Completed U.S. Medical Insurance Costs - Asking for Feedback

Projects Portfolio Project: U.S. Medical Insurance Costs
1

This project was good at challenging my ability to work with functions. I spent about 15 hours putting the code together. It was good work to practice declaring a class with methods, and calling those methods. I felt like the level of difficulty was good for the questions I was trying to solve.

I feel like I could have shortened up my print statements with another method, but I didn’t clean that part of the code.

I didn’t write specific questions in the code, but it is implied I am finding to distinguish highest to lowest cost based on each header. I built some methods that do a great job of sorting the information.

My code can be found here:
import csv
import statistics
import collections

#class for pulling information from each dictionary
class WranglingData:
def init(self):
pass
#print(‘Class for manipulating each dictionary’)

#define function for pulling values from dictionary
def reading_dictionary(self, dictionary, heading):
    self.dictionary = dictionary
    self.heading = heading
    list_of_heading = []

# filter the values by two attributes
def filter_by_two(self, dictionary, heading1, attribute1, heading2, attribute2 = 'null'):
    self.dictionary = dictionary
    self.heading1 = heading1
    self.heading2 = heading2
    self.attribute1 = attribute1
    self.attribute2 = attribute2
    filtered_list = []
    
    #scan through the dictionary and save values  
    for line in self.dictionary:
        if line.get(self.heading1) == attribute1:
            filtered_list.append(line[heading2])
    filtered_list = self.string_conversion(filtered_list)
    return filtered_list

# sort the data by ages and another value
def sort_by_age(self, dictionary, filter_by):
    self.dictionary = dictionary
    
    # Get values sorted by heading used as a filter in a dictionary
    new_dictionary = {}
    for line in self.dictionary:
        if line.get(filter_by) in new_dictionary:
            new_dictionary[line.get(filter_by)].append(float(line.get('charges')))
        else:
            new_dictionary.update({line.get(filter_by) : [float(line.get('charges'))]})

    #find the mean costs by each item in newly created dictionary
    for value in new_dictionary:
        new_dictionary[value] = statistics.mean(new_dictionary.get(value))
    
    return new_dictionary

def print_dictionary(self, dictionary):
    for key in sorted(dictionary):
        print("Key: ", key, "Value: ", str(round(dictionary[key],2)))

#convert to int or float a list of strings and returns a list of ints or floats
def string_conversion(self, list_arg, new_type = 'float'):
    conversion_list = []
    #filter by type of value
    if new_type == 'int':
        conversion_list = (list(map(int,list_arg)))
    elif new_type == 'float':
        conversion_list = (list(map(float,list_arg)))
    else:
        print("Types can only be int or float")
    return conversion_list

with open(‘insurance.csv’, newline = ‘\n’) as insurance_data:
new_insurance_data = csv.DictReader(insurance_data)

health_data = WranglingData()
new_list = []
for i in new_insurance_data:
    new_list.append(i)

#*********do men or women pay more in insurance on average? ******
print("\n\nThe cost averages of men and women are: ")
print("Men are charged: ", round(statistics.mean(health_data.filter_by_two(new_list,‘sex’,‘male’,‘charges’)),2))
print("Women are charged: ", round(statistics.mean(health_data.filter_by_two(new_list,‘sex’,‘female’,‘charges’)),2))

#What is the most expensive regaion?*
print("\n\nThe cost average breakdown by region is:")
print("Northwest is charged: ", round(statistics.mean(health_data.filter_by_two(new_list,‘region’,‘northwest’,‘charges’)),2))
print("Southwest is charged: ", round(statistics.mean(health_data.filter_by_two(new_list,‘region’,‘southwest’,‘charges’)),2))
print("Northeast is charged: ", round(statistics.mean(health_data.filter_by_two(new_list,‘region’,‘northeast’,‘charges’)),2))
print("Southeast is charged: ", round(statistics.mean(health_data.filter_by_two(new_list,‘region’,‘southeast’,‘charges’)),2))

#What is the premium for being a smoker?*
print("\n\nThe cost average for smokers and non-smokers is :")
print("Smokers are charged: ", round(statistics.mean(health_data.filter_by_two(new_list,‘smoker’,‘yes’,‘charges’)),2))
print("Non-smokers are charged: ", round(statistics.mean(health_data.filter_by_two(new_list,‘smoker’,‘no’,‘charges’)),2))

#What is the premium by age?*
print("\n\nThe cost average by age is :")
print(health_data.print_dictionary(health_data.sort_by_age(new_list, ‘age’)))

#What is the premium by number of children?*
print("\n\nThe cost average by number of children is :")
print(health_data.print_dictionary(health_data.sort_by_age(new_list, ‘children’)))

#What is the premium by body mass index?*
print("\n\nThe cost average by body mass index is :")
print(health_data.print_dictionary(health_data.sort_by_age(new_list, ‘bmi’)))