def merge_vps(i, v, s, l, thresh, lweight, lsim, wbias, pdfpar, lp, llen, distance_measure, max_stdd=0.01, outlier_stdd=1e-6): M = v.shape[1] num_cores = multiprocessing.cpu_count() tryAgain = True tries = 0 while tryAgain and M > 1: tries += 1 angles = Parallel(n_jobs=num_cores)( delayed(calc_angle_to_other_vp)(v, i, j) for j in range(M)) angles = np.stack(angles) argmin_angle = numpy.unravel_index(angles.argmin(), angles.shape) j = argmin_angle[0] k = argmin_angle[1] min_angle = angles[j, k] if min_angle < thresh: try: p = prob.calc_probabilities(i, pdfpar, v, l, lp, s, llen, distance_measure) w = weight_matrix(p.vl, lweight, lsim, bias=wbias) newVP = calc_new_vanishing_point(l, w[j, :] + w[k, :]) p_vl_sum = np.sum(p.vl[k, :] + p.vl[j, :]) s_log = np.log(np.sum(0.5 * (p.lvsq[:, j] + p.lvsq[:, k]) * (p.vl[k, :] + p.vl[j, :]))) - \ np.log(p_vl_sum) s[k] = np.exp(s_log) if newVP is None or s[k] > max_stdd: tryAgain = False continue else: v[i, k, :] = newVP v = np.delete(v, j, axis=1) s = np.delete(s, j, axis=0) except np.linalg.linalg.LinAlgError as err: continue else: tryAgain = False M = v.shape[1] return {'v': v, 's': s}
def main(version='100k', n_jobs=1, random_state=0, cross_val=False): dl_params = {} dl_params['100k'] = dict(learning_rate=1, batch_size=10, offset=0, alpha=1) dl_params['1m'] = dict(learning_rate=.75, batch_size=60, offset=0, alpha=.8) dl_params['10m'] = dict(learning_rate=.75, batch_size=600, offset=0, alpha=3) dl_params['netflix'] = dict(learning_rate=.8, batch_size=4000, offset=0, alpha=0.16) cd_params = { '100k': dict(alpha=.1), '1m': dict(alpha=.03), '10m': dict(alpha=.04), 'netflix': dict(alpha=.1) } if version in ['100k', '1m', '10m']: X = load_movielens(version) X_tr, X_te = train_test_split(X, train_size=0.75, random_state=random_state) X_tr = X_tr.tocsr() X_te = X_te.tocsr() elif version is 'netflix': X_tr = load(expanduser('~/spira_data/nf_prize/X_tr.pkl')) X_te = load(expanduser('~/spira_data/nf_prize/X_te.pkl')) cd_mf = ExplicitMF( n_components=60, max_iter=50, alpha=.1, normalize=True, verbose=1, ) dl_mf = DictMF(n_components=30, n_epochs=20, alpha=1.17, verbose=5, batch_size=10000, normalize=True, fit_intercept=True, random_state=0, learning_rate=.75, impute=False, partial=False, backend='python') dl_mf_partial = DictMF(n_components=60, n_epochs=20, alpha=1.17, verbose=5, batch_size=10000, normalize=True, fit_intercept=True, random_state=0, learning_rate=.75, impute=False, partial=True, backend='python') timestamp = datetime.datetime.now().strftime('%Y-%m-%d_%H' '-%M-%S') if cross_val: subdir = 'benches_ncv' else: subdir = 'benches' output_dir = expanduser(join('~/output/recommender/', timestamp, subdir)) if not os.path.exists(output_dir): os.makedirs(output_dir) alphas = np.logspace(-2, 1, 10) mf_list = [dl_mf_partial] dict_id = {cd_mf: 'cd', dl_mf: 'dl', dl_mf_partial: 'dl_partial'} names = { 'cd': 'Coordinate descent', 'dl': 'Proposed online masked MF', 'dl_partial': 'Proposed algorithm (with partial projection)' } if os.path.exists( join(output_dir, 'results_%s_%s.json' % (version, random_state))): with open( join(output_dir, 'results_%s_%s.json' % (version, random_state)), 'r') as f: results = json.load(f) else: results = {} for mf in mf_list: results[dict_id[mf]] = {} if not cross_val: if isinstance(mf, DictMF): mf.set_params( learning_rate=dl_params[version]['learning_rate'], batch_size=dl_params[version]['batch_size'], alpha=dl_params[version]['alpha']) else: mf.set_params(alpha=cd_params[version]['alpha']) else: if isinstance(mf, DictMF): mf.set_params( learning_rate=dl_params[version]['learning_rate'], batch_size=dl_params[version]['batch_size']) if version != 'netflix': cv = ShuffleSplit(n_iter=3, train_size=0.66, random_state=0) mf_scores = Parallel(n_jobs=n_jobs, verbose=10)( delayed(single_fit)(mf, alpha, X_tr, cv) for alpha in alphas) else: mf_scores = Parallel(n_jobs=n_jobs, verbose=10)( delayed(single_fit)(mf, alpha, X_tr, X_te, nested=False) for alpha in alphas) mf_scores = np.array(mf_scores).mean(axis=1) best_alpha_arg = mf_scores.argmin() best_alpha = alphas[best_alpha_arg] mf.set_params(alpha=best_alpha) cb = Callback(X_tr, X_te, refit=False) mf.set_params(callback=cb) mf.fit(X_tr) results[dict_id[mf]] = dict(name=names[dict_id[mf]], time=cb.times, rmse=cb.rmse) if cross_val: results[dict_id[mf]]['alphas'] = alphas.tolist() results[dict_id[mf]]['cv_alpha'] = mf_scores.tolist() results[dict_id[mf]]['best_alpha'] = mf.alpha with open( join(output_dir, 'results_%s_%s.json' % (version, random_state)), 'w+') as f: json.dump(results, f) print('Done')
def main(version='100k', n_jobs=1, random_state=0, cross_val=False): dl_params = {} dl_params['100k'] = dict(learning_rate=1, batch_size=10, offset=0, alpha=1) dl_params['1m'] = dict(learning_rate=.75, batch_size=60, offset=0, alpha=.8) dl_params['10m'] = dict(learning_rate=.75, batch_size=600, offset=0, alpha=3) dl_params['netflix'] = dict(learning_rate=.8, batch_size=4000, offset=0, alpha=0.16) cd_params = {'100k': dict(alpha=.1), '1m': dict(alpha=.03), '10m': dict(alpha=.04), 'netflix': dict(alpha=.1)} if version in ['100k', '1m', '10m']: X = load_movielens(version) X_tr, X_te = train_test_split(X, train_size=0.75, random_state=random_state) X_tr = X_tr.tocsr() X_te = X_te.tocsr() elif version is 'netflix': X_tr = load(expanduser('~/spira_data/nf_prize/X_tr.pkl')) X_te = load(expanduser('~/spira_data/nf_prize/X_te.pkl')) cd_mf = ExplicitMF(n_components=60, max_iter=50, alpha=.1, normalize=True, verbose=1, ) dl_mf = DictMF(n_components=30, n_epochs=20, alpha=1.17, verbose=5, batch_size=10000, normalize=True, fit_intercept=True, random_state=0, learning_rate=.75, impute=False, partial=False, backend='python') dl_mf_partial = DictMF(n_components=60, n_epochs=20, alpha=1.17, verbose=5, batch_size=10000, normalize=True, fit_intercept=True, random_state=0, learning_rate=.75, impute=False, partial=True, backend='python') timestamp = datetime.datetime.now().strftime('%Y-%m-%d_%H' '-%M-%S') if cross_val: subdir = 'benches_ncv' else: subdir = 'benches' output_dir = expanduser(join('~/output/recommender/', timestamp, subdir)) if not os.path.exists(output_dir): os.makedirs(output_dir) alphas = np.logspace(-2, 1, 10) mf_list = [dl_mf_partial] dict_id = {cd_mf: 'cd', dl_mf: 'dl', dl_mf_partial: 'dl_partial'} names = {'cd': 'Coordinate descent', 'dl': 'Proposed online masked MF', 'dl_partial': 'Proposed algorithm (with partial projection)'} if os.path.exists(join(output_dir, 'results_%s_%s.json' % (version, random_state))): with open(join(output_dir, 'results_%s_%s.json' % (version, random_state)), 'r') as f: results = json.load(f) else: results = {} for mf in mf_list: results[dict_id[mf]] = {} if not cross_val: if isinstance(mf, DictMF): mf.set_params( learning_rate=dl_params[version]['learning_rate'], batch_size=dl_params[version]['batch_size'], alpha=dl_params[version]['alpha']) else: mf.set_params(alpha=cd_params[version]['alpha']) else: if isinstance(mf, DictMF): mf.set_params( learning_rate=dl_params[version]['learning_rate'], batch_size=dl_params[version]['batch_size']) if version != 'netflix': cv = ShuffleSplit(n_iter=3, train_size=0.66, random_state=0) mf_scores = Parallel(n_jobs=n_jobs, verbose=10)( delayed(single_fit)(mf, alpha, X_tr, cv) for alpha in alphas) else: mf_scores = Parallel(n_jobs=n_jobs, verbose=10)( delayed(single_fit)(mf, alpha, X_tr, X_te, nested=False) for alpha in alphas) mf_scores = np.array(mf_scores).mean(axis=1) best_alpha_arg = mf_scores.argmin() best_alpha = alphas[best_alpha_arg] mf.set_params(alpha=best_alpha) cb = Callback(X_tr, X_te, refit=False) mf.set_params(callback=cb) mf.fit(X_tr) results[dict_id[mf]] = dict(name=names[dict_id[mf]], time=cb.times, rmse=cb.rmse) if cross_val: results[dict_id[mf]]['alphas'] = alphas.tolist() results[dict_id[mf]]['cv_alpha'] = mf_scores.tolist() results[dict_id[mf]]['best_alpha'] = mf.alpha with open(join(output_dir, 'results_%s_%s.json' % (version, random_state)), 'w+') as f: json.dump(results, f) print('Done')