Hugging Face's logo

justinsiow
/
schema_filter

Model card Files Community
schema_filter
File size: 4,634 Bytes 
1e712af
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
 
from schema_filter import filter_func

data = {
  "text": "Name movie titles released in year 1945. Sort the listing by the descending order of movie popularity.",
  "sql": "SELECT movie_title FROM movies WHERE movie_release_year = 1945 ORDER BY movie_popularity DESC LIMIT 1",
  "schema": {
    "schema_items": [
      {
        "table_name": "lists",
        "table_comment": "",
        "column_names": [
          "user_id",
          "list_id",
          "list_title",
          "list_movie_number",
          "list_update_timestamp_utc",
          "list_creation_timestamp_utc",
          "list_followers",
          "list_url",
          "list_comments",
          "list_description",
          "list_cover_image_url",
          "list_first_image_url",
          "list_second_image_url",
          "list_third_image_url"
        ],
        "column_comments": [
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          ""
        ]
      },
      {
        "table_name": "movies",
        "table_comment": "",
        "column_names": [
          "movie_id",
          "movie_title",
          "movie_release_year",
          "movie_url",
          "movie_title_language",
          "movie_popularity",
          "movie_image_url",
          "director_id",
          "director_name",
          "director_url"
        ],
        "column_comments": [
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          ""
        ]
      },
      {
        "table_name": "ratings_users",
        "table_comment": "",
        "column_names": [
          "user_id",
          "rating_date_utc",
          "user_trialist",
          "user_subscriber",
          "user_avatar_image_url",
          "user_cover_image_url",
          "user_eligible_for_trial",
          "user_has_payment_method"
        ],
        "column_comments": [
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          ""
        ]
      },
      {
        "table_name": "lists_users",
        "table_comment": "",
        "column_names": [
          "user_id",
          "list_id",
          "list_update_date_utc",
          "list_creation_date_utc",
          "user_trialist",
          "user_subscriber",
          "user_avatar_image_url",
          "user_cover_image_url",
          "user_eligible_for_trial",
          "user_has_payment_method"
        ],
        "column_comments": [
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          ""
        ]
      },
      {
        "table_name": "ratings",
        "table_comment": "",
        "column_names": [
          "movie_id",
          "rating_id",
          "rating_url",
          "rating_score",
          "rating_timestamp_utc",
          "critic",
          "critic_likes",
          "critic_comments",
          "user_id",
          "user_trialist",
          "user_subscriber",
          "user_eligible_for_trial",
          "user_has_payment_method"
        ],
        "column_comments": [
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          "",
          ""
        ]
      }
    ]
  }
}

def find_used_tables_and_columns(dataset):
    for data in dataset:
        sql = data["sql"].lower()
        data["table_labels"] = []
        data["column_labels"] = []
        
        for table_info in data["schema"]["schema_items"]:
            table_name = table_info["table_name"]
            data["table_labels"].append(1 if table_name.lower() in sql else 0)
            data["column_labels"].append([1 if column_name.lower() in sql else 0 \
                for column_name in table_info["column_names"]])
    return dataset

dataset = [data]

# 根据sql找到用到的表和列
dataset = find_used_tables_and_columns(dataset)

# 最多保留数据库中的6张表
num_top_k_tables = 6
# 对于每张保留的表，最多保留其中6个列，所以输入的prompt中最多有6*6=36个列
num_top_k_columns = 6

# 对于训练数据，我们可以根据sql来模拟filter的过程，这时，sic(schema item classifier)是None就行，不需要用到模型
dataset = filter_func(
    dataset = dataset, 
    dataset_type = "train",
    sic = None,
    num_top_k_tables = num_top_k_tables,
    num_top_k_columns = num_top_k_columns
)

print(dataset)