def adjust_mean_mtslice(tdata_mt, ref=None):
"""Adjust the mean of the mtslice by the given ref
"""
if ref is None:
ref = tdata_mt.mean_temp[0]
study_slices = utils.sizes_to_slices(tdata_mt.study_sizes)
for i in range(tdata_mt.num_studies):
obs_mean = tdata_mt.obs_mean[study_slices[i]]
obs_std = tdata_mt.obs_std[study_slices[i]]
cov = tdata_mt.daily_temp[study_slices[i]]
# fit the curve
if tdata_mt.study_sizes[i] >= 5:
spline = xspline.xspline(np.array([cov.min(), ref,
cov.max()]),
2,
l_linear=True)
else:
spline = xspline.xspline(np.array([cov.min(), cov.max()]), 1)
beta = utils.fit_spline(obs_mean, obs_std, cov, spline)
ref_lnrr = spline.designMat(ref).dot(beta)
# adjust the mean
tdata_mt.obs_mean[study_slices[i]] -= ref_lnrr
return tdata_mt
def offsite_data_at_mean_temp(tdata, mean_temp):
tdata_at_mean_temp = extract_at_mean_temp(tdata, mean_temp)
study_slices = utils.sizes_to_slices(tdata_at_mean_temp.study_sizes)
for i in range(tdata_at_mean_temp.num_studies):
obs_mean = tdata_at_mean_temp.obs_mean[study_slices[i]]
obs_std = tdata_at_mean_temp.obs_std[study_slices[i]]
cov = tdata_at_mean_temp.daily_temp[study_slices[i]]
# fit the curve
spline = xspline.xspline(np.array([cov.min(), mean_temp,
cov.max()]),
2,
l_linear=True)
beta = utils.fit_spline(obs_mean, obs_std, cov, spline)
ref_lnrr = spline.designMat(mean_temp).dot(beta)
# shift the data
tdata_at_mean_temp.obs_mean[study_slices[i]] -= ref_lnrr
# inflate the std if necessary
residual = (obs_mean - spline.designMat(cov).dot(beta)) / obs_std
tdata_at_mean_temp.obs_std[study_slices[i]] *= np.maximum(
1.0, np.std(residual))
return tdata_at_mean_temp
def plot_data_slice(mean_temp, tdata, ylim=None, ax=None, study_range=None):
"""scatter the data at given mean_temp"""
if ax is None:
handle = plt
if ylim is not None: handle.ylim(*ylim)
else:
handle = ax
if ylim is not None: handle.set_ylim(*ylim)
tdata_amt = process.extract_at_mean_temp(tdata, mean_temp)
study_slices = utils.sizes_to_slices(tdata_amt.study_sizes)
if study_range is None:
study_range = range(0, tdata_amt.num_studies)
else:
study_range = range(study_range[0], study_range[1])
# plot all the points
for i in study_range:
s = study_slices[i]
handle.scatter(tdata_amt.daily_temp[s],
tdata_amt.obs_mean[s],
s=1.0 / tdata_amt.obs_std[s])
# plot the trimmed data as red x
trimming_id = tdata_amt.trimming_weights <= 0.5
handle.scatter(tdata_amt.daily_temp[trimming_id],
tdata_amt.obs_mean[trimming_id],
marker='x',
color='r')
return tdata_amt
def plot_score(trend_result, tdata, mean_temp, outcome, score,
dt, shifted_draws, mean_draws, path_to_result_folder):
"""Plot the evidence score and shifted draws."""
tdata_amt = process.extract_at_mean_temp(tdata, mean_temp)
study_slices = utils.sizes_to_slices(tdata_amt.study_sizes)
study_range = range(0, tdata_amt.num_studies)
plt.figure(figsize=((16,8)))
# plot all the points
for i in study_range:
s = study_slices[i]
plt.scatter(tdata_amt.daily_temp[s],
tdata_amt.obs_mean[s] - np.min(mean_draws),
s=1.0/tdata_amt.obs_std[s])
# Trimmed data points
trimming_id = tdata_amt.trimming_weights <= 0.5
plt.scatter(tdata_amt.daily_temp[trimming_id],
tdata_amt.obs_mean[trimming_id],
marker='x',
color='r')
# Upper and lower bound
plt.fill_between(dt,
np.quantile(shifted_draws, 0.05, axis=1),
np.quantile(shifted_draws, 0.95, axis=1),
color='#808080', alpha=0.7)
# Mean draws after shifted
plt.plot(dt, np.mean(shifted_draws, axis=1), color='b')
plt.plot([dt.min(), dt.max()], [0.0, 0.0], "k--")
plt.xlabel("Daily temperature")
plt.title(f"Mean temperature at {mean_temp}, score: {np.round(score, 4)}")
plt.savefig(path_to_result_folder + "/" + outcome + "_score_%i.pdf" % mean_temp,
bbox_inches="tight")
plt.close()
def plot_mtslice(tdata, mt, ylim=None, ax=None, use_colors=True):
if ax is None:
ax = plt
if ylim is not None:
ax.ylim(ylim[0], ylim[1])
else:
if ylim is not None:
ax.set_ylim(ylim[0], ylim[1])
tdata_mt = extract_mtslice(tdata, mt)
if use_colors:
study_slices = utils.sizes_to_slices(tdata_mt.study_sizes)
for i in range(tdata_mt.num_studies):
ax.scatter(tdata_mt.daily_temp[study_slices[i]],
tdata_mt.obs_mean[study_slices[i]],
s=1.0 / tdata_mt.obs_std[study_slices[i]])
else:
ax.scatter(tdata_mt.daily_temp,
tdata_mt.obs_mean,
s=1.0 / tdata_mt.obs_std)