comparison vsnp_statistics.py @ 25:b908bb18008a draft

Uploaded

24:39ab5405b509

    # Gather Series into a data frame.
    fastq_df = pandas.DataFrame(dict(id=s1, seq=s2)).set_index(['id'])
    # Starting at row 3, keep every 4 row
    # random sample specified number of rows.
    file_size = nice_size(os.path.getsize(fastq_file))
    total_reads = int(len(fastq_df.index) / 4)
    # Mean Read Length
    if sampling_size > total_reads:
        sampling_size = total_reads
    fastq_df = fastq_df.iloc[3::4].sample(sampling_size)
    dict_mean = {}
    list_length = []
    i = 0
    for id, seq, in fastq_df.iterrows():
        dict_mean[id] = numpy.mean(letter_annotations[i])

25:b908bb18008a

    # Gather Series into a data frame.
    fastq_df = pandas.DataFrame(dict(id=s1, seq=s2)).set_index(['id'])
    # Starting at row 3, keep every 4 row
    # random sample specified number of rows.
    file_size = nice_size(os.path.getsize(fastq_file))
    total_reads = len(seqs)
    # Mean Read Length
    if sampling_size > total_reads:
        sampling_size = total_reads
    try:
        fastq_df = fastq_df.iloc[3::4].sample(sampling_size)
    except ValueError:
        fastq_df = fastq_df.iloc[3::4].sample(sampling_size, replace=True)
    dict_mean = {}
    list_length = []
    i = 0
    for id, seq, in fastq_df.iterrows():
        dict_mean[id] = numpy.mean(letter_annotations[i])