add new tag3 cold start

eda/smart_rank/new_tag3_cold_start.py

+import json
+
+import redis
+from es_tool import es_query
+
+keywords = [
+    "瘦脸", "双眼皮", "补水", "美白嫩肤", "瘦小腿", "除皱", "隆鼻", "牙齿矫正", "脱毛", "祛斑", "控油", "面部祛脂", "隆胸", "垫鼻基底", "缩鼻翼", "生头发", "开眼角", "瘦肩", "祛痘",
+    "缩毛孔", "轮廓改善", "除眼底细纹", "眼部修复", "垫下巴", "颧骨内推", "除法令纹", "缩咬肌", "瘦臀部", "丰眼窝", "瘦手臂", "丰唇", "瘦腰腹", "瘦大腿", "填充泪沟", "洁面", "除面部细纹",
+    "上眼睑提升", "大眼睛", "缩短眼距离", "除印第安纹", "瘦全身", "下巴改善", "祛双下巴", "祛痘印", "眼部护理", "缩窄下巴", "缩短下巴", "填充苹果肌", "祛痘坑", "填充卧蚕"
+]
+
+
+def get_es_diary(keywords, city_tag_id=-1, version=False):
+    q = {}
+    sort_list = [{
+        "_script": {
+            "lang": "groovy",
+            "script_file": "sort_diary-recommend",
+            "type": "number",
+            "params": {
+                "user_city_tag_id": city_tag_id,
+            },
+            "order": "desc",
+            "_cache": True,
+        }
+    }]
+    if version:
+        sort_list += [{
+            "has_video_cover": {
+                "order": "asc"
+            }
+        }, {
+            "offline_score_v1": {
+                "order": "desc"
+            }
+        }, {
+            "good_click": {
+                "order": "desc"
+            }
+        }, {
+            "last_update_time": {
+                "order": "desc"
+            }
+        }]
+    else:
+        sort_list += [{
+            "has_video_cover": {
+                "order": "asc"
+            }
+        }, {
+            "offline_score": {
+                "order": "desc"
+            }
+        }, {
+            "good_click": {
+                "order": "desc"
+            }
+        }, {
+            "last_update_time": {
+                "order": "desc"
+            }
+        }]
+    should_list = [{
+        "terms": {
+            "first_demands": keywords
+        }
+    }, {
+        "terms": {
+            "second_demands": keywords
+        }
+    }, {
+        "terms": {
+            "first_solutions": keywords
+        }
+    }, {
+        "terms": {
+            "second_solutions": keywords
+        }
+    }, {
+        "terms": {
+            "positions": keywords
+        }
+    }, {
+        "terms": {
+            "second_positions": keywords
+        }
+    }, {
+        "terms": {
+            "tags_v3": keywords
+        }
+    }]
+    q["query"] = {
+        "bool": {
+            "filter": [{
+                "term": {
+                    "is_online": True
+                }
+            }, {
+                "term": {
+                    "has_cover": True
+                }
+            }, {
+                "term": {
+                    "is_sink": False
+                }
+            }, {
+                "term": {
+                    "has_after_cover": True
+                }
+            }, {
+                "term": {
+                    "has_before_cover": True
+                }
+            }, {
+                "terms": {
+                    "content_level": [6, 5, 4, 3.5, 3]
+                }
+            }],
+            "should":
+            should_list,
+            "minimum_should_match":
+            1
+        }
+    }
+    q["sort"] = sort_list
+    q["_source"] = {"includes": ["id", "second_demands"]}
+    es_res = es_query("diary", q, offset=0, size=500)
+    diary_ids = []
+    for diary_info in es_res["hits"]["hits"]:
+        diary_ids.append(diary_info["_source"]["id"])
+    return diary_ids
+
+
+if __name__ == "__main__":
+    ids = get_es_diary(keywords)
+    print(ids)