EDA.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Exploratory Data Analysis** \\\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 seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "from pypair.association import binary_binary, continuous_continuous, binary_continuous\n",
    "from sklearn.feature_selection import VarianceThreshold\n",
    "from sklearn.feature_selection import SelectKBest\n",
    "from sklearn.feature_selection import f_classif\n",
    "from sklearn.feature_selection import mutual_info_classif"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### First Steps"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bd_all = pd.read_spss('./input/17_abril.sav')\n",
    "\n",
    "# Filter the dataset to work only with alcohol patients\n",
    "bd = bd_all[bd_all['Alcohol_DxCIE'] == 'Sí']\n",
    "\n",
    "# Filter the dataset to work only with 'Situacion_tratamiento' == 'Abandono' or 'Alta'\n",
    "bd = bd[(bd['Situacion_tratamiento'] == 'Abandono') | (bd['Situacion_tratamiento'] == 'Alta terapéutica')]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Pre-pandemic\n",
    "conj_pre = bd[bd['Pandemia_inicio_fin_tratamiento'] == 'Inicio y fin prepandemia']\n",
    "# Pre-pandemic abandono\n",
    "pre_abandono = conj_pre[conj_pre['Situacion_tratamiento'] == 'Abandono']\n",
    "# Pre-pandemic alta\n",
    "pre_alta = conj_pre[conj_pre['Situacion_tratamiento'] == 'Alta terapéutica']\n",
    "\n",
    "# Post-pandemic\n",
    "# Merging last two classes to balance sets\n",
    "conj_post = bd[(bd['Pandemia_inicio_fin_tratamiento'] == 'Inicio prepandemia y fin en pandemia') | \n",
    "               (bd['Pandemia_inicio_fin_tratamiento'] == 'inicio y fin en pandemia')]\n",
    "# Post-pandemic abandono\n",
    "post_abandono = conj_post[conj_post['Situacion_tratamiento'] == 'Abandono']\n",
    "# Post-pandemic alta\n",
    "post_alta = conj_post[conj_post['Situacion_tratamiento'] == 'Alta terapéutica']\n",
    "\n",
    "# Concatenate the two data frames and add a new column to distinguish between them. Useful for plots\n",
    "conj_post['Group'] = 'Post'\n",
    "conj_pre['Group'] = 'Pre'\n",
    "combined_pre_post = pd.concat([conj_post, conj_pre])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Printing size of different datasets\n",
    "print(f\"PRE: {len(conj_pre)}\")\n",
    "print(f\"\\tALTA: {len(pre_alta)}\")\n",
    "print(f\"\\tABANDONO: {len(pre_abandono)}\")\n",
    "\n",
    "print(f\"POST: {len(conj_post)}\")\n",
    "print(f\"\\tALTA: {len(post_alta)}\")\n",
    "print(f\"\\tABANDONO: {len(post_abandono)}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"PRE\")\n",
    "print(conj_pre.info())\n",
    "print (\"-------------------------------\")\n",
    "print(\"PRE-ABANDONO\")\n",
    "print(pre_abandono.info())\n",
    "print (\"-------------------------------\")\n",
    "print(\"PRE-ALTA\")\n",
    "print(pre_alta.info())\n",
    "print (\"-------------------------------\")\n",
    "\n",
    "print(\"\\n\\n\\n\")\n",
    "\n",
    "print (\"POST\")\n",
    "print(conj_post.info())\n",
    "print (\"-------------------------------\")\n",
    "print(\"POST-ABANDONO\")\n",
    "print(post_abandono.info())\n",
    "print (\"-------------------------------\")\n",
    "print(\"POST-ALTA\")\n",
    "print(post_alta.info())\n",
    "print (\"-------------------------------\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Missing and Unknown Values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 9.0 represents unknown according to Variables.docx \n",
    "print(bd['Social_inclusion'].unique())\n",
    "mode_soc_inc = bd['Social_inclusion'].mode()[0]\n",
    "bd['Social_inclusion'] = bd['Social_inclusion'].replace('9.0', mode_soc_inc)\n",
    "print(bd['Social_inclusion'].unique())\n",
    "\n",
    "print(bd['Alterations_early_childhood_develop'].unique())\n",
    "mode_alt = bd['Alterations_early_childhood_develop'].mode()[0]\n",
    "bd['Alterations_early_childhood_develop'] = bd['Alterations_early_childhood_develop'].replace('9', mode_alt)\n",
    "print(bd['Alterations_early_childhood_develop'].unique())\n",
    "\n",
    "print(bd['Risk_stigma'].unique())\n",
    "mode_stigma = bd['Risk_stigma'].mode()[0]\n",
    "bd['Risk_stigma'] = bd['Risk_stigma'].replace(99.0, mode_stigma)\n",
    "print(bd['Risk_stigma'].unique())\n",
    "\n",
    "print(bd['NumHijos'].unique())\n",
    "mode_hijos = bd['NumHijos'].mode()[0]\n",
    "bd['NumHijos'] = bd['NumHijos'].replace(99.0, mode_hijos)\n",
    "print(bd['NumHijos'].unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(f\"Total missing values Age: {bd['Age'].isnull().sum()}\")\n",
    "print(f\"Total missing values Años_consumo_droga: {bd['Años_consumo_droga'].isnull().sum()}\")\n",
    "print(f\"Total missing values Risk_stigma: {bd['Risk_stigma'].isnull().sum()}\")\n",
    "print(f\"Total missing values NumHijos: {bd['NumHijos'].isnull().sum()}\")\n",
    "\n",
    "print(\"\\tCONJUNTO PREPANDEMIA\")\n",
    "print(f\"\\t\\tMissing values Age: {conj_pre['Age'].isnull().sum()}\")\n",
    "print(f\"\\t\\tMissing values Años_consumo_droga: {conj_pre['Años_consumo_droga'].isnull().sum()}\")\n",
    "print(f\"\\t\\tMissing values Risk_stigma: {conj_pre['Risk_stigma'].isnull().sum()}\")\n",
    "print(f\"\\t\\tMissing values NumHijos: {conj_pre['NumHijos'].isnull().sum()}\")\n",
    "\n",
    "print(\"\\tCONJUNTO POSTPANDEMIA\")\n",
    "print(f\"\\t\\tMissing values Age: {conj_post['Age'].isnull().sum()}\")\n",
    "print(f\"\\t\\tMissing values Años_consumo_droga: {conj_post['Años_consumo_droga'].isnull().sum()}\")\n",
    "print(f\"\\t\\tMissing values Risk_stigma: {conj_post['Risk_stigma'].isnull().sum()}\")\n",
    "print(f\"\\t\\tMissing values NumHijos: {conj_post['NumHijos'].isnull().sum()}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "age_mode = bd['Age'].mode()[0]\n",
    "bd['Age'].fillna(age_mode, inplace=True)\n",
    "\n",
    "años_consumo_mode = bd['Años_consumo_droga'].mode()[0]\n",
    "bd['Años_consumo_droga'].fillna(años_consumo_mode, inplace=True)\n",
    "\n",
    "risk_stigma_mode = bd['Risk_stigma'].mode()[0]\n",
    "bd['Risk_stigma'].fillna(risk_stigma_mode, inplace=True)\n",
    "\n",
    "num_hijos_mode = bd['NumHijos'].mode()[0]\n",
    "bd['NumHijos'].fillna(num_hijos_mode, inplace=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Distribution of Variables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "disc_atts = ['Education', 'Social_protection', 'Job_insecurity', 'Housing',\n",
    "        'Alterations_early_childhood_develop', 'Social_inclusion',\n",
    "        'Risk_stigma', 'Sex', 'NumHijos', 'Smoking', 'Biological_vulnerability',\n",
    "        'Opiaceos_DxCIE', 'Cannabis_DXCIE', 'BZD_DxCIE', 'Cocaina_DxCIE',\n",
    "        'Alucinogenos_DXCIE', 'Tabaco_DXCIE', 'FrecuenciaConsumo30Dias',\n",
    "        'OtrosDx_Psiquiatrico', 'Tx_previos', 'Readmisiones_estudios', 'Nreadmision'\n",
    "        ]\n",
    "\n",
    "num_atts = ['Structural_conflic', 'Adherencia_tto_recalc', 'Age', 'Años_consumo_droga', 'Tiempo_tx']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Discrete"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Countplots"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "fig, axs = plt.subplots(len(disc_atts), 1, figsize=(15, 5*len(disc_atts)))\n",
    "plt.subplots_adjust(hspace=0.75, wspace=1.25)\n",
    "\n",
    "for i, disc_att in enumerate(disc_atts):\n",
    "    ax = sns.countplot(x=disc_att, data=combined_pre_post, hue=combined_pre_post[['Situacion_tratamiento', 'Group']].apply(tuple, axis=1),\n",
    "                       hue_order=[('Abandono', 'Pre'),('Alta terapéutica', 'Pre'), ('Abandono', 'Post'), ('Alta terapéutica', 'Post')],\n",
    "                       ax=axs[i])\n",
    "    ax.set_title(disc_att, fontsize=16, fontweight='bold')\n",
    "    ax.get_legend().set_title(\"Groups\")\n",
    "    \n",
    "    # Adding count annotations\n",
    "    for p in ax.patches:\n",
    "        if p.get_label() == '_nolegend_':\n",
    "            ax.annotate(format(p.get_height(), '.0f'), \n",
    "                        (p.get_x() + p.get_width() / 2., p.get_height()), \n",
    "                        ha = 'center', va = 'center', \n",
    "                        xytext = (0, 9), \n",
    "                        textcoords = 'offset points')\n",
    "\n",
    "# Adjust layout to prevent overlapping titles\n",
    "plt.tight_layout()\n",
    "\n",
    "plt.savefig('./output/plots/distributions/countplots.svg', dpi=600, bbox_inches='tight')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Normalized Countplots"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Function to plot countplot \n",
    "def plot_count_perc_norm(i: int, group:int, disc_att:str) -> None:\n",
    "    \"\"\"\n",
    "        group: 1 (all), 2 (pre), 3 (post) \n",
    "    \"\"\"\n",
    "\n",
    "    # Define data to work with based on group\n",
    "    if group == 1:\n",
    "        df = bd \n",
    "    elif group == 2:\n",
    "        df = conj_pre\n",
    "    elif group == 3:\n",
    "        df = conj_post\n",
    "\n",
    "    # GOAL: find percentage of each possible category within the total of its situacion_tto subset\n",
    "    # Group data by 'Situacion_tratamiento' and 'Education' and count occurrences\n",
    "    grouped_counts = df.groupby(['Situacion_tratamiento', disc_att]).size().reset_index(name='count')\n",
    "    # Calculate total count for each 'Situacion_tratamiento' group\n",
    "    total_counts = df.groupby('Situacion_tratamiento')[disc_att].count()\n",
    "    # Divide each count by its corresponding total count and calculate percentage\n",
    "    grouped_counts['percentage'] = grouped_counts.apply(lambda row: row['count'] / total_counts[row['Situacion_tratamiento']] * 100, axis=1)\n",
    "    \n",
    "    # Follow the same order in plot as in computations\n",
    "    col_order = grouped_counts[grouped_counts['Situacion_tratamiento'] == 'Abandono'][disc_att].tolist()\n",
    "\n",
    "    # Create countplot and split each bar into two based on the value of sit_tto\n",
    "    ax = sns.countplot(x=disc_att, hue='Situacion_tratamiento', data=df, order=col_order, ax=axs[i, group-2])\n",
    "\n",
    "    # Adjust y-axis to represent percentages out of the total count\n",
    "    ax.set_ylim(0, 100)\n",
    "\n",
    "    percentages = grouped_counts['percentage']\n",
    "    for i, p in enumerate(ax.patches):\n",
    "        # Skip going over the legend values\n",
    "        if p.get_label() == \"_nolegend_\":\n",
    "            # Set height to corresponding percentage and annotate result\n",
    "            height = percentages[i]\n",
    "            p.set_height(height)\n",
    "            ax.annotate(f'{height:.2f}%', (p.get_x() + p.get_width() / 2., height),\n",
    "                        ha='center', va='bottom', fontsize=6, color='black', xytext=(0, 5),\n",
    "                        textcoords='offset points')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "fig, axs = plt.subplots(len(disc_atts), 2, figsize=(15, 7*len(disc_atts)))\n",
    "plt.subplots_adjust(hspace=0.75, wspace=1.5)\n",
    "\n",
    "for i, disc_att in enumerate(disc_atts):\n",
    "\n",
    "    # # 1: ALL    \n",
    "    # plot_count_perc_norm(i, 1, disc_att)\n",
    "    # axs[i, 0].set_title(\"\\nALL\")\n",
    "    # axs[i, 0].set_xlabel(disc_att, fontweight='bold')\n",
    "    # axs[i, 0].set_ylabel(\"% of total within its Sit_tto group\")\n",
    "    # axs[i, 0].tick_params(axis='x', rotation=90)\n",
    "    \n",
    "    # 2: PRE\n",
    "    plot_count_perc_norm(i, 2, disc_att)\n",
    "    axs[i, 0].set_title(\"\\nPRE\")\n",
    "    axs[i, 0].set_xlabel(disc_att, fontweight='bold')\n",
    "    axs[i, 0].set_ylabel(\"% of total within its Sit_tto group\")\n",
    "    axs[i, 0].tick_params(axis='x', rotation=90)\n",
    "\n",
    "    # 3: POST\n",
    "    plot_count_perc_norm(i, 3, disc_att)\n",
    "    axs[i, 1].set_title(\"\\nPOST\")\n",
    "    axs[i, 1].set_xlabel(disc_att, fontweight='bold')\n",
    "    axs[i, 1].set_ylabel(\"% of total within its Sit_tto group\")\n",
    "    axs[i, 1].tick_params(axis='x', rotation=90)\n",
    "\n",
    "    \n",
    "# Adjust layout to prevent overlapping titles\n",
    "plt.tight_layout()\n",
    "\n",
    "# Save the figure in SVG format with DPI=600 in the \"._plots\" folder\n",
    "plt.savefig('./output/plots/distributions/norm_countplots.svg', dpi=600, bbox_inches='tight')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Numerical"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Summary Stats"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(bd[num_atts].describe())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Boxplots"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "fig, axs = plt.subplots(len(num_atts), 1, figsize=(12, 5*len(num_atts)))\n",
    "plt.subplots_adjust(hspace=0.75, wspace=1.5)\n",
    "\n",
    "for i, num_att in enumerate(num_atts):\n",
    "    plt.subplot(len(num_atts), 1, i+1)\n",
    "    sns.boxplot(\n",
    "        data=combined_pre_post,\n",
    "        x = num_att,\n",
    "        y = 'Group',\n",
    "        hue='Situacion_tratamiento',\n",
    "    )\n",
    "\n",
    "# Adjust layout to prevent overlapping titles\n",
    "plt.tight_layout()\n",
    "\n",
    "# Save the figure in SVG format with DPI=600 in the \"./EDA_plots\" folder\n",
    "plt.savefig('./output/plots/distributions/boxplots.svg', dpi=600, bbox_inches='tight')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Histograms"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "fig, axs = plt.subplots(len(num_atts), 3, figsize=(15, 6*len(num_atts)))\n",
    "plt.subplots_adjust(hspace=0.75, wspace=1.5)\n",
    "\n",
    "for i, num_att in enumerate(num_atts):\n",
    "\n",
    "    # 1: All alcohol patients\n",
    "    sns.histplot(data=bd,x=num_att,bins=15, hue='Situacion_tratamiento', stat='probability', common_norm=False, kde=True,\n",
    "                 line_kws={'lw': 5}, alpha = 0.4, ax=axs[i, 0])\n",
    "    axs[i, 0].set_title(f\"\\nDistr. of {num_att}  - ALL\")\n",
    "\n",
    "    # 2: PRE\n",
    "    sns.histplot(data=conj_pre,x=num_att,bins=15, hue='Situacion_tratamiento', stat='probability', common_norm=False, kde=True, \n",
    "                 line_kws={'lw': 5}, alpha = 0.4, ax=axs[i, 1])\n",
    "    axs[i, 1].set_title(f\"\\nDistr. of {num_att}  - PRE\")\n",
    "\n",
    "    # Subplot 3: POST\n",
    "    sns.histplot(data=conj_post,x=num_att,bins=15, hue='Situacion_tratamiento', stat='probability', common_norm=False, kde=True, \n",
    "                 line_kws={'lw': 5}, alpha = 0.4, ax=axs[i, 2])\n",
    "    axs[i, 2].set_title(f\"\\nDistr. of {num_att}  - POST\")\n",
    "\n",
    "# Adjust layout to prevent overlapping titles\n",
    "plt.tight_layout()\n",
    "\n",
    "# Save the figure in SVG format with DPI=600 in the \"./EDA_plots\" folder\n",
    "plt.savefig('./output/plots/distributions/histograms.svg', dpi=600, bbox_inches='tight')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Correlation Analysis"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Groups of Variables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "social_vars = ['Education', 'Social_protection', 'Job_insecurity', 'Housing', 'Alterations_early_childhood_develop', \n",
    "            'Social_inclusion', 'Risk_stigma', 'Structural_conflic']\n",
    "ind_vars = ['Age', 'Sex', 'NumHijos', 'Smoking', 'Biological_vulnerability', 'Opiaceos_DxCIE', \n",
    "            'Cannabis_DXCIE', 'BZD_DxCIE', 'Cocaina_DxCIE', 'Alucinogenos_DXCIE', 'Tabaco_DXCIE', \n",
    "            'FrecuenciaConsumo30Dias', 'Años_consumo_droga','OtrosDx_Psiquiatrico', 'Tx_previos', 'Adherencia_tto_recalc'] \n",
    "target_var = 'Situacion_tratamiento'\n",
    "\n",
    "# Columns that are already numeric and we don't need to redefine \n",
    "no_redef_cols = ['Structural_conflic', 'Age', 'NumHijos', 'Años_consumo_droga', 'Adherencia_tto_recalc']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### One-hot Encoding"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Binary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# --------------------------------------------------------------------------\n",
    "\n",
    "# 'Alterations_early_childhood_develop'\n",
    "alterations_mapping = {\n",
    "    'No alterations (first exposure at 11 or more years)' : 0,\n",
    "    'Alterations (first exposure before 11 years old)': 1,\n",
    "}\n",
    "\n",
    "bd['Alterations_early_childhood_develop_REDEF'] = bd['Alterations_early_childhood_develop'].map(alterations_mapping)\n",
    "\n",
    "# --------------------------------------------------------------------------\n",
    "\n",
    "# Social protection\n",
    "bd['Social_protection_REDEF'] = bd['Social_protection'].map({'No':0, 'Sí':1})\n",
    "\n",
    "# --------------------------------------------------------------------------\n",
    "\n",
    "# 'Risk_stigma'\n",
    "bd['Risk_stigma_REDEF'] = bd['Risk_stigma'].map({'No':0, 'Yes':1})\n",
    "\n",
    "# --------------------------------------------------------------------------\n",
    "\n",
    "# 'Sex'\n",
    "bd['Sex_REDEF'] = bd['Sex'].map({'Hombre':0, 'Mujer':1})\n",
    "\n",
    "# --------------------------------------------------------------------------\n",
    "\n",
    "# 'Smoking'\n",
    "bd['Smoking_REDEF'] = bd['Smoking'].map({'No':0, 'Sí':1})\n",
    "\n",
    "# --------------------------------------------------------------------------\n",
    "\n",
    "# 'Biological_vulnerability'\n",
    "bd['Biological_vulnerability_REDEF'] = bd['Biological_vulnerability'].map({'No':0, 'Sí':1})\n",
    "\n",
    "# --------------------------------------------------------------------------\n",
    "\n",
    "# 'Droga_DxCIE'\n",
    "bd['Opiaceos_DxCIE_REDEF'] = bd['Opiaceos_DxCIE'].map({'No': 0, 'Sí': 1})\n",
    "bd['Cannabis_DXCIE_REDEF'] = bd['Cannabis_DXCIE'].map({'No': 0, 'Sí': 1})\n",
    "bd['BZD_DxCIE_REDEF'] = bd['BZD_DxCIE'].map({'No': 0, 'Sí': 1})\n",
    "bd['Cocaina_DxCIE_REDEF'] = bd['Cocaina_DxCIE'].map({'No': 0, 'Sí': 1})\n",
    "bd['Alucinogenos_DXCIE_REDEF'] = bd['Alucinogenos_DXCIE'].map({'No': 0, 'Sí': 1})\n",
    "bd['Tabaco_DXCIE_REDEF'] = bd['Tabaco_DXCIE'].map({'No': 0, 'Sí': 1})\n",
    "\n",
    "# --------------------------------------------------------------------------\n",
    "\n",
    "# 'OtrosDx_Psiquiatrico'\n",
    "bd['OtrosDx_Psiquiatrico_REDEF'] = bd['OtrosDx_Psiquiatrico'].map({'No':0, 'Sí':1})\n",
    "\n",
    "# --------------------------------------------------------------------------\n",
    "\n",
    "# 'Tx_previos'\n",
    "bd['Tx_previos_REDEF'] = bd['Tx_previos'].map({'No':0, 'Sí':1})\n",
    "\n",
    "# --------------------------------------------------------------------------\n",
    "\n",
    "# 'Situacion_tratamiento (!!!!!)\n",
    "# Important to define properly\n",
    "bd['Situacion_tratamiento_REDEF'] = bd['Situacion_tratamiento'].map({'Abandono':1, 'Alta terapéutica':0})\n",
    "\n",
    "# --------------------------------------------------------------------------"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Categorical"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Specify columns to one hot encode; empty list otherwise\n",
    "one_hot_vars = ['Education', 'Job_insecurity', 'Housing', 'Social_inclusion', 'FrecuenciaConsumo30Dias']\n",
    "\n",
    "one_hots_vars_prefix = {\n",
    "    'Education': 'Ed',\n",
    "    'Job_insecurity': 'JobIn',\n",
    "    'Housing': 'Hous', \n",
    "    'Social_inclusion': 'SocInc',\n",
    "    'FrecuenciaConsumo30Dias': 'Frec30',\n",
    "}\n",
    "\n",
    "one_hot_cols_dic = {}\n",
    "\n",
    "for one_hot_var in one_hot_vars:\n",
    "    # Create one hot encoding version of attribute and concatenate new columns to main df\n",
    "    encoded_var = pd.get_dummies(bd[one_hot_var], prefix=one_hots_vars_prefix[one_hot_var])\n",
    "    bd = pd.concat([bd, encoded_var], axis=1)\n",
    "    one_hot_cols_dic[one_hot_var] = encoded_var.columns.tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Final Columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "soc_vars_enc = []\n",
    "for soc_var in social_vars:\n",
    "    # If no need to redefine, append directly\n",
    "    if soc_var in no_redef_cols:\n",
    "        soc_vars_enc.append(soc_var)\n",
    "    # If need to redefine\n",
    "    else:\n",
    "        # Check if it was one-hot encoded\n",
    "        if soc_var in one_hot_vars:\n",
    "            # Append all one hot columns\n",
    "            soc_vars_enc = soc_vars_enc + one_hot_cols_dic[soc_var]\n",
    "        # If not, use redefined version through mapping\n",
    "        else:\n",
    "            soc_vars_enc.append(soc_var + '_REDEF')\n",
    "\n",
    "ind_vars_enc = []\n",
    "for ind_var in ind_vars:\n",
    "    # If no need to redefine, append directly\n",
    "    if ind_var in no_redef_cols:\n",
    "        ind_vars_enc.append(ind_var)\n",
    "    # If need to redefine\n",
    "    else:\n",
    "        # Check if it was one-hot encoded\n",
    "        if ind_var in one_hot_vars:\n",
    "            # Append all one hot columns\n",
    "            ind_vars_enc = ind_vars_enc + one_hot_cols_dic[ind_var]\n",
    "        # If not, use redefined version through mapping\n",
    "        else:\n",
    "            ind_vars_enc.append(ind_var + '_REDEF')\n",
    "\n",
    "# Final version of columns we need to use for correlation analysis\n",
    "corr_cols = soc_vars_enc + ind_vars_enc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Drop unknown columns\n",
    "corr_cols = [corr_col for corr_col in corr_cols if corr_col not in ['Ed_Unknowledge', 'JobIn_unkwnodledge', 'Hous_unknowledge', 'Frec30_Desconocido']]\n",
    "soc_vars_enc = [corr_col for corr_col in soc_vars_enc if corr_col not in ['Ed_Unknowledge', 'JobIn_unkwnodledge', 'Hous_unknowledge', 'Frec30_Desconocido']]\n",
    "ind_vars_enc = [corr_col for corr_col in ind_vars_enc if corr_col not in ['Ed_Unknowledge', 'JobIn_unkwnodledge', 'Hous_unknowledge', 'Frec30_Desconocido']]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Renaming and Filtering"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "columns_to_keep = corr_cols + ['Situacion_tratamiento','Situacion_tratamiento_REDEF', 'Pandemia_inicio_fin_tratamiento']\n",
    "bd = bd[columns_to_keep]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "name_mapping = {\n",
    "    'Ed_Not Complete primary school': 'Ed_Not_Complete_Primary',\n",
    "    'Ed_Primary education': 'Ed_Primary',\n",
    "    'Ed_Secondary Education': 'Ed_Secondary',\n",
    "    'Ed_Secondary more technical education': 'Ed_Secondary_Technical',\n",
    "    'Ed_Tertiary': 'Ed_Tertiary',\n",
    "    'Social_protection_REDEF': 'Social_Protection',\n",
    "    'JobIn_Non-stable': 'JobIn_Unstable',\n",
    "    'JobIn_Stable': 'JobIn_Stable',\n",
    "    'JobIn_Unemployed': 'JobIn_Unemployed',\n",
    "    'Hous_Institutional': 'Hous_Institutional',\n",
    "    'Hous_Stable': 'Hous_Stable',\n",
    "    'Hous_Unstable': 'Hous_Unstable',\n",
    "    'Alterations_early_childhood_develop_REDEF': 'Early_Alterations',\n",
    "    'SocInc_Live with families or friends': 'SocInc_Family_Friends',\n",
    "    'SocInc_live alone': 'SocInc_Alone',\n",
    "    'SocInc_live in institutions': 'SocInc_Instit',\n",
    "    'Risk_stigma_REDEF': 'Risk_Stigma',\n",
    "    'Structural_conflic': 'Structural_Conflict',\n",
    "    'Age': 'Age',\n",
    "    'Sex_REDEF': 'Sex',\n",
    "    'NumHijos': 'Num_Children',\n",
    "    'Smoking_REDEF': 'Smoking',\n",
    "    'Biological_vulnerability_REDEF': 'Bio_Vulner',\n",
    "    'Opiaceos_DxCIE_REDEF': 'Opiods_DXCIE',\n",
    "    'Cannabis_DXCIE_REDEF': 'Cannabis_DXCIE',\n",
    "    'BZD_DxCIE_REDEF': 'BZD_DXCIE',\n",
    "    'Cocaina_DxCIE_REDEF': 'Cocaine_DXCIE',\n",
    "    'Alucinogenos_DXCIE_REDEF': 'Hallucin_DXCIE',\n",
    "    'Tabaco_DXCIE_REDEF': 'Tobacco_DXCIE',\n",
    "    'Frec30_1 día/semana': 'Freq_1dpw',\n",
    "    'Frec30_2-3 días\\u200e/semana': 'Freq_2-3dpw',\n",
    "    'Frec30_4-6 días/semana': 'Freq_4-6dpw',\n",
    "    'Frec30_Menos de 1 día\\u200e/semana': 'Freq_l1dpw',\n",
    "    'Frec30_No consumio': 'Freq_None',\n",
    "    'Frec30_Todos los días': 'Freq_Everyday',\n",
    "    'Años_consumo_droga': 'Years_Drug_Use',\n",
    "    'OtrosDx_Psiquiatrico_REDEF': 'Other_Psychiatric_DX',\n",
    "    'Tx_previos_REDEF': 'Previous_Treatments',\n",
    "    'Adherencia_tto_recalc': 'Treatment_Adherence',\n",
    "    'Situacion_tratamiento_REDEF': 'Treatment_Outcome',\n",
    "    'Situacion_tratamiento': 'Situacion_tratamiento',\n",
    "    'Pandemia_inicio_fin_tratamiento': 'Pandemia_inicio_fin_tratamiento'\n",
    "}\n",
    "\n",
    "# Update lists of feature names\n",
    "corr_cols = [name_mapping[corr_col] for corr_col in corr_cols]\n",
    "soc_vars_enc = [name_mapping[col] for col in soc_vars_enc]\n",
    "ind_vars_enc = [name_mapping[col] for col in ind_vars_enc]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Export feature names\n",
    "np.save('./output/feature_names/feature_names.npy', corr_cols)\n",
    "np.save('./output/feature_names/soc_vars_names.npy', soc_vars_enc)\n",
    "np.save('./output/feature_names/ind_vars_names.npy', ind_vars_enc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bd = bd.rename(columns=name_mapping)[list(name_mapping.values())]\n",
    "#print(bd.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Update main dfs\n",
    "# Pre-pandemic\n",
    "conj_pre = bd[bd['Pandemia_inicio_fin_tratamiento'] == 'Inicio y fin prepandemia']\n",
    "# Pre-pandemic abandono\n",
    "pre_abandono = conj_pre[conj_pre['Situacion_tratamiento'] == 'Abandono']\n",
    "# Pre-pandemic alta\n",
    "pre_alta = conj_pre[conj_pre['Situacion_tratamiento'] == 'Alta terapéutica']\n",
    "\n",
    "# Post-pandemic\n",
    "# Merging last two classes to balance sets\n",
    "conj_post = bd[(bd['Pandemia_inicio_fin_tratamiento'] == 'Inicio prepandemia y fin en pandemia') | \n",
    "               (bd['Pandemia_inicio_fin_tratamiento'] == 'inicio y fin en pandemia')]\n",
    "# Post-pandemic abandono\n",
    "post_abandono = conj_post[conj_post['Situacion_tratamiento'] == 'Abandono']\n",
    "# Post-pandemic alta\n",
    "post_alta = conj_post[conj_post['Situacion_tratamiento'] == 'Alta terapéutica']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Plotting Correlation Matrices"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "binary_vars = [col for col in corr_cols if len(bd[col].unique()) == 2] + [name_mapping['Situacion_tratamiento_REDEF'], name_mapping['Risk_stigma_REDEF']]\n",
    "cont_vars = [name_mapping[col] for col in ['Structural_conflic', 'Age', 'NumHijos', 'Años_consumo_droga', 'Adherencia_tto_recalc']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_corr_matrix(df, cols):\n",
    "    \n",
    "    # Initialize nxn matrix to zeroes\n",
    "    n = len(cols)\n",
    "    corr_matrix = np.zeros((n,n))\n",
    "\n",
    "    for i, var_i in enumerate(cols):\n",
    "        for j, var_j in enumerate(cols):\n",
    "            # Fill lower triangle of matrix\n",
    "            if i > j:\n",
    "                # Binary with binary correlation: tetrachoric\n",
    "                if var_i in binary_vars and var_j in binary_vars:\n",
    "                    corr = binary_binary(df[var_i], df[var_j], measure='tetrachoric')\n",
    "                # Continuous with continuous correlation: \n",
    "                elif var_i in cont_vars and var_j in cont_vars:\n",
    "                    # Returning nan sometimes:\n",
    "                    # corr_tuple = continuous_continuous(df[var_i], df[var_j], measure = 'spearman')\n",
    "                    # corr = corr_tuple[0]\n",
    "                    corr = df[var_i].corr(df[var_j], method='spearman')\n",
    "                # Binary vs Continuous correlation:\n",
    "                else:\n",
    "                    if var_i in binary_vars:\n",
    "                        bin_var = var_i\n",
    "                        cont_var = var_j\n",
    "                    else:\n",
    "                        bin_var = var_j\n",
    "                        cont_var = var_i\n",
    "                    corr = binary_continuous(df[bin_var], df[cont_var], measure='point_biserial')\n",
    "                # Assign value to matrix\n",
    "                corr_matrix[i][j] = corr \n",
    "                      \n",
    "    return corr_matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_heatmap(sit_tto: int, group:int) -> None:\n",
    "    \"\"\"\n",
    "        sit_tto: 1 (include it as another var), 2 (only abandono), 3 (only alta)\n",
    "        group: 1 (all alcohol patients), 2 (pre), 3 (post)\n",
    "    \"\"\"\n",
    "\n",
    "    # Define columns based on sit_tto arg\n",
    "    if sit_tto == 1:\n",
    "        # Include target as another variable\n",
    "        cols = ['Treatment_Outcome'] + corr_cols\n",
    "    else:\n",
    "        cols = corr_cols\n",
    "        \n",
    "    # Title plot and select datat based on group and sit_tto\n",
    "    if group == 1:\n",
    "        plot_title = \"Correl Matrix - ALL\"\n",
    "        if sit_tto == 1:\n",
    "            bd_ca = bd[cols]\n",
    "        elif sit_tto == 2:\n",
    "            bd_ca = bd[bd['Situacion_tratamiento'] == 'Abandono'][cols]\n",
    "        elif sit_tto == 3:\n",
    "            bd_ca = bd[bd['Situacion_tratamiento'] == 'Alta terapéutica'][cols]\n",
    "    elif group == 2:\n",
    "        plot_title = \"Correl Matrix - PRE\"\n",
    "        if sit_tto == 1:    \n",
    "            bd_ca = conj_pre[cols]\n",
    "        elif sit_tto == 2:\n",
    "            bd_ca = pre_abandono[cols]\n",
    "        elif sit_tto == 3:\n",
    "            bd_ca = pre_alta[cols]\n",
    "    elif group == 3:\n",
    "        plot_title = \"Correl Matrix - POST\"\n",
    "        if sit_tto == 1:    \n",
    "            bd_ca = conj_post[cols]\n",
    "        elif sit_tto == 2:\n",
    "            bd_ca = post_abandono[cols]\n",
    "        elif sit_tto == 3:\n",
    "            bd_ca = post_alta[cols]\n",
    "            \n",
    "    # Complete title\n",
    "    if sit_tto == 2:\n",
    "        plot_title += \" - ABANDONO\"\n",
    "    elif sit_tto == 3:\n",
    "        plot_title += \" - ALTA\"\n",
    "\n",
    "    corr_matrix = get_corr_matrix(bd_ca, cols)\n",
    "\n",
    "    # Create a mask for the upper triangle\n",
    "    mask = np.triu(np.ones_like(corr_matrix, dtype=bool))\n",
    "\n",
    "    # Create heatmap correlation matrix\n",
    "    dataplot = sns.heatmap(corr_matrix, mask=mask, xticklabels=cols, yticklabels=cols, cmap=\"coolwarm\", vmin=-1, vmax=1, annot=True, fmt=\".2f\", annot_kws={\"size\": 4})\n",
    "\n",
    "    # Group ind vs social vars by color and modify tick label names\n",
    "    for tick_label in dataplot.axes.xaxis.get_ticklabels():\n",
    "        if tick_label.get_text() in ind_vars_enc:\n",
    "            tick_label.set_color('green')\n",
    "        elif tick_label.get_text() in soc_vars_enc:\n",
    "            tick_label.set_color('purple')  \n",
    "    for tick_label in dataplot.axes.yaxis.get_ticklabels():\n",
    "        if tick_label.get_text() in ind_vars_enc:\n",
    "            tick_label.set_color('green')\n",
    "        elif tick_label.get_text() in soc_vars_enc:\n",
    "            tick_label.set_color('purple') \n",
    "\n",
    "    # Increase the size of xtick labels\n",
    "    # dataplot.tick_params(axis='x', labelsize=12)\n",
    "\n",
    "    # Increase the size of ytick labels\n",
    "    # dataplot.tick_params(axis='y', labelsize=12)\n",
    "\n",
    "    # Add legend and place it in lower left \n",
    "    plt.legend(handles=[\n",
    "        plt.Line2D([0], [0], marker='o', color='w', label='Social Factors', markerfacecolor='purple', markersize=10),\n",
    "        plt.Line2D([0], [0], marker='o', color='w', label='Individual Factors', markerfacecolor='green', markersize=10)\n",
    "    ], bbox_to_anchor=(-0.1, -0.1), fontsize = 20)\n",
    "\n",
    "    plt.title(\"\\n\\n\" + plot_title, fontdict={'fontsize': 30, 'fontweight': 'bold'})\n",
    "\n",
    "    return corr_matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "fig, axs = plt.subplots(3, 3, figsize=(50, 50))\n",
    "plt.subplots_adjust(hspace=0.75, wspace=2)\n",
    "corr_mats = [] # List of tuples (m1, m2) to store the 3 pairs of matrices to compare (pre vs post)\n",
    "\n",
    "# Go through possible values for 'Situacion_tratamiento' and 'Group'\n",
    "for sit_tto in range(1,4):\n",
    "    # ALL\n",
    "    plt.subplot(3, 3, 3*(sit_tto-1) + 1)  # Calculate the subplot position dynamically\n",
    "    _ = plot_heatmap(sit_tto, 1)\n",
    "    # PRE\n",
    "    plt.subplot(3, 3, 3*(sit_tto-1) + 2) \n",
    "    corr_matrix_pre = plot_heatmap(sit_tto, 2)\n",
    "    # POST\n",
    "    plt.subplot(3, 3, 3*(sit_tto-1) + 3)\n",
    "    corr_matrix_post = plot_heatmap(sit_tto, 3)\n",
    "\n",
    "    corr_mats.append((corr_matrix_pre, corr_matrix_post))\n",
    "        \n",
    "plt.tight_layout()\n",
    "\n",
    "plt.savefig('./output/plots/correlations/heatmaps_one_hot.svg', dpi=550, bbox_inches='tight')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Finding Differences PRE vs POST"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def find_diff (sit_tto:int, m_pre, m_post):\n",
    "\n",
    "    diff_list = []  # List to store tuples of (difference, variable_i, variable_j)\n",
    "\n",
    "    if sit_tto == 1:\n",
    "        cols = [target_var + '_REDEF'] + corr_cols\n",
    "    else:\n",
    "        cols = corr_cols\n",
    "    # Go through matrices\n",
    "    for i, var_i in enumerate(cols):\n",
    "        for j, var_j in enumerate(cols):\n",
    "            # If difference greater than certain threshold, print variables \n",
    "            val_pre = m_pre[i][j]\n",
    "            val_post = m_post[i][j]\n",
    "            diff = abs(val_pre - val_post)\n",
    "            diff_list.append((diff, var_i, var_j, val_pre, val_post))\n",
    "    \n",
    "    # Sort the list based on the difference value in descending order\n",
    "    diff_list.sort(key=lambda x: x[0], reverse=True)\n",
    "            \n",
    "    # Print the sorted list\n",
    "    for diff, var_i, var_j, val_pre, val_post in diff_list[0:100]:\n",
    "        # Give ind vs soc vars their corresponding color\n",
    "        if var_i in ind_vars_enc:\n",
    "            print(colors.GREEN + var_i + colors.RESET, end=' ')\n",
    "        else:\n",
    "            print(colors.PURPLE + var_i + colors.PURPLE, end=' ')\n",
    "        print(\"& \", end='')\n",
    "        if var_j in ind_vars_enc:\n",
    "            print(colors.GREEN + var_j + colors.RESET, end=' ')\n",
    "        else:\n",
    "            print(colors.PURPLE + var_j + colors.RESET, end=' ')\n",
    "        print(f\"--> Diff: {diff:.2f} (PRE: {val_pre:.2f}; POST: {val_post:.2f})\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "class colors:\n",
    "    RED = '\\033[91m'\n",
    "    GREEN = '\\033[92m'\n",
    "    YELLOW = '\\033[93m'\n",
    "    BLUE = '\\033[94m'\n",
    "    PURPLE = '\\033[95m'\n",
    "    CYAN = '\\033[96m'\n",
    "    WHITE = '\\033[97m'\n",
    "    RESET = '\\033[0m'\n",
    "\n",
    "# Print colored text\n",
    "print(colors.RED + \"This is red text.\" + colors.RESET)\n",
    "print(colors.GREEN + \"This is green text.\" + colors.RESET)\n",
    "print(colors.BLUE + \"This is blue text.\" + colors.RESET)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"------SIT_TTO 1: NO FILTERING------\")\n",
    "find_diff(1, corr_mats[0][0], corr_mats[0][1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"------SIT_TTO 2: ABANDONO-----\")\n",
    "find_diff(2, corr_mats[1][0], corr_mats[1][1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"------SIT_TTO 3: ALTA-----\")\n",
    "find_diff(3, corr_mats[2][0], corr_mats[2][1])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Final Datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bd = bd.drop(columns=['Situacion_tratamiento'])\n",
    "# print(len(bd.columns))\n",
    "\n",
    "# For conj_pre dataframe\n",
    "conj_pre = bd[bd['Pandemia_inicio_fin_tratamiento'] == 'Inicio y fin prepandemia']\n",
    "conj_pre = conj_pre.drop(columns=['Pandemia_inicio_fin_tratamiento'])\n",
    "\n",
    "# For conj_post dataframe\n",
    "conj_post = bd[(bd['Pandemia_inicio_fin_tratamiento'] == 'Inicio prepandemia y fin en pandemia') | \n",
    "                    (bd['Pandemia_inicio_fin_tratamiento'] == 'inicio y fin en pandemia')]\n",
    "conj_post = conj_post.drop(columns=['Pandemia_inicio_fin_tratamiento'])\n",
    "\n",
    "# print(conj_post.columns)\n",
    "# print(conj_pre.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_pre, y_pre = conj_pre.loc[:, conj_pre.columns != \"Treatment_Outcome\"].to_numpy(), conj_pre.Treatment_Outcome\n",
    "X_post, y_post = conj_post.loc[:, conj_post.columns != \"Treatment_Outcome\"].to_numpy(), conj_post.Treatment_Outcome\n",
    "feat = np.delete(conj_pre.columns.to_numpy(),-1) # Get labels and remove target \n",
    "\n",
    "# Export datasets\n",
    "conj_pre.to_csv('./output/datasets/pre_dataset.csv', index=False)\n",
    "conj_post.to_csv('./output/datasets/post_dataset.csv', index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Feature Analysis"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Mutual Info"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create subplots\n",
    "fig, axes = plt.subplots(1, 2, figsize=(12, 6))\n",
    "\n",
    "# PRE\n",
    "importances_MI = mutual_info_classif(X_pre, y_pre)\n",
    "feat_importances_MI = pd.Series(importances_MI, feat)\n",
    "feat_importances_MI.sort_values(inplace=True)\n",
    "axes[0].barh(feat_importances_MI[feat_importances_MI != 0][-20:].index, feat_importances_MI[feat_importances_MI != 0][-20:], color='teal')\n",
    "axes[0].set_xlabel(\"Mutual Information\")\n",
    "axes[0].set_title(\"PRE\")\n",
    "\n",
    "# POST\n",
    "importances_MI = mutual_info_classif(X_post, y_post)\n",
    "feat_importances_MI = pd.Series(importances_MI, feat)\n",
    "feat_importances_MI.sort_values(inplace=True)\n",
    "axes[1].barh(feat_importances_MI[feat_importances_MI != 0][-20:].index, feat_importances_MI[feat_importances_MI != 0][-20:], color='teal')\n",
    "axes[1].set_xlabel(\"Mutual Information\")\n",
    "axes[1].set_title(\"POST\")\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.savefig('./output/plots/feature_importance/mutual_info.svg', format='svg', dpi=1200)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### ANOVA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create subplots\n",
    "fig, axes = plt.subplots(1, 2, figsize=(12, 6))\n",
    "\n",
    "# PRE\n",
    "selector = SelectKBest(f_classif, k=39)\n",
    "selector.fit(X_pre, y_pre)\n",
    "feat_importances_AN_pre = pd.Series(selector.pvalues_, feat)\n",
    "feat_importances_AN_pre.sort_values(inplace=True)\n",
    "axes[0].barh(feat_importances_AN_pre[feat_importances_AN_pre > 0.005][-20:].index, feat_importances_AN_pre[feat_importances_AN_pre > 0.005][-20:], color='teal')\n",
    "axes[0].set_xlabel(\"p-value ANOVA\")\n",
    "axes[0].set_title(\"PRE\")\n",
    "\n",
    "# POST\n",
    "selector = SelectKBest(f_classif, k=39)\n",
    "selector.fit(X_post, y_post)\n",
    "feat_importances_AN_post = pd.Series(selector.pvalues_, feat)\n",
    "feat_importances_AN_post.sort_values(inplace=True)\n",
    "axes[1].barh(feat_importances_AN_post[feat_importances_AN_post > 0.005][-20:].index, feat_importances_AN_post[feat_importances_AN_post > 0.005][-20:], color='teal') \n",
    "axes[1].set_xlabel(\"p-value ANOVA\")\n",
    "axes[1].set_title(\"POST\")\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.savefig('./output/plots/feature_importance/ANOVA.svg', format='svg', dpi=1200)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Variance Threshold"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create subplots\n",
    "fig, axes = plt.subplots(1, 2, figsize=(15, 6))\n",
    "\n",
    "# PRE\n",
    "variance_filter = VarianceThreshold(threshold=0)\n",
    "variance_filter.fit(X_pre)\n",
    "feat_importances_var_pre = pd.Series(variance_filter.variances_, feat)\n",
    "feat_importances_var_pre.sort_values(inplace=True)\n",
    "axes[0].barh(feat_importances_var_pre[feat_importances_var_pre > 0.05][-20:].index, feat_importances_var_pre[feat_importances_var_pre > 0.05][-20:], color='teal')\n",
    "axes[0].set_xlabel(\"Variance\")\n",
    "axes[0].set_title(\"PRE\")\n",
    "\n",
    "# POST\n",
    "variance_filter = VarianceThreshold(threshold=0)\n",
    "variance_filter.fit(X_post)\n",
    "feat_importances_var_post = pd.Series(variance_filter.variances_, feat)\n",
    "feat_importances_var_post.sort_values(inplace=True)\n",
    "axes[1].barh(feat_importances_var_post[feat_importances_var_post > 0.05][-20:].index, feat_importances_var_post[feat_importances_var_post > 0.05][-20:], color='teal')\n",
    "axes[1].set_xlabel(\"Variance\")\n",
    "axes[1].set_title(\"POST\")\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.savefig('./output/plots/feature_importance/var_threshold.svg', format='svg', dpi=1200)\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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
}