def list_to_dict(input_single_dict):
'''
Create a dictionary from a single csv file
Inputs:
path of the csv file
Returns:
dictionary
'''
# create a new list with the values from csv
list_new = read_csv(input_single_dict, True)
# define a new empty dict to store the values
dict_new = {}
# define the name of vars to pass tests
names_for_tests = {'age': AGE,
'earnings_per_week': EARNWKE,
'employment_status_code': STATUS,
'ethnicity_code': ETHNIC,
'gender_code': GENDER,
'hours_worked_per_week': HRWKE,
'race_code': RACE}
# assign Key + value to each element of a list
# iterate through primary key (e.g. hid)
for i in range(1, len(list_new)):
# assign each home a unique dictionay key
key_home = list_new[i][0]
# create a dictionary within the dictionary
dict_hid = {}
# if list contains other sublistsinside
if len(list_new[0]) > 2:
# iterate through secondary keys (e.g. age)
for j in range(1, len(list_new[1])):
# key of variable is allways in element 0 of new_list
key_of_variable = list_new[0][j]
# name of variable
name_of_var = names_for_tests[key_of_variable]
# get value for each variable and each unique home
value_of_variable = list_new[i][j]
# create the hid dictuinary for each home
dict_hid[name_of_var] = value_of_variable
# add the hid dict to the greater dict
dict_new[key_home] = dict_hid
# if the list has only a key and a value
if len(list_new[0]) == 2:
value = list_new[i][1]
dict_new[key_home] = value
# return the dictionary of product and price
return dict_new
def initialize_code(filename, need_header = True):
'''
Reads the "codes.csv" filename and returns a dict based on
the given filename.
Inputs:
filename - string that represents one of the
csv code files
need_header - True if the header is needed, false otherwise
Returns:
dictionary with codes and corresponding val
'''
code = read_csv(filename, need_header)
d = {code[0]: (code[1])
for (code[0], code[1]) in
code[0:]}
return d
def build_morg_dict(input_dict):
'''
Build a dictionary that holds a set of CPS data
Inputs:
input_dict: dict
An example of input_dict is shown below:
{'morg':'data/morg_d14_mini.csv',
'gender_codes':'data/gender_code.csv',
'race_codes':'data/race_code.csv',
'ethnic_codes':'data/ethnic_code.csv',
'employment_codes':'data/employment_status_code.csv'}
Returns:
dict
'''
gender_codes_dict = initialize_code(
input_dict[GENDER_CODE])
race_codes_dict = initialize_code(
input_dict[RACE_CODE])
ethnic_codes_dict = initialize_code(
input_dict[ETHNIC_CODE])
employment_codes_dict = initialize_code(
input_dict[EMPLOYMENT_CODE])
morg_dict = {}
dataset = read_csv(input_dict[MORG_CODE], True)[1:]
for rowdata in dataset:
hid_key = rowdata[0]
hid_dict = format_row_data(rowdata,
gender_codes_dict, race_codes_dict, ethnic_codes_dict, employment_codes_dict)
morg_dict[hid_key] = hid_dict
return morg_dict
def make_subdict(input_dict):
'''
Builds a dictionary that contains the input Morg data
and the code files as values with keys of the provided Constants
for each attribute (GENDER, RACE, etc)
Inputs:
input_dict: dict
An example of input_dict is shown below:
{'morg':'data/morg_d14_mini.csv',
'gender_codes':'data/gender_code.csv',
'race_codes':'data/race_code.csv',
'ethnic_codes':'data/ethnic_code.csv',
'employment_codes':'data/employment_status_code.csv'}
Returns:
sub_dict: dict
'''
data_csv = input_dict['morg']
gen_csv = input_dict['gender_codes']
rc_csv = input_dict['race_codes']
ec_csv = input_dict['ethnic_codes']
emc_csv = input_dict['employment_codes']
csvs = [data_csv, gen_csv, rc_csv, ec_csv, emc_csv]
names = ['data', GENDER, RACE, ETHNIC, STATUS]
n = len(csvs)
sub_dict = {}
for n in range(n):
f = csvs[n]
read = read_csv(f, False)
sub_dict[names[n]] = read
return sub_dict
