# CS150 class example
# Tests timing of sets vs. lists

import random
import time

def generate_set(set_size):
    """Return a set containing set_size random integers"""
    data = set()
        
    while len(data) < set_size:
        data.add(random.randint(0, set_size*10))
    
    return data

def generate_list(list_size):
    """Return a list containing list_size random integers"""
    data = []
    
    for dummy in range(list_size):
        data.append(random.randint(0, list_size*10))
    
    return data

def query_data(data, num_queries, largest):
    """Compute time to execute random membership queries

    Args:
        data: List or Set
        num_queries: Number of membership queries to perform
        largest: Upper bound for random integers to query

    Returns:
        Elapsed time for all queries
    """
    
    # We'll count them for fun, but won't do anything with the count
    count = 0 
    
    begin = time.time()
    
    for i in range(num_queries):
        # Just check to see if a random number is in there
        random_num = random.randint(0, largest)
        if random_num in data:
            count += 1
            
    return time.time() - begin

def speed_test(set_size, num_queries):
    """Print timing for creating and querying of lists and sets
    
    Args:
        set_size: Size of set/list to query
        num_queries: Number of membership queries to perform
    """
    # Generate random list
    begin = time.time()
    list_data = generate_list(set_size)
    print("List creation took", time.time()-begin, "seconds")
    
    # Generate random set
    begin = time.time()
    set_data = generate_set(set_size)
    print("Set creation took", time.time()-begin, "seconds")
    
    print("--")
    
    # Time the list querying
    elapsed = query_data(list_data, num_queries, set_size*10)
    print("List querying took", elapsed, "seconds")

    # Time the list querying
    elapsed = query_data(set_data, num_queries, set_size*10)
    print("Set querying took", elapsed, "seconds")


def speed_data(num_queries, set_size_min, set_size_max, step_size):
    """Print a table of runtimes for querying lists and sets of
    different sizes.

    Args:
        num_queries: Number of membership queries to perform
        set_size_min, set_size_max, step_size: Range of set/list sizes to test query performance
    """
    print("size","list","set", sep="\t") # Instead of a space separate with a tab
    
    for set_size in range(set_size_min, set_size_max, step_size):
        # Generate random list
        list_data = generate_list(set_size)
    
        # Generate random set
        set_data = generate_set(set_size)
    
        # Time the list querying
        list_elapsed = query_data(list_data, num_queries, set_size*10)

        # Time the list querying
        set_elapsed = query_data(set_data, num_queries, set_size*10)
        
        print(set_size, list_elapsed, set_elapsed, sep="\t")


#speed_test(100000, 1000)
#speed_data(1000, 10000, 100000, 5000)