from cdfm.utils import load_cdfmdata

# loading dataset as a DataFrame object
# 1. features
features_path = '/path/to/features'
n_dimensions = 10
features = load_cdfmdata(features_path, n_dimensions)
# features.columns
# >>> Index(['label', 'qid', 'eid', 'features'], dtype='object')

# 2. proximities
proximities_path = '/path/to/proximities'
n_dimensions = 2
proximities = load_cdfmdata(proximities_path, n_dimensions, mode='proximity')
# proximities.columns
# >>> Index(['qid', 'eid', 'cid', 'proximities'], dtype='object')

# some preprocessing here...

# Finally, build a dataset
train = build_cdfmdata(features)  # using features only
train = build_cdfmdata(features, proximities)  # using proximities

from cdfm.models import CDFMRanker

# define your model
model = CDFMRanker(k=8, n_iter=300, init_eta=1e-2)
# fitting, printing out epoch losses if verbose is True
model.fit(train, verbose=True)

import pickle

with open('/path/to/file.pkl', mode='wb') as fp:
    pickle.dump(model, fp)

# loading test dataset
test_df = load_cdfmdata(test_path, n_dimensions)
test = build_cdfmdata(test_df)
pred = model.predict(test)