def main(): mecab_file = open(sys.argv[1], "r") all_sentences = takayuki.make_morphdicts(mecab_file) mecab_file.close() for one_sentence in all_sentences: for morphdict in one_sentence: if morphdict["pos"] == "動詞": print morphdict["base"]
def main(): mecab_file = open(sys.argv[1], "r") all_sentences = takayuki.make_morphdicts(mecab_file) mecab_file.close() for one_sentence in all_sentences: for morphdict in one_sentence: if morphdict["pos"] == "動詞": print morphdict["surface"]
def main(): mecab_file = open(sys.argv[1], "r") all_sentences = takayuki.make_morphdicts(mecab_file) mecab_file.close() for one_sentence in all_sentences: for morphdict in one_sentence: if morphdict["pos"] == "名詞" and \ morphdict["pos1"] == "サ変可能": print morphdict["surface"]
def main(): mecab_file = open(sys.argv[1], "r") all_sentences = takayuki.make_morphdicts(mecab_file) mecab_file.close() for one_sentence in all_sentences: for index in range(1, len(one_sentence)): if one_sentence[index]["surface"] == "の": if one_sentence[index-1]["pos"] == "名詞" and \ one_sentence[index+1]["pos"] == "名詞": print one_sentence[index-1]["surface"]\ + one_sentence[index]["surface"]\ + one_sentence[index+1]["surface"]
def main(): mecab_file = open(sys.argv[1], "r") all_sentences = takayuki.make_morphdicts(mecab_file) mecab_file.close() count_word = defaultdict(lambda: 0) for one_sentence in all_sentences: for morphdict in one_sentence: count_word[morphdict["base"]] += 1 for word, count in sorted(count_word.items(), key=lambda x: -x[1]): print word + "\t" + str(count)
def main(): mecab_file = open(sys.argv[1], "r") all_sentences = takayuki.make_morphdicts(mecab_file) mecab_file.close() count_word = defaultdict(lambda: 0) for one_sentence in all_sentences: for morphdict in one_sentence: count_word[morphdict["base"]] += 1 for word, count in sorted(count_word.items(), key = lambda x:-x[1]): print word + "\t" + str(count)
def main(): mecab_file = open(sys.argv[1], "r") all_sentences = takayuki.make_morphdicts(mecab_file) mecab_file.close() length_dict = dict() nounstring = str() noun_count = 0 for one_sentence in all_sentences: for morphdict in one_sentence: if morphdict["pos"] == "名詞": nounstring += morphdict["surface"] noun_count += 1 else: length_dict[noun_count] = nounstring nounstring = str() noun_count = 0 print length_dict[max(length_dict.keys())]