End_to_End_DataScience_Project/src/datascience/config/configuration.py at main · ashmi8/End_to_End_DataScience_Project · GitHub

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
from src.datascience.constants import *
from src.datascience.utils.common import read_yaml, create_directories

from src.datascience.entity.config_entity import (DataIngestionConfig,DataValidationConfig,
                                                  DataTransformationConfig,ModelTrainerConfig,
                                                  ModelEvaluationConfig)

class ConfigurationManager:
    def __init__(self,
                 config_filepath=CONFIG_FILE_PATH,
                 params_filepath = PARAMS_FILE_PATH,
                 schema_filepath = SCHEMA_FILE_PATH):
        self.config=read_yaml(config_filepath)
        self.params=read_yaml(params_filepath)
        self.schema=read_yaml(schema_filepath)

        create_directories([self.config.artifacts_root])


    def get_data_ingestion_config(self)-> DataIngestionConfig:
        config=self.config.data_ingestion
        create_directories([config.root_dir])

        data_ingestion_config=DataIngestionConfig(
            root_dir=config.root_dir,
            source_URL=config.source_URL,
            local_data_file=config.local_data_file,
            unzip_dir=config.unzip_dir

        )
        return data_ingestion_config

    def get_data_validation_config(self) -> DataValidationConfig:
        config = self.config.data_validation
        schema = self.schema.COLUMNS

        create_directories([config.root_dir])

        data_validation_config = DataValidationConfig(
            root_dir=config.root_dir,
            STATUS_FILE=config.STATUS_FILE,
            unzip_data_dir = config.unzip_data_dir,
            all_schema=schema,
        )

        return data_validation_config

    def get_data_transformation_config(self) -> DataTransformationConfig:
        config=self.config.data_transformation
        create_directories([config.root_dir])
        data_transformation_config=DataTransformationConfig(
            root_dir=config.root_dir,
            data_path=config.data_path
        )
        return data_transformation_config

    def get_model_trainer_config(self) -> ModelTrainerConfig:
        config = self.config.model_trainer
        params = self.params.ElasticNet
        schema =  self.schema.TARGET_COLUMN

        create_directories([config.root_dir])

        model_trainer_config = ModelTrainerConfig(
            root_dir=config.root_dir,
            train_data_path = config.train_data_path,
            test_data_path = config.test_data_path,
            model_name = config.model_name,
            alpha = params.alpha,
            l1_ratio = params.l1_ratio,
            target_column = schema.name

        )

        return model_trainer_config

    def get_model_evaluation_config(self) -> ModelEvaluationConfig:
        config=self.config.model_evaluation
        params=self.params.ElasticNet
        schema=self.schema.TARGET_COLUMN

        create_directories([config.root_dir])

        model_evaluation_config=ModelEvaluationConfig(
            root_dir=config.root_dir,
            test_data_path=config.test_data_path,
            model_path = config.model_path,
            all_params=params,
            metric_file_name = config.metric_file_name,
            target_column = schema.name,
            mlflow_uri="https://dagshub.com/ashmijha8/End_to_End_DataScience_Project.mlflow"


        )
        return model_evaluation_config