Lecture1.ipynb

Kernel: Python 3 (system-wide)

DATA = "2016Census_G24_AUS.csv"

with open(DATA, "r") as file:
    headings = file.readline().split(",")[1:]
    numbers = file.readline().split(",")[1:]

age_birth_cats = []
num_parents = []

for i in range(len(headings)):
    if "Tot" not in headings[i]:                      # Strip out "Total" entries
        age_birth_cats.append(headings[i][2:])        # Strip out "P_"
        num_parents.append(int(numbers[i]))        # Cast to int

print(age_birth_cats, len(age_birth_cats))            # Doublecheck
print(num_parents, len(num_parents))

['15_19_Num_chld_evr_brn_Nne', '15_19_Num_chld_evr_brn_1', '15_19_Num_chld_evr_brn_2', '15_19_Num_chld_evr_brn_3', '15_19_Num_chld_evr_brn_4', '15_19_Num_chld_evr_brn_5', '15_19_Num_chd_evr_brn_6_mr', '15_19_Num_chld_evr_brn_ns', '20_24_Num_chld_evr_brn_Nne', '20_24_Num_chld_evr_brn_1', '20_24_Num_chld_evr_brn_2', '20_24_Num_chld_evr_brn_3', '20_24_Num_chld_evr_brn_4', '20_24_Num_chld_evr_brn_5', '20_24_Num_chd_evr_brn_6_mr', '20_24_Num_chld_evr_brn_ns', '25_29_Num_chld_evr_brn_Nne', '25_29_Num_chld_evr_brn_1', '25_29_Num_chld_evr_brn_2', '25_29_Num_chld_evr_brn_3', '25_29_Num_chld_evr_brn_4', '25_29_Num_chld_evr_brn_5', '25_29_Num_chd_evr_brn_6_mr', '25_29_Num_chld_evr_brn_ns', '30_34_Num_chld_evr_brn_Nne', '30_34_Num_chld_evr_brn_1', '30_34_Num_chld_evr_brn_2', '30_34_Num_chld_evr_brn_3', '30_34_Num_chld_evr_brn_4', '30_34_Num_chld_evr_brn_5', '30_34_Num_chd_evr_brn_6_mr', '30_34_Num_chld_evr_brn_ns', '35_39_Num_chld_evr_brn_Nne', '35_39_Num_chld_evr_brn_1', '35_39_Num_chld_evr_brn_2', '35_39_Num_chld_evr_brn_3', '35_39_Num_chld_evr_brn_4', '35_39_Num_chld_evr_brn_5', '35_39_Num_chd_evr_brn_6_mr', '35_39_Num_chld_evr_brn_ns', '40_44_Num_chld_evr_brn_Nne', '40_44_Num_chld_evr_brn_1', '40_44_Num_chld_evr_brn_2', '40_44_Num_chld_evr_brn_3', '40_44_Num_chld_evr_brn_4', '40_44_Num_chld_evr_brn_5', '40_44_Num_chd_evr_brn_6_mr', '40_44_Num_chld_evr_brn_ns', '45_49_Num_chld_evr_brn_Nne', '45_49_Num_chld_evr_brn_1', '45_49_Num_chld_evr_brn_2', '45_49_Num_chld_evr_brn_3', '45_49_Num_chld_evr_brn_4', '45_49_Num_chld_evr_brn_5', '45_49_Num_chd_evr_brn_6_mr', '45_49_Num_chld_evr_brn_ns', '50_54_Num_chld_evr_brn_Nne', '50_54_Num_chld_evr_brn_1', '50_54_Num_chld_evr_brn_2', '50_54_Num_chld_evr_brn_3', '50_54_Num_chld_evr_brn_4', '50_54_Num_chld_evr_brn_5', '50_54_Num_chd_evr_brn_6_mr', '50_54_Num_chld_evr_brn_ns', '55_59_Num_chld_evr_brn_Nne', '55_59_Num_chld_evr_brn_1', '55_59_Num_chld_evr_brn_2', '55_59_Num_chld_evr_brn_3', '55_59_Num_chld_evr_brn_4', '55_59_Num_chld_evr_brn_5', '55_59_Num_chd_evr_brn_6_mr', '55_59_Num_chld_evr_brn_ns', '60_64_Num_chld_evr_brn_Nne', '60_64_Num_chld_evr_brn_1', '60_64_Num_chld_evr_brn_2', '60_64_Num_chld_evr_brn_3', '60_64_Num_chld_evr_brn_4', '60_64_Num_chld_evr_brn_5', '60_64_Num_chd_evr_brn_6_mr', '60_64_Num_chld_evr_brn_ns', '65_69_Num_chld_evr_brn_Nne', '65_69_Num_chld_evr_brn_1', '65_69_Num_chld_evr_brn_2', '65_69_Num_chld_evr_brn_3', '65_69_Num_chld_evr_brn_4', '65_69_Num_chld_evr_brn_5', '65_69_Num_chd_evr_brn_6_mr', '65_69_Num_chld_evr_brn_ns', '70_74_Num_chld_evr_brn_Nne', '70_74_Num_chld_evr_brn_1', '70_74_Num_chld_evr_brn_2', '70_74_Num_chld_evr_brn_3', '70_74_Num_chld_evr_brn_4', '70_74_Num_chld_evr_brn_5', '70_74_Num_chd_evr_brn_6_mr', '70_74_Num_chld_evr_brn_ns', '75_79_Num_chld_evr_brn_Nne', '75_79_Num_chld_evr_brn_1', '75_79_Num_chld_evr_brn_2', '75_79_Num_chld_evr_brn_3', '75_79_Num_chld_evr_brn_4', '75_79_Num_chld_evr_brn_5', '75_79_Num_chd_evr_brn_6_mr', '75_79_Num_chld_evr_brn_ns', '80_84_Num_chld_evr_brn_Nne', '80_84_Num_chld_evr_brn_1', '80_84_Num_chld_evr_brn_2', '80_84_Num_chld_evr_brn_3', '80_84_Num_chld_evr_brn_4', '80_84_Num_chld_evr_brn_5', '80_84_Num_chd_evr_brn_6_mr', '80_84_Num_chld_evr_brn_ns', '85_ov_Num_chld_evr_brn_Nne', '85_ov_Num_chld_evr_brn_1', '85_ov_Num_chld_evr_brn_2', '85_ov_Num_chld_evr_brn_3', '85_ov_Num_chld_evr_brn_4', '85_ov_Num_chld_evr_brn_5', '85_ov_Num_chd_evr_brn_6_mr', '85_ov_Num_chld_evr_brn_ns'] 120
[604590, 6815, 1008, 222, 94, 50, 174, 80957, 617569, 51331, 21731, 4846, 953, 191, 346, 74401, 526642, 121670, 80364, 27207, 7548, 1988, 1051, 74053, 322428, 184388, 190304, 70711, 21933, 6649, 3883, 63725, 168370, 135662, 260976, 115796, 37550, 11632, 7937, 50624, 128537, 114312, 292333, 145736, 48783, 15285, 11077, 49485, 119541, 109297, 294809, 153702, 52661, 16221, 11642, 50405, 109298, 97670, 276843, 156616, 56169, 17040, 11367, 49606, 95880, 87234, 260140, 162109, 61495, 18008, 11064, 49288, 76843, 73492, 233679, 151313, 59001, 17090, 10294, 45335, 59094, 57024, 217464, 143894, 57900, 17663, 10634, 44088, 39451, 36176, 149513, 113615, 51631, 17579, 12085, 36348, 26385, 23131, 92261, 85797, 49174, 20125, 16300, 32047, 18178, 17145, 58611, 58834, 38526, 18231, 17876, 29128, 22886, 24928, 66602, 59796, 39213, 19657, 21867, 51545] 120

num_categories = len(age_birth_cats)

sel0 = slice(0, num_categories, 8)
sel1 = slice(1, num_categories, 8)
sel2 = slice(2, num_categories, 8)
sel3 = slice(3, num_categories, 8)
sel4 = slice(4, num_categories, 8)
sel5 = slice(5, num_categories, 8)
sel6 = slice(6, num_categories, 8)
sel7 = slice(7, num_categories, 8)

children0 = num_parents[sel0]
children1 = num_parents[sel1]
children2 = num_parents[sel2]
children3 = num_parents[sel3]
children4 = num_parents[sel4]
children5 = num_parents[sel5]
children6 = num_parents[sel6]
children7 = num_parents[sel7]

import matplotlib.pyplot as plt

for i in range(8):
    plt.plot(num_parents[slice(i, len(num_parents), 8)])

# Setting the size of the figure
plt.figure(figsize = (9, 5))

for i in range(8):
    children = num_parents[slice(i, len(num_parents), 8)]
    if i == 6:
        lengend_label = "6 or more children"
    elif i == 7:
        lengend_label = "not specified"
    else:
        lengend_label = str(i) + "children"
    plt.plot(children, label = lengend_label, marker = 'o')

# Now we get the label of each ticks on x a-xis
xtick_labels = []
long_labels = age_birth_cats[slice(i, len(age_birth_cats), 8)]
for long_label in long_labels:                 # Each age category
    xtick_labels.append(long_label[:5])        # Get only the age range

# ticks para refers to a list specifying each tick in the x-axis
plt.xticks(ticks = range(len(xtick_labels)), labels = xtick_labels)
plt.tick_params(axis = "x", labelrotation = 90)

plt.xlabel("Age Range")
plt.ylabel("Number of Women")
plt.legend()                                   # Show the legend
plt.title("Number of Children Versus Age, 2016 Census")
plt.show()