def test_weight_broadcasting():
clrd = cl.load_sample("clrd")[["CumPaidLoss", "EarnedPremDIR"]]
clrd = clrd[clrd["LOB"] == "wkcomp"]
bcl = cl.Chainladder()
bf = cl.BornhuetterFerguson()
cc = cl.CapeCod()
estimators = [('bcl', bcl), ('bf', bf), ('cc', cc)]
min_dim_weights = np.array([[1, 2, 3]] * 4 + [[0, 0.5, 0.5]] * 3 +
[[0, 0, 1]] * 3)
mid_dim_weights = np.array(
[[[1, 2, 3]] * 4 + [[0, 0.5, 0.5]] * 3 + [[0, 0, 1]] * 3] * 1)
max_dim_weights = np.array(
[[[[1, 2, 3]] * 4 + [[0, 0.5, 0.5]] * 3 + [[0, 0, 1]] * 3] * 1] * 132)
min_dim_ult = cl.VotingChainladder(
estimators=estimators, weights=min_dim_weights).fit(
clrd['CumPaidLoss'],
sample_weight=clrd["EarnedPremDIR"].latest_diagonal,
).ultimate_.sum()
mid_dim_ult = cl.VotingChainladder(
estimators=estimators, weights=mid_dim_weights).fit(
clrd['CumPaidLoss'],
sample_weight=clrd["EarnedPremDIR"].latest_diagonal,
).ultimate_.sum()
max_dim_ult = cl.VotingChainladder(
estimators=estimators, weights=max_dim_weights).fit(
clrd['CumPaidLoss'],
sample_weight=clrd["EarnedPremDIR"].latest_diagonal,
).ultimate_.sum()
assert (abs(min_dim_ult - mid_dim_ult - max_dim_ult) < 1)
def test_voting_ultimate(triangle_data, estimators, weights):
bcl_ult = cl.Chainladder().fit(
triangle_data["CumPaidLoss"].sum(), ).ultimate_
bf_ult = cl.BornhuetterFerguson().fit(
triangle_data["CumPaidLoss"].sum(),
sample_weight=triangle_data["EarnedPremDIR"].sum(
).latest_diagonal).ultimate_
cc_ult = cl.CapeCod().fit(triangle_data["CumPaidLoss"].sum(),
sample_weight=triangle_data["EarnedPremDIR"].sum(
).latest_diagonal).ultimate_
vot_ult = cl.VotingChainladder(
estimators=estimators, weights=weights,
default_weighting=(1, 2, 3)).fit(
triangle_data["CumPaidLoss"].sum(),
sample_weight=triangle_data["EarnedPremDIR"].sum().latest_diagonal,
).ultimate_
direct_weight = np.array([[1, 2, 3]] * 4 + [[0, 0.5, 0.5]] * 3 +
[[0, 0, 1]] * 3)
direct_weight = direct_weight[..., np.newaxis]
assert abs((
(bcl_ult * direct_weight[..., 0, :] + bf_ult *
direct_weight[..., 1, :] + cc_ult * direct_weight[..., 2, :]) /
direct_weight.sum(axis=-2)).sum() - vot_ult.sum()) < 1
def test_voting_ultimate():
clrd = cl.load_sample("clrd")[["CumPaidLoss", "EarnedPremDIR"]]
clrd = clrd[clrd["LOB"] == "wkcomp"]
bcl_ult = cl.Chainladder().fit(clrd["CumPaidLoss"].sum(), ).ultimate_
bf_ult = cl.BornhuetterFerguson().fit(
clrd["CumPaidLoss"].sum(),
sample_weight=clrd["EarnedPremDIR"].sum().latest_diagonal).ultimate_
cc_ult = cl.CapeCod().fit(
clrd["CumPaidLoss"].sum(),
sample_weight=clrd["EarnedPremDIR"].sum().latest_diagonal).ultimate_
bcl = cl.Chainladder()
bf = cl.BornhuetterFerguson()
cc = cl.CapeCod()
estimators = [('bcl', bcl), ('bf', bf), ('cc', cc)]
weights = np.array([[0.25, 0.25, 0.5]] * 4 + [[0, 0.5, 0.5]] * 3 +
[[0, 0, 1]] * 3)
vot_ult = cl.VotingChainladder(estimators=estimators, weights=weights).fit(
clrd["CumPaidLoss"].sum(),
sample_weight=clrd["EarnedPremDIR"].sum().latest_diagonal,
).ultimate_
weights = weights[..., np.newaxis]
assert abs((bcl_ult * weights[..., 0, :] + bf_ult * weights[..., 1, :] +
cc_ult * weights[..., 2, :]).sum() - vot_ult.sum()) < 1
def test_weight_broadcasting(triangle_data, estimators, weights):
mid_dim_weights = np.array(
[[[1, 2, 3]] * 4 + [[0, 0.5, 0.5]] * 3 + [[0, 0, 1]] * 3] * 1)
max_dim_weights = np.array(mid_dim_weights * 132)
min_dim_ult = cl.VotingChainladder(
estimators=estimators, weights=weights).fit(
triangle_data['CumPaidLoss'],
sample_weight=triangle_data["EarnedPremDIR"].latest_diagonal,
).ultimate_.sum()
mid_dim_ult = cl.VotingChainladder(
estimators=estimators, weights=mid_dim_weights).fit(
triangle_data['CumPaidLoss'],
sample_weight=triangle_data["EarnedPremDIR"].latest_diagonal,
).ultimate_.sum()
max_dim_ult = cl.VotingChainladder(
estimators=estimators, weights=max_dim_weights).fit(
triangle_data['CumPaidLoss'],
sample_weight=triangle_data["EarnedPremDIR"].latest_diagonal,
).ultimate_.sum()
assert (abs(min_dim_ult - mid_dim_ult - max_dim_ult) < 1)
def test_different_backends(triangle_data, estimators, weights):
model = cl.VotingChainladder(
estimators=estimators, weights=weights,
default_weighting=(1, 2, 3)).fit(
triangle_data["CumPaidLoss"].sum().set_backend("numpy"),
sample_weight=triangle_data["EarnedPremDIR"].sum().latest_diagonal.
set_backend("numpy"),
)
assert (abs((model.predict(
triangle_data["CumPaidLoss"].sum().set_backend("sparse"),
sample_weight=triangle_data["EarnedPremDIR"].sum().latest_diagonal.
set_backend("sparse")).ultimate_.sum() - model.ultimate_.sum())) < 1)
def test_voting_predict():
bcl = cl.Chainladder()
bf = cl.BornhuetterFerguson()
cc = cl.CapeCod()
estimators = [('bcl', bcl), ('bf', bf), ('cc', cc)]
weights = np.array([[1, 2, 3]] * 3 + [[0, 0.5, 0.5]] * 3 + [[0, 0, 1]] * 3)
vot = cl.VotingChainladder(estimators=estimators, weights=weights).fit(
raa_1989,
sample_weight=apriori_1989,
)
vot.predict(raa_1990, sample_weight=apriori_1990)
def test_different_backends():
clrd = cl.load_sample("clrd")[["CumPaidLoss", "EarnedPremDIR"]]
clrd = clrd[clrd["LOB"] == "wkcomp"]
bcl = cl.Chainladder()
bf = cl.BornhuetterFerguson()
cc = cl.CapeCod()
estimators = [('bcl', bcl), ('bf', bf), ('cc', cc)]
weights = np.array([[1, 2, 3]] * 4 + [[0, 0.5, 0.5]] * 3 + [[0, 0, 1]] * 3)
model = cl.VotingChainladder(estimators=estimators, weights=weights).fit(
clrd["CumPaidLoss"].sum().set_backend("numpy"),
sample_weight=clrd["EarnedPremDIR"].sum().latest_diagonal.set_backend(
"numpy"),
)
assert (abs(
(model.predict(clrd["CumPaidLoss"].sum().set_backend("sparse"),
sample_weight=clrd["EarnedPremDIR"].sum().
latest_diagonal.set_backend("sparse")).ultimate_.sum() -
model.ultimate_.sum())) < 1)
import pandas as pd
import chainladder as cl
# Load the data
raa = cl.load_sample('raa')
cl_ult = cl.Chainladder().fit(raa).ultimate_ # Chainladder Ultimate
apriori = cl_ult * 0 + (float(cl_ult.sum()) / 10) # Mean Chainladder Ultimate
# Load estimators to vote between
bcl = cl.Chainladder()
cc = cl.CapeCod()
estimators = [('bcl', bcl), ('cc', cc)]
# Fit VotingChainladder using CC after 1987 and a blend of BCL and CC otherwise
vot = cl.VotingChainladder(
estimators=estimators,
weights=lambda origin: (0, 1) if origin.year > 1987 else (0.5, 0.5)
)
vot.fit(raa, sample_weight=apriori)
# Plotting
bcl_ibnr = bcl.fit(raa).ibnr_.to_frame()
cc_ibnr = cc.fit(raa, sample_weight=apriori).ibnr_.to_frame()
vot_ibnr = vot.ibnr_.to_frame()
plot_ibnr = pd.concat([bcl_ibnr, vot_ibnr, cc_ibnr], axis=1)
plot_ibnr.columns = ['BCL', 'Voting', 'CC']
g = plot_ibnr.plot(
kind='bar', ylim=(0, None), grid=True,
title='Voting Chainladder IBNR').set(
xlabel='Accident Year', ylabel='Loss');