:param sample_sets: sample sets of all target languages

	:return: ratio of correctly predicted samples, its absolute number and the theoretical maximum"""

	models = [s.create_model() for s in sample_sets]

	score = 0

	max_score = 0

	for s in sample_sets:

		for (test_text, partial_model) in s.generate_tests(CROSSVALIDATION_SOURCE_COUNT):

			real_lang = partial_model.language

			test_models = [partial_model] + [m for m in models if m.language != real_lang]

			for k in TEST_LENS:

				for i in range(10):

					j = random.randrange(0, len(test_text)-k)

					t = test_text[j:j+k]

					predicted_lang = identify(t, test_models)

					if predicted_lang == real_lang:

						score += 1

					else:

						print(real_lang, predicted_lang, t)

					max_score += 1

	return score/max_score, score, max_score

def train(data_dir: str, model_path: str):

	"""Run the training and create a prediction model.

	files

	:param data_dir: path to the data directory, with one subdirectory for each language

		containing several text files as separate sources.

	:param model_path: where to save the result language model as a .json.gz"""

	samples = []

	lang_dirs = sorted([x.path for x in os.scandir(data_dir)])

	for d in lang_dirs:

		lang = os.path.basename(d)

		lang_samples = SampleSet(lang)

		samples.append(lang_samples)

		for file in sorted(os.scandir(d), key=lambda f: f.name):

			with open(file) as f:

				text = f.read()

				text = preprocess(text)

				print(f"{lang}: {file.name} ({len(text)})")

				lang_samples.add(text)

	print(cross_validate(samples))

DATA_DIR = os.path.join(os.path.dirname(__file__), "../../data")

MODEL_PATH = os.path.join(os.path.dirname(__file__), "models.json.gz")

if __name__ == "__main__":

	train(DATA_DIR, MODEL_PATH)