Пример #1
0
def convert_pm(pm, us_pm, r):
    crawling = Crawling()
    pm_ = []
    # extract stations class
    for d in pm:
        pr = []
        for s in us_pm:
            v = d[s] * r
            #pr.append(get_aqi_class(crawling.AQIPM25(v)))
            pr.append(crawling.aqi_pm25_china_class(v))
        pm_.append(pr)

    # extract class for all pixels
    # for d in pm:
    #     pr = []
    #     for idx in d:
    #         pr.append(get_aqi_class(crawling.AQIPM25(idx)))
    #     pm_.append(pr)
    return pm_
Пример #2
0
def evaluate_china(url,
                   url2,
                   stations,
                   encoder_length=12,
                   decoder_length=24,
                   eval_stat=False):
    cr = Crawling()
    # missing = [136,156,824,1028,1053,1084,1085,1457,1460,1461,1462,1464,1465,1476,1477, \
    #         1478,1479,1481,1482,1484,1485,1486,1487,1510,1841,3814,4246,4268,4301,4311, \
    #         4313,4317,4329,4331,4333,4349,4360,4504,4524,4529,4532,4535,4580,4860,5270, \
    #         5457,5489,5509,5962,6007,6011,6039,6054,6125,6172,6189,6192,6201,6230,6234, \
    #         6246,6254,6255,6256,6257,6258,6295,6300,6319,6336,6356,6362,6371,6372,6394, \
    #         6491,6492,6493,6494,6497,6517,6519,6523,6539,6559,6564,6568,6569,6570,6612, \
    #         6613,6614,6615,6616,6617,6618,6619,6620,6621,6622,6623,6624,6625,6626,6627, \
    #         6628,6629,6630,6631,6632,6633,6634,6635,6636,6637,6638,6687,6704,6754,6832, \
    #         6849,6858,6873,6979,7255,8099,8100,8101,8225,8226,8227,8228,8229,8230,8231, \
    #         8232,8233,8234,8235,8236,8237,8238,8239,8240,8241,8273,8274,8275,8276,8277, \
    #         8278,8279,8280,8281,8282,8283,8284,8285,8286,8287,8288,8289,8290,8291,8344, \
    #         8421,8422,8423,8424,8425,8426,8427,8428,8429,8430,8431,8432,8495,8496,8497, \
    #         8498,8499,8500,8501,8502,8503,8504,8631,8759]
    data = utils.load_file(url)
    labels = utils.load_file(url2)
    if type(data) is list:
        data = np.asarray(data)
    if len(data.shape) == 4:
        lt = data.shape[0] * data.shape[1]
        data = np.reshape(data, (lt, data.shape[-2], data.shape[-1]))
        labels = np.reshape(labels, (lt, data.shape[-2], data.shape[-1]))
    else:
        lt = len(data)
        data = np.array(data)
        labels = np.array(labels)
    if not eval_stat:
        loss_mae = [0.0] * decoder_length
    else:
        loss_mae = np.array([[0.0] * decoder_length] * len(stations))
    classes = [0.0] * decoder_length
    # loss_lt = 0
    loss_total = [0.0] * decoder_length
    # ckt = 0
    valid = []
    for i, (d_, l_) in enumerate(zip(data, labels)):
        # st = 2 * i
        # ed = st + decoder_length
        # flag = False
        # for ck in range(st, ed):
        #     if ck in missing:
        #         flag = True
        #         break
        # if flag:
        #     continue
        d = d_[:decoder_length, :]
        lbt = l_[:decoder_length, :]
        for t_i, (t, l_t) in enumerate(zip(d, lbt)):
            pred_t = []
            label_t = []
            for r in stations:
                #pred_t.append(t[r])
                #label_t.append(l_t[r])
                # if not math.isnan(t[r]):
                pr = t[r]
                if pr < 0:
                    pr = 0
                print(pr)
                pred_t.append(cr.aqi_pm25_china(pr))
                label_t.append(cr.aqi_pm25_china(l_t[r] * 300))
                # label_t.append(l_t[r])
                # print(t[r], l_t[r])
            # if pred_t:
            if not eval_stat:
                mae = mean_absolute_error(pred_t, label_t)
                classes[t_i] += accuracy_score(
                    [cr.aqi_pm25_china_class(x) for x in pred_t],
                    [cr.aqi_pm25_china_class(x) for x in label_t])
                if mae > 80:
                    valid.append("%i,%i" % (i, t_i))
                if mae < 80:
                    loss_total[t_i] += 1
                    loss_mae[t_i] += mae
            else:
                mae = [abs(p_s - l_s) for p_s, l_s in zip(pred_t, label_t)]
                for m_i, m in enumerate(mae):
                    loss_mae[m_i, t_i] += m
        # loss_lt += 1
        # utils.update_progress((i + 1.0) / lt)
    va = "\n".join(valid)
    save_file("outline_china", va, False)
    loss_mae = [x / y if y > 0 else 0 for x, y in zip(loss_mae, loss_total)]
    for i, x in enumerate(loss_mae):
        # if not eval_stat:
        print(x, loss_total[i])
        # else:
        # print([y/loss_lt for y in x])
    # print("accumulated:", np.mean(loss_mae[1:6]))
    print(np.array(classes) / lt)