{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a8256e57",
   "metadata": {},
   "source": [
    "# SI Figure S15: per-solute RMSE with delta-22 composite coefficients applied\n",
    "\n",
    "Per-solute ¹H and ¹³C RMSE for the natural-products / olefin-isomer test set with delta-22\n",
    "coefficients applied (reproduces Figure 5C in ¹H, plus the ¹³C analogue), plus fitting-RMSE\n",
    "comparisons across coefficient choices, feature-space coverage by solvent, delta-22-plane residuals,\n",
    "and the RMSE distribution shift by solvent."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "64581ad1",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os, sys\n",
    "\n",
    "# make the in-repo modules importable (not pip-installed)\n",
    "REPO = os.path.abspath(\"../..\")\n",
    "for _p in (\"data/applications\", \"data/delta22\", \"analysis/code\", \"analysis/code/shared\"):\n",
    "    sys.path.insert(0, os.path.join(REPO, _p))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "206af146",
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "\n",
    "from applications_reader import Applications\n",
    "import applications\n",
    "import applications_plots\n",
    "import delta22\n",
    "import paths"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "69c8b5ee",
   "metadata": {},
   "outputs": [],
   "source": [
    "DATA = os.path.join(REPO, \"data\", \"applications\")\n",
    "DELTA22_HDF5 = paths.dataset_file(\"delta22\", root=REPO)\n",
    "DELTA22_XLSX = os.path.join(REPO, \"data\", \"delta22\", \"delta22_experimental.xlsx\")\n",
    "\n",
    "def figure_path(name):\n",
    "    os.makedirs(\"figures\", exist_ok=True)\n",
    "    return os.path.join(\"figures\", name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9cde73dc",
   "metadata": {},
   "outputs": [],
   "source": [
    "loader = Applications(paths.dataset_file(\"applications\", root=REPO),\n",
    "                      os.path.join(DATA, \"applications_experimental.xlsx\"))\n",
    "\n",
    "# assemble the feature table and run the composite-model fits + bootstrap\n",
    "query_df_nn = applications.build_query_df_nn(loader)\n",
    "site_counts = (query_df_nn.drop_duplicates(subset=[\"solute\", \"nucleus\", \"site\"])\n",
    "               .groupby([\"solute\", \"nucleus\"]).size().unstack(fill_value=0))\n",
    "\n",
    "per_solute = applications.per_solute_fits(query_df_nn)      # \"scaled to solute\" baseline\n",
    "all_solute = applications.per_solvent_fits(query_df_nn)     # \"scaled to test set\" full fit\n",
    "\n",
    "seed = applications.build_bootstrap_seed_coeffs(loader)\n",
    "bootstrap_rmses = {}\n",
    "for nuc in [\"H\", \"C\"]:\n",
    "    preds = applications.apply_bootstrap_params_to_full_dataset(query_df_nn, seed[nuc], nucleus=nuc)\n",
    "    bootstrap_rmses[nuc] = applications.compute_solute_rmses(preds)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d218de52",
   "metadata": {},
   "outputs": [],
   "source": [
    "# published solute order (isomers, then the two pyridines, then the natural products); matches\n",
    "# main-text Figure 5D. delta-22 is drawn first by the box-plot engine, so it is not listed here.\n",
    "S15_SOLUTE_ORDER = [\"isomer_1E\", \"isomer_1Z\", \"isomer_2E\", \"isomer_2Z\", \"isomer_3E\", \"isomer_3Z\",\n",
    "                    \"isomer_4N\", \"isomer_4O\", \"vomicine\", \"prednisone\", \"peptide\", \"flavone\",\n",
    "                    \"dihydrotanshinone_I\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "85097f2d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 1H panel (reproduces Figure 5C)\n",
    "applications_plots.plot_nps_on_boxplot_delta22_simplified(\n",
    "    loader.rmse_distribution(\"H\"), bootstrap_rmses[\"H\"], per_solute[\"H\"],\n",
    "    nucleus=\"H\", formulas=[\"stationary_plus_qcd + openMM\"], colors=[\"#61a89a\"],\n",
    "    site_counts=site_counts, formula_remap=applications.FORMULA_REMAP,\n",
    "    solute_remap=applications.SOLUTE_DISPLAY, solute_order=S15_SOLUTE_ORDER,\n",
    "    solute_color_remap=applications.PEPTIDE_HIGHLIGHT_H,\n",
    "    figsize=(14, 8), box_width=0.20, box_gap=0.1,\n",
    "    show_baseline=True, baseline_annotation_text=\"Scaled to solute\",\n",
    "    baseline_annotation_x=0.215, baseline_annotation_y=0.39,\n",
    "    show_full_fit_line=True, full_fit_line_label=\"Scaled to Test Set\", full_fit_line_label_x=0.835,\n",
    "    all_solute_fitting_results=all_solute,\n",
    "    max_bar_height=0.06, site_count_axis_mode=\"inset\", site_count_inset_area_frac=0.1,\n",
    "    site_count_inset_axis_offset=-0.06, site_count_inset_axis_label_pad=0.045,\n",
    "    save_path=figure_path(\"si_figure_s15_1H.png\"),\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "973af7b2",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 13C panel\n",
    "applications_plots.plot_nps_on_boxplot_delta22_simplified(\n",
    "    loader.rmse_distribution(\"C\"), bootstrap_rmses[\"C\"], per_solute[\"C\"],\n",
    "    nucleus=\"C\", formulas=[\"stationary_plus_op_vib + openMM\"], colors=[\"#61a89a\"],\n",
    "    site_counts=site_counts, formula_remap=applications.FORMULA_REMAP,\n",
    "    solute_remap=applications.SOLUTE_DISPLAY, solute_order=S15_SOLUTE_ORDER,\n",
    "    solute_color_remap=applications.PEPTIDE_HIGHLIGHT_C,\n",
    "    figsize=(14, 8), box_width=0.20, box_gap=0.1,\n",
    "    show_baseline=True, baseline_annotation_text=\"Scaled to solute\",\n",
    "    baseline_annotation_x=0.28, baseline_annotation_y=0.355,\n",
    "    show_full_fit_line=True, full_fit_line_label=\"Scaled to Test Set\", full_fit_line_label_x=0.98,\n",
    "    all_solute_fitting_results=all_solute,\n",
    "    max_bar_height=0.8, site_count_axis_mode=\"inset\", site_count_inset_area_frac=0.1,\n",
    "    site_count_inset_axis_offset=-0.06, site_count_inset_axis_label_pad=0.045,\n",
    "    save_path=figure_path(\"si_figure_s15_13C.png\"),\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f079c075",
   "metadata": {},
   "source": [
    "## Fitting RMSE Comparisons (chloroform)\n",
    "\n",
    "Per-solute RMSE under three coefficient choices (Scaled to Solute / Scaled to Test Set / Extrapolated\n",
    "from delta22)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "11ea3200",
   "metadata": {},
   "outputs": [],
   "source": [
    "for nucleus, formula in [(\"H\", \"stationary_plus_qcd + openMM\"), (\"C\", \"stationary_plus_op_vib + openMM\")]:\n",
    "    table = applications.fitting_rmse_comparison_table(query_df_nn, per_solute, all_solute, bootstrap_rmses[nucleus],\n",
    "                                            nucleus, \"chloroform\", formula)\n",
    "    table = table.rename(index=applications.SOLUTE_DISPLAY)\n",
    "    order = [applications.SOLUTE_DISPLAY.get(k, k) for k in S15_SOLUTE_ORDER]   # published order; peptide has no chloroform data\n",
    "    table = table.reindex([n for n in order if n in table.index])\n",
    "    print(f\"--- {nucleus} ---\")\n",
    "    display(table.round(3))\n",
    "    applications_plots.plot_fitting_rmse_comparison_bars(\n",
    "        table, nucleus, \"chloroform\",\n",
    "        save_path=figure_path(f\"si_figure_s15_fitting_rmse_comparisons_{'1H' if nucleus == 'H' else '13C'}.png\"))\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "47773c94",
   "metadata": {},
   "source": [
    "## Feature Space Coverage by Solvent\n",
    "\n",
    "Test-set vs delta-22 mean-centered feature values across the four explicit-solvent solvents."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fa1de7fe",
   "metadata": {},
   "outputs": [],
   "source": [
    "delta22_query_df_nn = delta22.add_composite_columns(delta22.load_query_df_nn(\n",
    "    DELTA22_HDF5, DELTA22_XLSX, verbose=False))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a19b095b",
   "metadata": {},
   "outputs": [],
   "source": [
    "_FEATURE_X_LABELS = {\n",
    "    \"H\": \"Gas-Phase Shielding + QCD Correction (centered, ppm)\",\n",
    "    \"C\": \"Gas-Phase Shielding + OpenMM Vibrational Correction (centered, ppm)\",\n",
    "}\n",
    "for nucleus in [\"H\", \"C\"]:\n",
    "    coverage = applications.feature_space_coverage_table(query_df_nn, delta22_query_df_nn, nucleus)\n",
    "    applications_plots.plot_feature_space_coverage_grid(\n",
    "        coverage, nucleus, _FEATURE_X_LABELS[nucleus],\n",
    "        save_path=figure_path(f\"si_figure_s15_feature_space_coverage_{'1H' if nucleus == 'H' else '13C'}.png\"))\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5d7bc6b3",
   "metadata": {},
   "source": [
    "## Residuals for Delta22 Fitting Coefficients\n",
    "\n",
    "Residuals of a delta-22-only 2-feature plane applied to both delta-22 and the test set, vs\n",
    "experimental shielding."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8dea4de5",
   "metadata": {},
   "outputs": [],
   "source": [
    "for nucleus in [\"H\", \"C\"]:\n",
    "    residuals = applications.delta22_plane_residuals_table(query_df_nn, delta22_query_df_nn, nucleus)\n",
    "    applications_plots.plot_delta22_plane_residuals_grid(\n",
    "        residuals, nucleus,\n",
    "        save_path=figure_path(f\"si_figure_s15_delta22_plane_residuals_{'1H' if nucleus == 'H' else '13C'}.png\"))\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3fd43b43",
   "metadata": {},
   "source": [
    "## Distribution Shift by Solvent\n",
    "\n",
    "Per-solvent mean test-set RMSE under the three coefficient choices."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "24d4b26e",
   "metadata": {},
   "outputs": [],
   "source": [
    "for nucleus, formula in [(\"H\", \"stationary_plus_qcd + openMM\"), (\"C\", \"stationary_plus_op_vib + openMM\")]:\n",
    "    shift = applications.distribution_shift_by_solvent_table(per_solute, all_solute, bootstrap_rmses[nucleus],\n",
    "                                                  nucleus, formula)\n",
    "    print(f\"--- {nucleus} ---\")\n",
    "    display(shift.round(3))\n",
    "    applications_plots.plot_distribution_shift_by_solvent_bars(\n",
    "        shift, nucleus,\n",
    "        save_path=figure_path(f\"si_figure_s15_distribution_shift_by_solvent_{'1H' if nucleus == 'H' else '13C'}.png\"))\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}