nisaba 0.2.4

Data quality, reconciliation, and validation across different data stores
Documentation 
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
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271

import os
from concurrent.futures import ThreadPoolExecutor, as_completed
from pathlib import Path
from typing import Dict, List

import pandas as pd
from pymongo import MongoClient
from sqlalchemy import create_engine


class DataSeeder:
    def __init__(self):
        self.files = [
            "albums.parquet",
            "album_images.parquet",
            "artist_album.parquet",
            "artist_genre.parquet",
            "artist_image.parquet",
            "artists.parquet",
            "available_markets.parquet",
            "track_artist.parquet",
            "tracks.parquet",
        ]

        self.mongo_client = MongoClient(
            "mongodb://mongodb:mongodb@localhost:27017/?authSource=admin"
        )
        self.mongo_db = self.mongo_client["mongo_store"]

        self.mysql_engine = create_engine(
            "mysql+mysqlconnector://mysql:mysql@localhost:3306/mysql_store"
        )

        self.postgres_engine = create_engine(
            "postgresql+psycopg2://postgres:postgres@localhost:5432/postgres"
        )

        os.makedirs("./assets/sqlite", exist_ok=True)

        self.sqlite_engine = create_engine("sqlite:///assets/sqlite/nisaba.sqlite")

    def to_csv(self, df: pd.DataFrame, filename: str) -> Dict:
        """Write DataFrame to CSV"""
        try:
            output_path = f"assets/csv/{filename.replace('.parquet', '.csv')}"

            Path(output_path).parent.mkdir(parents=True, exist_ok=True)

            df.to_csv(output_path, index=False)

            return {"destination": "CSV", "status": "success", "file": filename}
        except Exception as e:
            report = {
                "destination": "CSV",
                "status": "failed",
                "file": filename,
                "error": str(e),
            }
            raise Exception(report)

    def to_excel(self, df: pd.DataFrame, filename: str) -> Dict:
        """Write DataFrame to Excel"""
        try:
            output_path = f"assets/xlsx/{filename.replace('.parquet', '.xlsx')}"

            Path(output_path).parent.mkdir(parents=True, exist_ok=True)

            sheet_name = filename.split(".")[0]

            df.to_excel(output_path, sheet_name=sheet_name, index=False)

            return {"destination": "Excel", "status": "success", "file": filename}
        except Exception as e:
            report = {
                "destination": "Excel",
                "status": "failed",
                "file": filename,
                "error": str(e),
            }
            raise Exception(report)

    def to_mongo(self, df: pd.DataFrame, filename: str) -> Dict:
        """Write DataFrame to MongoDB"""
        try:
            df_copy = df.copy()
            collection_name = filename.split(".")[0]
            collection = self.mongo_db[collection_name]

            # Convert date columns to string
            if "release_date" in df_copy.columns:
                df_copy["release_date"] = df_copy["release_date"].astype("string")

            data_dict = df_copy.to_dict(orient="records")
            collection.delete_many({})  # Clear existing data

            collection.insert_many(data_dict)

            return {
                "destination": "MongoDB",
                "status": "success",
                "file": filename,
                "records": len(data_dict),
            }
        except Exception as e:
            report = {
                "destination": "MongoDB",
                "status": "failed",
                "file": filename,
                "error": str(e),
            }
            raise Exception(report)

    def to_mysql(self, df: pd.DataFrame, filename: str) -> Dict:
        """Write DataFrame to MySQL"""
        try:
            table_name = filename.split(".")[0]

            df.to_sql(
                name=table_name, con=self.mysql_engine, if_exists="replace", index=False
            )

            return {"destination": "MySQL", "status": "success", "file": filename}
        except Exception as e:
            report = {
                "destination": "MySQL",
                "status": "failed",
                "file": filename,
                "error": str(e),
            }
            raise Exception(report)

    def to_postgres(self, df: pd.DataFrame, filename: str) -> Dict:
        """Write DataFrame to PostgreSQL"""
        try:
            table_name = filename.split(".")[0]
            df.to_sql(
                name=table_name,
                con=self.postgres_engine,
                if_exists="replace",
                index=False,
            )

            return {"destination": "PostgreSQL", "status": "success", "file": filename}
        except Exception as e:
            report = {
                "destination": "PostgreSQL",
                "status": "failed",
                "file": filename,
                "error": str(e),
            }
            raise Exception(report)

    def to_sqlite(self, df: pd.DataFrame, filename: str):
        try:
            table_name = filename.split(".")[0]
            df.to_sql(
                name=table_name,
                con=self.sqlite_engine,
                if_exists="replace",
                index=False,
            )
        except Exception as e:
            report = {
                "destination": "Sqlite",
                "status": "failed",
                "file": filename,
                "error": str(e),
            }
            raise Exception(report)

    def seed_file_parallel(self, filename: str, destinations: List[str]) -> List[Dict]:
        """
        Read a file once and write to multiple destinations in parallel

        Args:
            filename: Name of the parquet file to process
            destinations: List of destinations ('csv', 'excel', 'mongo', 'mysql', 'postgres', 'sqlite')
                         If None, writes to all destinations
        """
        if len(destinations) == 0:
            destinations = ["csv", "excel", "mongo", "mysql", "postgres", "sqlite"]

        # Read once
        try:
            df = pd.read_parquet(f"assets/parquet/{filename}")

        except Exception as e:
            report = [{"status": "failed", "error": f"Read failed: {e}"}]
            raise Exception(report)

        # Map destinations to methods
        destination_map = {
            "csv": self.to_csv,
            "excel": self.to_excel,
            "mongo": self.to_mongo,
            "mysql": self.to_mysql,
            "postgres": self.to_postgres,
            "sqlite": self.to_sqlite,
        }

        results = []

        # Write to multiple destinations in parallel
        with ThreadPoolExecutor(max_workers=len(destinations)) as executor:
            futures = {
                executor.submit(destination_map[dest], df.copy(), filename): dest
                for dest in destinations
                if dest in destination_map
            }

            for future in as_completed(futures):
                try:
                    result = future.result()
                    results.append(result)
                except Exception as e:
                    dest = futures[future]

                    results.append(
                        {
                            "destination": dest,
                            "status": "failed",
                            "file": filename,
                            "error": str(e),
                        }
                    )

        return results

    def seed_all_files(self, destinations: List[str] = [], max_workers: int = 4):
        """
        Process all files, each with parallel writes to destinations

        Args:
            destinations: List of destinations to write to
            max_workers: Maximum number of files to process concurrently
        """

        all_results = []

        # Process files with limited concurrency to avoid overwhelming the system
        with ThreadPoolExecutor(max_workers=max_workers) as executor:
            future_to_file = {
                executor.submit(self.seed_file_parallel, file, destinations): file
                for file in self.files
            }

            for future in as_completed(future_to_file):
                filename = future_to_file[future]
                try:
                    results = future.result()
                    all_results.extend(results)
                except Exception as e:
                    raise Exception(f"Failed to process {filename}: {e}")

        print("Seeding Complete!")

        return all_results


def main():
    seeder = DataSeeder()

    try:
        seeder.seed_all_files(max_workers=4)

    except Exception as e:
        raise Exception(str(e))


if __name__ == "__main__":
    main()