def predict_LME(model_path, outdir, X, y, dv, partition_name, model_name=''):
stderr('Retrieving saved model %s...\n' % m)
with open(model_path, 'rb') as m_file:
lme = pickle.load(m_file)
summary = '=' * 50 + '\n'
summary += 'LME regression\n\n'
summary += 'Model name: %s\n\n' % m
summary += 'Formula:\n'
summary += ' ' + formula + '\n'
summary += str(lme.summary()) + '\n'
if args.mode in [None, 'response']:
lme_preds = lme.predict(X)
with open(outdir + '/%spreds_%s.txt' % ('' if model_name=='' else model_name + '_', partition_name), 'w') as p_file:
for i in range(len(lme_preds)):
p_file.write(str(lme_preds[i]) + '\n')
losses = np.array(y[dv] - lme_preds) ** 2
with open(outdir + '/%slosses_mse_%s.txt' % ('' if model_name=='' else model_name + '_', partition_name), 'w') as p_file:
for i in range(len(losses)):
p_file.write(str(losses[i]) + '\n')
lme_mse = mse(y[dv], lme_preds)
lme_mae = mae(y[dv], lme_preds)
summary += 'Loss (%s set):\n' % partition_name
summary += ' MSE: %.4f\n' % lme_mse
summary += ' MAE: %.4f\n' % lme_mae
summary += '=' * 50 + '\n'
with open(outdir + '/%seval_%s.txt' % ('' if model_name=='' else model_name + '_', partition_name), 'w') as f_out:
f_out.write(summary)
stderr(summary)
stderr(
'Retrieving saved L(ME) regression of CDR model %s...\n'
% m)
with open(model_path, 'rb') as m_file:
lm = pickle.load(m_file)
else:
stderr('Fitting L(ME) regression of CDR model %s...\n' % m)
if is_lme:
lm = LME(model_form, df_r)
else:
lm = LM(model_form, df_r)
with open(model_path, 'wb') as m_file:
pickle.dump(lm, m_file)
lm_preds = lm.predict(df_r)
lm_mse = mse(df[dv], lm_preds)
lm_mae = mae(df[dv], lm_preds)
summary = '=' * 50 + '\n'
summary += '%s regression\n\n' % ('LME'
if is_lme else 'Linear')
summary += 'Model name: %s\n\n' % m
summary += 'Formula:\n'
summary += ' ' + model_form + '\n'
summary += str(lm.summary()) + '\n'
summary += 'Training set loss:\n'
summary += ' MSE: %.4f\n' % lm_mse
summary += ' MAE: %.4f\n' % lm_mae
summary += '=' * 50 + '\n'
with open(model_summary_path, 'w') as f_out:
f_out.write(summary)
stderr(summary)
from cdr.baselines import LME
dv = formula.strip().split('~')[0].strip().replace('.', '')
if os.path.exists(p.outdir + '/' + m + '/m.obj'):
stderr('Retrieving saved model %s...\n' % m)
with open(p.outdir + '/' + m + '/m.obj', 'rb') as m_file:
lme = pickle.load(m_file)
else:
stderr('Fitting model %s...\n' % m)
lme = LME(formula, X_baseline)
with open(p.outdir + '/' + m + '/m.obj', 'wb') as m_file:
pickle.dump(lme, m_file)
lme_preds = lme.predict(X_baseline)
lme_mse = mse(y[dv], lme_preds)
lme_mae = mae(y[dv], lme_preds)
summary = '=' * 50 + '\n'
summary += 'LME regression\n\n'
summary += 'Model name: %s\n\n' % m
summary += 'Formula:\n'
summary += ' ' + formula + '\n'
summary += str(lme.summary()) + '\n'
summary += 'Training set loss:\n'
summary += ' MSE: %.4f\n' % lme_mse
summary += ' MAE: %.4f\n' % lme_mae
summary += '=' * 50 + '\n'
with open(p.outdir + '/' + m + '/summary.txt', 'w') as f_out:
f_out.write(summary)
stderr(summary)
stderr('\n\n')
stderr('Retrieving saved model %s...\n' % m)
with open(p.outdir + '/' + m + '/m.obj', 'rb') as m_file:
gam = pickle.load(m_file)
gam_preds = gam.predict(X_baseline)
with open(p.outdir + '/' + m + '/preds_%s.txt' % partition_str,
'w') as p_file:
for i in range(len(gam_preds)):
p_file.write(str(gam_preds[i]) + '\n')
losses = np.array(y[dv] - gam_preds)**2
with open(
p.outdir + '/' + m +
'/losses_mse_%s.txt' % partition_str, 'w') as p_file:
for i in range(len(losses)):
p_file.write(str(losses[i]) + '\n')
gam_mse = mse(y[dv], gam_preds)
gam_mae = mae(y[dv], gam_preds)
summary = '=' * 50 + '\n'
summary += 'GAM regression\n\n'
summary += 'Model name: %s\n\n' % m
summary += 'Formula:\n'
summary += ' ' + formula + '\n'
summary += str(gam.summary()) + '\n'
summary += 'Loss (%s set):\n' % partition_str
summary += ' MSE: %.4f\n' % gam_mse
summary += ' MAE: %.4f\n' % gam_mae
summary += '=' * 50 + '\n'
with open(p.outdir + '/' + m + '/eval_%s.txt' % partition_str,
'w') as f_out:
f_out.write(summary)
stderr(summary)