How to use the preshed.counter.PreshCounter function in preshed

def test_large_freqs():
    if 'TEST_FILE_LOC' in os.environ:
        loc = os.environ['TEST_FILE_LOC']
    else:
        return None
    counts = PreshCounter()
    for i, line in enumerate(open(loc)):
        line = line.strip()
        if not line:
            continue
        freq = int(line.split()[0])
        counts.inc(i+1, freq)
    oov = i+2
    assert counts.prob(oov) == 0.0
    assert counts.prob(1) < 0.1
    counts.smooth()
    assert counts.prob(oov) > 0
    assert counts.prob(oov) < counts.prob(i)

def test_count():
    counter = PreshCounter()
    assert counter[12] == 0
    counter.inc(12, 1)
    assert counter[12] == 1
    counter.inc(14, 10)
    counter.inc(9, 10)
    counter.inc(12, 4)
    assert counter[12] == 5
    assert counter[14] == 10
    assert counter[9] == 10

def _read_freqs(loc, max_length=100, min_doc_freq=5, min_freq=200):
    if not loc.exists():
        print("Warning: Frequencies file not found")
        return {}, 0.0
    counts = PreshCounter()
    total = 0
    if str(loc).endswith('gz'):
        file_ = gzip.open(str(loc))
    else:
        file_ = loc.open()
    for i, line in enumerate(file_):
        freq, doc_freq, key = line.rstrip().split('\t', 2)
        freq = int(freq)
        counts.inc(i+1, freq)
        total += freq
    counts.smooth()
    log_total = math.log(total)
    if str(loc).endswith('gz'):
        file_ = gzip.open(str(loc))
    else:
        file_ = loc.open()

def merge_counts(locs, out_loc):
    string_map = StringStore()
    counts = PreshCounter()
    for loc in locs:
        with io.open(loc, 'r', encoding='utf8') as file_:
            for line in file_:
                freq, word = line.strip().split('\t', 1)
                orth = string_map[word]
                counts.inc(orth, int(freq))
    with io.open(out_loc, 'w', encoding='utf8') as file_:
        for orth, count in counts:
            string = string_map[orth]
            file_.write('%d\t%s\n' % (count, string))

def read_freqs(freqs_loc, max_length=100, min_doc_freq=5, min_freq=50):
    counts = PreshCounter()
    total = 0
    with freqs_loc.open() as f:
        for i, line in enumerate(f):
            freq, doc_freq, key = line.rstrip().split("\t", 2)
            freq = int(freq)
            counts.inc(i + 1, freq)
            total += freq
    counts.smooth()
    log_total = math.log(total)
    probs = {}
    with freqs_loc.open() as f:
        for line in tqdm(f):
            freq, doc_freq, key = line.rstrip().split("\t", 2)
            doc_freq = int(doc_freq)
            freq = int(freq)
            if doc_freq >= min_doc_freq and freq >= min_freq and len(key) < max_length:

def read_freqs(freqs_loc, max_length=100, min_doc_freq=5, min_freq=50):
    print("Counting frequencies...")
    counts = PreshCounter()
    total = 0
    with freqs_loc.open() as f:
        for i, line in enumerate(f):
            freq, doc_freq, key = line.rstrip().split('\t', 2)
            freq = int(freq)
            counts.inc(i + 1, freq)
            total += freq
    counts.smooth()
    log_total = math.log(total)
    probs = {}
    with freqs_loc.open() as f:
        for line in tqdm(f):
            freq, doc_freq, key = line.rstrip().split('\t', 2)
            doc_freq = int(doc_freq)
            freq = int(freq)
            if doc_freq >= min_doc_freq and freq >= min_freq and len(key) < max_length:

def read_freqs(freqs_loc, max_length=100, min_doc_freq=5, min_freq=50):
    print("Counting frequencies...")
    counts = PreshCounter()
    total = 0
    with freqs_loc.open() as f:
        for i, line in enumerate(f):
            freq, doc_freq, key = line.rstrip().split('\t', 2)
            freq = int(freq)
            counts.inc(i + 1, freq)
            total += freq
    counts.smooth()
    log_total = math.log(total)
    probs = {}
    with freqs_loc.open() as f:
        for line in tqdm(f):
            freq, doc_freq, key = line.rstrip().split('\t', 2)
            doc_freq = int(doc_freq)
            freq = int(freq)
            if doc_freq >= min_doc_freq and freq >= min_freq and len(key) < max_length:

def _read_probs_from_freqs(loc, max_length=100, min_doc_freq=5, min_freq=200):
    if not loc.exists():
        print("Warning: Frequencies file not found")
        return {}, 0.0
    counts = PreshCounter()
    total = 0
    if str(loc).endswith('gz'):
        file_ = gzip.open(str(loc))
    else:
        file_ = loc.open()
    for i, line in enumerate(file_):
        freq, doc_freq, key = line.rstrip().split('\t', 2)
        freq = int(freq)
        counts.inc(i+1, freq)
        total += freq
    counts.smooth()
    log_total = math.log(total)
    if str(loc).endswith('gz'):
        file_ = gzip.open(str(loc))
    else:
        file_ = loc.open()

def make_matcher(patterns_path, text_path, counts_loc, n=10000000):
    nlp = English(parser=False, tagger=False, entity=False)
    print("Make matcher")
    phrases = read_gazetteer(nlp.tokenizer, patterns_path, n=n)
    counts = PreshCounter()
    for mwe in get_matches(nlp.tokenizer, phrases, open(text_path)):
        counts.inc(hash_string(mwe.text), 1)

    with codecs.open(counts_loc, 'w', 'utf8') as file_:
        for phrase in read_gazetteer(nlp.tokenizer, patterns_path, n=n):
            text = phrase.string
            key = hash_string(text)
            count = counts[key]
            if count != 0:
                file_.write('%d\t%s\n' % (count, text))

def __init__(self, directory, min_freq=10):
        self.directory = directory
        self.counts = PreshCounter()
        self.strings = {}
        self.min_freq = min_freq