comparison filter_kw_val.py @ 4:2080e2a4f209 draft

planemo upload commit ef71f7a32bb76c79052b535be1d0beceff6e03a5-dirty

3:68cee865018e

#Check if a variable is a float or an integer
def is_number(number_format, n):
    float_format = re.compile(r"^[-]?[0-9][0-9]*.?[0-9]+$")
    int_format = re.compile(r"^[-]?[0-9][0-9]*$")
    test = ""
    if number_format == "int":
        test = re.match(int_format, n)
    elif number_format == "float":
        test = re.match(float_format, n)
    if test:
        return True

#Filter the document
def filters(args):
    filename = args.input.split(",")[0]
    header = str_to_bool(args.input.split(",")[1])

    if args.value:
        for v in args.value:
            v[0] = v[0].replace(",",".")
            if is_number("float", v[0]):
                csv_file = comma_number_to_float(csv_file,v[1],header)
                results_dict = filter_value(csv_file, header, results_dict, v[0], v[1], v[2])
            else:
                raise ValueError("Please enter a number in filter by value")

    if args.values_range:
        for vr in args.values_range:
            vr[:2] = [value.replace(",",".") for value in vr[:2]]
            csv_file = comma_number_to_float(csv_file,vr[2],header)
            if (is_number("float", vr[0]) or is_number("int", vr[0])) and (is_number("float",vr[1]) or is_number("int",vr[1])):
                results_dict = filter_values_range(csv_file, header, results_dict, vr[0], vr[1], vr[2], vr[3])

    remaining_lines=[]
    filtered_lines=[]

        unsortable_lines = [i for i,line in enumerate(tab) if (line[sort_col]=='' or line[sort_col] == 'NA')]
        unsorted_tab=[ tab[i] for i in unsortable_lines]
        tab= [line for i,line in enumerate(tab) if i not in unsortable_lines]

        if only_number(tab,sort_col) and any_float(tab,sort_col)  : 
            tab = sorted(tab, key=lambda row: float(row[sort_col]), reverse=reverse)
        elif only_number(tab,sort_col):
            tab = sorted(tab, key=lambda row: int(row[sort_col]), reverse=reverse)      
        else :
            tab = sorted(tab, key=lambda row: row[sort_col], reverse=reverse)

    
    return tmp

#turn into float a column
def comma_number_to_float(csv_file,ncol,header) :
    ncol = int(ncol.replace("c","")) - 1
    if header : 
        tmp=[csv_file[0]]
        csv_file=csv_file[1:]
    else : 
        tmp=[]

            return True

    return False

def only_number(tab,col) :

    for line in tab :
        if not (is_number("float",line[col].replace(",",".")) or is_number("int",line[col].replace(",","."))) :
            return False
    return True

4:2080e2a4f209

#Check if a variable is a float or an integer
def is_number(number_format, n):
    float_format = re.compile(r"^[-]?[0-9][0-9]*.?[0-9]+$")
    int_format = re.compile(r"^[-]?[0-9][0-9]*$")
    scientific_number = re.compile(r"^[-+]?[\d]+\.?[\d]*[Ee](?:[-+]?[\d]+)?$")
    test = ""
    if number_format == "int":
        test = re.match(int_format, n)
    elif number_format == "float":
        test = re.match(float_format, n)
        if test is None : test = re.match(scientific_number,n)

    if test:
        return True
    else :
        return False

#Filter the document
def filters(args):
    filename = args.input.split(",")[0]
    header = str_to_bool(args.input.split(",")[1])

    if args.value:
        for v in args.value:
            v[0] = v[0].replace(",",".")
            if is_number("float", v[0]):
                csv_file = comma_number_to_float(csv_file,column_from_txt(v[1]),header)
                results_dict = filter_value(csv_file, header, results_dict, v[0], v[1], v[2])
            else:
                raise ValueError("Please enter a number in filter by value")

    if args.values_range:
        for vr in args.values_range:
            vr[:2] = [value.replace(",",".") for value in vr[:2]]
            csv_file = comma_number_to_float(csv_file,column_from_txt(vr[2]),header)
            if (is_number("float", vr[0]) or is_number("int", vr[0])) and (is_number("float",vr[1]) or is_number("int",vr[1])):
                results_dict = filter_values_range(csv_file, header, results_dict, vr[0], vr[1], vr[2], vr[3])

    remaining_lines=[]
    filtered_lines=[]

        unsortable_lines = [i for i,line in enumerate(tab) if (line[sort_col]=='' or line[sort_col] == 'NA')]
        unsorted_tab=[ tab[i] for i in unsortable_lines]
        tab= [line for i,line in enumerate(tab) if i not in unsortable_lines]

        if only_number(tab,sort_col) and any_float(tab,sort_col)  : 
            tab = comma_number_to_float(tab,sort_col,False)
            tab = sorted(tab, key=lambda row: float(row[sort_col]), reverse=reverse)
        elif only_number(tab,sort_col):
            tab = sorted(tab, key=lambda row: int(row[sort_col]), reverse=reverse)      
        else :
            tab = sorted(tab, key=lambda row: row[sort_col], reverse=reverse)

    
    return tmp

#turn into float a column
def comma_number_to_float(csv_file,ncol,header) :
    if header : 
        tmp=[csv_file[0]]
        csv_file=csv_file[1:]
    else : 
        tmp=[]

            return True

    return False

def only_number(tab,col) :
    for line in tab :
        if not (is_number("float",line[col].replace(",",".")) or is_number("int",line[col].replace(",","."))) :
            return False
    return True