我需要根据时间戳搜索索引。
文档具有以下字段组合：
或
伪查询：。
对于给定的时间戳，我希望返回ID匹配的所有文档，并且：
timestamp >= start_time && timestamp < end_time
但如果没有end_time字段，则查询必须为：
(not exists end_time) && (timestamp > start_time)
弹性查询。 这就是我生气的地方。我无法获得与上述伪查询相当的弹性查询。也许我正以错误的方式（完全可能）接近它。这是我所拥有的：
{
"query": {
"bool": {
"must": [
{
"term": {
"id_s": "SomeIdValue"
}
},
{
"bool": {
"should": [
{
"must": [
{
"must_not": [
{
"exists": {
"field": "end_time_dt"
}
}
]
},
{
"range": {
"start_time_dt": {
"lte": "2019-07-12T03:20:22"
}
}
}
]
},
{
"filter": [
{
"range": {
"start_time_dt": {
"lte": "2019-07-12T03:20:22"
}
}
},
{
"range": {
"end_time_dt": {
"gte": "2019-07-12T03:20:22"
}
}
}
]
}
]
}
}
]
}
}
}
但这给了我[must] query malformed, no start_object after query name
如何构造此查询？我在正确的轨道上吗？
提前谢谢！
答案 0 :(得分：1)
您的查询在语法上是错误的。正确的查询是：
{{1}}
答案 1 :(得分：0)
逻辑上有一个小错误。理想情况下，比较应该像这样gte start_time_dt和lte end_time_dt。您进行了其他操作，以便转换为时间戳<= start_time &&时间戳> end_time。
正确的查询是
{
"query": {
"bool": {
"filter": [
{
"term": {
"id_s": "SomeIdValue"
}
},
{
"bool": {
"should": [
{
"bool": {
"must_not": [
{
"exists": {
"field": "end_time_dt"
}
}
],
"must": [
{
"range": {
"start_time_dt": {
"gte": "2019-07-12T03:20:22"
}
}
}
]
}
},
{
"bool": {
"must": [
{
"range": {
"start_time_dt": {
"gte": "2019-07-12T03:20:22"
}
}
},
{
"range": {
"end_time_dt": {
"lte": "2019-07-12T03:20:22"
}
}
}
]
}
}
]
}
}
]
}
}
}
希望这会有所帮助！
答案 2 :(得分：0)
我相信答案应该是class DataGenerator(keras.utils.Sequence):
"""Generates data for Keras."""
def __init__(self,csv_path ,batch_size=32, dim=(224, 224), n_channels=3,
n_classes=8, shuffle=True):
self.img_files = pd.read_csv(csv_path)
self.labels = self.img_files.iloc[:, 7:16].values
self.batch_size = batch_size
self.dim = dim
self.n_channels = n_channels
self.n_classes = n_classes
self.shuffle = shuffle
self.on_epoch_end()
def __len__(self):
"""Denotes the number of batches per epoch."""
return int(np.floor(len(self.img_files) / self.batch_size))
def __getitem__(self, index):
indexes = self.indexes[index*self.batch_size:(index+1)*self.batch_size]
# Find list of IDs
img_files_temp = [self.img_files['Left-Fundus'][k] for k in indexes]
X, y = self.__data_generation(img_files_temp)
return X, y
def on_epoch_end(self):
"""Updates indexes after each epoch."""
self.indexes = np.arange(len(self.img_files))
if self.shuffle == True:
np.random.shuffle(self.indexes)
def __data_generation(self, img_files_temp):
X = np.empty((self.batch_size,self.dim[0], self.dim[1], self.n_channels))
y = np.empty((self.batch_size, self.n_classes))
for i, img_file in enumerate(img_files_temp):
img = skimage.io.imread(os.path.join('../Customized-DataLoader/data/train_img', img_file))
img = skimage.transform.resize(img, output_shape=self.dim, mode='constant', preserve_range=True)
X[i,:,:,:] = img
index_of_label= int(self.img_files.index[self.img_files['Left-Fundus'] ==img_file][0])
if len(self.img_files.loc[index_of_label][7:16].values)!= 8:
continue
y[:,] = self.img_files.loc[index_of_label][7:16].values
return X, y
model = keras.applications.densenet.DenseNet121(include_top=False, input_shape=(224, 224, 3))
x = model.output
x = Flatten()(x)
x = Dense(512)(x)
x = Activation('relu')(x)
x = Dropout(0.5)(x)
output1 = Dense(1, activation = 'sigmoid')(x)
output2 = Dense(1, activation = 'sigmoid')(x)
output3 = Dense(1, activation = 'sigmoid')(x)
output4 = Dense(1, activation = 'sigmoid')(x)
output5 = Dense(1, activation = 'sigmoid')(x)
output6 = Dense(1, activation = 'sigmoid')(x)
output7 = Dense(1, activation = 'sigmoid')(x)
output8 = Dense(1, activation = 'sigmoid')(x)
model = Model(model.inputs,[output1,output2,output3,output4,output5, output6, output7, output8])
# print(model.summary())
model.compile(optimizers.rmsprop(lr = 0.0001, decay = 1e-6),
loss = ["binary_crossentropy","binary_crossentropy","binary_crossentropy","binary_crossentropy", "binary_crossentropy","binary_crossentropy","binary_crossentropy","binary_crossentropy"],metrics = ["accuracy"])
def generator_wrapper(generator):
for batch_x,batch_y in generator:
yield (batch_x,[batch_y[:,i] for i in range(8)])
train_file = pd.read_csv('train.csv')
test_file = pd.read_csv('test.csv')
train_generator = DataGenerator(csv_path = 'train.csv')
valid_generator = DataGenerator(csv_path = 'test.csv')
batch_size = 32
num_epochs = 1
STEP_SIZE_VALID =len(train_file)//batch_size
STEP_SIZE_TRAIN=len(test_file)//batch_size
model.fit_generator(generator=generator_wrapper(train_generator),
steps_per_epoch=STEP_SIZE_TRAIN,validation_data=generator_wrapper(valid_generator),
validation_steps=STEP_SIZE_VALID,
epochs=5,verbose=1, workers =12,use_multiprocessing=True)
而不是must。我说这两个条件的原因：我认为OP意图是必须（不存在AND范围）
should