Skip to content

table

Classes

KiaraTable

Bases: KiaraModel

A wrapper class to manage tabular data in a memory efficient way.

Source code in /opt/hostedtoolcache/Python/3.11.4/x64/lib/python3.11/site-packages/kiara_plugin/tabular/models/table.py 
 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
class KiaraTable(KiaraModel):
    """A wrapper class to manage tabular data in a memory efficient way."""

    @classmethod
    def create_table(cls, data: Any) -> "KiaraTable":
        """Create a `KiaraTable` instance from an Apache Arrow Table, or dict of lists."""

        if isinstance(data, KiaraTable):
            return data
        elif isinstance(data, Value):
            if data.data_type_name != "table":
                raise KiaraException(
                    f"Invalid data type '{data.data_type_name}', need 'table'."
                )
            return data.data  # type: ignore

        table_obj = None
        if isinstance(data, (pa.Table)):
            table_obj = data
        else:
            try:
                table_obj = pa.table(data)
            except Exception:
                pass

        if table_obj is None:
            raise Exception(
                f"Can't create table, invalid source data type: {type(data)}."
            )

        column_metadata = extract_column_metadata(table_obj)

        obj = KiaraTable()
        obj._table_obj = table_obj
        obj._column_metadata = column_metadata
        return obj

    data_path: Union[None, str] = Field(
        description="The path to the (feather) file backing this array.", default=None
    )

    """The path where the table object is store (for internal or read-only use)."""
    _table_obj: pa.Table = PrivateAttr(default=None)
    _column_metadata: Union[Dict[str, Dict[str, KiaraModel]], None] = PrivateAttr(
        default=None
    )

    def _retrieve_data_to_hash(self) -> Any:
        raise NotImplementedError()

    @property
    def arrow_table(self) -> pa.Table:
        """Return the data as an Apache Arrow Table instance."""

        if self._table_obj is not None:
            return self._table_obj

        if not self.data_path:
            raise Exception("Can't retrieve table data, object not initialized (yet).")

        with pa.memory_map(self.data_path, "r") as source:
            table: pa.Table = pa.ipc.open_file(source).read_all()

        self._table_obj = table
        return self._table_obj

    @property
    def column_names(self) -> Iterable[str]:
        """Retrieve the names of all the columns of this table."""
        return self.arrow_table.column_names

    @property
    def column_metadata(self) -> Mapping[str, Mapping[str, KiaraModel]]:

        if self._column_metadata is None:
            self._column_metadata = {}
        return self._column_metadata

    @property
    def num_rows(self) -> int:
        """Return the number of rows in this table."""
        return self.arrow_table.num_rows

    def set_column_metadata(
        self,
        column_name: str,
        metadata_key: str,
        metadata: KiaraModel,
        overwrite_existing: bool = True,
    ):

        if column_name not in self.column_names:
            raise KiaraException(
                "Can't set column metadata, No column with name: " + column_name
            )

        if (
            not overwrite_existing
            and metadata_key in self.column_metadata.get(column_name, {}).keys()
        ):
            return

        self.column_metadata.setdefault(column_name, {})[metadata_key] = metadata  # type: ignore

    def get_column_metadata(self, column_name: str) -> Mapping[str, KiaraModel]:
        if column_name not in self.column_names:
            raise KiaraException("No column with name: " + column_name)

        if column_name not in self.column_metadata.keys():
            return {}

        return self.column_metadata[column_name]

    def get_column_metadata_for_key(
        self, column_name: str, metadata_key: str
    ) -> KiaraModel:

        if column_name not in self.column_names:
            raise KiaraException("No column with name: " + column_name)

        if column_name not in self.column_metadata.keys():
            raise KiaraException("No column metadata set for column: " + column_name)

        if metadata_key not in self.column_metadata[column_name].keys():
            raise KiaraException(
                "No column metadata set for column: "
                + column_name
                + " and key: "
                + metadata_key
            )

        return self.column_metadata[column_name][metadata_key]

    def to_pydict(self):
        """Convert and return the table data as a dictionary of lists.

        This will load all data into memory, so you might or might not want to do that.
        """
        return self.arrow_table.to_pydict()

    def to_pylist(self):
        """Convert and return the table data as a list of rows/dictionaries.

        This will load all data into memory, so you might or might not want to do that.
        """

        return self.arrow_table.to_pylist()

    def to_polars_dataframe(self) -> "pl.DataFrame":
        """Return the data as a Polars dataframe."""

        import polars as pl

        return pl.from_arrow(self.arrow_table)  # type: ignore

    def to_pandas_dataframe(
        self,
        include_columns: Union[None, str, Iterable[str]] = None,
        exclude_columns: Union[None, str, Iterable[str]] = None,
    ) -> "pd.DataFrame":
        """Convert and return the table data to a Pandas dataframe.

        This will load all data into memory, so you might or might not want to do that.

        Column names in the 'exclude_columns' argument take precedence over those in the 'include_columns' argument.

        """

        if include_columns is None:
            columns = self.arrow_table.column_names
        elif isinstance(include_columns, str):
            columns = [include_columns]
        else:
            columns = list(include_columns)

        if exclude_columns is not None:
            if isinstance(exclude_columns, str):
                columns = columns.remove(exclude_columns)
            elif exclude_columns:
                exclude_columns = list(exclude_columns)
                columns = [c for c in columns if c not in exclude_columns]

        table = self.arrow_table.select(columns)
        return table.to_pandas()

Attributes

data_path: Union[None, str] = Field(description='The path to the (feather) file backing this array.', default=None) class-attribute instance-attribute

The path where the table object is store (for internal or read-only use).

arrow_table: pa.Table property

Return the data as an Apache Arrow Table instance.

column_names: Iterable[str] property

Retrieve the names of all the columns of this table.

column_metadata: Mapping[str, Mapping[str, KiaraModel]] property
num_rows: int property

Return the number of rows in this table.

Functions

create_table(data: Any) -> KiaraTable classmethod

Create a KiaraTable instance from an Apache Arrow Table, or dict of lists.

Source code in /opt/hostedtoolcache/Python/3.11.4/x64/lib/python3.11/site-packages/kiara_plugin/tabular/models/table.py 
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
@classmethod
def create_table(cls, data: Any) -> "KiaraTable":
    """Create a `KiaraTable` instance from an Apache Arrow Table, or dict of lists."""

    if isinstance(data, KiaraTable):
        return data
    elif isinstance(data, Value):
        if data.data_type_name != "table":
            raise KiaraException(
                f"Invalid data type '{data.data_type_name}', need 'table'."
            )
        return data.data  # type: ignore

    table_obj = None
    if isinstance(data, (pa.Table)):
        table_obj = data
    else:
        try:
            table_obj = pa.table(data)
        except Exception:
            pass

    if table_obj is None:
        raise Exception(
            f"Can't create table, invalid source data type: {type(data)}."
        )

    column_metadata = extract_column_metadata(table_obj)

    obj = KiaraTable()
    obj._table_obj = table_obj
    obj._column_metadata = column_metadata
    return obj
set_column_metadata(column_name: str, metadata_key: str, metadata: KiaraModel, overwrite_existing: bool = True)
Source code in /opt/hostedtoolcache/Python/3.11.4/x64/lib/python3.11/site-packages/kiara_plugin/tabular/models/table.py 
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
def set_column_metadata(
    self,
    column_name: str,
    metadata_key: str,
    metadata: KiaraModel,
    overwrite_existing: bool = True,
):

    if column_name not in self.column_names:
        raise KiaraException(
            "Can't set column metadata, No column with name: " + column_name
        )

    if (
        not overwrite_existing
        and metadata_key in self.column_metadata.get(column_name, {}).keys()
    ):
        return

    self.column_metadata.setdefault(column_name, {})[metadata_key] = metadata  # type: ignore
get_column_metadata(column_name: str) -> Mapping[str, KiaraModel]
Source code in /opt/hostedtoolcache/Python/3.11.4/x64/lib/python3.11/site-packages/kiara_plugin/tabular/models/table.py 
123
124
125
126
127
128
129
130
def get_column_metadata(self, column_name: str) -> Mapping[str, KiaraModel]:
    if column_name not in self.column_names:
        raise KiaraException("No column with name: " + column_name)

    if column_name not in self.column_metadata.keys():
        return {}

    return self.column_metadata[column_name]
get_column_metadata_for_key(column_name: str, metadata_key: str) -> KiaraModel
Source code in /opt/hostedtoolcache/Python/3.11.4/x64/lib/python3.11/site-packages/kiara_plugin/tabular/models/table.py 
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
def get_column_metadata_for_key(
    self, column_name: str, metadata_key: str
) -> KiaraModel:

    if column_name not in self.column_names:
        raise KiaraException("No column with name: " + column_name)

    if column_name not in self.column_metadata.keys():
        raise KiaraException("No column metadata set for column: " + column_name)

    if metadata_key not in self.column_metadata[column_name].keys():
        raise KiaraException(
            "No column metadata set for column: "
            + column_name
            + " and key: "
            + metadata_key
        )

    return self.column_metadata[column_name][metadata_key]
to_pydict()

Convert and return the table data as a dictionary of lists.

This will load all data into memory, so you might or might not want to do that.

Source code in /opt/hostedtoolcache/Python/3.11.4/x64/lib/python3.11/site-packages/kiara_plugin/tabular/models/table.py 
152
153
154
155
156
157
def to_pydict(self):
    """Convert and return the table data as a dictionary of lists.

    This will load all data into memory, so you might or might not want to do that.
    """
    return self.arrow_table.to_pydict()
to_pylist()

Convert and return the table data as a list of rows/dictionaries.

This will load all data into memory, so you might or might not want to do that.

Source code in /opt/hostedtoolcache/Python/3.11.4/x64/lib/python3.11/site-packages/kiara_plugin/tabular/models/table.py 
159
160
161
162
163
164
165
def to_pylist(self):
    """Convert and return the table data as a list of rows/dictionaries.

    This will load all data into memory, so you might or might not want to do that.
    """

    return self.arrow_table.to_pylist()
to_polars_dataframe() -> pl.DataFrame

Return the data as a Polars dataframe.

Source code in /opt/hostedtoolcache/Python/3.11.4/x64/lib/python3.11/site-packages/kiara_plugin/tabular/models/table.py 
167
168
169
170
171
172
def to_polars_dataframe(self) -> "pl.DataFrame":
    """Return the data as a Polars dataframe."""

    import polars as pl

    return pl.from_arrow(self.arrow_table)  # type: ignore
to_pandas_dataframe(include_columns: Union[None, str, Iterable[str]] = None, exclude_columns: Union[None, str, Iterable[str]] = None) -> pd.DataFrame

Convert and return the table data to a Pandas dataframe.

This will load all data into memory, so you might or might not want to do that.

Column names in the 'exclude_columns' argument take precedence over those in the 'include_columns' argument.

Source code in /opt/hostedtoolcache/Python/3.11.4/x64/lib/python3.11/site-packages/kiara_plugin/tabular/models/table.py 
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
def to_pandas_dataframe(
    self,
    include_columns: Union[None, str, Iterable[str]] = None,
    exclude_columns: Union[None, str, Iterable[str]] = None,
) -> "pd.DataFrame":
    """Convert and return the table data to a Pandas dataframe.

    This will load all data into memory, so you might or might not want to do that.

    Column names in the 'exclude_columns' argument take precedence over those in the 'include_columns' argument.

    """

    if include_columns is None:
        columns = self.arrow_table.column_names
    elif isinstance(include_columns, str):
        columns = [include_columns]
    else:
        columns = list(include_columns)

    if exclude_columns is not None:
        if isinstance(exclude_columns, str):
            columns = columns.remove(exclude_columns)
        elif exclude_columns:
            exclude_columns = list(exclude_columns)
            columns = [c for c in columns if c not in exclude_columns]

    table = self.arrow_table.select(columns)
    return table.to_pandas()

KiaraTableMetadata

Bases: ValueMetadata

File stats.

Source code in /opt/hostedtoolcache/Python/3.11.4/x64/lib/python3.11/site-packages/kiara_plugin/tabular/models/table.py 
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
class KiaraTableMetadata(ValueMetadata):
    """File stats."""

    _metadata_key = "table"

    @classmethod
    def retrieve_supported_data_types(cls) -> Iterable[str]:
        return ["table"]

    @classmethod
    def create_value_metadata(cls, value: "Value") -> "KiaraTableMetadata":

        kiara_table: KiaraTable = value.data

        md = TableMetadata.create_from_table(kiara_table)

        return KiaraTableMetadata.construct(table=md)

    table: TableMetadata = Field(description="The table schema.")

Attributes

table: TableMetadata = Field(description='The table schema.') class-attribute instance-attribute

Functions

retrieve_supported_data_types() -> Iterable[str] classmethod
Source code in /opt/hostedtoolcache/Python/3.11.4/x64/lib/python3.11/site-packages/kiara_plugin/tabular/models/table.py 
210
211
212
@classmethod
def retrieve_supported_data_types(cls) -> Iterable[str]:
    return ["table"]
create_value_metadata(value: Value) -> KiaraTableMetadata classmethod
Source code in /opt/hostedtoolcache/Python/3.11.4/x64/lib/python3.11/site-packages/kiara_plugin/tabular/models/table.py 
214
215
216
217
218
219
220
221
@classmethod
def create_value_metadata(cls, value: "Value") -> "KiaraTableMetadata":

    kiara_table: KiaraTable = value.data

    md = TableMetadata.create_from_table(kiara_table)

    return KiaraTableMetadata.construct(table=md)

Functions