CSV_FOLDER, CSV_ALL, CONFIG_FILE, Q_NPZ, SKILL_WINS, SKILL_FAILS = dataio.build_new_paths(
DATASET_NAME)
config = dataio.get_config(CONFIG_FILE)
experiment_args = vars(options)
df_train, df_val, df_test = dataio.get_data(DATASET_NAME)
try:
skill_wins = load_npz(SKILL_WINS)
skill_fails = load_npz(SKILL_FAILS)
except:
skill_wins = None
skill_fails = None
short_legend, full_legend, latex_legend, active_agents = dataio.get_legend(
experiment_args)
EXPERIMENT_FOLDER = os.path.join(CSV_FOLDER, short_legend)
dataio.prepare_folder(EXPERIMENT_FOLDER)
def df_to_sparse(df, filename):
SPARSE_NPZ = os.path.join(EXPERIMENT_FOLDER, filename)
if os.path.isfile(SPARSE_NPZ):
X_fm = load_npz(SPARSE_NPZ)
return X_fm
X = {}
nb_events, _ = df.shape
rows = list(range(nb_events))
for key in ['users', 'items', 'speech']:
X[key] = coo_matrix(([1] * nb_events, (rows, df[key])),
shape=(nb_events, config['NUM'][key]))
# Tables
labels = {}
latex_labels = {}
TABLE_TEX = os.path.join(CSV_FOLDER, '{:s}-table.tex'.format(DATASET_NAME))
array = []
acc_values = {}
nll_values = {}
#with open(TABLE_TEX, 'w') as latex:
for filename in experiments:
df = pd.read_csv(filename.replace('results.json', 'rlog.csv'))
acc_values[filename] = df['accuracy']
nll_values[filename] = df['ll_mcmc_all']
with open(filename) as f:
results = json.load(f)
short_legend, full_legend, latex_legend, active_agents = dataio.get_legend(
results['args'])
# full_legend = full_legend
latex_legend = latex_legend.replace(
'users, items, skills, wins, fails, item_wins, item_fails',
'u, i, s, w, f, item_wins, item_fails').replace('_', r'\_')
print(filename)
print(latex_legend)
labels[filename] = full_legend
latex_labels[filename] = latex_legend + " $d = {:d}$".format(
results['args']['d'])
# line = '{:s} & '.format(latex_legend)
# line += ' & '.join('{:.4f}'.format(results['metrics'][metric]) for metric in ['ACC', 'AUC', 'NLL']) + r'\\'
row = [latex_legend, results['args']['d']] + [
results['metrics'][metric] for metric in ['ACC', 'AUC', 'NLL']
]
# MCMC NLL is different