mirror of
https://github.com/nushell/nushell.git
synced 2025-07-08 18:37:07 +02:00
# 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>
126 lines
3.6 KiB
Rust
126 lines
3.6 KiB
Rust
use nu_engine::CallExt;
|
|
use nu_protocol::{
|
|
ast::Call,
|
|
engine::{Command, EngineState, Stack},
|
|
Category, Example, PipelineData, ShellError, Signature, Span, SyntaxShape, Type, Value,
|
|
};
|
|
use polars::prelude::UniqueKeepStrategy;
|
|
|
|
use super::super::values::utils::convert_columns_string;
|
|
use super::super::values::{Column, NuDataFrame};
|
|
|
|
#[derive(Clone)]
|
|
pub struct DropDuplicates;
|
|
|
|
impl Command for DropDuplicates {
|
|
fn name(&self) -> &str {
|
|
"dfr drop-duplicates"
|
|
}
|
|
|
|
fn usage(&self) -> &str {
|
|
"Drops duplicate values in dataframe."
|
|
}
|
|
|
|
fn signature(&self) -> Signature {
|
|
Signature::build(self.name())
|
|
.optional(
|
|
"subset",
|
|
SyntaxShape::Table(vec![]),
|
|
"subset of columns to drop duplicates",
|
|
)
|
|
.switch("maintain", "maintain order", Some('m'))
|
|
.switch(
|
|
"last",
|
|
"keeps last duplicate value (by default keeps first)",
|
|
Some('l'),
|
|
)
|
|
.input_output_type(
|
|
Type::Custom("dataframe".into()),
|
|
Type::Custom("dataframe".into()),
|
|
)
|
|
.category(Category::Custom("dataframe".into()))
|
|
}
|
|
|
|
fn examples(&self) -> Vec<Example> {
|
|
vec![Example {
|
|
description: "drop duplicates",
|
|
example: "[[a b]; [1 2] [3 4] [1 2]] | dfr into-df | dfr drop-duplicates",
|
|
result: Some(
|
|
NuDataFrame::try_from_columns(
|
|
vec![
|
|
Column::new(
|
|
"a".to_string(),
|
|
vec![Value::test_int(3), Value::test_int(1)],
|
|
),
|
|
Column::new(
|
|
"b".to_string(),
|
|
vec![Value::test_int(4), Value::test_int(2)],
|
|
),
|
|
],
|
|
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 columns: Option<Vec<Value>> = call.opt(engine_state, stack, 0)?;
|
|
let (subset, col_span) = match columns {
|
|
Some(cols) => {
|
|
let (agg_string, col_span) = convert_columns_string(cols, call.head)?;
|
|
(Some(agg_string), col_span)
|
|
}
|
|
None => (None, call.head),
|
|
};
|
|
|
|
let df = NuDataFrame::try_from_pipeline(input, call.head)?;
|
|
|
|
let subset_slice = subset.as_ref().map(|cols| &cols[..]);
|
|
|
|
let keep_strategy = if call.has_flag(engine_state, stack, "last")? {
|
|
UniqueKeepStrategy::Last
|
|
} else {
|
|
UniqueKeepStrategy::First
|
|
};
|
|
|
|
df.as_ref()
|
|
.unique(subset_slice, keep_strategy, None)
|
|
.map_err(|e| ShellError::GenericError {
|
|
error: "Error dropping duplicates".into(),
|
|
msg: e.to_string(),
|
|
span: Some(col_span),
|
|
help: None,
|
|
inner: vec![],
|
|
})
|
|
.map(|df| PipelineData::Value(NuDataFrame::dataframe_into_value(df, 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(DropDuplicates {})])
|
|
}
|
|
}
|