{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**SHAP Explainability Plots** \\\n",
    "_Author: Joaquín Torres Bravo_"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import shap\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib.patches as mpatches\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Retrieve attribute names in order\n",
    "attribute_names = attribute_names = list(np.load('../EDA/output/feature_names/all_features.npy', allow_pickle=True))\n",
    "\n",
    "# Load test data\n",
    "X_test_pre = np.load('../gen_train_data/output/pre/X_test_pre.npy', allow_pickle=True)\n",
    "y_test_pre = np.load('../gen_train_data/output/pre/y_test_pre.npy', allow_pickle=True)\n",
    "X_test_post = np.load('../gen_train_data/output/post/X_test_post.npy', allow_pickle=True)\n",
    "y_test_post = np.load('../gen_train_data/output/post/y_test_post.npy', allow_pickle=True)\n",
    "\n",
    "# Type conversion needed    \n",
    "data_dic = {\n",
    "    \"X_test_pre\": pd.DataFrame(X_test_pre, columns=attribute_names).convert_dtypes(),\n",
    "    \"y_test_pre\": y_test_pre,\n",
    "    \"X_test_post\": pd.DataFrame(X_test_post, columns=attribute_names).convert_dtypes(),\n",
    "    \"y_test_post\": y_test_post,\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "method_names = {\n",
    "    0: \"ORIG\",\n",
    "    1: \"ORIG_CW\",\n",
    "    2: \"OVER\",\n",
    "    3: \"UNDER\"\n",
    "}\n",
    "model_choices = {\n",
    "    \"ORIG\": \"XGB\",\n",
    "    \"ORIG_CW\": \"RF\",\n",
    "    \"OVER\": \"XGB\",\n",
    "    \"UNDER\": \"XGB\"\n",
    "}\n",
    "\n",
    "# Load names of social and individual attributes\n",
    "soc_var_names = np.load('../EDA/output/feature_names/social_factors.npy', allow_pickle=True)\n",
    "ind_var_names = np.load('../EDA/output/feature_names/individual_factors.npy', allow_pickle=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### SHAP Plots"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "method_name = 'OVER'\n",
    "\n",
    "plt.figure(figsize=(35, 75))\n",
    "for i, group in enumerate(['pre', 'post']):\n",
    "            X_test = data_dic['X_test_' + group]\n",
    "            y_test = data_dic['y_test_' + group]\n",
    "            model_name = model_choices[method_name]\n",
    "            shap_vals = np.load(f'./output/shap_values/{group}_{method_name}.npy')\n",
    "            ax = plt.subplot(2,1,i+1) # 2 rows (pre - post) 1 column\n",
    "            # show = False to modify plot before showing\n",
    "            shap.summary_plot(shap_vals, X_test, max_display=len(attribute_names), show=False)\n",
    "            plt.title(group.upper(), fontsize = 12, fontweight='bold')\n",
    "            plt.xlabel('SHAP Value')\n",
    "            plt.xlim(-3,5)\n",
    "            used_colors = {'purple': 'Social factor', 'green': 'Individual factor'}\n",
    "            # Modify color of attributes\n",
    "            for label in ax.get_yticklabels():\n",
    "                label_text = label.get_text()  # Get the text of the label\n",
    "                label.set_fontsize(8)\n",
    "                if label_text in soc_var_names:\n",
    "                        label.set_color('purple')\n",
    "                else:\n",
    "                        label.set_color('green')\n",
    "                # Create custom legend for each subplot\n",
    "                handles = [mpatches.Patch(color=color, label=label) for color, label in used_colors.items()]\n",
    "                ax.legend(handles=handles, loc='lower right', fontsize=8)\n",
    "            \n",
    "plt.suptitle(f'SHAP Summary Plots PRE vs POST - Pipeline: Oversampling - Model: {model_name}\\n\\n')\n",
    "plt.subplots_adjust(wspace=1)\n",
    "plt.tight_layout()\n",
    "plt.savefig(f'./output/plots/shap_summary/{method_name}_{model_name}.svg', format='svg', dpi=1250)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "method_name = 'ORIG_CW'\n",
    "plt.figure(figsize=(35, 75))\n",
    "for i, group in enumerate(['pre', 'post']):\n",
    "            X_test = data_dic['X_test_' + group]\n",
    "            y_test = data_dic['y_test_' + group]\n",
    "            model_name = model_choices[method_name]\n",
    "            shap_vals = np.load(f'./output/shap_values/{group}_{method_name}.npy')\n",
    "            shap_vals = shap_vals[:,:,1] # Select shap values for positive class\n",
    "            ax = plt.subplot(2,1,i+1)\n",
    "            shap.summary_plot(shap_vals, X_test, max_display=len(attribute_names), show=False)\n",
    "            plt.title(group.upper(), fontsize = 12, fontweight='bold')\n",
    "            plt.xlabel('SHAP Value')\n",
    "            plt.xlim(-0.5,0.5)\n",
    "            used_colors = {'purple': 'Social factor', 'green': 'Individual factor'}\n",
    "            for label in ax.get_yticklabels():\n",
    "                label_text = label.get_text()\n",
    "                label.set_fontsize(8)\n",
    "                if label_text in soc_var_names:\n",
    "                        label.set_color('purple')\n",
    "                else:\n",
    "                        label.set_color('green')\n",
    "                handles = [mpatches.Patch(color=color, label=label) for color, label in used_colors.items()]\n",
    "                ax.legend(handles=handles, loc='lower right', fontsize=8)\n",
    "\n",
    "plt.suptitle(f'SHAP Summary Plots PRE vs POST - Pipeline: Original with Class Weight - Model: {model_name}\\n\\n')\n",
    "plt.subplots_adjust(wspace=1)\n",
    "plt.tight_layout()\n",
    "plt.savefig(f'./output/plots/shap_summary/{method_name}_{model_name}.svg', format='svg', dpi=1250)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### SHAP Interaction Plots"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**IMPORTANT NOTE** \\\n",
    "For the code to work as intended, the SHAP source code had to be modified: .venv/lib/python3.9/site-packages/shap/plots/_beeswarm.py \n",
    "\n",
    "sort_inds = np.argsort(-np.abs(shap_values.sum(1)).sum(0)) \\\n",
    "**replaced by** \\\n",
    "sort_inds = np.arange(39)\n",
    "\n",
    "The idea is to display the features in the original order instead of sorting them according to their absolute SHAP impact, as the library originally does\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "method_name = 'ORIG_CW'\n",
    "group = 'pre'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Figure size 1000x1000 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1150x660 with 7 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "X_test = data_dic['X_test_' + group]\n",
    "y_test = data_dic['y_test_' + group]\n",
    "model_name = model_choices[method_name]\n",
    "\n",
    "shap_inter_vals = np.load(f'./output/shap_inter_values/{group}_{method_name}.npy')\n",
    "if method_name == 'ORIG_CW':\n",
    "      shap_inter_vals = shap_inter_vals[:,:,:,1] # Take info about positive class\n",
    "\n",
    "num_instances = shap_inter_vals.shape[0]  # Dynamically get the number of instances\n",
    "num_features = shap_inter_vals.shape[1]  # Assuming the number of features is the second dimension size\n",
    "# Loop over each instance and set the diagonal and lower triangle of each 39x39 matrix to NaN\n",
    "for i in range(num_instances):\n",
    "    # Mask the diagonal\n",
    "    np.fill_diagonal(shap_inter_vals[i], np.nan)\n",
    "    # Get indices for the lower triangle, excluding the diagonal\n",
    "    lower_triangle_indices = np.tril_indices(num_features, -1)  # -1 excludes the diagonal\n",
    "    # Set the lower triangle to NaN\n",
    "    shap_inter_vals[i][lower_triangle_indices] = np.nan\n",
    "\n",
    "plt.figure(figsize=(10,10))\n",
    "shap.summary_plot(shap_inter_vals, X_test, show=False, sort=False)\n",
    "fig=plt.gcf()\n",
    "attr_names = []\n",
    "used_colors = {'purple': 'Social factor', 'green': 'Individual factor'}\n",
    "# Iterate over all axes in the figure\n",
    "for ax in fig.get_axes():\n",
    "    # Customize the y-axis tick labels\n",
    "    for label in ax.get_yticklabels():\n",
    "        label_text = label.get_text()  # Get the text of the label\n",
    "        attr_names.append(label_text)\n",
    "        label.set_fontsize(12)\n",
    "        if label_text in soc_var_names:\n",
    "                label.set_color('purple')\n",
    "        else:\n",
    "                label.set_color('green')\n",
    "\n",
    "# Assuming the top labels are treated as titles, let's try to modify them\n",
    "total_axes = len(fig.axes)\n",
    "for i, ax in enumerate(fig.axes):\n",
    "        reverse_index = total_axes - 1 - i\n",
    "        title = attr_names[reverse_index]\n",
    "        ax.set_title(title, color='purple' if title in soc_var_names else 'green', fontsize=12, rotation=90)\n",
    "        if method_name == 'ORIG_CW':\n",
    "              ax.set_xlim(-0.15, 0.15) # Use same scale for pre and post\n",
    "        elif method_name == 'OVER':\n",
    "              ax.set_xlim(-2,2)\n",
    "\n",
    "# Create a single general legend for the whole figure\n",
    "handles = [mpatches.Patch(color=color, label=label) for color, label in used_colors.items()]\n",
    "fig.legend(handles=handles, loc='lower right', fontsize=12)\n",
    "\n",
    "plt.suptitle(f'Simplified Example SHAP Summary Interaction Plot\\n', fontsize=15, fontweight='bold', x=0.5, y=0.95, ha='center')\n",
    "plt.tight_layout()\n",
    "plt.savefig(f'./output/plots/shap_inter_summary/example.svg', format='svg', dpi=600)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### SHAP Interaction Analysis (To Be Confirmed)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "method_name = 'OVER'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Normalization function\n",
    "def max_absolute_scale(matrix):\n",
    "    return matrix / np.max(np.abs(matrix))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load array of shap inter matrices for pre and post for the chosen method\n",
    "shap_inter_vals_pre = np.load(f'./output/shap_inter_values/pre_{method_name}.npy')\n",
    "shap_inter_vals_post = np.load(f'./output/shap_inter_values/post_{method_name}.npy')\n",
    "if method_name == 'ORIG_CW':\n",
    "    shap_inter_vals_pre = shap_inter_vals_pre[:,:,:,1]\n",
    "    shap_inter_vals_post = shap_inter_vals_post[:,:,:,1]\n",
    "\n",
    "# Normalize each matrix in each of the two arrays\n",
    "norm_shap_inter_vals_pre = np.array([max_absolute_scale(matrix) for matrix in shap_inter_vals_pre])\n",
    "norm_shap_inter_vals_post = np.array([max_absolute_scale(matrix) for matrix in shap_inter_vals_post])\n",
    "\n",
    "# Aggregate matrices in each group by calculating the mean\n",
    "agg_shap_inter_vals_pre = np.mean(norm_shap_inter_vals_pre, axis=0)\n",
    "agg_shap_inter_vals_post = np.mean(norm_shap_inter_vals_post, axis=0)\n",
    "\n",
    "# Compute the difference between the aggregated matrices and take the absolute value\n",
    "dist_matrix = np.abs(agg_shap_inter_vals_post - agg_shap_inter_vals_pre)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_inter_heatmap(matrix, feature_names, soc_var_names, method_name, group):\n",
    "    # Create a mask for the upper triangle\n",
    "    mask = np.triu(np.ones_like(matrix, dtype=bool))\n",
    "\n",
    "    # Create the heatmap using Seaborn\n",
    "    plt.figure(figsize=(12, 12))\n",
    "    ax = sns.heatmap(matrix, mask=mask, cmap='coolwarm', center=0, annot=False, cbar=True,\n",
    "                xticklabels=feature_names, yticklabels=feature_names)\n",
    "    \n",
    "    for tick_label in ax.get_yticklabels():\n",
    "        if tick_label.get_text() in soc_var_names:\n",
    "            tick_label.set_color('purple')  # Specific social variables\n",
    "        else:\n",
    "            tick_label.set_color('green')  # Other variables\n",
    "    \n",
    "    for tick_label in ax.get_xticklabels():\n",
    "        if tick_label.get_text() in soc_var_names:\n",
    "            tick_label.set_color('purple')  # Specific social variables\n",
    "        else:\n",
    "            tick_label.set_color('green')  # Other variables\n",
    "        \n",
    "    plt.title(f'Mean Interaction Matrix - Pipeline: {method_name} - Group: {group}\\n', fontdict={'fontstyle': 'normal', 'weight': 'bold'})\n",
    "    # Create a custom legend\n",
    "    purple_patch = mpatches.Patch(color='purple', label='Social factor')\n",
    "    green_patch = mpatches.Patch(color='green', label='Individual factor')\n",
    "    plt.legend(handles=[purple_patch, green_patch], loc='upper right')\n",
    "    # Add a title to the color bar\n",
    "    cbar = ax.collections[0].colorbar\n",
    "    cbar.set_label('Normalized SHAP Interaction Value', labelpad=15, rotation=270, verticalalignment='bottom')\n",
    "    \n",
    "    plt.savefig(f'./output/plots/heatmaps_interactions/{method_name}_{group}.svg', format='svg', dpi=600)\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plot_inter_heatmap(agg_shap_inter_vals_post, attribute_names, soc_var_names, method_name, 'POST')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_distance_heatmap(matrix, feature_names, soc_var_names, method_name):\n",
    "    # Create a mask for the upper triangle\n",
    "    mask = np.triu(np.ones_like(matrix, dtype=bool))\n",
    "\n",
    "    # Create the heatmap using Seaborn\n",
    "    plt.figure(figsize=(12, 12))\n",
    "    ax = sns.heatmap(matrix, mask=mask, cmap=sns.color_palette(\"light:r\", as_cmap=True), annot=False, cbar=True,\n",
    "                xticklabels=feature_names, yticklabels=feature_names)\n",
    "\n",
    "    for tick_label in ax.get_yticklabels():\n",
    "        if tick_label.get_text() in soc_var_names:\n",
    "            tick_label.set_color('purple')  # Specific social variables\n",
    "        else:\n",
    "            tick_label.set_color('green')  # Other variables\n",
    "    \n",
    "    for tick_label in ax.get_xticklabels():\n",
    "        if tick_label.get_text() in soc_var_names:\n",
    "            tick_label.set_color('purple')  # Specific social variables\n",
    "        else:\n",
    "            tick_label.set_color('green')  # Other variables\n",
    "        \n",
    "    plt.title(f'Distance Interaction Matrix between PRE and POST - Pipeline: {method_name}\\n', fontdict={'fontstyle': 'normal', 'weight': 'bold'})\n",
    "    # Create a custom legend\n",
    "    purple_patch = mpatches.Patch(color='purple', label='Social factor')\n",
    "    green_patch = mpatches.Patch(color='green', label='Individual factor')\n",
    "    plt.legend(handles=[purple_patch, green_patch], loc='upper right')\n",
    "    # Add a title to the color bar\n",
    "    cbar = ax.collections[0].colorbar\n",
    "    cbar.set_label('Abs (PRE - POST)', labelpad=15, rotation=270, verticalalignment='bottom')\n",
    "\n",
    "    plt.savefig(f'./output/plots/heatmaps_interactions/DIST_{method_name}.svg', format='svg', dpi=600)\n",
    "    \n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plot_distance_heatmap(dist_matrix, attribute_names, soc_var_names, method_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define tolerance\n",
    "tolerance = np.median(dist_matrix)\n",
    "# Create a DataFrame to hold the interactions\n",
    "interactions = []\n",
    "\n",
    "# Iterate over the matrix to extract interactions above the tolerance\n",
    "for i in range(1, dist_matrix.shape[0]):\n",
    "    for j in range(i):  # Lower triangle exclduing diagonal\n",
    "        if dist_matrix[i, j] > tolerance:\n",
    "            var1 = attribute_names[i]\n",
    "            var2 = attribute_names[j]\n",
    "            if var1 in soc_var_names and var2 in soc_var_names:\n",
    "                inter_type = 'Social'\n",
    "            elif var1 in ind_var_names and var2 in ind_var_names:\n",
    "                inter_type = 'Individual'\n",
    "            else:\n",
    "                inter_type = 'Mixed'\n",
    "            interactions.append({\n",
    "                'Variable 1': var1, \n",
    "                'Variable 2': var2,\n",
    "                'SHAP Inter Variation PRE-POST': dist_matrix[i, j],\n",
    "                'Interaction Type': inter_type\n",
    "            })\n",
    "\n",
    "# Convert the list of dictionaries to a DataFrame\n",
    "interactions_df = pd.DataFrame(interactions)\n",
    "\n",
    "# Sort the DataFrame by 'Interaction Strength' in descending order\n",
    "sorted_interactions_df = interactions_df.sort_values(by='SHAP Inter Variation PRE-POST', ascending=False)\n",
    "\n",
    "# Export to Excel\n",
    "sorted_interactions_df.to_excel(f'./output/inter_variation_{method_name}.xlsx', index=False)\n",
    "\n",
    "print(\"Excel file has been created.\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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": "3.12.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}