Skip to content

F
ffm-baseline
Commit a66215bd authored by 张彦钊's avatar 张彦钊
Browse files
Options

add

parent a803c722
Show whitespace changes
Inline Side-by-side
Showing with 407 additions and 28 deletions
es_tag.py
View file @ a66215bd
......@@ -56,11 +56,11 @@ def es_query(doc, body, offset, size, es=None):
from_=offset,
size=size)
number = res["hits"]["total"]
number = res["hits"]["total"] or 0
return number
def question():
def answer():
tags = ["下颌角切除术", "M唇", "瘦身", "抽脂", "隆胸", "丰乳房", "孕睫术", "眶隔脂肪释放术", "小腿神经阻断术", '瘦脸针',
'水光针',
'光子嫩肤',
......@@ -244,6 +244,380 @@ def question():
for i in tags:
tmp = [i]
query = i
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": {
"content_level": 3
}
}]
}
}
}
}
}
tmp.append(es_query('answer', 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
}
}]
}
}
}
}
}
tmp.append(es_query('answer', 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
}
}]
}
}
}
}
}
tmp.append(es_query('answer', 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": {
"content_type": 1
}
}, {"term": {
"content_level": 3
}
}]
}
}
}
}
}
tmp.append(es_query('answer', 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": {
"content_type": 1
}
}, {"term": {
"content_level": 4
}
}]
}
}
}
}
}
tmp.append(es_query('answer', 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": {
"content_type": 1
}
}, {"term": {
"content_level": 5
}
}]
}
}
}
}
}
tmp.append(es_query('answer', video_star5_q, 0, 1))
total_list.append(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)
def question():
tags = ["下颌角切除术", "M唇", "瘦身", "抽脂", "隆胸", "丰乳房", "孕睫术", "眶隔脂肪释放术", "小腿神经阻断术", '瘦脸针',
'水光针',
'光子嫩肤',
'热玛吉',
'瘦腿针',
'超声刀',
'面部吸脂',
'瘦肩针',
'皮秒',
'果酸焕肤',
'热拉提',
'微针',
'牙齿矫正',
'超皮秒',
'点阵激光',
'植发',
'小气泡',
'双眼皮修复',
'自体脂肪隆胸',
'鼻翼缩小',
'假体隆胸',
'玻尿酸丰下巴',
'埋线双眼皮',
'纹眉',
'颧骨内推',
'拉皮',
'玻尿酸隆鼻',
'女性私密紧致',
'嗨体',
'溶脂针瘦脸',
'黄金微针',
'磨骨',
'肋骨鼻',
'洗牙',
'植发际线',
'光纤溶脂',
'点痣',
'下颌角切除',
'切开双眼皮',
'腰腹吸脂',
'激光祛斑',
'白瓷娃娃',
'大腿吸脂',
'假体下巴',
'除皱针注射',
'溶解酶',
'吸脂瘦手臂',
'微针祛痘坑',
'厚唇改薄',
'玻尿酸',
'大分子玻尿酸',
'耳软骨',
'鼻中隔软骨',
'肋软骨',
'硅胶',
'膨体',
'假体',
'自体真皮',
'自体脂肪',
'自体软骨',
'自体血清',
'溶解酶',
'嗨体',
'胶原蛋白',
'双美胶原蛋白',
'黄金',
'药物',
'生长因子',
'肉毒素',
'埋线提升',
'悦升线',
'蛋白线',
'水杨酸',
'果酸',
'杏仁酸',
'奥美定',
'干细胞',
'纳米树脂',
'黑脸娃娃',
'眼睑下至',
'童颜针',
'微笑唇',
'减肥',
'瘦身',
'隆鼻',
'V脸',
'祛斑',
'祛痣',
'祛黑头',
'祛疤',
'祛痘',
'溶脂',
'吸脂',
'嘟嘟唇',
'丰唇',
'丰下巴',
'丰胸',
'皮秒',
'蜂巢皮秒',
'超皮秒',
'深蓝射频',
'美瞳',
'提眉',
'纹眉',
'孕睫',
'瓷贴面',
'全瓷牙',
'美容冠',
'黄金微雕',
'微雕',
'削骨',
'截骨',
'脂肪胶',
'prp',
'轮廓针',
'水光针',
'婴儿针',
'三文鱼针',
'少女针',
'素颜针',
'瘦脸针',
'熊猫针',
'瘦腿针',
'小气泡',
'正颌',
'一针降颧骨',
'脱毛',
'近视',
'面部提升',
'嫩肤',
'镭射净肤',
'红蓝光',
'二氧化碳点阵',
'狐臭',
'清洁',
'补水',
'内窥镜',
'热立塑',
'威塑',
'优立塑',
'酷塑',
'调Q激光',
'DPL',
'染料激光',
'体检',
'产后',
'正骨术',
'隔空溶脂',
'pst',
'唇裂',
'塑身',
'微晶瓷',
'ICL晶体植入',
'全飞秒',
'半飞秒',
'根管治疗',
'抗衰',
'紧致',
'飞梭雷射',
'三点双眼皮',
'颊脂垫',
'嫩红',
'眶隔脂肪释放',
'针清',
'美白',
'冷光美白',
'美白仓',
'小腿神经阻断',
'正畸',
'变性',
'干细胞疗法',
'月光脱毛',
'火凤凰溶脂',
'微拉美',
'剥落点阵',
'非剥落点阵']
total_list = []
query_operator = "and"
query_type = "cross_fields"
category = 'question'
for i in tags:
tmp = [i]
query = i
# TODO 下面两个q语句
q = {
"query": {"filtered": {
"filter": {
......@@ -266,7 +640,7 @@ def question():
}
}
}
tmp.append(es_query('answer', q, 0, 1))
tmp.append(es_query(category, q, 0, 1))
video_q = {
"query": {
......@@ -295,7 +669,7 @@ def question():
}
}
}
tmp.append(es_query('answer', video_q, 0, 1))
tmp.append(es_query(category, video_q, 0, 1))
total_list.append(tmp)
print(i)
......@@ -303,11 +677,11 @@ def question():
df = pd.DataFrame(total_list)
df = df.rename(columns={0: "tag", 1: "number", 2: "video_number"})
df.to_csv("/home/gmuser/qa.csv", index=False)
df.to_csv("/home/gmuser/question.csv", index=False)
if __name__ == "__main__":
tags = ["下颌角切除术","M唇","瘦身","抽脂","隆胸","丰乳房","孕睫术","眶隔脂肪释放术","小腿神经阻断术",'瘦脸针',
def topic():
tags = ["下颌角切除术", "M唇", "瘦身", "抽脂", "隆胸", "丰乳房", "孕睫术", "眶隔脂肪释放术", "小腿神经阻断术", '瘦脸针',
'水光针',
'光子嫩肤',
'热玛吉',
......@@ -486,6 +860,7 @@ if __name__ == "__main__":
total_list = []
query_operator = "and"
query_type = "cross_fields"
category = 'tractate'
for i in tags:
tmp = [i]
......@@ -505,7 +880,7 @@ if __name__ == "__main__":
"term": {
"is_online": True
}
},{"term": {
}, {"term": {
"content_level": 3
}
}]
......@@ -515,7 +890,7 @@ if __name__ == "__main__":
}
}
}
tmp.append(es_query('answer', star3_q, 0, 1))
tmp.append(es_query(category, star3_q, 0, 1))
star4_q = {
"query": {
......@@ -533,7 +908,7 @@ if __name__ == "__main__":
"term": {
"is_online": True
}
},{"term": {
}, {"term": {
"content_level": 4
}
}]
......@@ -543,7 +918,7 @@ if __name__ == "__main__":
}
}
}
tmp.append(es_query('answer', star4_q, 0, 1))
tmp.append(es_query(category, star4_q, 0, 1))
star5_q = {
"query": {
......@@ -561,7 +936,7 @@ if __name__ == "__main__":
"term": {
"is_online": True
}
},{"term": {
}, {"term": {
"content_level": 5
}
}]
......@@ -571,7 +946,7 @@ if __name__ == "__main__":
}
}
}
tmp.append(es_query('answer', star5_q, 0, 1))
tmp.append(es_query(category, star5_q, 0, 1))
video_star3_q = {
"query": {
......@@ -589,11 +964,11 @@ if __name__ == "__main__":
"term": {
"is_online": True
}
},{
}, {
"term": {
"content_type": 1
"is_video": True
}
},{"term": {
}, {"term": {
"content_level": 3
}
}]
......@@ -603,7 +978,7 @@ if __name__ == "__main__":
}
}
}
tmp.append(es_query('answer', video_star3_q, 0, 1))
tmp.append(es_query(category, video_star3_q, 0, 1))
video_star4_q = {
"query": {
......@@ -621,11 +996,11 @@ if __name__ == "__main__":
"term": {
"is_online": True
}
},{
}, {
"term": {
"content_type": 1
"is_video": True
}
},{"term": {
}, {"term": {
"content_level": 4
}
}]
......@@ -635,7 +1010,7 @@ if __name__ == "__main__":
}
}
}
tmp.append(es_query('answer', video_star4_q, 0, 1))
tmp.append(es_query(category, video_star4_q, 0, 1))
video_star5_q = {
"query": {
......@@ -653,11 +1028,11 @@ if __name__ == "__main__":
"term": {
"is_online": True
}
},{
}, {
"term": {
"content_type": 1
"is_video": True
}
},{"term": {
}, {"term": {
"content_level": 5
}
}]
......@@ -667,15 +1042,19 @@ if __name__ == "__main__":
}
}
}
tmp.append(es_query('answer', video_star5_q, 0, 1))
tmp.append(es_query(category, video_star5_q, 0, 1))
total_list.append(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/qa.csv",index = False)
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)
if __name__ == "__main__":
answer()
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