA object whose fastq files will be used
+        out_dir: str
+            Path to output directory
+        out_suffix: string
+            Suffix for the output sam file
+        objectid: str
+            Provide an id to attach with this command e.g. the SRR accession. This is useful for debugging, benchmarking and reports.
+        
         :return: Returns the path of fastq files after QC. tuple has one item for single end files and 2 for paired.
         :rtype: tuple
             
@@ -267,17 +269,8 @@ def perform_cleaning(self,sra_object,bbsplit_index,out_dir="",out_suffix="_bbspl
             Path to output dir. Default: sra_object.directory
         out_suffix: string
             Suffix for output file name
-        overwrite: bool
-            overwrite existing files
-        verbose: bool
-            Print stdout and std error
-        quiet: bool
-            Print nothing
-        logs: bool
-            Log this command to pyrpipe logs
         objectid: str
-            Provide an id to attach with this command e.g. the SRR accession. This is useful for debugging, benchmarking and reports.
-        
+            Provide an id to attach with this command e.g. the SRR accession. This is useful for debugging, benchmarking and reports.        
         kwargs: dict
             options passed to bbsplit
 
@@ -361,7 +354,7 @@ def perform_cleaning(self,sra_object,bbsplit_index,out_dir="",out_suffix="_bbspl
             return("",)
 
 
-
+    #used by perform_cleaning
     def run_bbsplit(self,objectid="NA",**kwargs):
         """wrapper to run bbsplit