def test_group_len_equals_vals_len():
# The groups need to be same shape as vals
vals = [1, None, 3, 5, 8, 7]
grps_1 = ['USA']
grps_2 = ['MA', 'RI', 'RI', 'CT', 'CT', 'CT']
weights = [.65]
with pytest.raises(ValueError):
group_adjust(vals, [grps_1, grps_2], weights)
pass
def test_weights_len_equals_group_len():
# Need to have 1 weight for each group
# vals = [1, np.NaN, 3, 5, 8, 7]
vals = [1, None, 3, 5, 8, 7]
grps_1 = ['USA', 'USA', 'USA', 'USA', 'USA', 'USA']
grps_2 = ['MA', 'RI', 'RI', 'CT', 'CT', 'CT']
weights = [.65]
with pytest.raises(ValueError):
group_adjust(vals, [grps_1, grps_2], weights)
pass
def test_performance():
#vals = 1000000*[1, None, 3, 5, 8, 7]
# If you're doing numpy, use the np.NaN instead
vals = 1000000 * [1, np.NaN, 3, 5, 8, 7]
grps_1 = 1000000 * [1, 1, 1, 1, 1, 1]
grps_2 = 1000000 * [1, 1, 1, 1, 2, 2]
grps_3 = 1000000 * [1, 2, 2, 3, 4, 5]
weights = [.20, .30, .50]
start = datetime.now()
group_adjust(vals, [grps_1, grps_2, grps_3], weights)
end = datetime.now()
diff = end - start
print(diff)
pass
def test_two_groups():
vals = [1, 2, 3, 8, 5]
grps_1 = ['USA', 'USA', 'USA', 'USA', 'USA']
grps_2 = ['MA', 'RI', 'CT', 'CT', 'CT']
weights = [.65, .35]
adj_vals = group_adjust(vals, [grps_1, grps_2], weights)
# 1 - (.65 * 3.8 + .35 * 1.0) = -1.82
# 2 - (.65 * 3.8 + .35 * 2.0) = -1.17
# 3 - (.65 * 3.8 + .35 * 5.33333) = -1.33666
answer = [-1.82, -1.17, -1.33666, 3.66333, 0.66333]
for ans, res in zip(answer, adj_vals):
assert abs(ans - res) < 1e-5
def test_three_groups():
vals = [1, 2, 3, 8, 5]
grps_1 = ['USA', 'USA', 'USA', 'USA', 'USA']
grps_2 = ['MA', 'MA', 'MA', 'RI', 'RI']
grps_3 = ['WEYMOUTH', 'BOSTON', 'BOSTON', 'PROVIDENCE', 'PROVIDENCE']
weights = [.15, .35, .5]
adj_vals = group_adjust(vals, [grps_1, grps_2, grps_3], weights)
# 1 - (USA_mean*.15 + MA_mean * .35 + WEYMOUTH_mean * .5)
# 2 - (USA_mean*.15 + MA_mean * .35 + BOSTON_mean * .5)
# 3 - (USA_mean*.15 + MA_mean * .35 + BOSTON_mean * .5)
# etc ...
# Plug in the numbers ...
# 1 - (.15 * 3.8 + .35 * 2.0 + .5 * 1.0) = -0.770
# 2 - (.15 * 3.8 + .35 * 2.0 + .5 * 2.5) = -0.520
# 3 - (.15 * 3.8 + .35 * 2.0 + .5 * 2.5) = 0.480
# etc...
answer = [-0.770, -0.520, 0.480, 1.905, -1.095]
for ans, res in zip(answer, adj_vals):
assert abs(ans - res) < 1e-5
def test_missing_vals():
# If you're using NumPy or Pandas, use np.NaN
# If you're writing pyton, use None
vals = [1, np.NaN, 3, 5, 8, 7]
#vals = [1, None, 3, 5, 8, 7]
grps_1 = ['USA', 'USA', 'USA', 'USA', 'USA', 'USA']
grps_2 = ['MA', 'RI', 'RI', 'CT', 'CT', 'CT']
weights = [.65, .35]
adj_vals = group_adjust(vals, [grps_1, grps_2], weights)
# This should be None or np.NaN depending on your implementation
# please feel free to change this line to match yours
answer = [-2.47, np.NaN, -1.170, -0.4533333, 2.54666666, 1.54666666]
#answer = [-2.47, None, -1.170, -0.4533333, 2.54666666, 1.54666666]
for ans, res in zip(answer, adj_vals):
if ans is None:
assert res is None
elif np.isnan(ans):
assert np.isnan(res)
else:
assert abs(ans - res) < 1e-5