Nanodegree > Project 2 > Lesson 4 > Problem 1

process_arachnid.py

def res_clean(line):
    #set name entry equal to label if broken
    n = re.match('^[a-zA-Z0-9_]+$',line["name"])
    if line["name"]=="NULL" or not n:
        line["name"]=line["rdf-schema#label"]
    #if value is null set to none
    for key, value in line.items():
        if value=="NULL":
            line[key]=None
    #trim redundant parentheses from rdf-schema#label
    out = []
    colsplit = line["rdf-schema#label"].split()
    exp=re.compile(r'\(+\S+\)', re.IGNORECASE)
    for value in range(len(colsplit)):
        m = exp.search(colsplit[value])
        if m:
            continue
        else:
            out.append(colsplit[value])
    line["rdf-schema#label"] =' '.join(out)
    #fix synonym entry
    if line["synonym"]:
        line["synonym"] = line["synonym"].replace("{", '').replace("}", '').replace("*", '').strip().split("|")
    #strip whitespace
    #for key, value in line.items():
    #    if value:
    #        line['key']=value.strip()
    return line

def process_file(filename, fields):
    process_fields = fields.keys()
    data = []
    with open(filename, "r") as f:
        reader = csv.DictReader(f)
        for i in range(3):
            next(reader)
        for line in reader:
            data1={}
            line_o = res_clean(line)
            for header in line_o.keys():
                if header in FIELDS.keys():
                    key_out = FIELDS[header]
                    data1[key_out] = line_o[header]
            classif_list = ["kingdom", "family", "order", "phylum", "genus", "class"]
            d_temp = {}
            for c in classif_list:
                d_temp[c] = data1[c]
                del data1[c]
            data1["classification"] = d_temp
            data.append(data1)         
    return data