Would you like to see your link here? Contact us

Notesclub

created by hec & contributors

terms privacy

Lab: Explorer

elixir/explorer.livemd

Charlie Roth

@charlieroth

lab

More notebooks

Lab: Explorer

Mix.install([
  {:explorer, "~> 0.10.0"},
  {:kino, "~> 0.14.2"},
  {:kino_explorer, "~> 0.1.23"}
])

Setup

alias Explorer.DataFrame
alias Explorer.Series

Explorer.Series

Reading and Writing Data

df = Explorer.Datasets.fossil_fuels()

#Explorer.DataFrame<
  Polars[1094 x 10]
  year s64 [2010, 2010, 2010, 2010, 2010, ...]
  country string ["AFGHANISTAN", "ALBANIA", "ALGERIA", "ANDORRA", "ANGOLA", ...]
  total s64 [2308, 1254, 32500, 141, 7924, ...]
  solid_fuel s64 [627, 117, 332, 0, 0, ...]
  liquid_fuel s64 [1601, 953, 12381, 141, 3649, ...]
  gas_fuel s64 [74, 7, 14565, 0, 374, ...]
  cement s64 [5, 177, 2598, 0, 204, ...]
  gas_flaring s64 [0, 0, 2623, 0, 3697, ...]
  per_capita f64 [0.08, 0.43, 0.9, 1.68, 0.37, ...]
  bunker_fuels s64 [9, 7, 663, 0, 321, ...]
>

input = Kino.Input.text("Filename")

filename = Kino.Input.read(input)
DataFrame.to_csv(df, filename)

:ok

Working with Series

Expolorer works up from the concept of a Series. A DataFrame can be thought of as a row-aligned map of Series. These are like vectors in R or series in Pandas.

Series can be constructed from Elixir basic types

s1 = Series.from_list([1, 2, 3])

#Explorer.Series<
  Polars[3]
  s64 [1, 2, 3]
>

s2 = Series.from_list(["a", "b", "c"])

#Explorer.Series<
  Polars[3]
  string ["a", "b", "c"]
>

s3 = Series.from_list([~D[2024-10-31], ~D[2024-11-01]])

#Explorer.Series<
  Polars[2]
  date [2024-10-31, 2024-11-01]
>

Series.dtype(s3)

:date

Series.size(s3)

Series are also nullable

s = Series.from_list([1.0, 2.0, nil, nil, 5.0])

#Explorer.Series<
  Polars[5]
  f64 [1.0, 2.0, nil, nil, 5.0]
>

Missing values can be filled using one of the following strategies:

:forward - replace nil with the previous value
:backward - replace nil with the next value
:max - replace nil with the series maximum
:min - replace nil with the series minimum
:mean - replace nil with the series mean

Series.fill_missing(s, :forward)

#Explorer.Series<
  Polars[5]
  f64 [1.0, 2.0, 2.0, 2.0, 5.0]
>

Series.fill_missing(s, :backward)

#Explorer.Series<
  Polars[5]
  f64 [1.0, 2.0, 5.0, 5.0, 5.0]
>

Series.fill_missing(s, :max)

#Explorer.Series<
  Polars[5]
  f64 [1.0, 2.0, 5.0, 5.0, 5.0]
>

Series.fill_missing(s, :min)

#Explorer.Series<
  Polars[5]
  f64 [1.0, 2.0, 1.0, 1.0, 5.0]
>

Series.fill_missing(s, :mean)

#Explorer.Series<
  Polars[5]
  f64 [1.0, 2.0, 2.6666666666666665, 2.6666666666666665, 5.0]
>

A goal of Explorer is useful error messages

Series.from_list([1, 2, 3, "a"])

Series implement the Access protocol. You can slice and dice a Series in many ways:

s = 1..10 |> Enum.to_list() |> Series.from_list()

#Explorer.Series<
  Polars[10]
  s64 [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
>

s[1]

s[-1]

s[0..4]

#Explorer.Series<
  Polars[5]
  s64 [1, 2, 3, 4, 5]
>

s[[0, 4, 4]]

#Explorer.Series<
  Polars[3]
  s64 [1, 5, 5]
>

Explorer comparisons return boolean series

s = 1..11 |> Enum.to_list() |> Series.from_list()
s1 = 11..1//-1 |> Enum.to_list() |> Series.from_list()
Series.equal(s, s1)

#Explorer.Series<
  Polars[11]
  boolean [false, false, false, false, false, true, false, false, false, false, false]
>

Series.equal(s, 5)

#Explorer.Series<
  Polars[11]
  boolean [false, false, false, false, true, false, false, false, false, false, false]
>

Series.not_equal(s, 10)

#Explorer.Series<
  Polars[11]
  boolean [true, true, true, true, true, true, true, true, true, false, true]
>

Series.greater_equal(s, 5)

#Explorer.Series<
  Polars[11]
  boolean [false, false, false, false, true, true, true, true, true, true, true]
>

Explorer supports arithmetic

Series.add(s, s1)

#Explorer.Series<
  Polars[11]
  s64 [12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12]
>

Series.subtract(s, 4)

#Explorer.Series<
  Polars[11]
  s64 [-3, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7]
>

Series.multiply(s, s1)

#Explorer.Series<
  Polars[11]
  s64 [11, 20, 27, 32, 35, 36, 35, 32, 27, 20, 11]
>

Sorting a Series is trivial as well

1..100
|> Enum.to_list()
|> Enum.shuffle()
|> Series.from_list()
|> Series.sort()

#Explorer.Series<
  Polars[100]
  s64 [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, ...]
>

s = 
  1..100
  |> Enum.to_list()
  |> Enum.shuffle()
  |> Series.from_list()

ids = 
  s
  |> Series.argsort()
  |> Series.to_list()

[7, 48, 70, 59, 64, 18, 62, 24, 60, 20, 45, 6, 38, 3, 41, 76, 72, 31, 92, 10, 5, 34, 42, 37, 91, 71,
 69, 22, 82, 68, 80, 30, 88, 95, 56, 84, 14, 77, 26, 74, 81, 99, 16, 29, 85, 13, 55, 53, 9, 40, ...]

Series.slice(s, ids)

#Explorer.Series<
  Polars[100]
  s64 [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, ...]
>

Calculating cumulative sumsn

s = 1..100 |> Enum.to_list() |> Series.from_list()
Series.cumulative_sum(s)

#Explorer.Series<
  Polars[100]
  s64 [1, 3, 6, 10, 15, 21, 28, 36, 45, 55, 66, 78, 91, 105, 120, 136, 153, 171, 190, 210, 231, 253, 276, 300, 325, 351, 378, 406, 435, 465, 496, 528, 561, 595, 630, 666, 703, 741, 780, 820, 861, 903, 946, 990, 1035, 1081, 1128, 1176, 1225, 1275, ...]
>

Calcuate rolling sum

Series.window_sum(s, 4)

#Explorer.Series<
  Polars[100]
  s64 [1, 3, 6, 10, 14, 18, 22, 26, 30, 34, 38, 42, 46, 50, 54, 58, 62, 66, 70, 74, 78, 82, 86, 90, 94, 98, 102, 106, 110, 114, 118, 122, 126, 130, 134, 138, 142, 146, 150, 154, 158, 162, 166, 170, 174, 178, 182, 186, 190, 194, ...]
>

Counting and listing unique values

s = Series.from_list(["a", "b", "b", "c", "c", "c"])
Series.distinct(s)

#Explorer.Series<
  Polars[3]
  string ["a", "b", "c"]
>

Series.n_distinct(s)

Series.frequencies(s)

#Explorer.DataFrame<
  Polars[3 x 2]
  values string ["c", "b", "a"]
  counts u32 [3, 2, 1]
>

Working with DataFrames

A DataFrame is a collection of Series of the same size, which is why you can create a DataFrame from a Keyword list

DataFrame.new(a: [1, 2, 3], b: ["a", "b", "c"])

#Explorer.DataFrame<
  Polars[3 x 2]
  a s64 [1, 2, 3]
  b string ["a", "b", "c"]
>

DataFrame.names(df)

["year", "country", "total", "solid_fuel", "liquid_fuel", "gas_fuel", "cement", "gas_flaring",
 "per_capita", "bunker_fuels"]

DataFrame.dtypes(df)

%{
  "bunker_fuels" => {:s, 64},
  "cement" => {:s, 64},
  "country" => :string,
  "gas_flaring" => {:s, 64},
  "gas_fuel" => {:s, 64},
  "liquid_fuel" => {:s, 64},
  "per_capita" => {:f, 64},
  "solid_fuel" => {:s, 64},
  "total" => {:s, 64},
  "year" => {:s, 64}
}

DataFrame.shape(df)

{1094, 10}

{DataFrame.n_rows(df), DataFrame.n_columns(df)}

{1094, 10}

DataFrame.head(df)

#Explorer.DataFrame<
  Polars[5 x 10]
  year s64 [2010, 2010, 2010, 2010, 2010]
  country string ["AFGHANISTAN", "ALBANIA", "ALGERIA", "ANDORRA", "ANGOLA"]
  total s64 [2308, 1254, 32500, 141, 7924]
  solid_fuel s64 [627, 117, 332, 0, 0]
  liquid_fuel s64 [1601, 953, 12381, 141, 3649]
  gas_fuel s64 [74, 7, 14565, 0, 374]
  cement s64 [5, 177, 2598, 0, 204]
  gas_flaring s64 [0, 0, 2623, 0, 3697]
  per_capita f64 [0.08, 0.43, 0.9, 1.68, 0.37]
  bunker_fuels s64 [9, 7, 663, 0, 321]
>

DataFrame.tail(df)

#Explorer.DataFrame<
  Polars[5 x 10]
  year s64 [2014, 2014, 2014, 2014, 2014]
  country string ["VIET NAM", "WALLIS AND FUTUNA ISLANDS", "YEMEN", "ZAMBIA", "ZIMBABWE"]
  total s64 [45517, 6, 6190, 1228, 3278]
  solid_fuel s64 [19246, 0, 137, 132, 2097]
  liquid_fuel s64 [12694, 6, 5090, 797, 1005]
  gas_fuel s64 [5349, 0, 581, 0, 0]
  cement s64 [8229, 0, 381, 299, 177]
  gas_flaring s64 [0, 0, 0, 0, 0]
  per_capita f64 [0.49, 0.44, 0.24, 0.08, 0.22]
  bunker_fuels s64 [761, 1, 153, 33, 9]
>

Verbs and Macros

In Explorer, like in dplyr, there are five main verbs to work with DataFrames

select
filter
mutate
sort
summarise

require DataFrame, as: DF

Explorer.DataFrame

Select

DF.select(df, ["year", "country"])

#Explorer.DataFrame<
  Polars[1094 x 2]
  year s64 [2010, 2010, 2010, 2010, 2010, ...]
  country string ["AFGHANISTAN", "ALBANIA", "ALGERIA", "ANDORRA", "ANGOLA", ...]
>

DF.select(df, &amp;String.ends_with?(&amp;1, "fuel"))

#Explorer.DataFrame<
  Polars[1094 x 3]
  solid_fuel s64 [627, 117, 332, 0, 0, ...]
  liquid_fuel s64 [1601, 953, 12381, 141, 3649, ...]
  gas_fuel s64 [74, 7, 14565, 0, 374, ...]
>

DF.discard(df, &amp;String.ends_with?(&amp;1, "fuel"))

#Explorer.DataFrame<
  Polars[1094 x 7]
  year s64 [2010, 2010, 2010, 2010, 2010, ...]
  country string ["AFGHANISTAN", "ALBANIA", "ALGERIA", "ANDORRA", "ANGOLA", ...]
  total s64 [2308, 1254, 32500, 141, 7924, ...]
  cement s64 [5, 177, 2598, 0, 204, ...]
  gas_flaring s64 [0, 0, 2623, 0, 3697, ...]
  per_capita f64 [0.08, 0.43, 0.9, 1.68, 0.37, ...]
  bunker_fuels s64 [9, 7, 663, 0, 321, ...]
>

Filter

DF.filter(df, country == "BRAZIL")

#Explorer.DataFrame<
  Polars[5 x 10]
  year s64 [2010, 2011, 2012, 2013, 2014]
  country string ["BRAZIL", "BRAZIL", "BRAZIL", "BRAZIL", "BRAZIL"]
  total s64 [114468, 119829, 128178, 137354, 144480]
  solid_fuel s64 [15965, 17498, 17165, 18773, 20089]
  liquid_fuel s64 [74689, 78849, 84409, 88898, 92454]
  gas_fuel s64 [14372, 13778, 16328, 19399, 21297]
  cement s64 [8040, 8717, 9428, 9517, 9691]
  gas_flaring s64 [1402, 987, 848, 767, 949]
  per_capita f64 [0.58, 0.6, 0.63, 0.67, 0.7]
  bunker_fuels s64 [5101, 5516, 5168, 4895, 4895]
>

DF.filter(df, country == "ALGERIA" and year > 2012)

#Explorer.DataFrame<
  Polars[2 x 10]
  year s64 [2013, 2014]
  country string ["ALGERIA", "ALGERIA"]
  total s64 [36669, 39651]
  solid_fuel s64 [198, 149]
  liquid_fuel s64 [14170, 14422]
  gas_fuel s64 [17863, 20151]
  cement s64 [2516, 2856]
  gas_flaring s64 [1922, 2073]
  per_capita f64 [0.96, 1.02]
  bunker_fuels s64 [687, 581]
>

DF.filter_with(df, fn ldf ->
  ldf["country"]
  |> Series.equal("ALGERIA")
  |> Series.and(Series.greater(ldf["year"], 2012))
end)

#Explorer.DataFrame<
  Polars[2 x 10]
  year s64 [2013, 2014]
  country string ["ALGERIA", "ALGERIA"]
  total s64 [36669, 39651]
  solid_fuel s64 [198, 149]
  liquid_fuel s64 [14170, 14422]
  gas_fuel s64 [17863, 20151]
  cement s64 [2516, 2856]
  gas_flaring s64 [1922, 2073]
  per_capita f64 [0.96, 1.02]
  bunker_fuels s64 [687, 581]
>

Mutate

DF.mutate(df, new_column: solid_fuel + cement)

#Explorer.DataFrame<
  Polars[1094 x 11]
  year s64 [2010, 2010, 2010, 2010, 2010, ...]
  country string ["AFGHANISTAN", "ALBANIA", "ALGERIA", "ANDORRA", "ANGOLA", ...]
  total s64 [2308, 1254, 32500, 141, 7924, ...]
  solid_fuel s64 [627, 117, 332, 0, 0, ...]
  liquid_fuel s64 [1601, 953, 12381, 141, 3649, ...]
  gas_fuel s64 [74, 7, 14565, 0, 374, ...]
  cement s64 [5, 177, 2598, 0, 204, ...]
  gas_flaring s64 [0, 0, 2623, 0, 3697, ...]
  per_capita f64 [0.08, 0.43, 0.9, 1.68, 0.37, ...]
  bunker_fuels s64 [9, 7, 663, 0, 321, ...]
  new_column s64 [632, 294, 2930, 0, 204, ...]
>

DF.mutate(
  df,
  gas_fuel: Series.cast(gas_fuel, :float),
  gas_and_liquid_fuel: gas_fuel + liquid_fuel
)

#Explorer.DataFrame<
  Polars[1094 x 11]
  year s64 [2010, 2010, 2010, 2010, 2010, ...]
  country string ["AFGHANISTAN", "ALBANIA", "ALGERIA", "ANDORRA", "ANGOLA", ...]
  total s64 [2308, 1254, 32500, 141, 7924, ...]
  solid_fuel s64 [627, 117, 332, 0, 0, ...]
  liquid_fuel s64 [1601, 953, 12381, 141, 3649, ...]
  gas_fuel f64 [74.0, 7.0, 14565.0, 0.0, 374.0, ...]
  cement s64 [5, 177, 2598, 0, 204, ...]
  gas_flaring s64 [0, 0, 2623, 0, 3697, ...]
  per_capita f64 [0.08, 0.43, 0.9, 1.68, 0.37, ...]
  bunker_fuels s64 [9, 7, 663, 0, 321, ...]
  gas_and_liquid_fuel s64 [1675, 960, 26946, 141, 4023, ...]
>

DF.mutate(
  df,
  %{"gas_fuel" => gas_fuel - 10}
)

#Explorer.DataFrame<
  Polars[1094 x 10]
  year s64 [2010, 2010, 2010, 2010, 2010, ...]
  country string ["AFGHANISTAN", "ALBANIA", "ALGERIA", "ANDORRA", "ANGOLA", ...]
  total s64 [2308, 1254, 32500, 141, 7924, ...]
  solid_fuel s64 [627, 117, 332, 0, 0, ...]
  liquid_fuel s64 [1601, 953, 12381, 141, 3649, ...]
  gas_fuel s64 [64, -3, 14555, -10, 364, ...]
  cement s64 [5, 177, 2598, 0, 204, ...]
  gas_flaring s64 [0, 0, 2623, 0, 3697, ...]
  per_capita f64 [0.08, 0.43, 0.9, 1.68, 0.37, ...]
  bunker_fuels s64 [9, 7, 663, 0, 321, ...]
>

Sort

DF.sort_by(df, year)

#Explorer.DataFrame<
  Polars[1094 x 10]
  year s64 [2010, 2010, 2010, 2010, 2010, ...]
  country string ["AFGHANISTAN", "ALBANIA", "ALGERIA", "ANDORRA", "ANGOLA", ...]
  total s64 [2308, 1254, 32500, 141, 7924, ...]
  solid_fuel s64 [627, 117, 332, 0, 0, ...]
  liquid_fuel s64 [1601, 953, 12381, 141, 3649, ...]
  gas_fuel s64 [74, 7, 14565, 0, 374, ...]
  cement s64 [5, 177, 2598, 0, 204, ...]
  gas_flaring s64 [0, 0, 2623, 0, 3697, ...]
  per_capita f64 [0.08, 0.43, 0.9, 1.68, 0.37, ...]
  bunker_fuels s64 [9, 7, 663, 0, 321, ...]
>

DF.sort_by(df, asc: total, desc: year)

#Explorer.DataFrame<
  Polars[1094 x 10]
  year s64 [2010, 2013, 2012, 2011, 2011, ...]
  country string ["NIUE", "NIUE", "NIUE", "NIUE", "TUVALU", ...]
  total s64 [1, 2, 2, 2, 2, ...]
  solid_fuel s64 [0, 0, 0, 0, 0, ...]
  liquid_fuel s64 [1, 2, 2, 2, 2, ...]
  gas_fuel s64 [0, 0, 0, 0, 0, ...]
  cement s64 [0, 0, 0, 0, 0, ...]
  gas_flaring s64 [0, 0, 0, 0, 0, ...]
  per_capita f64 [0.52, 1.04, 1.04, 1.04, 0.0, ...]
  bunker_fuels s64 [0, 0, 0, 0, 0, ...]
>

DF.sort_by(df, asc: window_sum(total, 2))

#Explorer.DataFrame<
  Polars[1094 x 10]
  year s64 [2010, 2011, 2012, 2010, 2011, ...]
  country string ["FEDERATED STATES OF MICRONESIA", "FEDERATED STATES OF MICRONESIA", "FEDERATED STATES OF MICRONESIA", "TUVALU", "TUVALU", ...]
  total s64 [31, 33, 37, 2, 2, ...]
  solid_fuel s64 [0, 0, 0, 0, 0, ...]
  liquid_fuel s64 [31, 33, 37, 2, 2, ...]
  gas_fuel s64 [0, 0, 0, 0, 0, ...]
  cement s64 [0, 0, 0, 0, 0, ...]
  gas_flaring s64 [0, 0, 0, 0, 0, ...]
  per_capita f64 [0.3, 0.32, 0.36, 0.0, 0.0, ...]
  bunker_fuels s64 [1, 1, 1, 0, 0, ...]
>

Distinct

DF.distinct(df, ["year", "country"])

#Explorer.DataFrame<
  Polars[1094 x 2]
  year s64 [2010, 2010, 2010, 2010, 2010, ...]
  country string ["AFGHANISTAN", "ALBANIA", "ALGERIA", "ANDORRA", "ANGOLA", ...]
>

DF.distinct(df, ["country"], keep_all: true)

#Explorer.DataFrame<
  Polars[222 x 10]
  year s64 [2010, 2010, 2010, 2010, 2010, ...]
  country string ["AFGHANISTAN", "ALBANIA", "ALGERIA", "ANDORRA", "ANGOLA", ...]
  total s64 [2308, 1254, 32500, 141, 7924, ...]
  solid_fuel s64 [627, 117, 332, 0, 0, ...]
  liquid_fuel s64 [1601, 953, 12381, 141, 3649, ...]
  gas_fuel s64 [74, 7, 14565, 0, 374, ...]
  cement s64 [5, 177, 2598, 0, 204, ...]
  gas_flaring s64 [0, 0, 2623, 0, 3697, ...]
  per_capita f64 [0.08, 0.43, 0.9, 1.68, 0.37, ...]
  bunker_fuels s64 [9, 7, 663, 0, 321, ...]
>

DF.rename(df, year: "year_test")

#Explorer.DataFrame<
  Polars[1094 x 10]
  year_test s64 [2010, 2010, 2010, 2010, 2010, ...]
  country string ["AFGHANISTAN", "ALBANIA", "ALGERIA", "ANDORRA", "ANGOLA", ...]
  total s64 [2308, 1254, 32500, 141, 7924, ...]
  solid_fuel s64 [627, 117, 332, 0, 0, ...]
  liquid_fuel s64 [1601, 953, 12381, 141, 3649, ...]
  gas_fuel s64 [74, 7, 14565, 0, 374, ...]
  cement s64 [5, 177, 2598, 0, 204, ...]
  gas_flaring s64 [0, 0, 2623, 0, 3697, ...]
  per_capita f64 [0.08, 0.43, 0.9, 1.68, 0.37, ...]
  bunker_fuels s64 [9, 7, 663, 0, 321, ...]
>

DF.rename_with(df, &amp;(&amp;1 <> "_test"))

#Explorer.DataFrame<
  Polars[1094 x 10]
  year_test s64 [2010, 2010, 2010, 2010, 2010, ...]
  country_test string ["AFGHANISTAN", "ALBANIA", "ALGERIA", "ANDORRA", "ANGOLA", ...]
  total_test s64 [2308, 1254, 32500, 141, 7924, ...]
  solid_fuel_test s64 [627, 117, 332, 0, 0, ...]
  liquid_fuel_test s64 [1601, 953, 12381, 141, 3649, ...]
  gas_fuel_test s64 [74, 7, 14565, 0, 374, ...]
  cement_test s64 [5, 177, 2598, 0, 204, ...]
  gas_flaring_test s64 [0, 0, 2623, 0, 3697, ...]
  per_capita_test f64 [0.08, 0.43, 0.9, 1.68, 0.37, ...]
  bunker_fuels_test s64 [9, 7, 663, 0, 321, ...]
>

Dummies

DF.dummies(df, ["year"])

#Explorer.DataFrame<
  Polars[1094 x 5]
  year_2010 u8 [1, 1, 1, 1, 1, ...]
  year_2011 u8 [0, 0, 0, 0, 0, ...]
  year_2012 u8 [0, 0, 0, 0, 0, ...]
  year_2013 u8 [0, 0, 0, 0, 0, ...]
  year_2014 u8 [0, 0, 0, 0, 0, ...]
>

DF.dummies(df, ["country"])

#Explorer.DataFrame<
  Polars[1094 x 222]
  country_AFGHANISTAN u8 [1, 0, 0, 0, 0, ...]
  country_ALBANIA u8 [0, 1, 0, 0, 0, ...]
  country_ALGERIA u8 [0, 0, 1, 0, 0, ...]
  country_ANDORRA u8 [0, 0, 0, 1, 0, ...]
  country_ANGOLA u8 [0, 0, 0, 0, 1, ...]
  country_ANGUILLA u8 [0, 0, 0, 0, 0, ...]
  country_ANTIGUA & BARBUDA u8 [0, 0, 0, 0, 0, ...]
  country_ARGENTINA u8 [0, 0, 0, 0, 0, ...]
  country_ARMENIA u8 [0, 0, 0, 0, 0, ...]
  country_ARUBA u8 [0, 0, 0, 0, 0, ...]
  country_AUSTRALIA u8 [0, 0, 0, 0, 0, ...]
  country_AUSTRIA u8 [0, 0, 0, 0, 0, ...]
  country_AZERBAIJAN u8 [0, 0, 0, 0, 0, ...]
  country_BAHAMAS u8 [0, 0, 0, 0, 0, ...]
  country_BAHRAIN u8 [0, 0, 0, 0, 0, ...]
  country_BANGLADESH u8 [0, 0, 0, 0, 0, ...]
  country_BARBADOS u8 [0, 0, 0, 0, 0, ...]
  country_BELARUS u8 [0, 0, 0, 0, 0, ...]
  country_BELGIUM u8 [0, 0, 0, 0, 0, ...]
  country_BELIZE u8 [0, 0, 0, 0, 0, ...]
  country_BENIN u8 [0, 0, 0, 0, 0, ...]
  country_BERMUDA u8 [0, 0, 0, 0, 0, ...]
  country_BHUTAN u8 [0, 0, 0, 0, 0, ...]
  country_BOSNIA & HERZEGOVINA u8 [0, 0, 0, 0, 0, ...]
  country_BOTSWANA u8 [0, 0, 0, 0, 0, ...]
  country_BRAZIL u8 [0, 0, 0, 0, 0, ...]
  country_BRITISH VIRGIN ISLANDS u8 [0, 0, 0, 0, 0, ...]
  country_BRUNEI (DARUSSALAM) u8 [0, 0, 0, 0, 0, ...]
  country_BULGARIA u8 [0, 0, 0, 0, 0, ...]
  country_BURKINA FASO u8 [0, 0, 0, 0, 0, ...]
  country_BURUNDI u8 [0, 0, 0, 0, 0, ...]
  country_CAMBODIA u8 [0, 0, 0, 0, 0, ...]
  country_CANADA u8 [0, 0, 0, 0, 0, ...]
  country_CAPE VERDE u8 [0, 0, 0, 0, 0, ...]
  country_CAYMAN ISLANDS u8 [0, 0, 0, 0, 0, ...]
  country_CENTRAL AFRICAN REPUBLIC u8 [0, 0, 0, 0, 0, ...]
  country_CHAD u8 [0, 0, 0, 0, 0, ...]
  country_CHILE u8 [0, 0, 0, 0, 0, ...]
  country_CHINA (MAINLAND) u8 [0, 0, 0, 0, 0, ...]
  country_COLOMBIA u8 [0, 0, 0, 0, 0, ...]
  country_COMOROS u8 [0, 0, 0, 0, 0, ...]
  country_CONGO u8 [0, 0, 0, 0, 0, ...]
  country_COOK ISLANDS u8 [0, 0, 0, 0, 0, ...]
  country_COSTA RICA u8 [0, 0, 0, 0, 0, ...]
  country_COTE D IVOIRE u8 [0, 0, 0, 0, 0, ...]
  country_CROATIA u8 [0, 0, 0, 0, 0, ...]
  country_CUBA u8 [0, 0, 0, 0, 0, ...]
  country_CYPRUS u8 [0, 0, 0, 0, 0, ...]
  country_CZECH REPUBLIC u8 [0, 0, 0, 0, 0, ...]
  country_DEMOCRATIC PEOPLE S REPUBLIC OF KOREA u8 [0, 0, 0, 0, 0, ...]
  country_DEMOCRATIC REPUBLIC OF THE CONGO (FORMERLY ZAIRE) u8 [0, 0, 0, 0, 0, ...]
  country_DENMARK u8 [0, 0, 0, 0, 0, ...]
  country_DJIBOUTI u8 [0, 0, 0, 0, 0, ...]
  country_DOMINICA u8 [0, 0, 0, 0, 0, ...]
  country_DOMINICAN REPUBLIC u8 [0, 0, 0, 0, 0, ...]
  country_ECUADOR u8 [0, 0, 0, 0, 0, ...]
  country_EGYPT u8 [0, 0, 0, 0, 0, ...]
  country_EL SALVADOR u8 [0, 0, 0, 0, 0, ...]
  country_EQUATORIAL GUINEA u8 [0, 0, 0, 0, 0, ...]
  country_ERITREA u8 [0, 0, 0, 0, 0, ...]
  country_ESTONIA u8 [0, 0, 0, 0, 0, ...]
  country_ETHIOPIA u8 [0, 0, 0, 0, 0, ...]
  country_FAEROE ISLANDS u8 [0, 0, 0, 0, 0, ...]
  country_FALKLAND ISLANDS (MALVINAS) u8 [0, 0, 0, 0, 0, ...]
  country_FEDERATED STATES OF MICRONESIA u8 [0, 0, 0, 0, 0, ...]
  country_FIJI u8 [0, 0, 0, 0, 0, ...]
  country_FINLAND u8 [0, 0, 0, 0, 0, ...]
  country_FRANCE (INCLUDING MONACO) u8 [0, 0, 0, 0, 0, ...]
  country_FRENCH GUIANA u8 [0, 0, 0, 0, 0, ...]
  country_FRENCH POLYNESIA u8 [0, 0, 0, 0, 0, ...]
  country_GABON u8 [0, 0, 0, 0, 0, ...]
  country_GAMBIA u8 [0, 0, 0, 0, 0, ...]
  country_GEORGIA u8 [0, 0, 0, 0, 0, ...]
  country_GERMANY u8 [0, 0, 0, 0, 0, ...]
  country_GHANA u8 [0, 0, 0, 0, 0, ...]
  country_GIBRALTAR u8 [0, 0, 0, 0, 0, ...]
  country_GREECE u8 [0, 0, 0, 0, 0, ...]
  country_GREENLAND u8 [0, 0, 0, 0, 0, ...]
  country_GRENADA u8 [0, 0, 0, 0, 0, ...]
  country_GUADELOUPE u8 [0, 0, 0, 0, 0, ...]
  country_GUATEMALA u8 [0, 0, 0, 0, 0, ...]
  country_GUINEA u8 [0, 0, 0, 0, 0, ...]
  country_GUINEA BISSAU u8 [0, 0, 0, 0, 0, ...]
  country_GUYANA u8 [0, 0, 0, 0, 0, ...]
  country_HAITI u8 [0, 0, 0, 0, 0, ...]
  country_HONDURAS u8 [0, 0, 0, 0, 0, ...]
  country_HONG KONG SPECIAL ADMINSTRATIVE REGION OF CHINA u8 [0, 0, 0, 0, 0, ...]
  country_HUNGARY u8 [0, 0, 0, 0, 0, ...]
  country_ICELAND u8 [0, 0, 0, 0, 0, ...]
  country_INDIA u8 [0, 0, 0, 0, 0, ...]
  country_INDONESIA u8 [0, 0, 0, 0, 0, ...]
  country_IRAQ u8 [0, 0, 0, 0, 0, ...]
  country_IRELAND u8 [0, 0, 0, 0, 0, ...]
  country_ISLAMIC REPUBLIC OF IRAN u8 [0, 0, 0, 0, 0, ...]
  country_ISRAEL u8 [0, 0, 0, 0, 0, ...]
  country_ITALY (INCLUDING SAN MARINO) u8 [0, 0, 0, 0, 0, ...]
  country_JAMAICA u8 [0, 0, 0, 0, 0, ...]
  country_JAPAN u8 [0, 0, 0, 0, 0, ...]
  country_JORDAN u8 [0, 0, 0, 0, 0, ...]
  country_KAZAKHSTAN u8 [0, 0, 0, 0, 0, ...]
  country_KENYA u8 [0, 0, 0, 0, 0, ...]
  country_KIRIBATI u8 [0, 0, 0, 0, 0, ...]
  country_KUWAIT u8 [0, 0, 0, 0, 0, ...]
  country_KYRGYZSTAN u8 [0, 0, 0, 0, 0, ...]
  country_LAO PEOPLE S DEMOCRATIC REPUBLIC u8 [0, 0, 0, 0, 0, ...]
  country_LATVIA u8 [0, 0, 0, 0, 0, ...]
  country_LEBANON u8 [0, 0, 0, 0, 0, ...]
  country_LESOTHO u8 [0, 0, 0, 0, 0, ...]
  country_LIBERIA u8 [0, 0, 0, 0, 0, ...]
  country_LIBYAN ARAB JAMAHIRIYAH u8 [0, 0, 0, 0, 0, ...]
  country_LIECHTENSTEIN u8 [0, 0, 0, 0, 0, ...]
  country_LITHUANIA u8 [0, 0, 0, 0, 0, ...]
  country_LUXEMBOURG u8 [0, 0, 0, 0, 0, ...]
  country_MACAU SPECIAL ADMINSTRATIVE REGION OF CHINA u8 [0, 0, 0, 0, 0, ...]
  country_MACEDONIA u8 [0, 0, 0, 0, 0, ...]
  country_MADAGASCAR u8 [0, 0, 0, 0, 0, ...]
  country_MALAWI u8 [0, 0, 0, 0, 0, ...]
  country_MALAYSIA u8 [0, 0, 0, 0, 0, ...]
  country_MALDIVES u8 [0, 0, 0, 0, 0, ...]
  country_MALI u8 [0, 0, 0, 0, 0, ...]
  country_MALTA u8 [0, 0, 0, 0, 0, ...]
  country_MARSHALL ISLANDS u8 [0, 0, 0, 0, 0, ...]
  country_MARTINIQUE u8 [0, 0, 0, 0, 0, ...]
  country_MAURITANIA u8 [0, 0, 0, 0, 0, ...]
  country_MAURITIUS u8 [0, 0, 0, 0, 0, ...]
  country_MEXICO u8 [0, 0, 0, 0, 0, ...]
  country_MONGOLIA u8 [0, 0, 0, 0, 0, ...]
  country_MONTENEGRO u8 [0, 0, 0, 0, 0, ...]
  country_MONTSERRAT u8 [0, 0, 0, 0, 0, ...]
  country_MOROCCO u8 [0, 0, 0, 0, 0, ...]
  country_MOZAMBIQUE u8 [0, 0, 0, 0, 0, ...]
  country_MYANMAR (FORMERLY BURMA) u8 [0, 0, 0, 0, 0, ...]
  country_NAMIBIA u8 [0, 0, 0, 0, 0, ...]
  country_NAURU u8 [0, 0, 0, 0, 0, ...]
  country_NEPAL u8 [0, 0, 0, 0, 0, ...]
  country_NETHERLAND ANTILLES u8 [0, 0, 0, 0, 0, ...]
  country_NETHERLANDS u8 [0, 0, 0, 0, 0, ...]
  country_NEW CALEDONIA u8 [0, 0, 0, 0, 0, ...]
  country_NEW ZEALAND u8 [0, 0, 0, 0, 0, ...]
  country_NICARAGUA u8 [0, 0, 0, 0, 0, ...]
  country_NIGER u8 [0, 0, 0, 0, 0, ...]
  country_NIGERIA u8 [0, 0, 0, 0, 0, ...]
  country_NIUE u8 [0, 0, 0, 0, 0, ...]
  country_NORWAY u8 [0, 0, 0, 0, 0, ...]
  country_OCCUPIED PALESTINIAN TERRITORY u8 [0, 0, 0, 0, 0, ...]
  country_OMAN u8 [0, 0, 0, 0, 0, ...]
  country_PAKISTAN u8 [0, 0, 0, 0, 0, ...]
  country_PALAU u8 [0, 0, 0, 0, 0, ...]
  country_PANAMA u8 [0, 0, 0, 0, 0, ...]
  country_PAPUA NEW GUINEA u8 [0, 0, 0, 0, 0, ...]
  country_PARAGUAY u8 [0, 0, 0, 0, 0, ...]
  country_PERU u8 [0, 0, 0, 0, 0, ...]
  country_PHILIPPINES u8 [0, 0, 0, 0, 0, ...]
  country_PLURINATIONAL STATE OF BOLIVIA u8 [0, 0, 0, 0, 0, ...]
  country_POLAND u8 [0, 0, 0, 0, 0, ...]
  country_PORTUGAL u8 [0, 0, 0, 0, 0, ...]
  country_QATAR u8 [0, 0, 0, 0, 0, ...]
  country_REPUBLIC OF CAMEROON u8 [0, 0, 0, 0, 0, ...]
  country_REPUBLIC OF KOREA u8 [0, 0, 0, 0, 0, ...]
  country_REPUBLIC OF MOLDOVA u8 [0, 0, 0, 0, 0, ...]
  country_REUNION u8 [0, 0, 0, 0, 0, ...]
  country_ROMANIA u8 [0, 0, 0, 0, 0, ...]
  country_RUSSIAN FEDERATION u8 [0, 0, 0, 0, 0, ...]
  country_RWANDA u8 [0, 0, 0, 0, 0, ...]
  country_SAINT HELENA u8 [0, 0, 0, 0, 0, ...]
  country_SAINT LUCIA u8 [0, 0, 0, 0, 0, ...]
  country_SAMOA u8 [0, 0, 0, 0, 0, ...]
  country_SAO TOME & PRINCIPE u8 [0, 0, 0, 0, 0, ...]
  country_SAUDI ARABIA u8 [0, 0, 0, 0, 0, ...]
  country_SENEGAL u8 [0, 0, 0, 0, 0, ...]
  country_SERBIA u8 [0, 0, 0, 0, 0, ...]
  country_SEYCHELLES u8 [0, 0, 0, 0, 0, ...]
  country_SIERRA LEONE u8 [0, 0, 0, 0, 0, ...]
  country_SINGAPORE u8 [0, 0, 0, 0, 0, ...]
  country_SLOVAKIA u8 [0, 0, 0, 0, 0, ...]
  country_SLOVENIA u8 [0, 0, 0, 0, 0, ...]
  country_SOLOMON ISLANDS u8 [0, 0, 0, 0, 0, ...]
  country_SOMALIA u8 [0, 0, 0, 0, 0, ...]
  country_SOUTH AFRICA u8 [0, 0, 0, 0, 0, ...]
  country_SPAIN u8 [0, 0, 0, 0, 0, ...]
  country_SRI LANKA u8 [0, 0, 0, 0, 0, ...]
  country_ST. KITTS-NEVIS u8 [0, 0, 0, 0, 0, ...]
  country_ST. PIERRE & MIQUELON u8 [0, 0, 0, 0, 0, ...]
  country_ST. VINCENT & THE GRENADINES u8 [0, 0, 0, 0, 0, ...]
  country_SUDAN u8 [0, 0, 0, 0, 0, ...]
  country_SURINAME u8 [0, 0, 0, 0, 0, ...]
  country_SWAZILAND u8 [0, 0, 0, 0, 0, ...]
  country_SWEDEN u8 [0, 0, 0, 0, 0, ...]
  country_SWITZERLAND u8 [0, 0, 0, 0, 0, ...]
  country_SYRIAN ARAB REPUBLIC u8 [0, 0, 0, 0, 0, ...]
  country_TAIWAN u8 [0, 0, 0, 0, 0, ...]
  country_TAJIKISTAN u8 [0, 0, 0, 0, 0, ...]
  country_THAILAND u8 [0, 0, 0, 0, 0, ...]
  country_TIMOR-LESTE (FORMERLY EAST TIMOR) u8 [0, 0, 0, 0, 0, ...]
  country_TOGO u8 [0, 0, 0, 0, 0, ...]
  country_TONGA u8 [0, 0, 0, 0, 0, ...]
  country_TRINIDAD AND TOBAGO u8 [0, 0, 0, 0, 0, ...]
  country_TUNISIA u8 [0, 0, 0, 0, 0, ...]
  country_TURKEY u8 [0, 0, 0, 0, 0, ...]
  country_TURKMENISTAN u8 [0, 0, 0, 0, 0, ...]
  country_TURKS AND CAICOS ISLANDS u8 [0, 0, 0, 0, 0, ...]
  country_TUVALU u8 [0, 0, 0, 0, 0, ...]
  country_UGANDA u8 [0, 0, 0, 0, 0, ...]
  country_UKRAINE u8 [0, 0, 0, 0, 0, ...]
  country_UNITED ARAB EMIRATES u8 [0, 0, 0, 0, 0, ...]
  country_UNITED KINGDOM u8 [0, 0, 0, 0, 0, ...]
  country_UNITED REPUBLIC OF TANZANIA u8 [0, 0, 0, 0, 0, ...]
  country_UNITED STATES OF AMERICA u8 [0, 0, 0, 0, 0, ...]
  country_URUGUAY u8 [0, 0, 0, 0, 0, ...]
  country_UZBEKISTAN u8 [0, 0, 0, 0, 0, ...]
  country_VANUATU u8 [0, 0, 0, 0, 0, ...]
  country_VENEZUELA u8 [0, 0, 0, 0, 0, ...]
  country_VIET NAM u8 [0, 0, 0, 0, 0, ...]
  country_WALLIS AND FUTUNA ISLANDS u8 [0, 0, 0, 0, 0, ...]
  country_YEMEN u8 [0, 0, 0, 0, 0, ...]
  country_ZAMBIA u8 [0, 0, 0, 0, 0, ...]
  country_ZIMBABWE u8 [0, 0, 0, 0, 0, ...]
  country_BONAIRE, SAINT EUSTATIUS, AND SABA u8 [0, 0, 0, 0, 0, ...]
  country_CURACAO u8 [0, 0, 0, 0, 0, ...]
  country_REPUBLIC OF SOUTH SUDAN u8 [0, 0, 0, 0, 0, ...]
  country_REPUBLIC OF SUDAN u8 [0, 0, 0, 0, 0, ...]
  country_SAINT MARTIN (DUTCH PORTION) u8 [0, 0, 0, 0, 0, ...]
>

Sampling

DF.sample(df, 10)

#Explorer.DataFrame<
  Polars[10 x 10]
  year s64 [2010, 2013, 2013, 2012, 2010, ...]
  country string ["MADAGASCAR", "TOGO", "COLOMBIA", "MYANMAR (FORMERLY BURMA)", "CYPRUS", ...]
  total s64 [534, 725, 24441, 3019, 2102, ...]
  solid_fuel s64 [29, 0, 3581, 301, 19, ...]
  liquid_fuel s64 [483, 470, 11564, 1613, 1901, ...]
  gas_fuel s64 [0, 11, 6306, 976, 0, ...]
  cement s64 [22, 244, 1530, 125, 181, ...]
  gas_flaring s64 [0, 0, 1459, 3, 0, ...]
  per_capita f64 [0.03, 0.1, 0.52, 0.06, 1.9, ...]
  bunker_fuels s64 [54, 77, 1547, 31, 391, ...]
>

DF.sample(df, 0.4)

#Explorer.DataFrame<
  Polars[437 x 10]
  year s64 [2013, 2013, 2010, 2012, 2010, ...]
  country string ["PALAU", "NAURU", "NIUE", "GREECE", "MACEDONIA", ...]
  total s64 [70, 12, 1, 21828, 2346, ...]
  solid_fuel s64 [0, 0, 0, 8760, 1426, ...]
  liquid_fuel s64 [70, 12, 1, 10099, 749, ...]
  gas_fuel s64 [0, 0, 0, 2287, 60, ...]
  cement s64 [0, 0, 0, 681, 112, ...]
  gas_flaring s64 [0, 0, 0, 0, 0, ...]
  per_capita f64 [3.36, 1.16, 0.52, 1.96, 1.14, ...]
  bunker_fuels s64 [15, 4, 0, 2545, 6, ...]
>

DF.sample(df, 10000, replace: true)

#Explorer.DataFrame<
  Polars[10000 x 10]
  year s64 [2010, 2013, 2014, 2013, 2013, ...]
  country string ["MALAYSIA", "LESOTHO", "UZBEKISTAN", "CROATIA", "ICELAND", ...]
  total s64 [59579, 664, 28692, 4786, 518, ...]
  solid_fuel s64 [15103, 500, 1677, 699, 101, ...]
  liquid_fuel s64 [20006, 164, 2086, 2344, 417, ...]
  gas_fuel s64 [16596, 0, 23929, 1425, 0, ...]
  cement s64 [2688, 0, 1000, 317, 0, ...]
  gas_flaring s64 [5186, 0, 0, 0, 0, ...]
  per_capita f64 [2.12, 0.32, 0.97, 1.12, 1.59, ...]
  bunker_fuels s64 [1432, 0, 0, 98, 156, ...]
>

Pull and Slice

Slicing and dicing can be done with the Access protocol or with explicit pull/slice/take functions

df["year"]

#Explorer.Series<
  Polars[1094]
  s64 [2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, ...]
>

DF.pull(df, "year")

#Explorer.Series<
  Polars[1094]
  s64 [2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, ...]
>

df[["year", "country"]]

#Explorer.DataFrame<
  Polars[1094 x 2]
  year s64 [2010, 2010, 2010, 2010, 2010, ...]
  country string ["AFGHANISTAN", "ALBANIA", "ALGERIA", "ANDORRA", "ANGOLA", ...]
>

DF.slice(df, [1, 20, 50])

#Explorer.DataFrame<
  Polars[3 x 10]
  year s64 [2010, 2010, 2010]
  country string ["ALBANIA", "BENIN", "DEMOCRATIC REPUBLIC OF THE CONGO (FORMERLY ZAIRE)"]
  total s64 [1254, 1388, 551]
  solid_fuel s64 [117, 0, 0]
  liquid_fuel s64 [953, 1211, 471]
  gas_fuel s64 [7, 0, 12]
  cement s64 [177, 177, 67]
  gas_flaring s64 [0, 0, 0]
  per_capita f64 [0.43, 0.15, 0.01]
  bunker_fuels s64 [7, 127, 126]
>

DF.slice(df, -10, 5)

#Explorer.DataFrame<
  Polars[5 x 10]
  year s64 [2014, 2014, 2014, 2014, 2014]
  country string ["UNITED STATES OF AMERICA", "URUGUAY", "UZBEKISTAN", "VANUATU", "VENEZUELA"]
  total s64 [1432855, 1840, 28692, 42, 50510]
  solid_fuel s64 [450047, 2, 1677, 0, 204]
  liquid_fuel s64 [576531, 1700, 2086, 42, 28445]
  gas_fuel s64 [390719, 25, 23929, 0, 12731]
  cement s64 [11314, 112, 1000, 0, 1088]
  gas_flaring s64 [4244, 0, 0, 0, 8042]
  per_capita f64 [4.43, 0.54, 0.97, 0.16, 1.65]
  bunker_fuels s64 [30722, 251, 0, 10, 1256]
>

DF.slice(df, 10, 5)

#Explorer.DataFrame<
  Polars[5 x 10]
  year s64 [2010, 2010, 2010, 2010, 2010]
  country string ["AUSTRALIA", "AUSTRIA", "AZERBAIJAN", "BAHAMAS", "BAHRAIN"]
  total s64 [106589, 18408, 8366, 451, 7981]
  solid_fuel s64 [56257, 3537, 6, 1, 0]
  liquid_fuel s64 [31308, 9218, 2373, 450, 1123]
  gas_fuel s64 [17763, 5073, 4904, 0, 6696]
  cement s64 [1129, 579, 174, 0, 163]
  gas_flaring s64 [132, 0, 909, 0, 0]
  per_capita f64 [4.81, 2.19, 0.92, 1.25, 6.33]
  bunker_fuels s64 [3307, 575, 398, 179, 545]
>

DF.slice(df, 12..42)

#Explorer.DataFrame<
  Polars[31 x 10]
  year s64 [2010, 2010, 2010, 2010, 2010, ...]
  country string ["AZERBAIJAN", "BAHAMAS", "BAHRAIN", "BANGLADESH", "BARBADOS", ...]
  total s64 [8366, 451, 7981, 16345, 403, ...]
  solid_fuel s64 [6, 1, 0, 839, 0, ...]
  liquid_fuel s64 [2373, 450, 1123, 2881, 363, ...]
  gas_fuel s64 [4904, 0, 6696, 10753, 8, ...]
  cement s64 [174, 0, 163, 1873, 31, ...]
  gas_flaring s64 [909, 0, 0, 0, 1, ...]
  per_capita f64 [0.92, 1.25, 6.33, 0.11, 1.44, ...]
  bunker_fuels s64 [398, 179, 545, 313, 108, ...]
>

Joins

Joining is fast and easy. Specify the columns to join on and how to join. Polars even supports cartesian (cross) joins, so Explorer does too

df1 = DF.select(df, ["year", "country", "total"])
df2 = DF.select(df, ["year", "country", "cement"])

DF.join(df1, df2)

#Explorer.DataFrame<
  Polars[1094 x 4]
  year s64 [2010, 2010, 2010, 2010, 2010, ...]
  country string ["AFGHANISTAN", "ALBANIA", "ALGERIA", "ANDORRA", "ANGOLA", ...]
  total s64 [2308, 1254, 32500, 141, 7924, ...]
  cement s64 [5, 177, 2598, 0, 204, ...]
>

df3 = df |> DF.select(["year", "cement"]) |> DF.slice(0, 500)

#Explorer.DataFrame<
  Polars[500 x 2]
  year s64 [2010, 2010, 2010, 2010, 2010, ...]
  cement s64 [5, 177, 2598, 0, 204, ...]
>

Grouping

Explorer supports groupby operations. These operations are limited based on what is possible in Polars, but they do most of what you need to do.

grouped = DF.group_by(df, ["country"])

#Explorer.DataFrame<
  Polars[1094 x 10]
  year s64 [2010, 2010, 2010, 2010, 2010, ...]
  country string ["AFGHANISTAN", "ALBANIA", "ALGERIA", "ANDORRA", "ANGOLA", ...]
  total s64 [2308, 1254, 32500, 141, 7924, ...]
  solid_fuel s64 [627, 117, 332, 0, 0, ...]
  liquid_fuel s64 [1601, 953, 12381, 141, 3649, ...]
  gas_fuel s64 [74, 7, 14565, 0, 374, ...]
  cement s64 [5, 177, 2598, 0, 204, ...]
  gas_flaring s64 [0, 0, 2623, 0, 3697, ...]
  per_capita f64 [0.08, 0.43, 0.9, 1.68, 0.37, ...]
  bunker_fuels s64 [9, 7, 663, 0, 321, ...]
>

DF.groups(grouped)

["country"]

DF.ungroup(grouped)

#Explorer.DataFrame<
  Polars[1094 x 10]
  year s64 [2010, 2010, 2010, 2010, 2010, ...]
  country string ["AFGHANISTAN", "ALBANIA", "ALGERIA", "ANDORRA", "ANGOLA", ...]
  total s64 [2308, 1254, 32500, 141, 7924, ...]
  solid_fuel s64 [627, 117, 332, 0, 0, ...]
  liquid_fuel s64 [1601, 953, 12381, 141, 3649, ...]
  gas_fuel s64 [74, 7, 14565, 0, 374, ...]
  cement s64 [5, 177, 2598, 0, 204, ...]
  gas_flaring s64 [0, 0, 2623, 0, 3697, ...]
  per_capita f64 [0.08, 0.43, 0.9, 1.68, 0.37, ...]
  bunker_fuels s64 [9, 7, 663, 0, 321, ...]
>

What most really care about is aggregation. Which country has the max per_capita value?

grouped
|> DF.summarise(max_per_capita: max(per_capita))
|> DF.sort_by(desc: max_per_capita)

#Explorer.DataFrame<
  Polars[222 x 2]
  country string ["QATAR", "CURACAO", "TRINIDAD AND TOBAGO", "KUWAIT", "NETHERLAND ANTILLES", ...]
  max_per_capita f64 [13.54, 10.72, 9.84, 8.16, 7.45, ...]
>

Back