Guided Project: Explore U.S. Births

Posted on Wed 08 July 2015 in Projects

Introduction To The Dataset

In [136]:
csv_list = open("US_births_1994-2003_CDC_NCHS.csv").read().split("\n")
In [137]:
csv_list[0:10]
Out[137]:
['year,month,date_of_month,day_of_week,births',
 '1994,1,1,6,8096',
 '1994,1,2,7,7772',
 '1994,1,3,1,10142',
 '1994,1,4,2,11248',
 '1994,1,5,3,11053',
 '1994,1,6,4,11406',
 '1994,1,7,5,11251',
 '1994,1,8,6,8653',
 '1994,1,9,7,7910']

Converting Data Into A List Of Lists

In [138]:
def read_csv(filename):
    string_data = open(filename).read()
    string_list = string_data.split("\n")[1:]
    final_list = []
    
    for row in string_list:
        string_fields = row.split(",")
        int_fields = []
        for value in string_fields:
            int_fields.append(int(value))
        final_list.append(int_fields)
    return final_list
        
cdc_list = read_csv("US_births_1994-2003_CDC_NCHS.csv")
In [139]:
cdc_list[0:10]
Out[139]:
[[1994, 1, 1, 6, 8096],
 [1994, 1, 2, 7, 7772],
 [1994, 1, 3, 1, 10142],
 [1994, 1, 4, 2, 11248],
 [1994, 1, 5, 3, 11053],
 [1994, 1, 6, 4, 11406],
 [1994, 1, 7, 5, 11251],
 [1994, 1, 8, 6, 8653],
 [1994, 1, 9, 7, 7910],
 [1994, 1, 10, 1, 10498]]

Calculating Number Of Births Each Month

In [140]:
def read_csv(filename):
    string_data = open(filename).read()
    string_list = string_data.split("\n")[1:]
    final_list = []
    
    for row in string_list:
        string_fields = row.split(",")
        int_fields = []
        for value in string_fields:
            int_fields.append(int(value))
        final_list.append(int_fields)
    return final_list
        
cdc_list = read_csv("US_births_1994-2003_CDC_NCHS.csv")


def month_births(data):
    births_per_month = {}
    
    for row in data:
        month = row[1]
        births = row[4]
        if month in births_per_month:
            births_per_month[month] = births_per_month[month] + births
        else:
            births_per_month[month] = births
    return births_per_month
    
cdc_month_births = month_births(cdc_list)
In [141]:
cdc_month_births
Out[141]:
{1: 3232517,
 2: 3018140,
 3: 3322069,
 4: 3185314,
 5: 3350907,
 6: 3296530,
 7: 3498783,
 8: 3525858,
 9: 3439698,
 10: 3378814,
 11: 3171647,
 12: 3301860}

Calculating Number Of Births Each Day Of Week

In [142]:
def dow_births(data):
    births_per_dow = {}
    
    for row in data:
        dow = row[3]
        births = row[4]
        if dow in births_per_dow:
            births_per_dow[dow] = births_per_dow[dow] + births
        else:
            births_per_dow[dow] = births
    return births_per_dow
    
cdc_dow_births = dow_births(cdc_list)
In [143]:
cdc_dow_births
Out[143]:
{1: 5789166,
 2: 6446196,
 3: 6322855,
 4: 6288429,
 5: 6233657,
 6: 4562111,
 7: 4079723}

Creating A More General Function

In [144]:
def calc_counts(data, column):
    sums_dict = {}
    
    for row in data:
        col_value = row[column]
        births = row[4]
        if col_value in sums_dict:
            sums_dict[col_value] = sums_dict[col_value] + births
        else:
            sums_dict[col_value] = births
    return sums_dict

cdc_year_births = calc_counts(cdc_list, 0)
cdc_month_births = calc_counts(cdc_list, 1)
cdc_dom_births = calc_counts(cdc_list, 2)
cdc_dow_births = calc_counts(cdc_list, 3)
In [145]:
cdc_year_births
Out[145]:
{1994: 3952767,
 1995: 3899589,
 1996: 3891494,
 1997: 3880894,
 1998: 3941553,
 1999: 3959417,
 2000: 4058814,
 2001: 4025933,
 2002: 4021726,
 2003: 4089950}
In [146]:
cdc_month_births
Out[146]:
{1: 3232517,
 2: 3018140,
 3: 3322069,
 4: 3185314,
 5: 3350907,
 6: 3296530,
 7: 3498783,
 8: 3525858,
 9: 3439698,
 10: 3378814,
 11: 3171647,
 12: 3301860}
In [147]:
cdc_dom_births
Out[147]:
{1: 1276557,
 2: 1288739,
 3: 1304499,
 4: 1288154,
 5: 1299953,
 6: 1304474,
 7: 1310459,
 8: 1312297,
 9: 1303292,
 10: 1320764,
 11: 1314361,
 12: 1318437,
 13: 1277684,
 14: 1320153,
 15: 1319171,
 16: 1315192,
 17: 1324953,
 18: 1326855,
 19: 1318727,
 20: 1324821,
 21: 1322897,
 22: 1317381,
 23: 1293290,
 24: 1288083,
 25: 1272116,
 26: 1284796,
 27: 1294395,
 28: 1307685,
 29: 1223161,
 30: 1202095,
 31: 746696}
In [148]:
cdc_dow_births
Out[148]:
{1: 5789166,
 2: 6446196,
 3: 6322855,
 4: 6288429,
 5: 6233657,
 6: 4562111,
 7: 4079723}

python