mirror of
https://github.com/nushell/nushell.git
synced 2025-04-14 16:28:17 +02:00
f879c00f9d
# Description
There are times where explicitly specifying a schema for a dataframe is
needed such as:
- Opening CSV and JSON lines files and needing provide more information
to polars to keep it from failing or in a desire to override default
type conversion
- When converting a nushell value to a dataframe and wanting to override
the default conversion behaviors.
This pull requests provides:
- A flag to allow specifying a schema when using dfr into-df
- A flag to allow specifying a schema when using dfr open that works for
CSV and JSON types
- A new command `dfr schema` which displays schema information and will
allow display support schema dtypes
Schema is specified creating a record that has the key value and the
dtype. Examples usages:
```
{a:1, b:{a:2}} | dfr into-df -s {a: u8, b: {a: i32}} | dfr schema
{a: 1, b: {a: [1 2 3]}, c: [a b c]} | dfr into-df -s {a: u8, b: {a: list<u64>}, c: list<str>} | dfr schema
dfr open -s {pid: i32, ppid: i32, name: str, status: str, cpu: f64, mem: i64, virtual: i64} /tmp/ps.jsonl | dfr schema
```
Supported dtypes:
null
bool
u8
u16
u32
u64
i8
i16
i32
i64
f32
f64
str
binary
date
datetime[time_unit: (ms, us, ns) timezone (optional)]
duration[time_unit: (ms, us, ns)]
time
object
unknown
list[dtype]
structs are also supported but are specified via another record:
{a: u8, b: {d: str}}
Another feature with the dfr schema command is that it returns the data
back in a format that can be passed to provide a valid schema that can
be passed in as schema argument:
<img width="638" alt="Screenshot 2024-01-29 at 10 23 58"
src="https://github.com/nushell/nushell/assets/56345/b49c3bff-5cda-4c86-975a-dfd91d991373">
---------
Co-authored-by: Jack Wright <jack.wright@disqo.com>
96 lines
2.7 KiB
Rust
96 lines
2.7 KiB
Rust
use super::super::super::values::{Column, NuDataFrame};
|
|
|
|
use nu_protocol::{
|
|
ast::Call,
|
|
engine::{Command, EngineState, Stack},
|
|
Category, Example, PipelineData, ShellError, Signature, Span, Type, Value,
|
|
};
|
|
use polars::prelude::{DatetimeMethods, IntoSeries};
|
|
|
|
#[derive(Clone)]
|
|
pub struct GetMinute;
|
|
|
|
impl Command for GetMinute {
|
|
fn name(&self) -> &str {
|
|
"dfr get-minute"
|
|
}
|
|
|
|
fn usage(&self) -> &str {
|
|
"Gets minute from date."
|
|
}
|
|
|
|
fn signature(&self) -> Signature {
|
|
Signature::build(self.name())
|
|
.input_output_type(
|
|
Type::Custom("dataframe".into()),
|
|
Type::Custom("dataframe".into()),
|
|
)
|
|
.category(Category::Custom("dataframe".into()))
|
|
}
|
|
|
|
fn examples(&self) -> Vec<Example> {
|
|
vec![Example {
|
|
description: "Returns minute from a date",
|
|
example: r#"let dt = ('2020-08-04T16:39:18+00:00' | into datetime --timezone 'UTC');
|
|
let df = ([$dt $dt] | dfr into-df);
|
|
$df | dfr get-minute"#,
|
|
result: Some(
|
|
NuDataFrame::try_from_columns(
|
|
vec![Column::new(
|
|
"0".to_string(),
|
|
vec![Value::test_int(39), Value::test_int(39)],
|
|
)],
|
|
None,
|
|
)
|
|
.expect("simple df for test should not fail")
|
|
.into_value(Span::test_data()),
|
|
),
|
|
}]
|
|
}
|
|
|
|
fn run(
|
|
&self,
|
|
engine_state: &EngineState,
|
|
stack: &mut Stack,
|
|
call: &Call,
|
|
input: PipelineData,
|
|
) -> Result<PipelineData, ShellError> {
|
|
command(engine_state, stack, call, input)
|
|
}
|
|
}
|
|
|
|
fn command(
|
|
_engine_state: &EngineState,
|
|
_stack: &mut Stack,
|
|
call: &Call,
|
|
input: PipelineData,
|
|
) -> Result<PipelineData, ShellError> {
|
|
let df = NuDataFrame::try_from_pipeline(input, call.head)?;
|
|
let series = df.as_series(call.head)?;
|
|
|
|
let casted = series.datetime().map_err(|e| ShellError::GenericError {
|
|
error: "Error casting to datetime type".into(),
|
|
msg: e.to_string(),
|
|
span: Some(call.head),
|
|
help: None,
|
|
inner: vec![],
|
|
})?;
|
|
|
|
let res = casted.minute().into_series();
|
|
|
|
NuDataFrame::try_from_series(vec![res], call.head)
|
|
.map(|df| PipelineData::Value(NuDataFrame::into_value(df, call.head), None))
|
|
}
|
|
|
|
#[cfg(explore_refactor_IntoDatetime)]
|
|
mod test {
|
|
use super::super::super::super::super::IntoDatetime;
|
|
use super::super::super::super::test_dataframe::test_dataframe;
|
|
use super::*;
|
|
|
|
#[test]
|
|
fn test_examples() {
|
|
test_dataframe(vec![Box::new(GetMinute {}), Box::new(IntoDatetime {})])
|
|
}
|
|
}
|