Пример #1
0
    def getUserStatuses(self, screen_name):
        url = 'https://api.twitter.com/1.1/statuses/user_timeline.json'
        params = {'screen_name': screen_name, 'count': 100}
        psql = psql_save()

        req = self.api.get(url, params=params)
        if req.status_code == 200:
            req_text = json.loads(req.text)
            for status in req_text:
                try:
                    psql.insert_status(status['user']['id'],
                                       status['user']['screen_name'],
                                       status['id'], status['text'])
                except:
                    pass
        else:
            print("Error: %d at getUserInfo()" % req.status_code)
Пример #2
0
    def getUserInfo(self, query_screen_name, ids):
        url = 'https://api.twitter.com/1.1/users/lookup.json'
        ids = np.array(ids).astype(str)
        psql = psql_save()

        for i in range(0, len(ids), 100):
            _ids = ','.join(ids[i:i + 100])
            params = {'user_id': _ids}

            req = self.api.get(url, params=params)
            if req.status_code == 200:
                req_text = json.loads(req.text)
                for user in req_text:
                    try:
                        psql.insert_user_info(query_screen_name, user)
                    except:
                        print("Error: %d at getUserInfo()" % req.status_code)

            time.sleep(2 * random.uniform(0.5, 1.5))
Пример #3
0
    df_cmx = pd.DataFrame(cmx_data, index=labels, columns=labels)

    plt.figure(figsize = (10,7))
    sn.heatmap(df_cmx, annot=True)
    plt.show()

def cos_sim(v1, v2):
    res = np.dot(v1, v2) / (np.linalg.norm(v1) * np.linalg.norm(v2))
    if np.isnan(res):
      return 0
    else:
      return res

# DBから取得
db = psql_save()
rows = db.select_description_all()

with open("lang.json","rb") as f:
  lang_list = json.load(f)

# 正規表現の文字列作成
langnames = ["id"]
lang_regexes = []
for lang in lang_list:
  lang_regex = '|'.join(lang_list[lang])
  lang_regexes.append(lang_regex)
  langnames.append(lang) 

data = []
for row in rows: