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>
149 lines
5.1 KiB
Rust
149 lines
5.1 KiB
Rust
use crate::dataframe::values::{Column, NuDataFrame, NuExpression};
|
|
use nu_engine::CallExt;
|
|
use nu_protocol::{
|
|
ast::Call,
|
|
engine::{Command, EngineState, Stack},
|
|
Category, Example, PipelineData, ShellError, Signature, Span, SyntaxShape, Type, Value,
|
|
};
|
|
|
|
#[derive(Clone)]
|
|
pub struct LazyFillNA;
|
|
|
|
impl Command for LazyFillNA {
|
|
fn name(&self) -> &str {
|
|
"dfr fill-nan"
|
|
}
|
|
|
|
fn usage(&self) -> &str {
|
|
"Replaces NaN values with the given expression."
|
|
}
|
|
|
|
fn signature(&self) -> Signature {
|
|
Signature::build(self.name())
|
|
.required(
|
|
"fill",
|
|
SyntaxShape::Any,
|
|
"Expression to use to fill the NAN values",
|
|
)
|
|
.input_output_type(
|
|
Type::Custom("dataframe".into()),
|
|
Type::Custom("dataframe".into()),
|
|
)
|
|
.category(Category::Custom("lazyframe".into()))
|
|
}
|
|
|
|
fn examples(&self) -> Vec<Example> {
|
|
vec![
|
|
Example {
|
|
description: "Fills the NaN values with 0",
|
|
example: "[1 2 NaN 3 NaN] | dfr into-df | dfr fill-nan 0",
|
|
result: Some(
|
|
NuDataFrame::try_from_columns(
|
|
vec![Column::new(
|
|
"0".to_string(),
|
|
vec![
|
|
Value::test_int(1),
|
|
Value::test_int(2),
|
|
Value::test_int(0),
|
|
Value::test_int(3),
|
|
Value::test_int(0),
|
|
],
|
|
)],
|
|
None,
|
|
)
|
|
.expect("Df for test should not fail")
|
|
.into_value(Span::test_data()),
|
|
),
|
|
},
|
|
Example {
|
|
description: "Fills the NaN values of a whole dataframe",
|
|
example: "[[a b]; [0.2 1] [0.1 NaN]] | dfr into-df | dfr fill-nan 0",
|
|
result: Some(
|
|
NuDataFrame::try_from_columns(
|
|
vec![
|
|
Column::new(
|
|
"a".to_string(),
|
|
vec![Value::test_float(0.2), Value::test_float(0.1)],
|
|
),
|
|
Column::new(
|
|
"b".to_string(),
|
|
vec![Value::test_int(1), Value::test_int(0)],
|
|
),
|
|
],
|
|
None,
|
|
)
|
|
.expect("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> {
|
|
let fill: Value = call.req(engine_state, stack, 0)?;
|
|
let value = input.into_value(call.head);
|
|
|
|
if NuExpression::can_downcast(&value) {
|
|
let expr = NuExpression::try_from_value(value)?;
|
|
let fill = NuExpression::try_from_value(fill)?.into_polars();
|
|
let expr: NuExpression = expr.into_polars().fill_nan(fill).into();
|
|
|
|
Ok(PipelineData::Value(
|
|
NuExpression::into_value(expr, call.head),
|
|
None,
|
|
))
|
|
} else {
|
|
let val_span = value.span();
|
|
let frame = NuDataFrame::try_from_value(value)?;
|
|
let columns = frame.columns(val_span)?;
|
|
let dataframe = columns
|
|
.into_iter()
|
|
.map(|column| {
|
|
let column_name = column.name().to_string();
|
|
let values = column
|
|
.into_iter()
|
|
.map(|value| {
|
|
let span = value.span();
|
|
match value {
|
|
Value::Float { val, .. } => {
|
|
if val.is_nan() {
|
|
fill.clone()
|
|
} else {
|
|
value
|
|
}
|
|
}
|
|
Value::List { vals, .. } => {
|
|
NuDataFrame::fill_list_nan(vals, span, fill.clone())
|
|
}
|
|
_ => value,
|
|
}
|
|
})
|
|
.collect::<Vec<Value>>();
|
|
Column::new(column_name, values)
|
|
})
|
|
.collect::<Vec<Column>>();
|
|
Ok(PipelineData::Value(
|
|
NuDataFrame::try_from_columns(dataframe, None)?.into_value(call.head),
|
|
None,
|
|
))
|
|
}
|
|
}
|
|
}
|
|
|
|
#[cfg(test)]
|
|
mod test {
|
|
use super::super::super::test_dataframe::test_dataframe;
|
|
use super::*;
|
|
|
|
#[test]
|
|
fn test_examples() {
|
|
test_dataframe(vec![Box::new(LazyFillNA {})])
|
|
}
|
|
}
|