Skip to content

F
ffm-baseline
Commit 3db822c1 authored by 张彦钊's avatar 张彦钊
Browse files
Options

add

parent a66215bd
Hide whitespace changes
Inline Side-by-side
Showing with 144 additions and 122 deletions
es_tag.py
View file @ 3db822c1
......@@ -56,7 +56,7 @@ def es_query(doc, body, offset, size, es=None):
from_=offset,
size=size)
number = res["hits"]["total"] or 0
number = res["hits"]["total"]
return number
......@@ -424,13 +424,13 @@ def answer():
tmp.append(es_query('answer', video_star5_q, 0, 1))
total_list.append(tmp)
print(i)
print(tmp)
# print(i)
# print(tmp)
df = pd.DataFrame(total_list)
df = df.rename(columns={0: "tag", 1: "star_3", 2: "star_4", 3: "star_5",
4: "video_star_3", 5: "video_star_4", 6: "video_star_5"})
df.to_csv("/home/gmuser/answer.csv", index=False)
df.to_csv("/home/gmuser/answer.csv", index=False, encoding="utf_8_sig")
def question():
......@@ -617,14 +617,13 @@ def question():
for i in tags:
tmp = [i]
query = i
# TODO 下面两个q语句
q = {
"query": {"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["title^1", "desc^1", "answer^1"],
"fields": ["title^1", "content^1", "tags^1"],
"operator": query_operator,
"type": query_type,
"query": query
......@@ -649,7 +648,7 @@ def question():
"bool": {
"must": [{
"multi_match": {
"fields": ["title^1", "desc^1", "answer^1"],
"fields": ["title^1", "content^1", "tags^1"],
"operator": query_operator,
"type": query_type,
"query": query
......@@ -672,12 +671,12 @@ def question():
tmp.append(es_query(category, video_q, 0, 1))
total_list.append(tmp)
print(i)
print(tmp)
# print(i)
# print(tmp)
df = pd.DataFrame(total_list)
df = df.rename(columns={0: "tag", 1: "number", 2: "video_number"})
df.to_csv("/home/gmuser/question.csv", index=False)
df.to_csv("/home/gmuser/question.csv", index=False, encoding="utf_8_sig")
def topic():
......@@ -871,7 +870,8 @@ def topic():
"bool": {
"must": [{
"multi_match": {
"fields": ["title^1", "desc^1", "answer^1"],
"fields": ["content^1", "author^1", "tractate_tag_name^1",
"tractate_tag_name_content^1"],
"operator": query_operator,
"type": query_type,
"query": query
......@@ -883,7 +883,12 @@ def topic():
}, {"term": {
"content_level": 3
}
}]
},
{
"term": {
"status": "3"
}
}]
}
}
......@@ -893,168 +898,185 @@ def topic():
tmp.append(es_query(category, star3_q, 0, 1))
star4_q = {
"query": {
"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["title^1", "desc^1", "answer^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}, {"term": {
"content_level": 4
"query": {"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["content^1", "author^1", "tractate_tag_name^1",
"tractate_tag_name_content^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}]
}, {
"term": {
"is_online": True
}
}, {"term": {
"content_level": 4
}
},
{
"term": {
"status": "3"
}
}]
}
}
}
}
}
tmp.append(es_query(category, star4_q, 0, 1))
star5_q = {
"query": {
"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["title^1", "desc^1", "answer^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}, {"term": {
"content_level": 5
"query": {"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["content^1", "author^1", "tractate_tag_name^1",
"tractate_tag_name_content^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}]
}, {
"term": {
"is_online": True
}
}, {"term": {
"content_level": 5
}
},
{
"term": {
"status": "3"
}
}]
}
}
}
}
}
tmp.append(es_query(category, star5_q, 0, 1))
video_star3_q = {
"query": {
"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["title^1", "desc^1", "answer^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}, {
"term": {
"is_video": True
}
}, {"term": {
"content_level": 3
"query": {"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["content^1", "author^1", "tractate_tag_name^1",
"tractate_tag_name_content^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}]
}, {
"term": {
"is_online": True
}
}, {"term": {
"content_level": 3
}
},
{
"term": {
"status": "3"
}
}, {"term": {"is_video": True}}]
}
}
}
}
}
tmp.append(es_query(category, video_star3_q, 0, 1))
video_star4_q = {
"query": {
"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["title^1", "desc^1", "answer^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}, {
"term": {
"is_video": True
}
}, {"term": {
"content_level": 4
"query": {"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["content^1", "author^1", "tractate_tag_name^1",
"tractate_tag_name_content^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}]
}, {
"term": {
"is_online": True
}
}, {"term": {
"content_level": 4
}
},
{
"term": {
"status": "3"
}
}, {"term": {"is_video": True}}]
}
}
}
}
}
tmp.append(es_query(category, video_star4_q, 0, 1))
video_star5_q = {
"query": {
"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["title^1", "desc^1", "answer^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}, {
"term": {
"is_video": True
}
}, {"term": {
"content_level": 5
"query": {"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["content^1", "author^1", "tractate_tag_name^1",
"tractate_tag_name_content^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}]
}, {
"term": {
"is_online": True
}
}, {"term": {
"content_level": 5
}
},
{
"term": {
"status": "3"
}
}, {"term": {"is_video": True}}]
}
}
}
}
}
tmp.append(es_query(category, video_star5_q, 0, 1))
total_list.append(tmp)
print(i)
print(tmp)
# print(i)
# print(tmp)
df = pd.DataFrame(total_list)
df = df.rename(columns={0: "tag", 1: "star_3", 2: "star_4", 3: "star_5",
4: "video_star_3", 5: "video_star_4", 6: "video_star_5"})
df.to_csv("/home/gmuser/topic.csv", index=False)
df.to_csv("/home/gmuser/topic.csv", index=False, encoding="utf_8_sig")
if __name__ == "__main__":
answer()
topic()
print("topic")
question()
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment