Python load bin vec

8 Python code examples are found related to " load bin vec". You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example.
Example 1
Source File: process_sst2_data.py    From crnn with MIT License 6 votes vote down vote up 
def load_bin_vec(fname, vocab):
    """
    Loads 300x1 word vecs from Google (Mikolov) word2vec
    """
    word_vecs = {}
    with open(fname, "rb") as f:
        header = f.readline()
        vocab_size, layer1_size = map(int, header.split())
        binary_len = np.dtype('float32').itemsize * layer1_size
        for line in xrange(vocab_size):
            word = []
            while True:
                ch = f.read(1)
                if ch == ' ':
                    word = ''.join(word)
                    break
                if ch != '\n':
                    word.append(ch)
            if word in vocab:
               word_vecs[word] = np.fromstring(f.read(binary_len), dtype='float32')
            else:
                f.read(binary_len)
    return word_vecs
Example 2
Source File: preprocess_trec.py    From sentence_classification with MIT License 6 votes vote down vote up 
def load_bin_vec(fname, vocab):
    """
    Loads 300x1 word vecs from Google (Mikolov) word2vec
    """
    word_vecs = {}
    with open(fname, "rb") as f:
        header = f.readline()
        vocab_size, layer1_size = map(int, header.split())
        binary_len = np.dtype('float32').itemsize * layer1_size
        for line in xrange(vocab_size):
            word = []
            while True:
                ch = f.read(1)
                if ch == ' ':
                    word = ''.join(word)
                    break
                if ch != '\n':
                    word.append(ch)   
            if word in vocab:
               word_vecs[word] = np.fromstring(f.read(binary_len), dtype='float32')  
            else:
                f.read(binary_len)
    return word_vecs
Example 3
Source File: process_data.py    From personality-detection with MIT License 6 votes vote down vote up 
def load_bin_vec(fname, vocab):
    """
    Loads 300x1 word vecs from Google (Mikolov) word2vec
    """
    word_vecs = {}
    with open(fname, "rb") as f:
        header = f.readline()
        vocab_size, layer1_size = map(int, header.split())
        binary_len = np.dtype(theano.config.floatX).itemsize * layer1_size
        for line in xrange(vocab_size):
            word = []
            while True:
                ch = f.read(1)
                if ch == ' ':
                    word = ''.join(word)
                    break
                if ch != '\n':
                    word.append(ch)
            if word in vocab:
               word_vecs[word] = np.fromstring(f.read(binary_len), dtype=theano.config.floatX)
            else:
                f.read(binary_len)
    return word_vecs
Example 4
Source File: utils.py    From HATN with MIT License 6 votes vote down vote up 
def load_bin_vec(fname, vocab):
    """
    Loads 300x1 word vecs from Google (Mikolov) word2vec
    """
    word_vecs = {}
    with open(fname, "rb") as f:
        header = f.readline()
        vocab_size, layer1_size = map(int, header.split())
        binary_len = np.dtype('float32').itemsize * layer1_size
        for line in xrange(vocab_size):
            word = []
            while True:
                ch = f.read(1)
                if ch == ' ':
                    word = ''.join(word)
                    break
                if ch != '\n':
                    word.append(ch)
            if word in vocab:
                word_vecs[word] = np.fromstring(f.read(binary_len), dtype='float32')
            else:
                f.read(binary_len)
    return word_vecs
Example 5
Source File: data_helpers.py    From qclass_dl with GNU General Public License v3.0 6 votes vote down vote up 
def load_bin_vec(fname, vocab):
    """
    Loads 300x1 word vecs from Google (Mikolov) word2vec
    """
    word_vecs = {}
    with open(fname, "rb") as f:
        header = f.readline()
        vocab_size, layer1_size = map(int, header.split())
        binary_len = np.dtype('float32').itemsize * layer1_size
        for line in xrange(vocab_size):
            word = []
            while True:
                ch = f.read(1)
                if ch == ' ':
                    word = ''.join(word)
                    break
                if ch != '\n':
                    word.append(ch)
            if word in vocab:
                word_vecs[word] = np.fromstring(f.read(binary_len), dtype='float32')  
            else:
                f.read(binary_len)
    return word_vecs
Example 6
Source File: ii_data_process.py    From pick_a_name with GNU General Public License v3.0 5 votes vote down vote up 
def load_bin_vec(fname):
    """
    加载 400x1 自训练的char2vecs。
    char2vecs是一个dict，key是word，value是vector。
    """
    char2vecs = {}
    with open(fname, "rb") as f:
        header = f.readline()
        char_num, vector_dim = map(int, header.split())
        # print char_num, vector_dim
        for line in xrange(char_num):
            ch = f.read(3)
            char2vecs[ch] = np.asarray(map(float, f.readline().split()), dtype="float32")
    return char2vecs