Add notebook to create pickle file for fms and labels

.gitignore

@@ -1,3 +1,6 @@
+
+synergy-dataset/
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

feature_matrices.ipynb

@@ -0,0 +1,69 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pathlib import Path\n",
+    "import pickle\n",
+    "\n",
+    "import synergy_dataset as sd\n",
+    "import asreview as asr\n",
+    "\n",
+    "from asreview.models.feature_extraction import Tfidf\n",
+    "\n",
+    "print(\"synergy-dataset version\", sd.__version__)\n",
+    "print(\"asreview version:\", asr.__version__)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "folder_pickle_files = Path(\"synergy-dataset\", \"pickles\")\n",
+    "folder_pickle_files.mkdir(parents=True, exist_ok=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for dataset in sd.iter_datasets():\n",
+    "\n",
+    "    df = dataset.to_frame().reset_index()\n",
+    "\n",
+    "    X = Tfidf().fit_transform(df[\"title\"].fillna(\"\").values, df[\"abstract\"].fillna(\"\").values)\n",
+    "\n",
+    "    with open(folder_pickle_files / f\"{dataset.name}.pkl\", \"wb\") as f:\n",
+    "        pickle.dump((X, df[\"label_included\"]), f)\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "asreview-dev",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}