examples of my frequently used Python functions and slight variations

my_python_functions.py

# generate output file name
def generate_output_file_name(id_of_seq_element,id_of_seq_scanned):
    '''
    Takes a file name as an argument and returns string for the name of the
    output file. The generated name is based on a prefix that can be adjusted
    under the section ' USER ADJUSTABLE VALUES ', plus the provided text in 
    the function call.
    If there is no `id_of_seq_element` specified, the sequence element will be
    used, limited to the first number of bases specified in `limit_of_name`.

    Specific examples
    =================
    Calling function with
        ("elem1","chrmt")
    returns
        "seq_account_elem1_chrmt.tsv"

    Calling function with
        (None,"chrmt")
    returns
        "seq_account_GAATTC_chrmt.tsv"
    if `GAATTC` happened to be the provided sequence element.
    '''
    if id_of_seq_element:
        elem_id = id_of_seq_element
    elif len(element) > limit_of_name:
        elem_id = element[:limit_of_name]
    else:
        elem_id = element
    return "{prefix}_{elem_id}_{seq}.tsv".format(
        prefix=output_file_name_prefix,elem_id=id_of_seq_element,
        seq=id_of_seq_scanned)
  
  
  def generate_output_file_name(file_name):
    '''
    Takes a file name as an argument and returns string for the name of the
    output file. The generated name is based on the original file
    name.

    Specific example
    =================
    Calling function with
        ("mito_transcripts_dataframeplusSUTs.pkl")
    returns
        "mito_transcripts_dataframeplusSUTs_n_XUTs.pkl"
    '''
    main_part_of_name, file_extension = os.path.splitext(
        file_name) #from http://stackoverflow.com/questions/541390/extracting-extension-from-filename-in-python
    if '.' in file_name:  #I don't know if this is needed with the os.path.splitext method but I had it before so left it
        return main_part_of_name + suffix_for_saving  + file_extension
    else:
        return file_name + suffix_for_saving + ".pkl"
  
  
  def generate_output_file_name(file_name):
    '''
    Takes a file name as an argument and returns string for the name of the
    output file. The generated name is based on the original file
    name.

    Specific examples
    =================
    Calling function with
        ("test.pk1")
    returns
        "test.pkl"

    Calling function with
        ("test")
    returns
        "test.pkl"
    '''
    main_part_of_name, file_extension = os.path.splitext(
        file_name) #from 
    # http://stackoverflow.com/questions/541390/extracting-extension-from-filename-in-python
    if file_extension:
        return file_name
    else:
        return main_part_of_name + ".pkl"
    
    
    


    
    
    
# FASTA READING    
# Read sequence from FASTA file using Biopython
# Read sequence, treating source as a filepath.
# Use of `with` on next line based on http://biopython.org/wiki/SeqIO , 
# under "Sequence Input". Otherwise, backbone based on 
# https://www.biostars.org/p/209383/, and fact `rU` mode depecated.
with open(source, "r") as handle:
    for record in SeqIO.parse(handle, "fasta"):
        # print(record.seq) # for debugging
        fasta_seq = record.seq



# Reading a single sequence from URL using Biopython
from Bio import SeqIO

source = "https://downloads.yeastgenome.org/sequence/S288C_reference/chromosomes/fasta/chrmt.fsa"
def get_seq_from_URL(url):
    '''
    takes a URL and gets the sequence
    '''
    try:
        from StringIO import StringIO
    except ImportError:
        from io import StringIO
    
    chromosomes_and_length = {}
    # Getting html originally for just Python 3, adapted from 
    # https://stackoverflow.com/a/17510727/8508004 and then updated from to 
    # handle Python 2 and 3 according to same link.
    try:
        # For Python 3.0 and later
        from urllib.request import urlopen
    except ImportError:
        # Fall back to Python 2's urllib2
        from urllib2 import urlopen
    html = urlopen(url)
    record = SeqIO.read(StringIO(html.read().decode(encoding='UTF-8')), "fasta") # use of
    # SeqIO.read here based on http://biopython.org/DIST/docs/api/Bio.SeqIO-module.html ,
    # "This style is useful when you expect a single record only (and would consider 
    # multiple records an error). For example, when dealing with GenBank files for 
    # bacterial genomes or chromosomes, there is normally only a single record. 
    # Alternatively, use this with a handle when downloading a single record 
    # from the internet."
    # I found I needed `StringIO()` or got issues with trying to handle long file name.
    return record.seq
    
t = get_seq_from_URL(source)
print (len(t))


# Reading potentially multiple sequences from URL but only taking first one using Biopython
from Bio import SeqIO

source = "https://downloads.yeastgenome.org/sequence/S288C_reference/chromosomes/fasta/chrmt.fsa"
def get_seq_from_URL(url):
    '''
    takes a URL and gets the sequence
    '''
    try:
        from StringIO import StringIO
    except ImportError:
        from io import StringIO
        
    chromosomes_and_length = {}
    # Getting html originally for just Python 3, adapted from 
    # https://stackoverflow.com/a/17510727/8508004 and then updated from to 
    # handle Python 2 and 3 according to same link.
    try:
        # For Python 3.0 and later
        from urllib.request import urlopen
    except ImportError:
        # Fall back to Python 2's urllib2
        from urllib2 import urlopen
    html = urlopen(url)
    fasta_iterator = SeqIO.parse(StringIO(html.read().decode(encoding='UTF-8')), "fasta")
    # Use of `next()` on next line to get first FASTA -formatted sequence is 
    # based on http://biopython.org/DIST/docs/api/Bio.SeqIO-module.html
    # I think difference from `SeqIO.read()` in this approach is that it won't
    # give an error of more than one entry is in the html.
    # I found I needed `StringIO()` or got issues with trying to handle long file name.
    record = next(fasta_iterator)
    return record.seq
    
t = get_seq_from_URL(source)
print (len(t))


# Reading a single sequence from URL not using Biopython
from Bio import SeqIO

source = "https://downloads.yeastgenome.org/sequence/S288C_reference/chromosomes/fasta/chrmt.fsa"
def get_seq_from_URL(url):
    '''
    takes a URL and gets the sequence
    '''
    chromosomes_and_length = {}
    # Getting html originally for just Python 3, adapted from 
    # https://stackoverflow.com/a/17510727/8508004 and then updated from to 
    # handle Python 2 and 3 according to same link.
    try:
        # For Python 3.0 and later
        from urllib.request import urlopen
    except ImportError:
        # Fall back to Python 2's urllib2
        from urllib2 import urlopen
    html = urlopen(url)
    needs_more_parsing = html.read().decode(encoding='UTF-8')
    print(needs_more_parsing)
    
get_seq_from_URL(source)




#make and save tab-separated values / tab-delimited TSV/ .tab output file
def make_and_save_karyotype(chromosomes_and_length, species_code):
    '''
    Takes a dictionary of chromosome identifiers and length and makes a karyotype
    file with that information.

    Result will look like this at start of output file:
    chr - Sc-chrIV chrIV 0 1531933 black
    chr - Sc-chrXV chrXV 0 1091291 black
    ...

    Function returns None.
    '''
    # prepare output file for saving so it will be open and ready
    with open(output_file_name, 'w') as output_file:
        for indx,(chrom,length) in enumerate(chromosomes_and_length.items()):
            next_line = ("chr\t-\t{species_code}-{chrom}\t{chrom}\t0"
                "\t{length}\tblack".format(
                species_code=species_code,chrom=chrom, length=length))
            if indx < (len(chromosomes_and_length)-1):
                next_line += "\n" # don't add new line character to last line
            # Send the built line to output
            output_file.write(next_line)
    sys.stderr.write( "\n\nThe karyotype file for {} chromosomes has been saved "
            "as a file named"
            " '{}'.".format(len(chromosomes_and_length),output_file_name))