tfidf.py 文件源码

def set_new_path(self, new_idf_path):
        if self.path != new_idf_path:
            self.path = new_idf_path
            cache_file = "idf.cache"
            cache_file = os.path.join(tempfile.gettempdir(), cache_file)
            try:
                with open(cache_file, 'rb') as cf:
                    self.idf_freq, self.median_idf = marshal.load(cf)
                # print("Loading model from cache %s" % cache_file)
            except Exception:
                content = open(new_idf_path, 'rb').read().decode('utf-8')
                self.idf_freq = {}
                for line in content.splitlines():
                    word, freq = line.strip().split(' ')
                    self.idf_freq[word] = float(freq)
                self.median_idf = sorted(
                    self.idf_freq.values())[len(self.idf_freq) // 2]
                with open(cache_file, 'wb') as cf:
                    marshal.dump((self.idf_freq, self.median_idf), cf)