from typing import List, Tuple, Union, Dict

with open("names.txt") as f:
    names = [line.strip() for line in f if line]
print(f"Number of names: {len(names)}")
print(names[::1000])

class NamesDataset:
    """
    Implement all methods in this class,
    such that the output type fulfills the type annotations
    and their behavior follows the description in the doc-strings. 
    """
    def __init__(self, names: List[str]):
        """
        The constructor must save the names as an attribute.
        """
    
    def query(self, prefix: str) -> List[str]:
        """
        The query method takes in a prefix and returns a list 
        of all names in the dataset that start with the given prefix.
        """
    
    def longest_name(self, prefix: str = None, return_len: bool = False) -> Union[str, Tuple[str, int]]:
        """
        The longest_name method returns the longest name in the dataset.
        
        It also must support filtering the names by the prefix.
        If a prefix is given, than it should return the longest name, starting with the prefix
        
        Additionally, if the return_len argument is True, it should output the longest name. 
        AND its length (as tuple). 
        """
    
    def mean_name_length(self) -> float:
        """
        This method computes the mean length of all names in the dataset.
        """
    
    def ngrams(self, size: int, prefix: str = None) -> List[str]:
        """
        This method returns a list of all character n_grams of all names (or those starting with a given prefix).
        The size determines the size of the n_grams.
        """
        
    def count_ngrams(self, size: int, prefix: str = None) -> List[Tuple[str, int]]:
        """
        This method returns a list of tuples containing all n_grams created with the given the arguments
        and their frequency within all n_grams found under the parameters.
        The list should be sorted in ascending order.
        """