File size: 3,451 Bytes
5ec2fc9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import json
import pandas as pd

from Data.database.sql_connector import engine
from src.similarity_model.preprocessing import preprocess_dataset
from src.similarity_model.embedding_engine import (
    train_embedding_engine
)


def sync_projects():

    projects_query = """
    SELECT *
    FROM Projects
    WHERE Status IN (
        'Completed',
        'UnderReview',
        'In_Progress'
    )
    """

    projects_df = pd.read_sql(
        projects_query,
        engine
    )

    existing_df = pd.read_sql(
        """
        SELECT id
        FROM PreProcessed_Projects
        """,
        engine
    )

    allowed_ids = set(
        projects_df["Id"].tolist()
    )

    processed_ids = set(
        existing_df["id"].tolist()
    )

    # ---------------------------------
    # Remove projects no longer allowed
    # ---------------------------------

    ids_to_remove = (
        processed_ids - allowed_ids
    )

    changed = False

    if ids_to_remove:

        ids_str = ",".join(
            map(str, ids_to_remove)
        )

        with engine.begin() as conn:

            conn.exec_driver_sql(
                f"""
                DELETE FROM PreProcessed_Projects
                WHERE id IN ({ids_str})
                """
            )

        print(
            f"Removed {len(ids_to_remove)} projects"
        )

        changed = True

    # ---------------------------------
    # Add new projects
    # ---------------------------------

    new_projects = projects_df[
        ~projects_df["Id"].isin(
            processed_ids
        )
    ].copy()

    if len(new_projects) > 0:

        print(
            f"Found {len(new_projects)} new projects"
        )

        processed_df = preprocess_dataset(
            new_projects
        )

        processed_df = processed_df[
            [
                "id",
                "submittedat",
                "project_title",
                "studentnames",
                "year",
                "abstract",
                "description",
                "problemstatement",
                "proposedsolution",
                "objectives",
                "full_content",
                "clean_text",
                "word_count",
                "features"
            ]
        ]

        processed_df = processed_df.rename(
            columns={
                "submittedat": "submitted_at",
                "studentnames": "student_names",
                "problemstatement": "problem_statement",
                "proposedsolution": "proposed_solution"
            }
        )

        processed_df["features"] = (
            processed_df["features"]
            .apply(json.dumps)
        )

        processed_df.to_sql(
            "PreProcessed_Projects",
            engine,
            if_exists="append",
            index=False
        )

        print(
            f"Processed and inserted {len(processed_df)} projects"
        )

        changed = True

    else:

        print(
            "No new projects found"
        )

    # ---------------------------------
    # Rebuild FAISS only if changed
    # ---------------------------------

    if changed:

        print(
            "Updating embeddings..."
        )

        train_embedding_engine()

        print(
            "Embeddings updated"
        )

    else:

        print(
            "No changes detected"
        )


if __name__ == "__main__":

    sync_projects()