{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Inspect user interactions\n",
    "\n",
    "Inspecting the user interactions obtained from the NN, DTC and TC graphs."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Import the dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "casename = '...'\n",
    "case = '...'\n",
    "\n",
    "df_data = pd.read_csv(f'../datasets/{case}-closed-s-users.csv')\n",
    "\n",
    "df_data.describe()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Plot the distributions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "plt.subplot(2,3,1)\n",
    "sns.histplot(df_data['nn-count'], bins=20)\n",
    "plt.yscale('log')\n",
    "plt.title('Distribution of NN interactions')\n",
    "plt.xlabel('NN interactions')\n",
    "plt.ylabel('Count')\n",
    "plt.grid()\n",
    "plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
    "\n",
    "plt.subplot(2,3,2)\n",
    "sns.histplot(df_data['dtc-count'], bins=20)\n",
    "plt.yscale('log')\n",
    "plt.title('Distribution of DTC interactions')\n",
    "plt.xlabel('DTC interactions')\n",
    "plt.ylabel('Count')\n",
    "plt.grid()\n",
    "plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
    "\n",
    "plt.subplot(2,3,3)\n",
    "sns.histplot(df_data['tc-count'], bins=20)\n",
    "plt.yscale('log')\n",
    "plt.title('Distribution of TC interactions')\n",
    "plt.xlabel('TC interactions')\n",
    "plt.ylabel('Count')\n",
    "plt.grid()\n",
    "plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
    "\n",
    "plt.subplot(2,3,4)\n",
    "sns.histplot(df_data['post-count'], bins=20)\n",
    "plt.yscale('log')\n",
    "plt.title('Distribution of posts')\n",
    "plt.xlabel('Number of posts')\n",
    "plt.ylabel('Count')\n",
    "plt.grid()\n",
    "plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
    "\n",
    "plt.subplot(2,3,5)\n",
    "sns.histplot(df_data['mean-sentiment'], bins=20, kde=True)\n",
    "plt.title('Distribution of mean sentiment')\n",
    "plt.xlabel('Mean sentiment')\n",
    "plt.ylabel('Count')\n",
    "plt.grid()\n",
    "plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
    "\n",
    "plt.subplot(2,3,6)\n",
    "sns.histplot(df_data['std-sentiment'], bins=20, kde=True)\n",
    "plt.title('Distribution of SD sentiment')\n",
    "plt.xlabel('SD sentiment')\n",
    "plt.ylabel('Count')\n",
    "plt.grid()\n",
    "plt.tick_params(axis='both', direction='in',top=True, right=True)\n",
    "\n",
    "plt.suptitle(f'Distribution of user metrics {casename} case', fontsize=16)\n",
    "plt.tight_layout(rect=[0, 0, 1, 0.99])\n",
    "\n",
    "plt.savefig(f'../datasets/{case}-user-metrics.png')\n",
    "plt.show()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Plot interaction count against mean sentiment, SD sentiment and post count."
   ]
  },
  {
   "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",
    "\n",
    "# Define the pairs of variables for the subplots\n",
    "variables = [\n",
    "    (\"nn-count\", \"mean-sentiment\"),\n",
    "    (\"dtc-count\", \"mean-sentiment\"),\n",
    "    (\"tc-count\", \"mean-sentiment\"),\n",
    "    (\"nn-count\", \"std-sentiment\"),\n",
    "    (\"dtc-count\", \"std-sentiment\"),\n",
    "    (\"tc-count\", \"std-sentiment\"),\n",
    "    (\"nn-count\", \"post-count\"),\n",
    "    (\"dtc-count\", \"post-count\"),\n",
    "    (\"tc-count\", \"post-count\"),\n",
    "]\n",
    "\n",
    "# Create the figure\n",
    "plt.figure(figsize=(15, 15))\n",
    "\n",
    "# Loop through the variables and create subplots\n",
    "for i, (x_var, y_var) in enumerate(variables):\n",
    "    plt.subplot(3, 3, i + 1)\n",
    "    \n",
    "    # Drop NaN values for the current pair of variables\n",
    "    df_nonan = df_data.dropna(subset=[x_var, y_var])\n",
    "    \n",
    "    # Create scatter plot\n",
    "    sns.scatterplot(x=x_var, y=y_var, data=df_nonan, alpha=0.4, color=\"black\", edgecolor=None)\n",
    "    \n",
    "    # Create Lowess regression plot\n",
    "    sns.regplot(x=x_var, y=y_var, data=df_nonan, scatter=False, lowess=True, line_kws={'color': 'blue', 'linewidth': 2}, label=\"Lowess fit\")\n",
    "    \n",
    "    # Set logarithmic scale for x-axis\n",
    "    plt.xscale(\"log\")\n",
    "    \n",
    "    # Set labels and grid\n",
    "    plt.xlabel(x_var.replace('-', ' '))\n",
    "    plt.ylabel(y_var.replace('-', ' '))\n",
    "    plt.grid()\n",
    "    plt.legend()\n",
    "    plt.tick_params(axis='both', direction='in', top=True, right=True)\n",
    "\n",
    "# Set the overall title and layout\n",
    "plt.suptitle(f'Scatter plot of user metrics against interaction count {casename} case', fontsize=16)\n",
    "plt.tight_layout(rect=[0, 0, 1, 0.99])\n",
    "\n",
    "# Save the figure\n",
    "plt.savefig(f'../datasets/{case}-user-interaction-scatter.png')\n",
    "plt.show()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Plot (simplified) interaction count against mean sentiment, SD sentiment and post count. "
   ]
  },
  {
   "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",
    "from scipy import stats\n",
    "\n",
    "# Assuming df_data is your DataFrame and casename and case are defined\n",
    "plt.figure(figsize=(15, 15))\n",
    "\n",
    "# Define the pairs of variables for the subplots\n",
    "variables = [\n",
    "    (\"nn-count\", \"mean-sentiment\"),\n",
    "    (\"dtc-count\", \"mean-sentiment\"),\n",
    "    (\"tc-count\", \"mean-sentiment\"),\n",
    "    (\"nn-count\", \"std-sentiment\"),\n",
    "    (\"dtc-count\", \"std-sentiment\"),\n",
    "    (\"tc-count\", \"std-sentiment\"),\n",
    "    (\"nn-count\", \"post-count\"),\n",
    "    (\"dtc-count\", \"post-count\"),\n",
    "    (\"tc-count\", \"post-count\"),\n",
    "]\n",
    "\n",
    "# Loop through the variables and create subplots\n",
    "for i, (x_var, y_var) in enumerate(variables):\n",
    "    plt.subplot(3, 3, i + 1)\n",
    "    \n",
    "    # Drop NaN values for the current pair of variables\n",
    "    df_nonan = df_data.dropna(subset=[x_var, y_var])\n",
    "    \n",
    "    # Create the regression plot\n",
    "    sns.regplot(x=x_var, y=y_var, data=df_nonan, scatter=False, ci=68, line_kws={'color': 'blue', 'linewidth': 2})\n",
    "    \n",
    "    # Fit the regression model and get r and p values\n",
    "    slope, intercept, r_value, p_value, std_err = stats.linregress(df_nonan[x_var], df_nonan[y_var])\n",
    "    \n",
    "    # Add labels and grid\n",
    "    plt.xlabel(x_var.replace('-', ' '))\n",
    "    plt.ylabel(y_var.replace('-', ' '))\n",
    "    plt.grid()\n",
    "    plt.tick_params(axis='both', direction='in', top=True, right=True)\n",
    "    \n",
    "    # Add text annotation for r and p values\n",
    "    plt.text(0.05, 0.95, f'r = {r_value:.4f}\\np = {max(p_value, 0.0001):.4f}', transform=plt.gca().transAxes, fontsize=12, verticalalignment='top', bbox=dict(facecolor='white', alpha=0.5))\n",
    "\n",
    "# Set the overall title and layout\n",
    "plt.suptitle(f'Regression plot of user metrics against interaction count {casename} case', fontsize=16)\n",
    "plt.tight_layout(rect=[0, 0, 1, 0.99])\n",
    "\n",
    "# Save the figure\n",
    "plt.savefig(f'../datasets/{case}-user-interaction-regression.png')\n",
    "plt.show()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Take out change in sentiment regressions."
   ]
  },
  {
   "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",
    "from scipy import stats\n",
    "\n",
    "# Assuming df_data is your DataFrame and casename and case are defined\n",
    "fig, axes = plt.subplots(1, 3, figsize=(15, 6), sharey=True)\n",
    "\n",
    "# Define the variables for std-sentiment plots\n",
    "variables = [\n",
    "    (\"nn-count\", \"std-sentiment\"),\n",
    "    (\"dtc-count\", \"std-sentiment\"),\n",
    "    (\"tc-count\", \"std-sentiment\"),\n",
    "]\n",
    "\n",
    "# Loop through the variables and create subplots\n",
    "for i, (ax, (x_var, y_var)) in enumerate(zip(axes, variables)):\n",
    "    # Drop NaN values for the current pair of variables\n",
    "    df_nonan = df_data.dropna(subset=[x_var, y_var])\n",
    "    \n",
    "    # Create the regression plot\n",
    "    sns.regplot(x=x_var, y=y_var, data=df_nonan, scatter=False, ci=68, line_kws={'color': 'blue', 'linewidth': 2}, ax=ax)\n",
    "    \n",
    "    # Fit the regression model and get r and p values\n",
    "    slope, intercept, r_value, p_value, std_err = stats.linregress(df_nonan[x_var], df_nonan[y_var])\n",
    "    \n",
    "    # Add labels and grid\n",
    "    ax.set_xlabel(x_var.replace('-', ' '))\n",
    "    if i == 0:\n",
    "        ax.set_ylabel(y_var.replace('-', ' '))\n",
    "    else:\n",
    "        ax.set_ylabel('')\n",
    "    ax.grid()\n",
    "    ax.tick_params(axis='both', direction='in', top=True, right=True)\n",
    "    \n",
    "    # Add text annotation for r and p values\n",
    "    ax.text(0.05, 0.95, f'r = {r_value:.4f}\\np = {max(p_value, 0.0001):.4f}', transform=ax.transAxes, fontsize=12, verticalalignment='top', bbox=dict(facecolor='white', alpha=0.5))\n",
    "\n",
    "# Set the overall title and layout\n",
    "plt.suptitle(f'Regression plot of standard deviation of sentiment against interaction count {casename} case', fontsize=16)\n",
    "plt.tight_layout(rect=[0, 0, 1, 0.95])\n",
    "\n",
    "# Save the figure\n",
    "plt.savefig(f'../datasets/{case}-user-std-sentiment-regression.png')\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "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": "3.14.6"
  },
  "vscode": {
   "interpreter": {
    "hash": "8c75c0fdd1a718867cdcb84b32adcfdbeaad00b3a4e00a59385211aeed084d4c"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}