Initial

notebooks/make_basedata.ipynb

@@ -0,0 +1,135 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "import-libs",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from pyprojroot import here"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "load-data",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = pd.read_csv(here() / 'data/raw/experimental_data.csv', encoding='utf-8')\n",
+    "print(f\"Loaded {data.shape[0]} measurements\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "filter-complete",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Filter to complete measurements only\n",
+    "data = data[data['Complete?'] == 'Complete']\n",
+    "print(f\"Complete measurements: {data.shape[0]}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "filter-test",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Remove test entries\n",
+    "data = data[data['Study ID'] != 26]\n",
+    "print(f\"After removing test entries: {data.shape[0]}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "clean-names",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Clean up text fields\n",
+    "data['Country'] = data['Country'].str.strip()\n",
+    "data['Institution'] = data['Institution'].str.strip()\n",
+    "data['Lab Name'] = data['Lab Name'].str.strip()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "add-country-code",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Add country codes\n",
+    "from utils import country_abbrev\n",
+    "data['Country Code'] = data['Country'].map(country_abbrev)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "calculate-metrics",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Calculate derived metrics\n",
+    "data['CAR'] = data['Coincidence Rate (Hz)'] / np.sqrt(data['Singles Rate A (Hz)'] * data['Singles Rate B (Hz)'])\n",
+    "data['Bell Violation Sigma'] = (data['Bell Parameter (S)'] - 2.0) / 0.1  # Simplified error"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "categorize",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Categorize fidelity\n",
+    "def fidelity_category(f):\n",
+    "    if f >= 0.98:\n",
+    "        return 'Excellent'\n",
+    "    elif f >= 0.95:\n",
+    "        return 'Good'\n",
+    "    elif f >= 0.90:\n",
+    "        return 'Acceptable'\n",
+    "    else:\n",
+    "        return 'Poor'\n",
+    "\n",
+    "data['Fidelity Category'] = data['Entanglement Fidelity'].apply(fidelity_category)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "save-data",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Save processed data\n",
+    "data.to_csv(here() / 'data/base/data.csv', index=False)\n",
+    "data.to_pickle(here() / 'data/base/data.pkl')\n",
+    "print(f\"Saved {data.shape[0]} processed measurements\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.9.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}