Skip to content

Update Polars to 0.52.0 #1139

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
billylanchantin wants to merge 11 commits into
base: main
Choose a base branch
from
Open

Update Polars to 0.52.0 #1139

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
36ba3fc
Upgrade polars to 0.52.0
billylanchantin Jan 31, 2026
aea34cd
DOZENS of changes
billylanchantin Jan 31, 2026
cee60ca
Merge branch 'main' into bl-update-dep-polars-0.52.0
billylanchantin Jan 31, 2026
4e72811
Add fixes from `main`
billylanchantin Jan 31, 2026
8b676e7
Remote has the old error?
billylanchantin Jan 31, 2026
b701f0c
Add another category exclusion
billylanchantin Jan 31, 2026
07fcecf
Exclude category again
billylanchantin Jan 31, 2026
41b8580
Keep variable name the same
billylanchantin Feb 1, 2026
430624d
Update toolchain to match Polars
billylanchantin Feb 1, 2026
462b1ec
Update toolchain
billylanchantin Feb 1, 2026
134234b
Remove unneeded file
billylanchantin Feb 1, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
76 changes: 38 additions & 38 deletions lib/explorer/data_frame.ex
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4404,16 +4404,16 @@ defmodule Explorer.DataFrame do
iex> Explorer.DataFrame.sample(df, 3, seed: 100)
#Explorer.DataFrame<
Polars[3 x 10]
year s64 [2012, 2013, 2014]
country string ["SYRIAN ARAB REPUBLIC", "EGYPT", "AFGHANISTAN"]
total s64 [12198, 58198, 2675]
solid_fuel s64 [1, 224, 1194]
liquid_fuel s64 [7909, 26501, 1393]
gas_fuel s64 [3265, 24672, 74]
cement s64 [816, 6800, 14]
gas_flaring s64 [208, 0, 0]
per_capita f64 [0.61, 0.66, 0.08]
bunker_fuels s64 [437, 694, 9]
year s64 [2014, 2014, 2014]
country string ["GUYANA", "MALDIVES", "CAYMAN ISLANDS"]
total s64 [548, 364, 148]
solid_fuel s64 [0, 0, 0]
liquid_fuel s64 [548, 364, 148]
gas_fuel s64 [0, 0, 0]
cement s64 [0, 0, 0]
gas_flaring s64 [0, 0, 0]
per_capita f64 [0.72, 1.02, 2.5]
bunker_fuels s64 [8, 204, 9]
>

Or you can sample a proportion of rows:
Expand All @@ -4422,16 +4422,16 @@ defmodule Explorer.DataFrame do
iex> Explorer.DataFrame.sample(df, 0.03, seed: 100)
#Explorer.DataFrame<
Polars[32 x 10]
year s64 [2013, 2012, 2014, 2011, 2011, ...]
country string ["BRITISH VIRGIN ISLANDS", "TAJIKISTAN", "AFGHANISTAN", "ICELAND", "SINGAPORE", ...]
total s64 [48, 800, 2675, 513, 12332, ...]
solid_fuel s64 [0, 192, 1194, 94, 7, ...]
liquid_fuel s64 [48, 501, 1393, 400, 7774, ...]
gas_fuel s64 [0, 74, 74, 0, 4551, ...]
cement s64 [0, 34, 14, 19, 0, ...]
gas_flaring s64 [0, 0, 0, 0, 0, ...]
per_capita f64 [1.64, 0.1, 0.08, 1.6, 2.38, ...]
bunker_fuels s64 [0, 28, 9, 168, 41786, ...]
year s64 [2014, 2014, 2014, 2011, 2014, ...]
country string ["HAITI", "MALI", "CENTRAL AFRICAN REPUBLIC", "RUSSIAN FEDERATION", "HONG KONG SPECIAL ADMINSTRATIVE REGION OF CHINA", ...]
total s64 [780, 385, 82, 480885, 12605, ...]
solid_fuel s64 [0, 0, 0, 109218, 8420, ...]
liquid_fuel s64 [739, 385, 82, 108312, 2659, ...]
gas_fuel s64 [0, 0, 0, 247327, 1268, ...]
cement s64 [41, 0, 0, 7643, 258, ...]
gas_flaring s64 [0, 0, 0, 8385, 0, ...]
per_capita f64 [0.07, 0.02, 0.02, 3.36, 1.74, ...]
bunker_fuels s64 [29, 20, 29, 7962, 12769, ...]
>

## Grouped examples
Expand All @@ -4446,10 +4446,10 @@ defmodule Explorer.DataFrame do
#Explorer.DataFrame<
Polars[6 x 5]
Groups: ["species"]
sepal_length f64 [4.8, 5.0, 5.5, 6.5, 7.4, ...]
sepal_width f64 [3.1, 3.6, 2.4, 2.8, 2.8, ...]
petal_length f64 [1.6, 1.4, 3.8, 4.6, 6.1, ...]
petal_width f64 [0.2, 0.2, 1.1, 1.5, 1.9, ...]
sepal_length f64 [5.0, 4.8, 5.0, 5.7, 6.8, ...]
sepal_width f64 [3.5, 3.0, 2.3, 3.0, 3.2, ...]
petal_length f64 [1.6, 1.4, 3.3, 4.2, 5.9, ...]
petal_width f64 [0.6, 0.3, 1.0, 1.2, 2.3, ...]
species string ["Iris-setosa", "Iris-setosa", "Iris-versicolor", "Iris-versicolor", "Iris-virginica", ...]
>

Expand All @@ -4462,10 +4462,10 @@ defmodule Explorer.DataFrame do
#Explorer.DataFrame<
Polars[15 x 5]
Groups: ["species"]
sepal_length f64 [5.2, 5.0, 5.2, 5.0, 5.0, ...]
sepal_width f64 [3.4, 3.6, 3.5, 3.0, 3.4, ...]
petal_length f64 [1.4, 1.4, 1.5, 1.6, 1.6, ...]
petal_width f64 [0.2, 0.2, 0.2, 0.2, 0.4, ...]
sepal_length f64 [5.0, 4.4, 5.1, 5.4, 5.0, ...]
sepal_width f64 [3.5, 3.2, 3.4, 3.9, 3.5, ...]
petal_length f64 [1.3, 1.3, 1.5, 1.3, 1.6, ...]
petal_width f64 [0.3, 0.2, 0.2, 0.4, 0.6, ...]
species string ["Iris-setosa", "Iris-setosa", "Iris-setosa", "Iris-setosa", "Iris-setosa", ...]
>

Expand Down Expand Up @@ -4507,16 +4507,16 @@ defmodule Explorer.DataFrame do
iex> Explorer.DataFrame.shuffle(df, seed: 100)
#Explorer.DataFrame<
Polars[1094 x 10]
year s64 [2014, 2014, 2014, 2012, 2010, ...]
country string ["ISRAEL", "ARGENTINA", "NETHERLANDS", "YEMEN", "GRENADA", ...]
total s64 [17617, 55638, 45624, 5091, 71, ...]
solid_fuel s64 [6775, 1588, 9070, 129, 0, ...]
liquid_fuel s64 [6013, 25685, 18272, 4173, 71, ...]
gas_fuel s64 [3930, 26368, 18010, 414, 0, ...]
cement s64 [898, 1551, 272, 375, 0, ...]
gas_flaring s64 [0, 446, 0, 0, 0, ...]
per_capita f64 [2.22, 1.29, 2.7, 0.2, 0.68, ...]
bunker_fuels s64 [1011, 2079, 14210, 111, 4, ...]
year s64 [2011, 2011, 2014, 2013, 2010, ...]
country string ["MARTINIQUE", "PARAGUAY", "HONDURAS", "GERMANY", "GERMANY", ...]
total s64 [605, 1451, 2583, 206521, 206943, ...]
solid_fuel s64 [0, 1, 145, 86226, 83574, ...]
liquid_fuel s64 [585, 1362, 2207, 70373, 71983, ...]
gas_fuel s64 [0, 0, 0, 45658, 47408, ...]
cement s64 [20, 88, 231, 4258, 3972, ...]
gas_flaring s64 [0, 0, 0, 5, 6, ...]
per_capita f64 [1.53, 0.23, 0.32, 2.56, 2.57, ...]
bunker_fuels s64 [120, 22, 57, 8982, 9078, ...]
>

"""
Expand Down
3 changes: 1 addition & 2 deletions lib/explorer/polars_backend/lazy_frame.ex
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -525,8 +525,7 @@ defmodule Explorer.PolarsBackend.LazyFrame do

@impl true
def drop_nil(%DF{} = df, columns) do
exprs = for col <- columns, do: Native.expr_column(col)
Shared.apply_dataframe(df, df, :lf_drop_nils, [exprs])
Shared.apply_dataframe(df, df, :lf_drop_nils, [columns])
end

@impl true
Expand Down
2 changes: 1 addition & 1 deletion lib/explorer/polars_backend/native.ex
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -285,7 +285,7 @@ defmodule Explorer.PolarsBackend.Native do
def lf_mutate_with(_df, _exprs), do: err()
def lf_summarise_with(_df, _groups, _stable_groups?, _aggs), do: err()
def lf_rename_columns(_df, _column_pairs), do: err()
def lf_drop_nils(_df, _column_pairs), do: err()
def lf_drop_nils(_df, _columns), do: err()
def lf_pivot_longer(_df, _id_vars, _value_vars, _names_to, _values_to), do: err()
def lf_join(_df, _other, _left_on, _right_on, _how, _suffix), do: err()

Expand Down
65 changes: 37 additions & 28 deletions lib/explorer/series.ex
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1577,28 +1577,28 @@ defmodule Explorer.Series do
iex> Explorer.Series.sample(s, 10, seed: 100)
#Explorer.Series<
Polars[10]
s64 [57, 9, 54, 62, 50, 77, 35, 88, 1, 69]
s64 [80, 95, 78, 33, 84, 100, 23, 58, 21, 30]
>

iex> s = 1..100 |> Enum.to_list() |> Explorer.Series.from_list()
iex> Explorer.Series.sample(s, 0.05, seed: 100)
#Explorer.Series<
Polars[5]
s64 [9, 56, 79, 28, 54]
s64 [85, 89, 82, 35, 88]
>

iex> s = 1..5 |> Enum.to_list() |> Explorer.Series.from_list()
iex> Explorer.Series.sample(s, 7, seed: 100, replace: true)
#Explorer.Series<
Polars[7]
s64 [4, 1, 3, 4, 3, 4, 2]
s64 [5, 5, 5, 2, 5, 2, 2]
>

iex> s = 1..5 |> Enum.to_list() |> Explorer.Series.from_list()
iex> Explorer.Series.sample(s, 1.2, seed: 100, replace: true)
#Explorer.Series<
Polars[6]
s64 [4, 1, 3, 4, 3, 4]
s64 [5, 5, 5, 2, 5, 2]
>

iex> s = 0..9 |> Enum.to_list() |> Explorer.Series.from_list()
Expand All @@ -1612,7 +1612,7 @@ defmodule Explorer.Series do
iex> Explorer.Series.sample(s, 1.0, seed: 100, shuffle: true)
#Explorer.Series<
Polars[10]
s64 [7, 9, 2, 0, 4, 1, 3, 8, 5, 6]
s64 [3, 7, 8, 0, 5, 1, 2, 6, 4, 9]
>

"""
Expand Down Expand Up @@ -1655,7 +1655,7 @@ defmodule Explorer.Series do
iex> Explorer.Series.shuffle(s, seed: 100)
#Explorer.Series<
Polars[10]
s64 [8, 10, 3, 1, 5, 2, 4, 9, 6, 7]
s64 [4, 8, 9, 1, 6, 2, 3, 7, 5, 10]
>

"""
Expand Down Expand Up @@ -2055,7 +2055,7 @@ defmodule Explorer.Series do
iex> Explorer.Series.rank(s, method: :random, seed: 42)
#Explorer.Series<
Polars[5]
s64 [3, 4, 2, 1, 5]
s64 [3, 5, 1, 2, 4]
>
"""
@doc type: :element_wise
Expand Down Expand Up @@ -5116,7 +5116,7 @@ defmodule Explorer.Series do
iex> Explorer.Series.window_sum(s, 2, weights: [1.0, 2.0])
#Explorer.Series<
Polars[10]
f64 [1.0, 5.0, 8.0, 11.0, 14.0, 17.0, 20.0, 23.0, 26.0, 29.0]
f64 [2.0, 5.0, 8.0, 11.0, 14.0, 17.0, 20.0, 23.0, 26.0, 29.0]
>
"""
@doc type: :window
Expand Down Expand Up @@ -5149,7 +5149,7 @@ defmodule Explorer.Series do
iex> Explorer.Series.window_mean(s, 2, weights: [0.25, 0.75])
#Explorer.Series<
Polars[10]
f64 [0.25, 1.75, 2.75, 3.75, 4.75, 5.75, 6.75, 7.75, 8.75, 9.75]
f64 [1.0, 1.75, 2.75, 3.75, 4.75, 5.75, 6.75, 7.75, 8.75, 9.75]
>

iex> s = 1..10 |> Enum.to_list() |> Explorer.Series.from_list()
Expand Down Expand Up @@ -5229,7 +5229,7 @@ defmodule Explorer.Series do
iex> Explorer.Series.window_min(s, 2, weights: [1.0, 2.0])
#Explorer.Series<
Polars[10]
f64 [1.0, 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0]
f64 [2.0, 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0]
>
"""
@doc type: :window
Expand Down Expand Up @@ -5262,7 +5262,7 @@ defmodule Explorer.Series do
iex> Explorer.Series.window_max(s, 2, weights: [1.0, 2.0])
#Explorer.Series<
Polars[10]
f64 [1.0, 4.0, 6.0, 8.0, 10.0, 12.0, 14.0, 16.0, 18.0, 20.0]
f64 [2.0, 4.0, 6.0, 8.0, 10.0, 12.0, 14.0, 16.0, 18.0, 20.0]
>
"""
@doc type: :window
Expand Down Expand Up @@ -5295,7 +5295,7 @@ defmodule Explorer.Series do
iex> Explorer.Series.window_standard_deviation(s, 2, weights: [0.25, 0.75])
#Explorer.Series<
Polars[6]
f64 [0.4330127018922193, 0.4330127018922193, 0.4330127018922193, 0.4330127018922193, 0.4330127018922193, 0.4330127018922193]
f64 [0.0, 0.4330127018922193, 0.4330127018922193, 0.4330127018922193, 0.4330127018922193, 0.4330127018922193]
>
"""
@doc type: :window
Expand Down Expand Up @@ -5330,21 +5330,39 @@ defmodule Explorer.Series do
iex> Explorer.Series.ewm_mean(s)
#Explorer.Series<
Polars[5]
f64 [1.0, 1.6666666666666667, 2.4285714285714284, 3.2666666666666666, 4.161290322580645]
f64 [1.0, 1.6666666666666665, 2.4285714285714284, 3.2666666666666666, 4.161290322580645]
>

iex> s = 1..5 |> Enum.to_list() |> Explorer.Series.from_list()
iex> Explorer.Series.ewm_mean(s, alpha: 0.1)
#Explorer.Series<
Polars[5]
f64 [1.0, 1.5263157894736843, 2.070110701107011, 2.6312881651642916, 3.2097140484969833]
f64 [1.0, 1.526315789473684, 2.0701107011070112, 2.631288165164292, 3.209714048496984]
>
"""
@doc type: :window
def ewm_mean(series, opts \\ []) do
opts = Keyword.validate!(opts, alpha: 0.5, adjust: true, min_periods: 1, ignore_nils: true)

apply_series(series, :ewm_mean, [
float_series =
case dtype(series) do
:f32 ->
series

:f64 ->
series

_ ->
try do
cast(series, :f64)
rescue
_ ->
raise ArgumentError,
"must pass float-compatible series, found dtype #{series.dtype}"
end
end

apply_series(float_series, :ewm_mean, [
opts[:alpha],
opts[:adjust],
opts[:min_periods],
Expand Down Expand Up @@ -5377,14 +5395,14 @@ defmodule Explorer.Series do
iex> Explorer.Series.ewm_standard_deviation(s)
#Explorer.Series<
Polars[5]
f64 [0.0, 0.7071067811865476, 0.9636241116594314, 1.1771636613972951, 1.3452425132127066]
f64 [0.0, 0.7071067811865476, 0.9636241116594315, 1.1771636613972953, 1.3452425132127066]
>

iex> s = 1..5 |> Enum.to_list() |> Explorer.Series.from_list()
iex> Explorer.Series.ewm_standard_deviation(s, alpha: 0.1)
#Explorer.Series<
Polars[5]
f64 [0.0, 0.7071067811865476, 0.9990770648702808, 1.2879021599718157, 1.5741638698820746]
f64 [0.0, 0.7071067811865476, 0.999077064870281, 1.2879021599718157, 1.5741638698820741]
>
"""
@doc type: :window
Expand Down Expand Up @@ -5432,14 +5450,14 @@ defmodule Explorer.Series do
iex> Explorer.Series.ewm_variance(s)
#Explorer.Series<
Polars[5]
f64 [0.0, 0.5, 0.9285714285714284, 1.385714285714286, 1.8096774193548393]
f64 [0.0, 0.5, 0.9285714285714286, 1.3857142857142861, 1.8096774193548393]
>

iex> s = 1..5 |> Enum.to_list() |> Explorer.Series.from_list()
iex> Explorer.Series.ewm_variance(s, alpha: 0.1)
#Explorer.Series<
Polars[5]
f64 [0.0, 0.5, 0.9981549815498153, 1.6586919736600685, 2.4779918892421087]
f64 [0.0, 0.5000000000000001, 0.9981549815498157, 1.658691973660068, 2.477991889242108]
>
"""
@doc type: :window
Expand Down Expand Up @@ -6932,15 +6950,6 @@ defmodule Explorer.Series do
Polars[1]
struct[1] [%{"a" => 1}]
>

If the decoded value does not match the given `dtype`,
an error is raised:

iex> s = Series.from_list(["\\"1\\""])
iex> Series.json_decode(s, {:s, 64})
** (RuntimeError) Polars Error: error deserializing JSON: error deserializing value \"String(\"1\")\" as numeric. \\\n Try increasing `infer_schema_length` or specifying a schema.\n

It raises an exception if the string is invalid JSON.
"""
@doc type: :string_wise
@spec json_decode(Series.t(), dtype() | dtype_alias()) :: Series.t()
Expand Down
Loading
Loading