0

我正在开发一个来自 python/pandas 的小型实用程序应用程序,并尝试重建一些可以通过可执行文件分发的基本工具。我很难解释文档似乎应该是一个相当简单的过程,即读取一些原始数据,根据 datetime 列重新采样,然后根据需要对其进行插值以填充缺失的数据。

我的 cargo.toml 看起来像:

[dependencies]
polars = "0.19.0"

到目前为止我写的代码是:

use polars::prelude::*;
use std::fs::File;

fn main() {
    let mut df = CsvReader::new("raw.csv".into())
        .finish();

    //interpolate to clean up blank/nan
    //resample/groupby 15Min-1D using mean, blank/nan if missing
    
    let mut file = File::create("final.csv").expect("File not written!!!");

    CsvWriter::new(&mut file)
        .has_header(true)
        .with_delimiter(b',')
        .finish(&df);

}

raw.csv 数据可能如下所示:

site,datetime,val1,val2,val3,val4,val5,val6
XX1,2021-01-01 00:45,,,,4.60,,
XX1,2021-01-01 00:50,,,,2.30,,
XX1,2021-01-01 00:53,21.90,16.00,77.67,3.45,1027.20,0.00
XX1,2021-01-01 01:20,,,,4.60,,
XX1,2021-01-01 01:53,21.90,16.00,77.67,3.45,1026.90,0.00
XX1,2021-01-01 01:55,,,,0.00,,
XX1,2021-01-01 02:00,,,,0.00,,
XX1,2021-01-01 02:45,,,,5.75,,
XX1,2021-01-01 02:50,,,,8.05,,
XX1,2021-01-01 02:53,21.00,16.00,80.69,8.05,1026.80,0.00

但我似乎无法调用这些方法,因为我收到如下错误:

method not found in `Result<DataFrame, PolarsError>`

或者

expected struct `DataFrame`, found enum `Result`

而且我不确定如何在课程之间正确切换。

我已经尝试过明显错误的答案,例如:

let grouped = df.lazy().groupby_dynamic("datetime", "1h").agg("datetime", mean());

但基本上,我正在寻找与熊猫代码等效的极地:

df = df.interpolate()
df = df.resample(sample_frequency).mean()

任何帮助,将不胜感激!

4

2 回答 2

1

这是一个示例,说明您可以如何:

  • 通过日期范围内的左连接进行上采样
  • 用插值填充缺失值
  • 通过groupby_dynamic下采样
use chrono::prelude::*;
use polars::prelude::*;
use polars_core::time::*;
use std::io::Cursor;
use polars::frame::groupby::DynamicGroupOptions;

fn main() -> Result<()> {
    let csv = "site,datetime,val1,val2,val3,val4,val5,val6
XX1,2021-01-01 00:45,,,,4.60,,
XX1,2021-01-01 00:50,,,,2.30,,
XX1,2021-01-01 00:53,21.90,16.00,77.67,3.45,1027.20,0.00
XX1,2021-01-01 01:20,,,,4.60,,
XX1,2021-01-01 01:53,21.90,16.00,77.67,3.45,1026.90,0.00
XX1,2021-01-01 01:55,,,,0.00,,
XX1,2021-01-01 02:00,,,,0.00,,
XX1,2021-01-01 02:45,,,,5.75,,
XX1,2021-01-01 02:50,,,,8.05,,
XX1,2021-01-01 02:53,21.00,16.00,80.69,8.05,1026.80,0.00
";
    let cursor = Cursor::new(csv);

    // prefer scan csv when your data is not in memory
    let mut df = CsvReader::new(cursor).finish()?;
    df.try_apply("datetime", |s| {
        s.utf8()?
            .as_datetime(Some("%Y-%m-%d %H:%M"), TimeUnit::Nanoseconds)
            .map(|ca| ca.into_series())
    })?;
    
    // now we take the datetime column and extract timestamps from them
    // with these timestamps we create a `date_range` with an interval of 1 minute
    let dt = df.column("datetime")?;

    let timestamp = dt.cast(&DataType::Int64)?;
    let timestamp_ca = timestamp.i64()?;

    let first = timestamp_ca.get(0).unwrap();
    let last = timestamp_ca.get(timestamp_ca.len() - 1).unwrap();

    let range = date_range(
        first,
        last,
        Duration::parse("1m"),
        ClosedWindow::Both,
        "date_range",
        TimeUnit::Nanoseconds,
    );
    let range_df = DataFrame::new(vec![range.into_series()])?;

    // now that we got the date_range we use it to upsample the dataframe.
    // after that we interpolate the missing values
    // and then we groupby in a fixed time interval to get more regular output
    let out = range_df
        .lazy()
        .join(
            df.lazy(),
            [col("date_range")],
            [col("datetime")],
            JoinType::Left,
        )
        .select([col("*").interpolate()])
        .groupby_dynamic([], DynamicGroupOptions {
            index_column: "date_range".into(),
            every: Duration::parse("15m"),
            period: Duration::parse("15m"),
            offset: Duration::parse("0m"),
            truncate: true,
            include_boundaries: false,
            closed_window: ClosedWindow::Left,
        }).agg([col("*").first()])
        .collect()?;

    dbg!(out);

    Ok(())
}

这些是我使用的功能:

["csv-file", "pretty_fmt", "temporal", "dtype-date", "dtype-datetime", "lazy", "interpolate", "dynamic_groupby"]

输出

这输出

[src/main.rs:68] out = shape: (9, 9)
┌─────────────────────┬─────────────────────┬────────────┬────────────┬─────┬────────────┬────────────┬─────────────┬────────────┐
│ date_range          ┆ date_range_first    ┆ site_first ┆ val1_first ┆ ... ┆ val3_first ┆ val4_first ┆ val5_first  ┆ val6_first │
│ ---                 ┆ ---                 ┆ ---        ┆ ---        ┆     ┆ ---        ┆ ---        ┆ ---         ┆ ---        │
│ datetime[ns]        ┆ datetime[ns]        ┆ str        ┆ f64        ┆     ┆ f64        ┆ f64        ┆ f64         ┆ f64        │
╞═════════════════════╪═════════════════════╪════════════╪════════════╪═════╪════════════╪════════════╪═════════════╪════════════╡
│ 2021-01-01 00:45:00 ┆ 2021-01-01 00:45:00 ┆ XX1        ┆ null       ┆ ... ┆ null       ┆ 4.6        ┆ null        ┆ null       │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┤
│ 2021-01-01 01:00:00 ┆ 2021-01-01 01:00:00 ┆ null       ┆ 21.9       ┆ ... ┆ 77.67      ┆ 4.6        ┆ 1027.165    ┆ 0.0        │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┤
│ 2021-01-01 01:15:00 ┆ 2021-01-01 01:15:00 ┆ null       ┆ 21.9       ┆ ... ┆ 77.67      ┆ 4.6        ┆ 1027.09     ┆ 0.0        │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┤
│ 2021-01-01 01:30:00 ┆ 2021-01-01 01:30:00 ┆ null       ┆ 21.9       ┆ ... ┆ 77.67      ┆ 4.251515   ┆ 1027.015    ┆ 0.0        │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┤
│ ...                 ┆ ...                 ┆ ...        ┆ ...        ┆ ... ┆ ...        ┆ ...        ┆ ...         ┆ ...        │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┤
│ 2021-01-01 02:00:00 ┆ 2021-01-01 02:00:00 ┆ XX1        ┆ 21.795     ┆ ... ┆ 78.022333  ┆ 0.0        ┆ 1027.153333 ┆ 0.0        │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┤
│ 2021-01-01 02:15:00 ┆ 2021-01-01 02:15:00 ┆ null       ┆ 21.57      ┆ ... ┆ 78.777333  ┆ 4.983333   ┆ 1027.053333 ┆ 0.0        │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┤
│ 2021-01-01 02:30:00 ┆ 2021-01-01 02:30:00 ┆ null       ┆ 21.345     ┆ ... ┆ 79.532333  ┆ 5.366667   ┆ 1026.953333 ┆ 0.0        │
├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┤
│ 2021-01-01 02:45:00 ┆ 2021-01-01 02:45:00 ┆ XX1        ┆ 21.12      ┆ ... ┆ 80.287333  ┆ 5.75       ┆ 1026.853333 ┆ 0.0        │
└─────────────────────┴─────────────────────┴────────────┴────────────┴─────┴────────────┴────────────┴─────────────┴────────────┘

请注意,polars_core时间模块也需要,这将在下一个补丁中导出到 Polars。

于 2022-01-24T19:35:58.653 回答
0

尝试这样的事情:

use polars::prelude::*;
use std::fs::File;

fn main() {
    let mut df = CsvReader::new("raw.csv".into())
        .finish()
        .unwrap();

    //interpolate to clean up blank/nan
    //resample/groupby 15Min-1D using mean, blank/nan if missing
    
    let mut file = File::create("final.csv").expect("File not written!!!");

    CsvWriter::new(&mut file)
        .has_header(true)
        .with_delimiter(b',')
        .finish(&df)
        .unwrap();

}

一般来说,如果您收到关于 的错误Result,请尝试添加.unwrap().expect(...)

于 2022-01-22T00:06:09.147 回答