//! ```cargo
  //! [dependencies]
  //! chrono = "0.4.45"
  //! polars = { version = "0.54.4", features = ["lazy", "temporal", "sql"] }
  //! ```

  use chrono::NaiveDate;
  use polars::{
      df,
      error::PolarsError,
      frame::DataFrame,
      prelude::{IntoLazy, col},
  };


  fn main() -> Result<(), PolarsError> {
      let mut df: DataFrame = df!(
            "name" => ["Alice Archer", "Ben Brown", "Chloe Cooper", "Daniel Donovan"],
            "birthdate" => [
                NaiveDate::from_ymd_opt(1997, 1, 10).unwrap(),
                NaiveDate::from_ymd_opt(1985, 2, 15).unwrap(),
                NaiveDate::from_ymd_opt(1997, 3, 22).unwrap(),
                NaiveDate::from_ymd_opt(1997, 4, 30).unwrap(),
            ],
            "weight" => [57.9, 72.5, 54.6, 83.1], // (kg)
            "height" => [1.56, 1.77, 1.65, 1.75], // (m)
        )
        .unwrap();
        println!("Data:");
        print!("{df}\n");

        let head = df.head(Some(2));
        println!("Head:");
        print!("{head}\n");

      Ok(())
  }

Data:
shape: (4, 4)
┌────────────────┬────────────┬────────┬────────┐
│ name           ┆ birthdate  ┆ weight ┆ height │
│ ---            ┆ ---        ┆ ---    ┆ ---    │
│ str            ┆ date       ┆ f64    ┆ f64    │
╞════════════════╪════════════╪════════╪════════╡
│ Alice Archer   ┆ 1997-01-10 ┆ 57.9   ┆ 1.56   │
│ Ben Brown      ┆ 1985-02-15 ┆ 72.5   ┆ 1.77   │
│ Chloe Cooper   ┆ 1997-03-22 ┆ 54.6   ┆ 1.65   │
│ Daniel Donovan ┆ 1997-04-30 ┆ 83.1   ┆ 1.75   │
└────────────────┴────────────┴────────┴────────┘
Head:
shape: (2, 4)
┌──────────────┬────────────┬────────┬────────┐
│ name         ┆ birthdate  ┆ weight ┆ height │
│ ---          ┆ ---        ┆ ---    ┆ ---    │
│ str          ┆ date       ┆ f64    ┆ f64    │
╞══════════════╪════════════╪════════╪════════╡
│ Alice Archer ┆ 1997-01-10 ┆ 57.9   ┆ 1.56   │
│ Ben Brown    ┆ 1985-02-15 ┆ 72.5   ┆ 1.77   │
└──────────────┴────────────┴────────┴────────┘

  //! ```cargo
  //! [dependencies]
  //! chrono = "0.4.45"
  //! polars = { version = "0.54.4", features = ["lazy", "temporal", "sql"] }
  //! ```

  use chrono::NaiveDate;
  use polars::{
      df,
      error::PolarsError,
      frame::DataFrame,
      prelude::{IntoLazy, col},
  };


  fn main() -> Result<(), PolarsError> {
      let mut df: DataFrame = df!(
            "name" => ["Alice Archer", "Ben Brown", "Chloe Cooper", "Daniel Donovan"],
            "birthdate" => [
                NaiveDate::from_ymd_opt(1997, 1, 10).unwrap(),
                NaiveDate::from_ymd_opt(1985, 2, 15).unwrap(),
                NaiveDate::from_ymd_opt(1997, 3, 22).unwrap(),
                NaiveDate::from_ymd_opt(1997, 4, 30).unwrap(),
            ],
            "weight" => [57.9, 72.5, 54.6, 83.1], // (kg)
            "height" => [1.56, 1.77, 1.65, 1.75], // (m)
        )
        .unwrap();

        let result = df
            .clone()
            .lazy()
            .select([
                col("name"),
                col("birthdate").dt().year().alias("birth_year"),
                (col("weight") / col("height").pow(2)).alias("bmi"),
            ])
            .collect()?;
        println!("Column selection:");
        print!("{result}\n");

      Ok(())
  }

Column selection:
shape: (4, 3)
┌────────────────┬────────────┬───────────┐
│ name           ┆ birth_year ┆ bmi       │
│ ---            ┆ ---        ┆ ---       │
│ str            ┆ i32        ┆ f64       │
╞════════════════╪════════════╪═══════════╡
│ Alice Archer   ┆ 1997       ┆ 23.791913 │
│ Ben Brown      ┆ 1985       ┆ 23.141498 │
│ Chloe Cooper   ┆ 1997       ┆ 20.055096 │
│ Daniel Donovan ┆ 1997       ┆ 27.134694 │
└────────────────┴────────────┴───────────┘

  //! ```cargo
  //! [dependencies]
  //! chrono = "0.4.45"
  //! polars = { version = "0.54.4", features = ["lazy", "temporal", "sql"] }
  //! ```

  use chrono::NaiveDate;
  use polars::{
      df,
      error::PolarsError,
      frame::{DataFrame},
      prelude::{LazyFrame, IntoLazy, col},
  };


  fn main() -> Result<(), PolarsError> {
      let mut df: DataFrame = df!(
            "name" => ["Alice Archer", "Ben Brown", "Chloe Cooper", "Daniel Donovan"],
            "birthdate" => [
                NaiveDate::from_ymd_opt(1997, 1, 10).unwrap(),
                NaiveDate::from_ymd_opt(1985, 2, 15).unwrap(),
                NaiveDate::from_ymd_opt(1997, 3, 22).unwrap(),
                NaiveDate::from_ymd_opt(1997, 4, 30).unwrap(),
            ],
            "weight" => [57.9, 72.5, 54.6, 83.1], // (kg)
            "height" => [1.56, 1.77, 1.65, 1.75], // (m)
        )
        .unwrap();

        let result = df
            .clone()
            .lazy()
            .with_columns([
                col("birthdate").dt().year().alias("birth_year"),
                (col("weight") / col("height").pow(2)).alias("bmi"),
            ])
            .collect()?;
        println!("With added colums:");
        print!("{result}\n");

      Ok(())
  }

With added colums:
shape: (4, 6)
┌────────────────┬────────────┬────────┬────────┬────────────┬───────────┐
│ name           ┆ birthdate  ┆ weight ┆ height ┆ birth_year ┆ bmi       │
│ ---            ┆ ---        ┆ ---    ┆ ---    ┆ ---        ┆ ---       │
│ str            ┆ date       ┆ f64    ┆ f64    ┆ i32        ┆ f64       │
╞════════════════╪════════════╪════════╪════════╪════════════╪═══════════╡
│ Alice Archer   ┆ 1997-01-10 ┆ 57.9   ┆ 1.56   ┆ 1997       ┆ 23.791913 │
│ Ben Brown      ┆ 1985-02-15 ┆ 72.5   ┆ 1.77   ┆ 1985       ┆ 23.141498 │
│ Chloe Cooper   ┆ 1997-03-22 ┆ 54.6   ┆ 1.65   ┆ 1997       ┆ 20.055096 │
│ Daniel Donovan ┆ 1997-04-30 ┆ 83.1   ┆ 1.75   ┆ 1997       ┆ 27.134694 │
└────────────────┴────────────┴────────┴────────┴────────────┴───────────┘

lit का अर्थ है लिटरल और यह Polars² की लेज़ी विशेषता के लेज़ी एक्सप्रेशन API का हिस्सा है।

  //! ```cargo
  //! [dependencies]
  //! chrono = "0.4.45"
  //! polars = { version = "0.54.4", features = ["lazy", "temporal", "sql"] }
  //! ```

  use chrono::NaiveDate;
  use polars::{
      df,
      error::PolarsError,
      frame::DataFrame,
      prelude::{IntoLazy, col, cols, lit, RoundMode},
  };


  fn main() -> Result<(), PolarsError> {
      let mut df: DataFrame = df!(
            "name" => ["Alice Archer", "Ben Brown", "Chloe Cooper", "Daniel Donovan"],
            "birthdate" => [
                NaiveDate::from_ymd_opt(1997, 1, 10).unwrap(),
                NaiveDate::from_ymd_opt(1985, 2, 15).unwrap(),
                NaiveDate::from_ymd_opt(1997, 3, 22).unwrap(),
                NaiveDate::from_ymd_opt(1997, 4, 30).unwrap(),
            ],
            "weight" => [57.9, 72.5, 54.6, 83.1], // (kg)
            "height" => [1.56, 1.77, 1.65, 1.75], // (m)
        )
        .unwrap();

        let result = df
            .clone()
            .lazy()
            .select([
                col("name"),
                (cols(["weight", "height"]).as_expr() * lit(0.95))
                    .round(2, RoundMode::default())
                    .name()
                    .suffix("-5%"),
            ])
            .collect()?;
        println!("Transform:");
        print!("{result}\n");

      Ok(())
  }

Transform:
shape: (4, 3)
┌────────────────┬───────────┬───────────┐
│ name           ┆ weight-5% ┆ height-5% │
│ ---            ┆ ---       ┆ ---       │
│ str            ┆ f64       ┆ f64       │
╞════════════════╪═══════════╪═══════════╡
│ Alice Archer   ┆ 55.0      ┆ 1.48      │
│ Ben Brown      ┆ 68.88     ┆ 1.68      │
│ Chloe Cooper   ┆ 51.87     ┆ 1.57      │
│ Daniel Donovan ┆ 78.94     ┆ 1.66      │
└────────────────┴───────────┴───────────┘

  //! ```cargo
  //! [dependencies]
  //! chrono = "0.4.45"
  //! polars = { version = "0.54.4", features = ["lazy", "temporal", "is_between", "sql"] }
  //! ```

  use chrono::NaiveDate;
  use polars::{
      df,
      error::PolarsError,
      frame::{DataFrame},
      prelude::{IntoLazy, col, lit, ClosedInterval},
  };


  fn main() -> Result<(), PolarsError> {
      let mut df: DataFrame = df!(
            "name" => ["Alice Archer", "Ben Brown", "Chloe Cooper", "Daniel Donovan"],
            "birthdate" => [
                NaiveDate::from_ymd_opt(1997, 1, 10).unwrap(),
                NaiveDate::from_ymd_opt(1985, 2, 15).unwrap(),
                NaiveDate::from_ymd_opt(1997, 3, 22).unwrap(),
                NaiveDate::from_ymd_opt(1997, 4, 30).unwrap(),
            ],
            "weight" => [57.9, 72.5, 54.6, 83.1], // (kg)
            "height" => [1.56, 1.77, 1.65, 1.75], // (m)
        )
        .unwrap();

        let result = df
            .clone()
            .lazy()
            .filter(col("birthdate").dt().year().lt(lit(1990)))
            .collect()?;
        println!("With row filtering:");
        print!("{result}\n");

        let result = df
              .clone()
              .lazy()
              .filter(
                  col("birthdate")
                      .is_between(
                          lit(NaiveDate::from_ymd_opt(1982, 12, 31).unwrap()),
                          lit(NaiveDate::from_ymd_opt(1996, 1, 1).unwrap()),
                          ClosedInterval::Both,
                      )
                      .and(col("height").gt(lit(1.7))),
              )
              .collect()?;
        println!("With complex row filtering:");
        print!("{result}\n");

      Ok(())
  }

With row filtering:
shape: (1, 4)
┌───────────┬────────────┬────────┬────────┐
│ name      ┆ birthdate  ┆ weight ┆ height │
│ ---       ┆ ---        ┆ ---    ┆ ---    │
│ str       ┆ date       ┆ f64    ┆ f64    │
╞═══════════╪════════════╪════════╪════════╡
│ Ben Brown ┆ 1985-02-15 ┆ 72.5   ┆ 1.77   │
└───────────┴────────────┴────────┴────────┘
With complex row filtering:
shape: (1, 4)
┌───────────┬────────────┬────────┬────────┐
│ name      ┆ birthdate  ┆ weight ┆ height │
│ ---       ┆ ---        ┆ ---    ┆ ---    │
│ str       ┆ date       ┆ f64    ┆ f64    │
╞═══════════╪════════════╪════════╪════════╡
│ Ben Brown ┆ 1985-02-15 ┆ 72.5   ┆ 1.77   │
└───────────┴────────────┴────────┴────────┘

  //! ```cargo
  //! [dependencies]
  //! chrono = "0.4.45"
  //! polars = { version = "0.54.4", features = ["lazy", "temporal", "sql"] }
  //! ```

  use chrono::NaiveDate;
  use polars::{
      df,
      error::PolarsError,
      frame::DataFrame,
      prelude::{IntoLazy, col, lit, len, RoundMode},
  };


  fn main() -> Result<(), PolarsError> {
      let mut df: DataFrame = df!(
            "name" => ["Alice Archer", "Ben Brown", "Chloe Cooper", "Daniel Donovan"],
            "birthdate" => [
                NaiveDate::from_ymd_opt(1997, 1, 10).unwrap(),
                NaiveDate::from_ymd_opt(1985, 2, 15).unwrap(),
                NaiveDate::from_ymd_opt(1997, 3, 22).unwrap(),
                NaiveDate::from_ymd_opt(1997, 4, 30).unwrap(),
            ],
            "weight" => [57.9, 72.5, 54.6, 83.1], // (kg)
            "height" => [1.56, 1.77, 1.65, 1.75], // (m)
        )
        .unwrap();

        let result = df
            .clone()
            .lazy()
            .group_by([(col("birthdate").dt().year() / lit(10) * lit(10)).alias("decade")])
            .agg([len()])
            .collect()?;
        println!("Grouping by birth decade:");
        print!("{result}\n");

        let result = df
            .clone()
            .lazy()
            .group_by([(col("birthdate").dt().year() / lit(10) * lit(10)).alias("decade")])
            .agg([
                len().alias("sample_size"),
                col("weight")
                    .mean()
                    .round(2, RoundMode::default())
                    .alias("avg_weight"),
                col("height").max().alias("tallest"),
            ])
            .collect()?;
        println!("Grouping by derived features:");
        println!("{result}");

      Ok(())
  }

Grouping by birth decade:
shape: (2, 2)
┌────────┬─────┐
│ decade ┆ len │
│ ---    ┆ --- │
│ i32    ┆ u32 │
╞════════╪═════╡
│ 1990   ┆ 3   │
│ 1980   ┆ 1   │
└────────┴─────┘
Grouping by derived features:
shape: (2, 4)
┌────────┬─────────────┬────────────┬─────────┐
│ decade ┆ sample_size ┆ avg_weight ┆ tallest │
│ ---    ┆ ---         ┆ ---        ┆ ---     │
│ i32    ┆ u32         ┆ f64        ┆ f64     │
╞════════╪═════════════╪════════════╪═════════╡
│ 1980   ┆ 1           ┆ 72.5       ┆ 1.77    │
│ 1990   ┆ 3           ┆ 65.2       ┆ 1.75    │
└────────┴─────────────┴────────────┴─────────┘

डेटा डाउनलोड करें, इसे Polars² के साथ लोड करें और फिर हेड प्रिंट करें

  //! ```cargo
  //! [dependencies]
  //! chrono = "0.4.45"
  //! polars = { version = "0.54.4", features = ["lazy", "temporal", "sql", "csv"] }
  //! ```

  use polars::{
      error::PolarsError,
      prelude::{CsvParseOptions, CsvReadOptions, SerReader},
  };

  fn main() -> Result<(), PolarsError> {
      let df_csv = CsvReadOptions::default()
          .with_has_header(true)
          .with_parse_options(CsvParseOptions::default().with_try_parse_dates(true))
          .try_into_reader_with_file_path(Some(
              "data/Water Quality Monitoring Dataset_ Ireland.csv".into(),
          ))?
          .finish()?;
      println!("{df_csv}");
      Ok(())
  }

rust-script failed with exit code 1

[stderr]
Error: ComputeError(ErrString("could not parse `50.5` as dtype `i64` at column 'Alkalinity-total (as CaCO3)' (column number 4)\n\nThe current offset in the file is 7606 bytes.\n\nYou might want to try:\n- increasing `infer_schema_length` (e.g. `infer_schema_length=10000`),\n- specifying correct dtype with the `schema_overrides` argument\n- setting `ignore_errors` to `True`,\n- adding `50.5` to the `null_values` list.\n\nOriginal error: ```invalid primitive value found during CSV parsing```"))

Polars² कुछ कॉलम के प्रकार (type) का सही अनुमान नहीं लगा रहा है। आइए इसे डिफ़ॉल्ट रूप से 100 पंक्तियों से अनुमान लगाने दें।

  //! ```cargo
  //! [dependencies]
  //! chrono = "0.4.45"
  //! polars = { version = "0.54.4", features = ["lazy", "temporal", "sql", "csv"] }
  //! ```

  use polars::{
      error::PolarsError,
      prelude::{CsvParseOptions, CsvReadOptions, SerReader},
  };

  fn main() -> Result<(), PolarsError> {
      let df_csv = CsvReadOptions::default()
          .with_has_header(true)
          .with_infer_schema_length(None)
          .with_parse_options(CsvParseOptions::default().with_try_parse_dates(true))
          .try_into_reader_with_file_path(Some(
              "data/Water Quality Monitoring Dataset_ Ireland.csv".into(),
          ))?
          .finish()?;
      println!("{df_csv}");
      Ok(())
  }

shape: (29_159, 14)
┌──────────────┬───────┬────────────┬──────────────┬───┬──────┬─────────────┬─────────────┬────────┐
│ WaterbodyNam ┆ Years ┆ SampleDate ┆ Alkalinity-t ┆ … ┆ pH   ┆ Temperature ┆ Total       ┆ True   │
│ e            ┆ ---   ┆ ---        ┆ otal (as     ┆   ┆ ---  ┆ ---         ┆ Hardness    ┆ Colour │
│ ---          ┆ i64   ┆ str        ┆ CaCO3)       ┆   ┆ f64  ┆ f64         ┆ (as CaCO3)  ┆ ---    │
│ str          ┆       ┆            ┆ ---          ┆   ┆      ┆             ┆ ---         ┆ f64    │
│              ┆       ┆            ┆ f64          ┆   ┆      ┆             ┆ f64         ┆        │
╞══════════════╪═══════╪════════════╪══════════════╪═══╪══════╪═════════════╪═════════════╪════════╡
│ ABBEYTOWN_01 ┆ 2023  ┆ Feb        ┆ 314.0        ┆ … ┆ 7.8  ┆ 10.4        ┆ 370.0       ┆ 24.0   │
│ 0            ┆       ┆            ┆              ┆   ┆      ┆             ┆             ┆        │
│ Allua        ┆ 2007  ┆ Aug        ┆ 14.0         ┆ … ┆ 7.42 ┆ 17.8        ┆ 13.4        ┆ 35.0   │
│ Allua        ┆ 2007  ┆ Aug        ┆ 17.0         ┆ … ┆ 7.67 ┆ 18.1        ┆ 15.8        ┆ 29.0   │
│ Allua        ┆ 2007  ┆ Aug        ┆ 18.0         ┆ … ┆ 7.63 ┆ 17.8        ┆ 15.9        ┆ 31.0   │
│ Allua        ┆ 2007  ┆ Sep        ┆ 19.0         ┆ … ┆ 7.33 ┆ 20.1        ┆ 15.4        ┆ 23.0   │
│ …            ┆ …     ┆ …          ┆ …            ┆ … ┆ …    ┆ …           ┆ …           ┆ …      │
│ SULLANE_060  ┆ 2022  ┆ Sep        ┆ 31.0         ┆ … ┆ 7.1  ┆ 14.9        ┆ 45.0        ┆ 27.0   │
│ SULLANE_060  ┆ 2022  ┆ Nov        ┆ 22.0         ┆ … ┆ 6.9  ┆ 12.3        ┆ 34.0        ┆ 58.0   │
│ SULLANE_060  ┆ 2023  ┆ Mar        ┆ 36.0         ┆ … ┆ 7.2  ┆ 7.1         ┆ 44.0        ┆ 20.0   │
│ TWO POT      ┆ 2023  ┆ Feb        ┆ 81.0         ┆ … ┆ 7.4  ┆ 8.6         ┆ 120.0       ┆ 9.0    │
│ (Cork        ┆       ┆            ┆              ┆   ┆      ┆             ┆             ┆        │
│ City)_010    ┆       ┆            ┆              ┆   ┆      ┆             ┆             ┆        │
│ TWO POT      ┆ 2023  ┆ Feb        ┆ 82.0         ┆ … ┆ 7.8  ┆ 8.1         ┆ 121.0       ┆ 5.0    │
│ (Cork        ┆       ┆            ┆              ┆   ┆      ┆             ┆             ┆        │
│ City)_010    ┆       ┆            ┆              ┆   ┆      ┆             ┆             ┆        │
└──────────────┴───────┴────────────┴──────────────┴───┴──────┴─────────────┴─────────────┴────────┘

आइए अब Polars⁴ को 10000 पंक्तियों से कॉलम के उचित प्रकार (types) का अनुमान लगाने दें

  //! ```cargo
  //! [dependencies]
  //! chrono = "0.4.45"
  //! polars = { version = "0.54.4", features = ["lazy", "temporal", "sql", "csv"] }
  //! ```

  use polars::{
      error::PolarsError,
      prelude::{CsvParseOptions, CsvReadOptions, SerReader},
  };

  fn main() -> Result<(), PolarsError> {
      let df_csv = CsvReadOptions::default()
          .with_has_header(true)
          .with_infer_schema_length(Some(10_000))
          .with_parse_options(CsvParseOptions::default().with_try_parse_dates(true))
          .try_into_reader_with_file_path(Some(
              "data/Water Quality Monitoring Dataset_ Ireland.csv".into(),
          ))?
          .finish()?;
      println!("{df_csv}");
      Ok(())
  }

shape: (29_159, 14)
┌──────────────┬───────┬────────────┬──────────────┬───┬──────┬─────────────┬─────────────┬────────┐
│ WaterbodyNam ┆ Years ┆ SampleDate ┆ Alkalinity-t ┆ … ┆ pH   ┆ Temperature ┆ Total       ┆ True   │
│ e            ┆ ---   ┆ ---        ┆ otal (as     ┆   ┆ ---  ┆ ---         ┆ Hardness    ┆ Colour │
│ ---          ┆ i64   ┆ str        ┆ CaCO3)       ┆   ┆ f64  ┆ f64         ┆ (as CaCO3)  ┆ ---    │
│ str          ┆       ┆            ┆ ---          ┆   ┆      ┆             ┆ ---         ┆ f64    │
│              ┆       ┆            ┆ f64          ┆   ┆      ┆             ┆ f64         ┆        │
╞══════════════╪═══════╪════════════╪══════════════╪═══╪══════╪═════════════╪═════════════╪════════╡
│ ABBEYTOWN_01 ┆ 2023  ┆ Feb        ┆ 314.0        ┆ … ┆ 7.8  ┆ 10.4        ┆ 370.0       ┆ 24.0   │
│ 0            ┆       ┆            ┆              ┆   ┆      ┆             ┆             ┆        │
│ Allua        ┆ 2007  ┆ Aug        ┆ 14.0         ┆ … ┆ 7.42 ┆ 17.8        ┆ 13.4        ┆ 35.0   │
│ Allua        ┆ 2007  ┆ Aug        ┆ 17.0         ┆ … ┆ 7.67 ┆ 18.1        ┆ 15.8        ┆ 29.0   │
│ Allua        ┆ 2007  ┆ Aug        ┆ 18.0         ┆ … ┆ 7.63 ┆ 17.8        ┆ 15.9        ┆ 31.0   │
│ Allua        ┆ 2007  ┆ Sep        ┆ 19.0         ┆ … ┆ 7.33 ┆ 20.1        ┆ 15.4        ┆ 23.0   │
│ …            ┆ …     ┆ …          ┆ …            ┆ … ┆ …    ┆ …           ┆ …           ┆ …      │
│ SULLANE_060  ┆ 2022  ┆ Sep        ┆ 31.0         ┆ … ┆ 7.1  ┆ 14.9        ┆ 45.0        ┆ 27.0   │
│ SULLANE_060  ┆ 2022  ┆ Nov        ┆ 22.0         ┆ … ┆ 6.9  ┆ 12.3        ┆ 34.0        ┆ 58.0   │
│ SULLANE_060  ┆ 2023  ┆ Mar        ┆ 36.0         ┆ … ┆ 7.2  ┆ 7.1         ┆ 44.0        ┆ 20.0   │
│ TWO POT      ┆ 2023  ┆ Feb        ┆ 81.0         ┆ … ┆ 7.4  ┆ 8.6         ┆ 120.0       ┆ 9.0    │
│ (Cork        ┆       ┆            ┆              ┆   ┆      ┆             ┆             ┆        │
│ City)_010    ┆       ┆            ┆              ┆   ┆      ┆             ┆             ┆        │
│ TWO POT      ┆ 2023  ┆ Feb        ┆ 82.0         ┆ … ┆ 7.8  ┆ 8.1         ┆ 121.0       ┆ 5.0    │
│ (Cork        ┆       ┆            ┆              ┆   ┆      ┆             ┆             ┆        │
│ City)_010    ┆       ┆            ┆              ┆   ┆      ┆             ┆             ┆        │
└──────────────┴───────┴────────────┴──────────────┴───┴──────┴─────────────┴─────────────┴────────┘

// imports go here

fn main() -> PolarsResult<()> {
    let df = CsvReadOptions::default()
        .with_has_header(true)
        // Discovery step: scan the file because we do not know columns yet.
        .with_infer_schema_length(Some(10_000))
        .with_parse_options(CsvParseOptions::default().with_try_parse_dates(true))
        .try_into_reader_with_file_path(Some(
            "data/Water Quality Monitoring Dataset_ Ireland.csv".into(),
        ))?
        .finish()?;

    inspect_raw_data(df.clone())?;

    Ok(())
}

rows: 29159
columns: 14

columns and types:
WaterbodyName: String (text or mixed)
Years: Int64 (number)
SampleDate: String (text or mixed)
Alkalinity-total (as CaCO3): Float64 (number)
Ammonia-Total (as N): Float64 (number)
BOD - 5 days (Total): Float64 (number)
Chloride: Float64 (number)
Conductivity @25°C: Float64 (number)
Dissolved Oxygen: Float64 (number)
ortho-Phosphate (as P) - unspecified: Float64 (number)
pH: Float64 (number)
Temperature: Float64 (number)
Total Hardness (as CaCO3): Float64 (number)
True Colour: Float64 (number)

one raw row:
shape: (1, 14)
┌───────────────┬───────┬────────────┬─────────────────────┬───┬─────┬─────────────┬────────────────────┬─────────────┐
│ WaterbodyName ┆ Years ┆ SampleDate ┆ Alkalinity-total    ┆ … ┆ pH  ┆ Temperature ┆ Total Hardness (as ┆ True Colour │
│ ---           ┆ ---   ┆ ---        ┆ (as CaCO3)          ┆   ┆ --- ┆ ---         ┆ CaCO3)             ┆ ---         │
│ str           ┆ i64   ┆ str        ┆ ---                 ┆   ┆ f64 ┆ f64         ┆ ---                ┆ f64         │
│               ┆       ┆            ┆ f64                 ┆   ┆     ┆             ┆ f64                ┆             │
╞═══════════════╪═══════╪════════════╪═════════════════════╪═══╪═════╪═════════════╪════════════════════╪═════════════╡
│ ABBEYTOWN_010 ┆ 2023  ┆ Feb        ┆ 314.0               ┆ … ┆ 7.8 ┆ 10.4        ┆ 370.0              ┆ 24.0        │
└───────────────┴───────┴────────────┴─────────────────────┴───┴─────┴─────────────┴────────────────────┴─────────────┘

location/date columns: ["WaterbodyName", "Years", "SampleDate"]
measurement columns: ["Alkalinity-total (as CaCO3)", "Ammonia-Total (as N)", "BOD - 5 days (Total)", "Chloride", "Conductivity @25°C", "Dissolved Oxygen", "ortho-Phosphate (as P) - unspecified", "pH", "Temperature", "Total Hardness (as CaCO3)", "True Colour"]

long water-quality shape:
shape: (10, 7)
┌───────────────┬───────┬────────────┬─────────────────────────────┬───────────────────┬──────────────────┬──────────┐
│ WaterbodyName ┆ Years ┆ SampleDate ┆ source_column               ┆ measurement_value ┆ parameter        ┆ unit     │
│ ---           ┆ ---   ┆ ---        ┆ ---                         ┆ ---               ┆ ---              ┆ ---      │
│ str           ┆ i64   ┆ str        ┆ str                         ┆ f64               ┆ str              ┆ str      │
╞═══════════════╪═══════╪════════════╪═════════════════════════════╪═══════════════════╪══════════════════╪══════════╡
│ ABBEYTOWN_010 ┆ 2023  ┆ Feb        ┆ Alkalinity-total (as CaCO3) ┆ 314.0             ┆ Alkalinity-total ┆ as CaCO3 │
│ Allua         ┆ 2007  ┆ Aug        ┆ Alkalinity-total (as CaCO3) ┆ 14.0              ┆ Alkalinity-total ┆ as CaCO3 │
│ Allua         ┆ 2007  ┆ Aug        ┆ Alkalinity-total (as CaCO3) ┆ 17.0              ┆ Alkalinity-total ┆ as CaCO3 │
│ Allua         ┆ 2007  ┆ Aug        ┆ Alkalinity-total (as CaCO3) ┆ 18.0              ┆ Alkalinity-total ┆ as CaCO3 │
│ Allua         ┆ 2007  ┆ Sep        ┆ Alkalinity-total (as CaCO3) ┆ 19.0              ┆ Alkalinity-total ┆ as CaCO3 │
│ Allua         ┆ 2007  ┆ Sep        ┆ Alkalinity-total (as CaCO3) ┆ 19.0              ┆ Alkalinity-total ┆ as CaCO3 │
│ Allua         ┆ 2007  ┆ Sep        ┆ Alkalinity-total (as CaCO3) ┆ 18.0              ┆ Alkalinity-total ┆ as CaCO3 │
│ Allua         ┆ 2008  ┆ Jan        ┆ Alkalinity-total (as CaCO3) ┆ 8.0               ┆ Alkalinity-total ┆ as CaCO3 │
│ Allua         ┆ 2008  ┆ Jan        ┆ Alkalinity-total (as CaCO3) ┆ 9.0               ┆ Alkalinity-total ┆ as CaCO3 │
│ Allua         ┆ 2008  ┆ Jan        ┆ Alkalinity-total (as CaCO3) ┆ 10.0              ┆ Alkalinity-total ┆ as CaCO3 │
└───────────────┴───────┴────────────┴─────────────────────────────┴───────────────────┴──────────────────┴──────────┘