"""
Felix Muzny
DS 2000
Lecture 15
November 1, 2024

Reading in files as dictionaries
Lists of dictionaries
"""

import csv
import matplotlib.pyplot as plt

FILENAME = "ds2000_staff.csv"
AGE_COL = "age"
NUM_BINS = 10

def read_file_dict(filename):
    """
    Reads the file in as a single dictionary, ignoring the first (header) row

    :param filename: string location of the file
    :return: dictionary mapping strings to ints
    """
    data = {}
    with open(filename, "r") as file:
        # ignore the headers
        headers = file.readline()
        # read the rest of the lines
        for line in file:
            pieces = line.strip().split(",")

            # the first item will be the key
            # the second item will be the value, and should be
            # converted to ints
            data[pieces[0]] = int(pieces[1])
    return data

# partially provided
def read_file_as_list_of_dicts(filename):
    """
    Reads the given file as a list of dictionaries, using
    the first row of headers as key names
    :param filename: string location of file
    :return: list of dicts mapping strings to strings
    """
    data = []
    with open(filename, "r") as file:
        reader = csv.DictReader(file)
        for row in reader:
            # each row is pre-processed as a dictionary
            data.append(row)

    # return the data!
    return data

def make_age_hist(data, age_col, bins):
    """
    Make a histogram of the ages in the data
    :param data: list of dictionaries
    :param age_col: string name of column key associated with ages data
    :param bins: int number of bins for the histogram
    :return: none
    """
    # get the ages as integers
    # this is like accessing the ages column from the file
    ages = []
    for dict_row in data:
        int_val = int(dict_row[age_col])
        ages.append(int_val)

    plt.hist(ages, bins = bins)
    plt.xlabel("ages")
    plt.ylabel("count")
    plt.show()

def main():
    print("Lecture 15 - reading files into dicts")

    # read the file into a dictionary
    data = read_file_dict(FILENAME)
    print(data)

    # access all of the keys and make into a list
    print(list(data.keys()))

    # access all of the values and make into a list
    print(list(data.values()))

    # read the file into a list of dictionaries, using the
    # column headers as keys for each individual dictionary
    list_dicts_data = read_file_as_list_of_dicts(FILENAME)
    print(list_dicts_data)

    # make our beautiful visualization!
    make_age_hist(list_dicts_data, AGE_COL, NUM_BINS)

main()