Skip to content

core.data_store

Central in-memory repository (quasi-singleton) that keeps all intermediate DataFrames while the import workflow is running.

This class uses only class attributes – no instance is ever created. Access is always via DataStore., so every window/controller can read/write data without passing objects around.

DataStore

Source code in src/core/data_store.py 
 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
class DataStore:
    # --------------------------------------------------------------------------
    #  User data (statistics)
    # --------------------------------------------------------------------------
    file_path: Optional[str] = None  # Absolute path of uploaded file
    df_user: Optional[pd.DataFrame] = None  # Filtered statistics DataFrame
    selected_columns: Optional[list[str]] = None  # Columns chosen by the user

    # --------------------------------------------------------------------------
    #  Geo data
    # --------------------------------------------------------------------------
    geo_meta: Optional[GeoMeta] = None  # Metadata about the loaded geo CSV
    df_geo: Optional[pd.DataFrame] = None  # Geo reference DataFrame

    # --------------------------------------------------------------------------
    #  Mapping result
    # --------------------------------------------------------------------------
    df_mapped: Optional[pd.DataFrame] = None  # Combined statistics-geo mapping

    # ========================================================================
    #  Mutators – always make a copy() so that external code cannot mutate store
    # ========================================================================
    @classmethod
    def set_upload(cls, path: str) -> None:
        """
        Store the absolute path of the user-uploaded file.

        Steps:
          1. Assign the given path to the class attribute `file_path`.
        """
        cls.file_path = path

    @classmethod
    def set_selection(cls, df: pd.DataFrame, columns: Optional[list[str]] | None = None) -> None:
        """
        Store the statistics DataFrame after column selection/filtering.

        Steps:
          1. Copy the given DataFrame to prevent external mutations.
          2. Store the user-selected columns for downstream steps.
        """
        cls.df_user = df.copy()
        cls.selected_columns = columns

    @classmethod
    def set_geo(cls, df: pd.DataFrame, meta: dict) -> None:
        """
        Store the geo reference table together with its meta-information.

        Steps:
          1. Copy the DataFrame to keep the original immutable.
          2. Convert the incoming metadata dict into a GeoMeta instance.
          3. Store both DataFrame and GeoMeta.
        """
        cls.df_geo = df.copy()
        cls.geo_meta = GeoMeta(**meta)

    @classmethod
    def set_mapping(cls, df: pd.DataFrame) -> None:
        """
        Persist the matched table (auto or manual).

        Steps:
          1. Copy the combined mapping DataFrame.
          2. Store it in `df_mapped` for downstream preview/export.
        """
        cls.df_mapped = df.copy()

    # --------------------------------------------------------------------------
    #  House-keeping
    # --------------------------------------------------------------------------
    @classmethod
    def clear(cls) -> None:
        """
        Reset all stored data – used when the user starts a new workflow run.

        Steps:
          1. Iterate over all relevant class attributes.
          2. Set each attribute to None to release references to DataFrames.
        """
        for attr in ("file_path", "df_user", "df_geo", "geo_meta", "df_mapped", "selected_columns"):
            setattr(cls, attr, None)

clear() classmethod

Reset all stored data – used when the user starts a new workflow run.

Steps
  1. Iterate over all relevant class attributes.
  2. Set each attribute to None to release references to DataFrames.
Source code in src/core/data_store.py 
111
112
113
114
115
116
117
118
119
120
121
@classmethod
def clear(cls) -> None:
    """
    Reset all stored data – used when the user starts a new workflow run.

    Steps:
      1. Iterate over all relevant class attributes.
      2. Set each attribute to None to release references to DataFrames.
    """
    for attr in ("file_path", "df_user", "df_geo", "geo_meta", "df_mapped", "selected_columns"):
        setattr(cls, attr, None)

set_geo(df, meta) classmethod

Store the geo reference table together with its meta-information.

Steps
  1. Copy the DataFrame to keep the original immutable.
  2. Convert the incoming metadata dict into a GeoMeta instance.
  3. Store both DataFrame and GeoMeta.
Source code in src/core/data_store.py 
84
85
86
87
88
89
90
91
92
93
94
95
@classmethod
def set_geo(cls, df: pd.DataFrame, meta: dict) -> None:
    """
    Store the geo reference table together with its meta-information.

    Steps:
      1. Copy the DataFrame to keep the original immutable.
      2. Convert the incoming metadata dict into a GeoMeta instance.
      3. Store both DataFrame and GeoMeta.
    """
    cls.df_geo = df.copy()
    cls.geo_meta = GeoMeta(**meta)

set_mapping(df) classmethod

Persist the matched table (auto or manual).

Steps
  1. Copy the combined mapping DataFrame.
  2. Store it in df_mapped for downstream preview/export.
Source code in src/core/data_store.py 
 97
 98
 99
100
101
102
103
104
105
106
@classmethod
def set_mapping(cls, df: pd.DataFrame) -> None:
    """
    Persist the matched table (auto or manual).

    Steps:
      1. Copy the combined mapping DataFrame.
      2. Store it in `df_mapped` for downstream preview/export.
    """
    cls.df_mapped = df.copy()

set_selection(df, columns=None) classmethod

Store the statistics DataFrame after column selection/filtering.

Steps
  1. Copy the given DataFrame to prevent external mutations.
  2. Store the user-selected columns for downstream steps.
Source code in src/core/data_store.py 
72
73
74
75
76
77
78
79
80
81
82
@classmethod
def set_selection(cls, df: pd.DataFrame, columns: Optional[list[str]] | None = None) -> None:
    """
    Store the statistics DataFrame after column selection/filtering.

    Steps:
      1. Copy the given DataFrame to prevent external mutations.
      2. Store the user-selected columns for downstream steps.
    """
    cls.df_user = df.copy()
    cls.selected_columns = columns

set_upload(path) classmethod

Store the absolute path of the user-uploaded file.

Steps
  1. Assign the given path to the class attribute file_path.
Source code in src/core/data_store.py 
62
63
64
65
66
67
68
69
70
@classmethod
def set_upload(cls, path: str) -> None:
    """
    Store the absolute path of the user-uploaded file.

    Steps:
      1. Assign the given path to the class attribute `file_path`.
    """
    cls.file_path = path

GeoMeta dataclass

Thin container for meta-information accompanying a geographical CSV selection.

Attributes:

Name Type Description
type

Data set family (e.g. 'NUTS', 'LAU', …).
version

Release/vintage identifier (e.g. '2023-01').
level

Resolution or administrative level of the chosen CSV file.
Source code in src/core/data_store.py 
21
22
23
24
25
26
27
28
29
30
31
32
33
34
@dataclass(slots=True)
class GeoMeta:
    """
    Thin container for meta-information accompanying a geographical CSV selection.

    Attributes:
      type : Data set family (e.g. 'NUTS', 'LAU', …).
      version : Release/vintage identifier (e.g. '2023-01').
      level : Resolution or administrative level of the chosen CSV file.
    """

    type: str
    version: str
    level: str