{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "id": "aSxhoE7a0yU0"
   },
   "outputs": [],
   "source": [
    "\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import networkx as nx\n",
    "import seaborn as sns\n",
    "from mlxtend.frequent_patterns import apriori, association_rules\n",
    "from mlxtend.preprocessing import TransactionEncoder\n",
    "\n",
    "# Step 1: Load Healthcare Dataset\n",
    "# Simulating a healthcare dataset with patient diagnoses\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "dn9q1e0wFJjD",
    "outputId": "87ee4f0a-d5fa-4503-bd1c-c379c3d27cf2"
   },
   "outputs": [],
   "source": [
    "# Load the data from CSV file\n",
    "data = pd.read_csv('healthcare_data.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "x0h8r-OD1s9t",
    "outputId": "1dcf4acc-eda7-4edc-a3a4-8b8ec9786310"
   },
   "outputs": [],
   "source": [
    "# Step 2: Data Preprocessing\n",
    "\n",
    "# Convert the 'Diagnoses' column into a list of transactions\n",
    "import ast\n",
    "\n",
    "data['Diagnoses'] = data['Diagnoses'].apply(ast.literal_eval)  # Convert string representation of list back to list\n",
    "transactions = data['Diagnoses'].tolist()\n",
    "\n",
    "# Apply TransactionEncoder to prepare the dataset for Apriori\n",
    "te = TransactionEncoder()\n",
    "transaction_data = te.fit_transform(transactions)\n",
    "transaction_df = pd.DataFrame(transaction_data, columns=te.columns_)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0             [Hypertension, Diabetes]\n",
       "1                    [Asthma, Allergy]\n",
       "2                  [Diabetes, Obesity]\n",
       "3               [Hypertension, Asthma]\n",
       "4    [Diabetes, Hypertension, Obesity]\n",
       "Name: Diagnoses, dtype: object"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data['Diagnoses'].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 262
    },
    "id": "2lHHH2DZFugN",
    "outputId": "893b08c5-8d86-4dc6-98de-2ce5026f60de"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Allergy</th>\n",
       "      <th>Asthma</th>\n",
       "      <th>Diabetes</th>\n",
       "      <th>Heart Disease</th>\n",
       "      <th>Hypertension</th>\n",
       "      <th>Obesity</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Allergy  Asthma  Diabetes  Heart Disease  Hypertension  Obesity\n",
       "0    False   False      True          False          True    False\n",
       "1     True    True     False          False         False    False\n",
       "2    False   False      True          False         False     True\n",
       "3    False    True     False          False          True    False\n",
       "4    False   False      True          False          True     True"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "transaction_df.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "fmlmMZnw1xU4",
    "outputId": "5334259d-da2b-4644-a139-f33a292252b5"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Target Prediction Rules (Co-occurring Diagnoses):\n",
      "       antecedents     consequents  support  confidence      lift\n",
      "2        (Obesity)      (Diabetes)      0.2    0.666667  1.333333\n",
      "3  (Heart Disease)  (Hypertension)      0.2    1.000000  2.000000\n",
      "0   (Hypertension)      (Diabetes)      0.3    0.600000  1.200000\n",
      "1       (Diabetes)  (Hypertension)      0.3    0.600000  1.200000\n"
     ]
    }
   ],
   "source": [
    "# Step 3: Analysis - Finding Rules to Predict Diagnoses\n",
    "\n",
    "# Apply the Apriori algorithm to find frequent itemsets with a lower support threshold\n",
    "frequent_itemsets = apriori(transaction_df, min_support=0.2, use_colnames=True)\n",
    "\n",
    "# Generate association rules with a focus on predicting diagnoses\n",
    "rules = association_rules(frequent_itemsets, metric=\"confidence\", min_threshold=0.5)\n",
    "\n",
    "# Limit the number of rules to avoid overwhelming memory usage\n",
    "target_rules = rules.sort_values(by='support').head(10)\n",
    "\n",
    "# Display the first few target prediction rules\n",
    "target_rules = target_rules[['antecedents', 'consequents', 'support', 'confidence', 'lift']]\n",
    "print(\"Target Prediction Rules (Co-occurring Diagnoses):\")\n",
    "print(target_rules)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "UXH1khsJ12G5",
    "outputId": "dfe6e0a9-165b-44d5-f9c8-df5b7b2bddbb"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Rules Showing Diagnoses That Occur Together:\n",
      "       antecedents      consequents  support  confidence      lift\n",
      "2       (Diabetes)        (Obesity)      0.2    0.400000  1.333333\n",
      "3        (Obesity)       (Diabetes)      0.2    0.666667  1.333333\n",
      "4  (Heart Disease)   (Hypertension)      0.2    1.000000  2.000000\n",
      "5   (Hypertension)  (Heart Disease)      0.2    0.400000  2.000000\n",
      "0   (Hypertension)       (Diabetes)      0.3    0.600000  1.200000\n",
      "1       (Diabetes)   (Hypertension)      0.3    0.600000  1.200000\n"
     ]
    }
   ],
   "source": [
    "# Step 4: Analysis - Finding Diagnoses That Occur Together\n",
    "\n",
    "# Generate association rules to discover diagnoses that occur together\n",
    "Lift_rules = association_rules(frequent_itemsets, metric=\"lift\", min_threshold=1.0)\n",
    "\n",
    "# Limit the number of supervised rules to avoid overwhelming memory usage\n",
    "Lift_rules = Lift_rules.sort_values(by='support').head(10)\n",
    "\n",
    "# Display the first few rules showing diagnoses that occur together\n",
    "Lift_rules = Lift_rules[['antecedents', 'consequents', 'support', 'confidence', 'lift']]\n",
    "print(\"Rules Showing Diagnoses That Occur Together:\")\n",
    "print(Lift_rules)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "bDI2BgX517p4",
    "outputId": "bdb8b4e4-70f3-47a3-81f2-8a1f70605e4c"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Goodness of Rules (Co-occurring Diagnoses):\n",
      "   support  confidence      lift\n",
      "2      0.2    0.666667  1.333333\n",
      "3      0.2    1.000000  2.000000\n",
      "0      0.3    0.600000  1.200000\n",
      "1      0.3    0.600000  1.200000\n",
      "\n",
      "Goodness of Lift Rules (Diagnoses Occurring Together):\n",
      "   support  confidence      lift\n",
      "2      0.2    0.400000  1.333333\n",
      "3      0.2    0.666667  1.333333\n",
      "4      0.2    1.000000  2.000000\n",
      "5      0.2    0.400000  2.000000\n",
      "0      0.3    0.600000  1.200000\n",
      "1      0.3    0.600000  1.200000\n"
     ]
    }
   ],
   "source": [
    "# Step 5: Goodness of Rules - Support, Confidence, and Lift\n",
    "\n",
    "# Evaluate the goodness of rules\n",
    "print(\"\\nGoodness of Rules (Co-occurring Diagnoses):\")\n",
    "print(target_rules[['support', 'confidence', 'lift']])\n",
    "\n",
    "print(\"\\nGoodness of Lift Rules (Diagnoses Occurring Together):\")\n",
    "print(Lift_rules[['support', 'confidence', 'lift']])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "Ai5Z8uyV2CI1",
    "outputId": "e47a9fa0-2710-4256-bece-e4a3eb4d77ad"
   },
   "outputs": [],
   "source": [
    "# Step 6: Save the Rules for Further Analysis\n",
    "# Save the target prediction rules to a CSV file\n",
    "target_rules.to_csv('healthcare_target_prediction_rules.csv', index=False)\n",
    "\n",
    "# Save the supervised rules to a CSV file\n",
    "Lift_rules.to_csv('healthcare_diagnoses_occurring_together_rules.csv', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000
    },
    "id": "ozdbWcTJ2ICT",
    "outputId": "71ef492d-532f-4f08-87cf-a9ce0fca5cb9"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x800 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x800 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Step 7: Visualization\n",
    "\n",
    "# Visualization of Supervised Rules - Diagnoses Occurring Together\n",
    "plt.figure(figsize=(12, 8))\n",
    "G = nx.DiGraph()\n",
    "\n",
    "for _, row in target_rules.iterrows():\n",
    "    for ant in row['antecedents']:\n",
    "        for cons in row['consequents']:\n",
    "            G.add_edge(ant, cons, weight=row['lift'])\n",
    "\n",
    "pos = nx.spring_layout(G, k=0.5, seed=42)\n",
    "nx.draw(G, pos, with_labels=True, node_size=2000, font_size=10, font_weight='bold', node_color='skyblue', edge_color='gray')\n",
    "nx.draw_networkx_edge_labels(G, pos, edge_labels={(u, v): f\"lift: {d['weight']:.2f}\" for u, v, d in G.edges(data=True)}, font_size=8)\n",
    "plt.title('Visualization of Diagnoses Occurring Together (Target Rules)')\n",
    "plt.show()\n",
    "\n",
    "# Visualization of Unsupervised Rules - Co-occurring Diagnoses\n",
    "plt.figure(figsize=(12, 8))\n",
    "G = nx.DiGraph()\n",
    "\n",
    "for _, row in target_rules.iterrows():\n",
    "    for ant in row['antecedents']:\n",
    "        for cons in row['consequents']:\n",
    "            G.add_edge(ant, cons, weight=row['lift'])\n",
    "\n",
    "pos = nx.spring_layout(G, k=0.5, seed=42)\n",
    "nx.draw(G, pos, with_labels=True, node_size=2000, font_size=10, font_weight='bold', node_color='lightcoral', edge_color='gray')\n",
    "nx.draw_networkx_edge_labels(G, pos, edge_labels={(u, v): f\"lift: {d['weight']:.2f}\" for u, v, d in G.edges(data=True)}, font_size=8)\n",
    "plt.title('Visualization of Co-occurring Diagnoses (Lift Rules)')\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.12.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}