ParquetFileReader class

This class enables you to interact with Parquet files.

Factory

The ParquetFileReader$create() factory method instantiates the object and takes the following arguments:

• file A character file name, raw vector, or Arrow file connection object (e.g. RandomAccessFile).

• props Optional ParquetReaderProperties

• mmap Logical: whether to memory-map the file (default TRUE)

• ... Additional arguments, currently ignored

Methods

• $ReadTable(col_select): get an arrow::Table from the file, possibly with columns filtered by a character vector of column names or a tidyselect specification.

• $GetSchema(): get the arrow::Schema of the data in the file

Super class

arrow::Object -> ParquetFileReader

Methods

Public methods

• ParquetFileReader$ReadTable()

• ParquetFileReader$GetSchema()

• ParquetFileReader$clone()

Inherited methods

• arrow::Object$initialize()

• arrow::Object$pointer()

• arrow::Object$print()

• arrow::Object$set_pointer()

---

Method ReadTable()

Usage

ParquetFileReader$ReadTable(col_select = NULL)

---

Method GetSchema()

Usage

ParquetFileReader$GetSchema()

---

Method clone()

The objects of this class are cloneable with this method.

Usage

ParquetFileReader$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

# \donttest{
f <- system.file("v0.7.1.parquet", package="arrow")
pq <- ParquetFileReader$create(f)
pq$GetSchema()
#> Schema
#> carat: double
#> cut: string
#> color: string
#> clarity: string
#> depth: double
#> table: double
#> price: int64
#> x: double
#> y: double
#> z: double
#> __index_level_0__: int64
#> -- metadata --
#> pandas: {"index_columns": ["__index_level_0__"], "column_indexes": [{"name": null, "pandas_type": "string", "numpy_type": "object", "metadata": null}], "columns": [{"name": "carat", "pandas_type": "float64", "numpy_type": "float64", "metadata": null}, {"name": "cut", "pandas_type": "unicode", "numpy_type": "object", "metadata": null}, {"name": "color", "pandas_type": "unicode", "numpy_type": "object", "metadata": null}, {"name": "clarity", "pandas_type": "unicode", "numpy_type": "object", "metadata": null}, {"name": "depth", "pandas_type": "float64", "numpy_type": "float64", "metadata": null}, {"name": "table", "pandas_type": "float64", "numpy_type": "float64", "metadata": null}, {"name": "price", "pandas_type": "int64", "numpy_type": "int64", "metadata": null}, {"name": "x", "pandas_type": "float64", "numpy_type": "float64", "metadata": null}, {"name": "y", "pandas_type": "float64", "numpy_type": "float64", "metadata": null}, {"name": "z", "pandas_type": "float64", "numpy_type": "float64", "metadata": null}, {"name": "__index_level_0__", "pandas_type": "int64", "numpy_type": "int64", "metadata": null}], "pandas_version": "0.20.1"}
tab <- pq$ReadTable(starts_with("c"))
tab$schema
#> Schema
#> carat: double
#> cut: string
#> color: string
#> clarity: string
#> -- metadata --
#> pandas: {"index_columns": ["__index_level_0__"], "column_indexes": [{"name": null, "pandas_type": "string", "numpy_type": "object", "metadata": null}], "columns": [{"name": "carat", "pandas_type": "float64", "numpy_type": "float64", "metadata": null}, {"name": "cut", "pandas_type": "unicode", "numpy_type": "object", "metadata": null}, {"name": "color", "pandas_type": "unicode", "numpy_type": "object", "metadata": null}, {"name": "clarity", "pandas_type": "unicode", "numpy_type": "object", "metadata": null}, {"name": "depth", "pandas_type": "float64", "numpy_type": "float64", "metadata": null}, {"name": "table", "pandas_type": "float64", "numpy_type": "float64", "metadata": null}, {"name": "price", "pandas_type": "int64", "numpy_type": "int64", "metadata": null}, {"name": "x", "pandas_type": "float64", "numpy_type": "float64", "metadata": null}, {"name": "y", "pandas_type": "float64", "numpy_type": "float64", "metadata": null}, {"name": "z", "pandas_type": "float64", "numpy_type": "float64", "metadata": null}, {"name": "__index_level_0__", "pandas_type": "int64", "numpy_type": "int64", "metadata": null}], "pandas_version": "0.20.1"}
# }