Move target partition outside base sequence quality function

Author: jwinter3

docs/notebooks/base_sequence_quality.ipynb

@@ -10,10 +10,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 1,
    "id": "58b40aa6",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/jwinter/TBD/proj2/polars-bio/venv/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n",
+      "INFO:polars_bio:Creating BioSessionContext\n"
+     ]
+    }
+   ],
    "source": [
     "import pandas as pd\n",
     "\n",
@@ -28,6 +38,16 @@
     "### Usage examples"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "b0d81403",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pb.set_option(\"datafusion.execution.target_partitions\", \"2\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "b238193d",
@@ -38,33 +58,33 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": null,
    "id": "0420c240",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "    pos     avg    q1  median    q3  lower  upper\n",
-      "87    0  30.135  31.0    33.0  34.0   26.5   38.5\n",
-      "66    1  31.210  31.0    34.0  34.0   26.5   38.5\n",
-      "69    2  32.015  31.0    34.0  34.0   26.5   38.5\n",
-      "45    3  35.690  35.0    37.0  37.0   32.0   40.0\n",
-      "14    4  35.680  35.0    37.0  37.0   32.0   40.0\n",
-      "..  ...     ...   ...     ...   ...    ...    ...\n",
-      "40   96  31.315  32.0    34.0  35.0   27.5   39.5\n",
-      "23   97  30.670  31.0    34.0  35.0   25.0   41.0\n",
-      "37   98  31.550  32.0    34.0  35.0   27.5   39.5\n",
-      "6    99  31.250  32.0    34.0  35.0   27.5   39.5\n",
-      "4   100  31.105  31.0    34.0  35.0   25.0   41.0\n",
+      "    pos        avg    q1  median    q3  lower  upper\n",
+      "88    0  32.548723  31.0    34.0  34.0   26.5   38.5\n",
+      "46    1  32.719772  31.0    34.0  34.0   26.5   38.5\n",
+      "99    2  32.789697  31.0    34.0  34.0   26.5   38.5\n",
+      "75    3  36.162011  37.0    37.0  37.0   37.0   37.0\n",
+      "84    4  36.122733  37.0    37.0  37.0   37.0   37.0\n",
+      "..  ...        ...   ...     ...   ...    ...    ...\n",
+      "19   96  32.998462  34.0    35.0  35.0   32.5   36.5\n",
+      "64   97  32.922582  33.0    35.0  35.0   30.0   38.0\n",
+      "70   98  32.883908  33.0    35.0  35.0   30.0   38.0\n",
+      "80   99  32.836223  33.0    35.0  35.0   30.0   38.0\n",
+      "51  100  31.190304  30.0    34.0  35.0   22.5   42.5\n",
       "\n",
       "[101 rows x 7 columns]\n"
      ]
     }
    ],
    "source": [
-    "result = pb.base_sequence_quality(\"example.fastq\", output_type=\"pandas.DataFrame\", target_partitions=2).sort_values(by=\"pos\")\n",
+    "result = pb.base_sequence_quality(\"example.fastq\", output_type=\"pandas.DataFrame\").sort_values(by=\"pos\")\n",
     "print(result)"
    ]
   },
@@ -107,9 +127,9 @@
     "| -------------- | ----------------- | ----- |\n",
     "| fastqc-rs      | -                 | 22.9s |\n",
     "| polars_bio     | 1                 | 9.0s  |\n",
-    "| polars_bio     | 2                 | 8.5s  |\n",
-    "| polars_bio     | 4                 | 15.6s |\n",
-    "| polars_bio     | 8                 | 7.8s  |\n",
+    "| polars_bio     | 2                 | 7.8s  |\n",
+    "| polars_bio     | 4                 | 14.9s |\n",
+    "| polars_bio     | 8                 | 7.4s  |\n",
     "\n",
     "- The measured execution time is for the algorithm to run on file ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR194/ERR194147/ERR194147.fastq.gz, which contains about 8,240,000 records.\n",
     "- The `fastqc-rs` execution time applies only to the base sequence quality task (pieces of code relating to other tasks have been removed for the purpose of this comparison).\n"

polars_bio/quality_stats.py

@@ -15,7 +15,6 @@ def base_sequence_quality(
     df: Union[str, Path, pl.DataFrame, pl.LazyFrame, pd.DataFrame],
     quality_scores_column: str = "quality_scores",
     output_type: str = "polars.DataFrame",
-    target_partitions: int = 8,
 ) -> Union[pl.DataFrame, pd.DataFrame]:
     """
     Compute base sequence quality statistics from various dataframe/file types.
@@ -28,10 +27,6 @@ def base_sequence_quality(
     Returns:
         DataFrame with base sequence quality statistics.
     """
-    ctx.set_option(
-        "datafusion.execution.target_partitions", str(target_partitions), False
-    )
-
     if isinstance(df, (str, Path)):
         df = str(df)
         supported_exts = {".parquet", ".csv", ".bed", ".vcf", ".fastq"}