polars-bio 0.11.0__tar.gz → 0.12.0__tar.gz

{polars_bio-0.11.0 → polars_bio-0.12.0}/Cargo.lock

@@ -105,6 +105,16 @@ dependencies = [
  "memchr",
 ]
 
+[[package]]
+name = "aligned-vec"
+version = "0.6.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc890384c8602f339876ded803c97ad529f3842aba97f6392b3dba0dd171769b"
+dependencies = [
+ "equator",
+ "serde",
+]
+
 [[package]]
 name = "alloc-no-stdlib"
 version = "2.0.4"
@@ -1373,7 +1383,7 @@ dependencies = [
 [[package]]
 name = "datafusion-bio-format-bam"
 version = "0.1.0"
-source = "git+https://github.com/biodatageeks/datafusion-bio-formats.git?rev=89648086098023a3544f2735fb3395c83118c7e3#89648086098023a3544f2735fb3395c83118c7e3"
+source = "git+https://github.com/biodatageeks/datafusion-bio-formats.git?rev=0b9746c77aeb0e3a29f6460cb29f48aa17625c1d#0b9746c77aeb0e3a29f6460cb29f48aa17625c1d"
 dependencies = [
  "async-stream",
  "async-trait",
@@ -1394,7 +1404,7 @@ dependencies = [
 [[package]]
 name = "datafusion-bio-format-bed"
 version = "0.1.0"
-source = "git+https://github.com/biodatageeks/datafusion-bio-formats.git?rev=89648086098023a3544f2735fb3395c83118c7e3#89648086098023a3544f2735fb3395c83118c7e3"
+source = "git+https://github.com/biodatageeks/datafusion-bio-formats.git?rev=0b9746c77aeb0e3a29f6460cb29f48aa17625c1d#0b9746c77aeb0e3a29f6460cb29f48aa17625c1d"
 dependencies = [
  "async-compression",
  "async-stream",
@@ -1407,7 +1417,7 @@ dependencies = [
  "futures",
  "futures-util",
  "log",
- "noodles",
+ "noodles 0.93.0",
  "noodles-bed",
  "noodles-bgzf 0.36.0",
  "opendal",
@@ -1418,14 +1428,15 @@ dependencies = [
 [[package]]
 name = "datafusion-bio-format-core"
 version = "0.1.0"
-source = "git+https://github.com/biodatageeks/datafusion-bio-formats.git?rev=89648086098023a3544f2735fb3395c83118c7e3#89648086098023a3544f2735fb3395c83118c7e3"
+source = "git+https://github.com/biodatageeks/datafusion-bio-formats.git?rev=0b9746c77aeb0e3a29f6460cb29f48aa17625c1d#0b9746c77aeb0e3a29f6460cb29f48aa17625c1d"
 dependencies = [
  "async-compression",
  "bytes",
  "datafusion",
  "datafusion-execution",
+ "futures",
  "log",
- "noodles",
+ "noodles 0.93.0",
  "noodles-bgzf 0.36.0",
  "opendal",
  "tokio",
@@ -1436,7 +1447,7 @@ dependencies = [
 [[package]]
 name = "datafusion-bio-format-fasta"
 version = "0.1.0"
-source = "git+https://github.com/biodatageeks/datafusion-bio-formats.git?rev=89648086098023a3544f2735fb3395c83118c7e3#89648086098023a3544f2735fb3395c83118c7e3"
+source = "git+https://github.com/biodatageeks/datafusion-bio-formats.git?rev=0b9746c77aeb0e3a29f6460cb29f48aa17625c1d#0b9746c77aeb0e3a29f6460cb29f48aa17625c1d"
 dependencies = [
  "async-compression",
  "async-stream",
@@ -1447,7 +1458,7 @@ dependencies = [
  "futures",
  "futures-util",
  "log",
- "noodles",
+ "noodles 0.93.0",
  "noodles-bgzf 0.36.0",
  "noodles-fasta 0.55.0",
  "opendal",
@@ -1458,7 +1469,7 @@ dependencies = [
 [[package]]
 name = "datafusion-bio-format-fastq"
 version = "0.1.0"
-source = "git+https://github.com/biodatageeks/datafusion-bio-formats.git?rev=89648086098023a3544f2735fb3395c83118c7e3#89648086098023a3544f2735fb3395c83118c7e3"
+source = "git+https://github.com/biodatageeks/datafusion-bio-formats.git?rev=0b9746c77aeb0e3a29f6460cb29f48aa17625c1d#0b9746c77aeb0e3a29f6460cb29f48aa17625c1d"
 dependencies = [
  "async-compression",
  "async-stream",
@@ -1469,7 +1480,7 @@ dependencies = [
  "futures",
  "futures-util",
  "log",
- "noodles",
+ "noodles 0.93.0",
  "noodles-bgzf 0.36.0",
  "noodles-fastq 0.19.0",
  "opendal",
@@ -1482,7 +1493,7 @@ dependencies = [
 [[package]]
 name = "datafusion-bio-format-gff"
 version = "0.1.0"
-source = "git+https://github.com/biodatageeks/datafusion-bio-formats.git?rev=89648086098023a3544f2735fb3395c83118c7e3#89648086098023a3544f2735fb3395c83118c7e3"
+source = "git+https://github.com/biodatageeks/datafusion-bio-formats.git?rev=0b9746c77aeb0e3a29f6460cb29f48aa17625c1d#0b9746c77aeb0e3a29f6460cb29f48aa17625c1d"
 dependencies = [
  "async-compression",
  "async-stream",
@@ -1494,7 +1505,7 @@ dependencies = [
  "futures",
  "futures-util",
  "log",
- "noodles",
+ "noodles 0.93.0",
  "noodles-gff 0.50.0",
  "opendal",
  "tokio",
@@ -1504,7 +1515,7 @@ dependencies = [
 [[package]]
 name = "datafusion-bio-format-vcf"
 version = "0.1.0"
-source = "git+https://github.com/biodatageeks/datafusion-bio-formats.git?rev=89648086098023a3544f2735fb3395c83118c7e3#89648086098023a3544f2735fb3395c83118c7e3"
+source = "git+https://github.com/biodatageeks/datafusion-bio-formats.git?rev=0b9746c77aeb0e3a29f6460cb29f48aa17625c1d#0b9746c77aeb0e3a29f6460cb29f48aa17625c1d"
 dependencies = [
  "async-compression",
  "async-stream",
@@ -1516,6 +1527,7 @@ dependencies = [
  "env_logger",
  "futures",
  "log",
+ "noodles 0.100.0",
  "noodles-bgzf 0.36.0",
  "noodles-vcf 0.80.0",
  "opendal",
@@ -2332,6 +2344,26 @@ dependencies = [
  "log",
 ]
 
+[[package]]
+name = "equator"
+version = "0.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4711b213838dfee0117e3be6ac926007d7f433d7bbe33595975d4190cb07e6fc"
+dependencies = [
+ "equator-macro",
+]
+
+[[package]]
+name = "equator-macro"
+version = "0.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "44f23cf4b44bfce11a86ace86f8a73ffdec849c9fd00a386a53d278bd9e81fb3"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.106",
+]
+
 [[package]]
 name = "equivalent"
 version = "1.0.2"
@@ -2772,19 +2804,21 @@ checksum = "9b112acc8b3adf4b107a8ec20977da0273a8c386765a3ec0229bd500a1443f9f"
 
 [[package]]
 name = "hyper"
-version = "1.6.0"
+version = "1.7.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cc2b571658e38e0c01b1fdca3bbbe93c00d3d71693ff2770043f8c29bc7d6f80"
+checksum = "eb3aa54a13a0dfe7fbe3a59e0c76093041720fdc77b110cc0fc260fafb4dc51e"
 dependencies = [
+ "atomic-waker",
  "bytes",
  "futures-channel",
- "futures-util",
+ "futures-core",
  "h2",
  "http",
  "http-body",
  "httparse",
  "itoa",
  "pin-project-lite",
+ "pin-utils",
  "smallvec",
  "tokio",
  "want",
@@ -3557,6 +3591,15 @@ dependencies = [
  "noodles-vcf 0.74.0",
 ]
 
+[[package]]
+name = "noodles"
+version = "0.100.0"
+source = "git+https://github.com/biodatageeks/noodles.git?rev=289ef32e7d43d142914fb3f02335044ae293871c#289ef32e7d43d142914fb3f02335044ae293871c"
+dependencies = [
+ "noodles-bgzf 0.42.0",
+ "noodles-vcf 0.80.0",
+]
+
 [[package]]
 name = "noodles-bam"
 version = "0.76.0"
@@ -5150,7 +5193,7 @@ dependencies = [
 
 [[package]]
 name = "polars_bio"
-version = "0.11.0"
+version = "0.12.0"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -6027,7 +6070,7 @@ checksum = "1bc711410fbe7399f390ca1c3b60ad0f53f80e95c5eb935e52268a0e2cd49acc"
 [[package]]
 name = "sequila-core"
 version = "0.1.0"
-source = "git+https://github.com/biodatageeks/sequila-native.git?rev=21eb221d65fe2514b6c83d386adb33540828d22d#21eb221d65fe2514b6c83d386adb33540828d22d"
+source = "git+https://github.com/biodatageeks/sequila-native.git?rev=745d40f77da7ced5d540f9285eb5123ba12682ff#745d40f77da7ced5d540f9285eb5123ba12682ff"
 dependencies = [
  "ahash",
  "async-trait",
@@ -6042,6 +6085,7 @@ dependencies = [
  "parking_lot",
  "rand 0.8.5",
  "rust-lapper",
+ "superintervals",
  "tokio",
 ]
 
@@ -6407,6 +6451,15 @@ version = "2.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "13c2bddecc57b384dee18652358fb23172facb8a2c51ccc10d74c157bdea3292"
 
+[[package]]
+name = "superintervals"
+version = "0.3.6"
+source = "git+https://github.com/biodatageeks/sequila-native.git?rev=745d40f77da7ced5d540f9285eb5123ba12682ff#745d40f77da7ced5d540f9285eb5123ba12682ff"
+dependencies = [
+ "aligned-vec",
+ "serde",
+]
+
 [[package]]
 name = "syn"
 version = "1.0.109"

{polars_bio-0.11.0 → polars_bio-0.12.0}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "polars_bio"
-version = "0.11.0"
+version = "0.12.0"
 edition = "2021"
 readme = "README.md"
 
@@ -15,7 +15,7 @@ crate-type= ["cdylib"]
 datafusion-python = "48.0.0"
 pyo3 = { version = "0.24.2", features = ["extension-module", "abi3"] }
 pyo3-log = "0.12.4"
-sequila-core = { git = "https://github.com/biodatageeks/sequila-native.git", rev = "21eb221d65fe2514b6c83d386adb33540828d22d" }
+sequila-core = { git = "https://github.com/biodatageeks/sequila-native.git", rev = "745d40f77da7ced5d540f9285eb5123ba12682ff" }
 
 datafusion = { version = "48.0.1"}
 arrow = "55.0.0"
@@ -36,13 +36,13 @@ polars-arrow =  { git = "https://github.com/mwiewior/polars.git" , rev = "49142b
 polars-python = { git = "https://github.com/mwiewior/polars.git" , rev = "49142b2e89dbc93888154dccfb7c6a4e4233c7b0"}
 
 
-datafusion-bio-format-vcf = { git = "https://github.com/biodatageeks/datafusion-bio-formats.git", rev = "89648086098023a3544f2735fb3395c83118c7e3" }
-datafusion-bio-format-core = { git = "https://github.com/biodatageeks/datafusion-bio-formats.git", rev = "89648086098023a3544f2735fb3395c83118c7e3" }
-datafusion-bio-format-gff = { git = "https://github.com/biodatageeks/datafusion-bio-formats.git", rev = "89648086098023a3544f2735fb3395c83118c7e3" }
-datafusion-bio-format-fastq = { git = "https://github.com/biodatageeks/datafusion-bio-formats.git", rev = "89648086098023a3544f2735fb3395c83118c7e3" }
-datafusion-bio-format-bam = { git = "https://github.com/biodatageeks/datafusion-bio-formats.git", rev = "89648086098023a3544f2735fb3395c83118c7e3" }
-datafusion-bio-format-bed = { git = "https://github.com/biodatageeks/datafusion-bio-formats.git", rev = "89648086098023a3544f2735fb3395c83118c7e3" }
-datafusion-bio-format-fasta = { git = "https://github.com/biodatageeks/datafusion-bio-formats.git", rev = "89648086098023a3544f2735fb3395c83118c7e3" }
+datafusion-bio-format-vcf = { git = "https://github.com/biodatageeks/datafusion-bio-formats.git", rev = "0b9746c77aeb0e3a29f6460cb29f48aa17625c1d" }
+datafusion-bio-format-core = { git = "https://github.com/biodatageeks/datafusion-bio-formats.git", rev = "0b9746c77aeb0e3a29f6460cb29f48aa17625c1d" }
+datafusion-bio-format-gff = { git = "https://github.com/biodatageeks/datafusion-bio-formats.git", rev = "0b9746c77aeb0e3a29f6460cb29f48aa17625c1d" }
+datafusion-bio-format-fastq = { git = "https://github.com/biodatageeks/datafusion-bio-formats.git", rev = "0b9746c77aeb0e3a29f6460cb29f48aa17625c1d" }
+datafusion-bio-format-bam = { git = "https://github.com/biodatageeks/datafusion-bio-formats.git", rev = "0b9746c77aeb0e3a29f6460cb29f48aa17625c1d" }
+datafusion-bio-format-bed = { git = "https://github.com/biodatageeks/datafusion-bio-formats.git", rev = "0b9746c77aeb0e3a29f6460cb29f48aa17625c1d" }
+datafusion-bio-format-fasta = { git = "https://github.com/biodatageeks/datafusion-bio-formats.git", rev = "0b9746c77aeb0e3a29f6460cb29f48aa17625c1d" }
 
 
 

{polars_bio-0.11.0 → polars_bio-0.12.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: polars-bio
-Version: 0.11.0
+Version: 0.12.0
 Classifier: Programming Language :: Rust
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy

{polars_bio-0.11.0 → polars_bio-0.12.0}/docs/faq.md

@@ -1,8 +1,8 @@
 1. What versions of Polars are supported?
 
-    Short answer: Polars <= **1.17.1** is supported.
+    Short answer: Polars <= **1.21.0** is supported.
 
-    Longer answer: Since Polars has recently  [upgraded py03 to 0.23.x](https://github.com/pola-rs/polars/pull/20111) any many other dependencies still rely on 0.22.x, we are currently limited to Polars <= 1.17.1. We are working on upgrading to the latest version of Polars.
+    Long answer: We recommend handling most of the heavy lifting on the DataFusion side (e.g., using SQL and views) and relying on Polars’ streaming capabilities primarily for sinking results. This means we are not making use of the latest Polars features, and we are not in a hurry to upgrade to the newest version. However, we do plan to adopt the new Polars streaming engine in the near future. [Reference](https://github.com/pola-rs/polars/issues/20947).
 
 2. What to do if I get  `Illegal instruction (core dumped)` when using polars-bio?
 This error is likely due to the fact that the ABI of the polars-bio wheel package does not match the ABI of the Python interpreter.

{polars_bio-0.11.0 → polars_bio-0.12.0}/docs/quickstart.md

@@ -32,7 +32,7 @@ pip install /Users/mwiewior/research/git/polars-bio/target/wheels/polars_bio-0.1
 !!! tip
     Required dependencies:
 
-    * Python>=3.9<3.13 (3.12 is recommended),
+    * Python>=3.9<3.14 (3.12 is recommended),
     * [poetry](https://python-poetry.org/)
     * cmake,
     * Rust compiler

{polars_bio-0.11.0 → polars_bio-0.12.0}/polars_bio/__init__.py

@@ -59,7 +59,7 @@ except ImportError:
 POLARS_BIO_MAX_THREADS = "datafusion.execution.target_partitions"
 
 
-__version__ = "0.11.0"
+__version__ = "0.12.0"
 __all__ = [
     "ctx",
     "FilterOp",

{polars_bio-0.11.0 → polars_bio-0.12.0}/polars_bio/range_op.py

@@ -64,7 +64,7 @@ class IntervalOperations:
                 genomic intervals, provided separately for each set.
             suffixes: Suffixes for the columns of the two overlapped sets.
             on_cols: List of additional column names to join on. default is None.
-            algorithm: The algorithm to use for the overlap operation. Available options: Coitrees, IntervalTree, ArrayIntervalTree, Lapper
+            algorithm: The algorithm to use for the overlap operation. Available options: Coitrees, IntervalTree, ArrayIntervalTree, Lapper, SuperIntervals
             output_type: Type of the output. default is "polars.LazyFrame", "polars.DataFrame", or "pandas.DataFrame" or "datafusion.DataFrame" are also supported.
             streaming: **EXPERIMENTAL** If True, use Polars [streaming](features.md#streaming) engine.
             read_options1: Additional options for reading the input files.

{polars_bio-0.11.0 → polars_bio-0.12.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "maturin"
 
 [project]
 name = "polars-bio"
-version = "0.11.0"
+version = "0.12.0"
 description = "Blazing fast genomic operations on large Python dataframes"
 authors = []
 requires-python = ">=3.9"

polars_bio-0.12.0/tests/data/io/fasta/test.fasta

@@ -0,0 +1,4 @@
+>seq1 First sequence
+ACTG
+>seq2 Second sequence
+GATTACA

{polars_bio-0.11.0 → polars_bio-0.12.0}/tests/test_overlap_algorithms.py

@@ -106,6 +106,27 @@ class TestOverlapAlgorithms:
         algorithm="ArrayIntervalTree",
     )
 
+    result_overlap_superintervals = pb.overlap(
+        BIO_PD_DF1,
+        BIO_PD_DF2,
+        cols1=("contig", "pos_start", "pos_end"),
+        cols2=("contig", "pos_start", "pos_end"),
+        output_type="pandas.DataFrame",
+        suffixes=("_1", "_3"),
+        use_zero_based=True,
+        algorithm="SuperIntervals",
+    )
+
+    result_overlap_superintervals_log = pb.overlap(
+        BIO_PD_DF1,
+        BIO_PD_DF2,
+        cols1=("contig", "pos_start", "pos_end"),
+        cols2=("contig", "pos_start", "pos_end"),
+        suffixes=("_1", "_3"),
+        use_zero_based=True,
+        algorithm="SuperIntervals",
+    )
+
     expected = result_bio_overlap.sort_values(
         by=list(result_bio_overlap.columns)
     ).reset_index(drop=True)
@@ -122,6 +143,9 @@ class TestOverlapAlgorithms:
     def test_overlap_count_ait(self):
         assert len(self.result_overlap_ait) == len(self.result_bio_overlap)
 
+    def test_overlap_count_superintervals(self):
+        assert len(self.result_overlap_superintervals) == len(self.result_bio_overlap)
+
     def test_overlap_schema_rows_coitrees(self):
         result = self.result_overlap_coitrees.sort_values(
             by=list(self.result_overlap_coitrees.columns)
@@ -146,6 +170,12 @@ class TestOverlapAlgorithms:
         ).reset_index(drop=True)
         pd.testing.assert_frame_equal(result_ait, self.expected)
 
+    def test_overlap_schema_rows_superintervals(self):
+        result_superintervals = self.result_overlap_superintervals.sort_values(
+            by=list(self.result_overlap_superintervals.columns)
+        ).reset_index(drop=True)
+        pd.testing.assert_frame_equal(result_superintervals, self.expected)
+
     def test_overlap_schema_rows_it_log(self, caplog):
         caplog.set_level("INFO")
         self.result_overlap_it_log.count().collect()
@@ -173,3 +203,11 @@ class TestOverlapAlgorithms:
         caplog.set_level("INFO")
         self.result_overlap_lapper_log.count().collect()
         assert "Optimizing into IntervalJoinExec using Lapper algorithm" in caplog.text
+
+    def test_overlap_schema_rows_superintervals_log(self, caplog):
+        caplog.set_level("INFO")
+        self.result_overlap_superintervals_log.count().collect()
+        assert (
+            "Optimizing into IntervalJoinExec using SuperIntervals algorithm"
+            in caplog.text
+        )