def validate_format(number):
    length = len(number)
    if length == 14:
        if (re.match(formats[0], number)):
            return True
        return False
    if length == 12:
        if (re.match(formats[1], number)):
            return True
        return False
    if length == 11:
        if (re.match(formats[2], number)):
            return True
        return False
    if length == 10:
        if (re.match(formats[3], number)):
            return True
        return False
    return False


def create_dataframe(spark):
    my_cols = Row("Column1", "Column2", "Column3", "Column4")
    row_1 = my_cols('(617)-283-3811', 'Salah', 'Messi', None)
    row_2 = my_cols('617-2833811', 'Messi', 'Virgil', 'Messi')
    row_3 = my_cols('617-283-3811', 'Ronaldo', 'Messi', 'Ronaldo')
    row_seq = [row_1, row_2, row_3]
    df = spark.createDataFrame(row_seq)
    spark.udf.register("validateFormat", validate_format, BooleanType())
    df = df.select([c for c in df.columns if validateFormat(c)])