def get_comments_raw(oid: int,
type_: str,
order: str = "time",
pn: int = 1,
verify: utils.Verify = None):
"""
通用获取评论
:param oid:
:param type_:
:param order:
:param pn:
:param verify:
:return:
"""
if verify is None:
verify = utils.Verify()
type_ = COMMENT_TYPE_MAP.get(type_, None)
assert type_ is not None, exceptions.BilibiliApiException("不支持的评论类型")
order = COMMENT_SORT_MAP.get(order, None)
assert order is not None, exceptions.BilibiliApiException(
"不支持的排序方式，支持：time（时间倒序），like（热度倒序）")
# 参数检查完毕
params = {"oid": oid, "type": type_, "sort": order, "pn": pn}
#comment_api = API["common"]["comment"]
#api = comment_api.get("get", None)
api = {}
api["url"] = "https://api.bilibili.com/x/v2/reply"
resp = get_response(api["url"],
params=params,
cookies=verify.get_cookies())
return resp
def GetResult(model):
df = GetDataFrame()
dists = []
labels = []
for idx in tqdm(range(len(df))):
path1 = join(dir_image, df.loc[idx, 'img1'])
path2 = join(dir_image, df.loc[idx, 'img2'])
if (not isfile(path1)) or (not isfile(path2)):
continue
dist = Verify(path1, path2, model)
dists.append(dist)
labels.append(df.loc[idx, 'class'])
labels = np.array(labels)
dists = np.array(dists)
return labels, dists
def _VerifyFolder(path_to_folder, model):
paths = listdir(path_to_folder)
assert len(paths) == 2
path01 = join(path_to_folder, paths[0])
path02 = join(path_to_folder, paths[1])
dist = Verify(path01, path02, model)
result = 'same' if dist < threshold else 'different'
color = (0, 255, 0) if dist < threshold else (255, 0, 0)
img1 = Inputs2ArrayImage(path01, dtype=np.uint8)
img2 = Inputs2ArrayImage(path02, dtype=np.uint8)
img_merged = MergeImage(img1, img2, color=color)
name1 = _GetPersonName(paths[0])
name2 = _GetPersonName(paths[1])
title = '(' + name1 + ')' + ' - ' + result + ' - ' + '(' + name2 + ')'
return img_merged, title
d1 = env.from_elements(1, 6, 12)
d2 = env.from_elements((1, 0.5, "hello", True), (2, 0.4, "world", False))
d3 = env.from_elements(("hello",), ("world",))
d4 = env.from_elements((1, 0.5, "hello", True), (1, 0.4, "hello", False), (1, 0.5, "hello", True), (2, 0.4, "world", False))
d5 = env.from_elements((1, 2.4), (1, 3.7), (1, 0.4), (1, 5.4))
d6 = env.from_elements(1, 1, 12)
d7 = env.generate_sequence(0, 999)
#Generate Sequence Source
d7.map(Id()).map_partition(Verify(range(1000), "Sequence")).output()
#Zip with Index
#check that IDs (first field of each element) are consecutive
d7.zip_with_index()\
.map(lambda x: x[0])\
.map_partition(Verify(range(1000), "ZipWithIndex")).output()
#CSV Source/Sink
csv_data = env.read_csv("src/test/python/org/apache/flink/python/api/data_csv", (INT, INT, STRING))
csv_data.write_csv("/tmp/flink/result1", line_delimiter="\n", field_delimiter="|", write_mode=WriteMode.OVERWRITE)
#Text Source/Sink
text_data = env.read_text("src/test/python/org/apache/flink/python/api/data_text")
d5 = env.from_elements((4.4, 4.3, 1), (4.3, 4.4, 1), (4.2, 4.1, 3),
(4.1, 4.1, 3))
d6 = env.from_elements(1, 1, 12)
#Join
class Join(JoinFunction):
def join(self, value1, value2):
if value1[3]:
return value2[0] + str(value1[0])
else:
return value2[0] + str(value1[1])
d2 \
.join(d3).where(2).equal_to(0).using(Join()) \
.map_partition(Verify(["hello1", "world0.4"], "Join")).output()
d2 \
.join(d3).where(lambda x: x[2]).equal_to(0).using(Join()) \
.map_partition(Verify(["hello1", "world0.4"], "JoinWithKeySelector")).output()
d2 \
.join(d3).where(2).equal_to(0).project_first(0, 3).project_second(0) \
.map_partition(Verify([(1, True, "hello"), (2, False, "world")], "Project Join")).output()
d2 \
.join(d3).where(2).equal_to(0) \
.map_partition(Verify([((1, 0.5, "hello", True), ("hello",)), ((2, 0.4, "world", False), ("world",))], "Default Join")).output()
#Cross
class Cross(CrossFunction):
def cross(self, value1, value2):
return (value1, value2[3])
d1 \
################################################################################
from flink.plan.Environment import get_environment
from flink.functions.MapFunction import MapFunction
from flink.functions.CrossFunction import CrossFunction
from flink.functions.JoinFunction import JoinFunction
from flink.functions.CoGroupFunction import CoGroupFunction
from flink.functions.Aggregation import Max, Min, Sum
from utils import Verify, Verify2, Id
# Test multiple jobs in one Python plan file
if __name__ == "__main__":
env = get_environment()
env.set_parallelism(1)
d1 = env.from_elements(1, 6, 12)
d1 \
.first(1) \
.map_partition(Verify([1], "First with multiple jobs in one Python plan file")).output()
env.execute(local=True)
env2 = get_environment()
env2.set_parallelism(1)
d2 = env2.from_elements(1, 1, 12)
d2 \
.map(lambda x: x * 2) \
.map_partition(Verify([2, 2, 24], "Lambda Map with multiple jobs in one Python plan file")).output()
env2.execute(local=True)
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
################################################################################
from flink.plan.Environment import get_environment
import sys
from utils import Verify
if __name__ == "__main__":
env = get_environment()
d1 = env.from_elements(len(sys.argv))
d1.map_partition(Verify([1], "NoArgument")).output()
#Execution
env.set_parallelism(1)
env.execute(local=True)
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
################################################################################
from flink.plan.Environment import get_environment
import sys
from utils import Verify
if __name__ == "__main__":
env = get_environment()
d1 = env.from_elements(len(sys.argv))
d1.map_partition(Verify([3], "MultipleArguments")).output()
#Execution
env.set_parallelism(1)
env.execute(local=True)