def test_weighted_quantile():
Q = [0, 0.5, 1]
EXPECTED_UNWEIGHTED = [1, 2, 5]
res_unweighted = mdf.weighted_quantile(X, Q).tolist()
assert EXPECTED_UNWEIGHTED == res_unweighted
res_weighted = mdf.weighted_quantile(X, Q, W).tolist()
# Waiting for a better test, given the result isn't exactly the same as
# stacking values.
# See stackoverflow.com/q/21844024#comment102342137_29677616
# EXPECTED_WEIGHTED = [1, 1, 5]
# For now, check that median is less than the unweighted median.
assert res_weighted[1] < res_unweighted[1]
def top_x_pct_share(df, col, top_x_pct, w=None):
"""Calculates top x% share.
:param df: DataFrame.
:param col: Name of column in df representing value.
:param top_x_pct: Decimal between 0 and 1 of the top %, e.g. 0.1, 0.001.
:param w: Column representing weight in df.
:returns: The share of w-weighted val held by the top x%.
"""
threshold = mdf.weighted_quantile(df, col, w, 1 - top_x_pct)
top_x_pct_sum = mdf.weighted_sum(df[df[col] >= threshold], col, w)
total_sum = mdf.weighted_sum(df, col, w)
return top_x_pct_sum / total_sum
def top_x_pct_share(val, top_x_pct, w=None):
"""Calculates top x% share.
Args:
val: Value (list-like).
top_x_pct: Decimal between 0 and 1 of the top %, e.g. 0.1, 0.001.
w: Weight (list-like, same length as val).
Returns:
The share of w-weighted val held by the top x%.
"""
val = pd.Series(val)
if w is None:
w = np.ones(val.size)
w = pd.Series(w)
threshold = mdf.weighted_quantile(val, 1 - top_x_pct, w)
filt = val >= threshold
top_x_pct_sum = (val[filt] * w[filt]).sum()
total_sum = (val * w).sum()
return top_x_pct_sum / total_sum
def total_wealth_by_decile(data, measure):
quant_df = pd.DataFrame()
for race2 in data.race2.unique():
race_df = data[data.race2 == race2].copy(deep=True)
decile_bounds = np.arange(0, 1.1, 0.1)
deciles = mdf.weighted_quantile(race_df, measure, "wgt", decile_bounds)
race_total_nw = mdf.weighted_sum(race_df, measure, "wgt")
quantile_nws = []
for index, value in enumerate(deciles):
if index + 1 < len(deciles):
quantile_subset = race_df[race_df.networth.between(
value, deciles[index + 1])]
quantile_nws.append(
mdf.weighted_sum(quantile_subset, measure, "wgt"))
quantile_nw_pct = (quantile_nws / race_total_nw) * 100
race_quant_df = pd.DataFrame({race2: quantile_nw_pct},
index=np.arange(1, 11, 1))
quant_df = pd.concat([quant_df, race_quant_df], axis=1)
return quant_df
def test_weighted_quantile():
Q = [0, 0.5, 1]
mdf.weighted_quantile(df, "x", "w", Q).tolist()
def _top_x_pct_share(df, col, top_x_pct, w=None):
threshold = mdf.weighted_quantile(df, col, w, 1 - top_x_pct)
top_x_pct_sum = mdf.weighted_sum(df[df[col] >= threshold], col, w)
total_sum = mdf.weighted_sum(df, col, w)
return top_x_pct_sum / total_sum
