Method read

python/pyarrow/parquet/core.py:599–643

Read a Table from Parquet format. Parameters ---------- columns : list If not None, only these columns will be read from the file. A column name may be a prefix of a nested field, e.g. 'a' will select 'a.b', 'a.c', and 'a.d.e'.

(self, columns=None, use_threads=True, use_pandas_metadata=False)

        return batches

    def read(self, columns=None, use_threads=True, use_pandas_metadata=False):
        """
        Read a Table from Parquet format.

        Parameters
        ----------
        columns : list
            If not None, only these columns will be read from the file. A
            column name may be a prefix of a nested field, e.g. 'a' will select
            'a.b', 'a.c', and 'a.d.e'.
        use_threads : bool, default True
            Perform multi-threaded column reads.
        use_pandas_metadata : bool, default False
            If True and file has custom pandas schema metadata, ensure that
            index columns are also loaded.

        Returns
        -------
        pyarrow.table.Table
            Content of the file as a table (of columns).

        Examples
        --------
        Generate an example Parquet file:

        >>> import pyarrow as pa
        >>> table = pa.table({'n_legs': [2, 2, 4, 4, 5, 100],
        ...                   'animal': ["Flamingo", "Parrot", "Dog", "Horse",
        ...                              "Brittle stars", "Centipede"]})
        >>> import pyarrow.parquet as pq
        >>> pq.write_table(table, 'example.parquet')
        >>> parquet_file = pq.ParquetFile('example.parquet')

        Read a Table:

        >>> parquet_file.read(columns=["animal"])
        pyarrow.Table
        animal: string
        ----
        animal: [["Flamingo","Parrot",...,"Brittle stars","Centipede"]]
        """
        column_indices = self._get_column_indices(
            columns, use_pandas_metadata=use_pandas_metadata)
        return self.reader.read_all(column_indices=column_indices,
                                    use_threads=use_threads)

    def scan_contents(self, columns=None, batch_size=65536):
        """