{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "fd2cb5be",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x800 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Regression Analysis for Age:\n",
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                Friends   R-squared:                       0.039\n",
      "Model:                            OLS   Adj. R-squared:                  0.038\n",
      "Method:                 Least Squares   F-statistic:                     29.27\n",
      "Date:                Sun, 01 Oct 2023   Prob (F-statistic):           8.61e-08\n",
      "Time:                        17:48:08   Log-Likelihood:                -5572.9\n",
      "No. Observations:                 715   AIC:                         1.115e+04\n",
      "Df Residuals:                     713   BIC:                         1.116e+04\n",
      "Df Model:                           1                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const       1112.7647     80.137     13.886      0.000     955.431    1270.098\n",
      "Age          -17.0816      3.157     -5.410      0.000     -23.280     -10.883\n",
      "==============================================================================\n",
      "Omnibus:                      511.614   Durbin-Watson:                   1.641\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):             8730.929\n",
      "Skew:                           3.036   Prob(JB):                         0.00\n",
      "Kurtosis:                      19.006   Cond. No.                         92.6\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
      "\n",
      "\n",
      "Regression Analysis for Photos:\n",
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                Friends   R-squared:                       0.060\n",
      "Model:                            OLS   Adj. R-squared:                  0.059\n",
      "Method:                 Least Squares   F-statistic:                     45.79\n",
      "Date:                Sun, 01 Oct 2023   Prob (F-statistic):           2.75e-11\n",
      "Time:                        17:48:08   Log-Likelihood:                -5565.0\n",
      "No. Observations:                 715   AIC:                         1.113e+04\n",
      "Df Residuals:                     713   BIC:                         1.114e+04\n",
      "Df Model:                           1                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const        611.5835     25.063     24.402      0.000     562.378     660.789\n",
      "Photos         0.1164      0.017      6.766      0.000       0.083       0.150\n",
      "==============================================================================\n",
      "Omnibus:                      528.533   Durbin-Watson:                   1.639\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):            10056.607\n",
      "Skew:                           3.139   Prob(JB):                         0.00\n",
      "Kurtosis:                      20.267   Cond. No.                     1.68e+03\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
      "[2] The condition number is large, 1.68e+03. This might indicate that there are\n",
      "strong multicollinearity or other numerical problems.\n",
      "\n",
      "\n",
      "Regression Analysis for # of Tags:\n",
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                Friends   R-squared:                       0.057\n",
      "Model:                            OLS   Adj. R-squared:                  0.055\n",
      "Method:                 Least Squares   F-statistic:                     42.87\n",
      "Date:                Sun, 01 Oct 2023   Prob (F-statistic):           1.12e-10\n",
      "Time:                        17:48:08   Log-Likelihood:                -5566.4\n",
      "No. Observations:                 715   AIC:                         1.114e+04\n",
      "Df Residuals:                     713   BIC:                         1.115e+04\n",
      "Df Model:                           1                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const        605.1193     25.825     23.432      0.000     554.418     655.821\n",
      "# of Tags      0.1981      0.030      6.547      0.000       0.139       0.257\n",
      "==============================================================================\n",
      "Omnibus:                      519.930   Durbin-Watson:                   1.636\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):             9709.290\n",
      "Skew:                           3.071   Prob(JB):                         0.00\n",
      "Kurtosis:                      19.976   Cond. No.                     1.01e+03\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
      "[2] The condition number is large, 1.01e+03. This might indicate that there are\n",
      "strong multicollinearity or other numerical problems.\n",
      "\n",
      "\n",
      "Regression Analysis for Albums:\n",
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                Friends   R-squared:                       0.052\n",
      "Model:                            OLS   Adj. R-squared:                  0.051\n",
      "Method:                 Least Squares   F-statistic:                     39.25\n",
      "Date:                Sun, 01 Oct 2023   Prob (F-statistic):           6.45e-10\n",
      "Time:                        17:48:08   Log-Likelihood:                -5568.1\n",
      "No. Observations:                 715   AIC:                         1.114e+04\n",
      "Df Residuals:                     713   BIC:                         1.115e+04\n",
      "Df Model:                           1                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const        580.5135     28.567     20.321      0.000     524.428     636.599\n",
      "Albums         6.0857      0.971      6.265      0.000       4.179       7.993\n",
      "==============================================================================\n",
      "Omnibus:                      525.737   Durbin-Watson:                   1.672\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):             9573.127\n",
      "Skew:                           3.134   Prob(JB):                         0.00\n",
      "Kurtosis:                      19.795   Cond. No.                         38.5\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
      "\n",
      "\n",
      "Regression Analysis for Posts:\n",
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                Friends   R-squared:                       0.002\n",
      "Model:                            OLS   Adj. R-squared:                  0.001\n",
      "Method:                 Least Squares   F-statistic:                     1.723\n",
      "Date:                Sun, 01 Oct 2023   Prob (F-statistic):              0.190\n",
      "Time:                        17:48:08   Log-Likelihood:                -5586.4\n",
      "No. Observations:                 715   AIC:                         1.118e+04\n",
      "Df Residuals:                     713   BIC:                         1.119e+04\n",
      "Df Model:                           1                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const        683.6227     24.270     28.168      0.000     635.974     731.272\n",
      "Posts          0.3255      0.248      1.313      0.190      -0.161       0.812\n",
      "==============================================================================\n",
      "Omnibus:                      494.645   Durbin-Watson:                   1.621\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):             7580.646\n",
      "Skew:                           2.935   Prob(JB):                         0.00\n",
      "Kurtosis:                      17.832   Cond. No.                         106.\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
      "\n",
      "\n",
      "Regression Analysis for Replies:\n",
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                Friends   R-squared:                       0.001\n",
      "Model:                            OLS   Adj. R-squared:                 -0.000\n",
      "Method:                 Least Squares   F-statistic:                    0.6610\n",
      "Date:                Sun, 01 Oct 2023   Prob (F-statistic):              0.416\n",
      "Time:                        17:48:08   Log-Likelihood:                -5587.0\n",
      "No. Observations:                 715   AIC:                         1.118e+04\n",
      "Df Residuals:                     713   BIC:                         1.119e+04\n",
      "Df Model:                           1                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const        688.2570     24.295     28.329      0.000     640.559     735.955\n",
      "Replies        0.2182      0.268      0.813      0.416      -0.309       0.745\n",
      "==============================================================================\n",
      "Omnibus:                      494.853   Durbin-Watson:                   1.620\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):             7609.023\n",
      "Skew:                           2.935   Prob(JB):                         0.00\n",
      "Kurtosis:                      17.864   Cond. No.                         98.1\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
      "\n",
      "\n",
      "Regression Analysis for Children:\n",
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                Friends   R-squared:                       0.027\n",
      "Model:                            OLS   Adj. R-squared:                  0.025\n",
      "Method:                 Least Squares   F-statistic:                     19.62\n",
      "Date:                Sun, 01 Oct 2023   Prob (F-statistic):           1.09e-05\n",
      "Time:                        17:48:08   Log-Likelihood:                -5577.6\n",
      "No. Observations:                 715   AIC:                         1.116e+04\n",
      "Df Residuals:                     713   BIC:                         1.117e+04\n",
      "Df Model:                           1                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const        727.6564     23.270     31.271      0.000     681.971     773.341\n",
      "Children    -150.5914     33.995     -4.430      0.000    -217.334     -83.849\n",
      "==============================================================================\n",
      "Omnibus:                      500.357   Durbin-Watson:                   1.648\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):             7956.183\n",
      "Skew:                           2.969   Prob(JB):                         0.00\n",
      "Kurtosis:                      18.225   Cond. No.                         1.65\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
      "\n",
      "\n",
      "Regression Analysis for Likes:\n",
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                Friends   R-squared:                       0.054\n",
      "Model:                            OLS   Adj. R-squared:                  0.052\n",
      "Method:                 Least Squares   F-statistic:                     40.56\n",
      "Date:                Sun, 01 Oct 2023   Prob (F-statistic):           3.42e-10\n",
      "Time:                        17:48:08   Log-Likelihood:                -5567.5\n",
      "No. Observations:                 715   AIC:                         1.114e+04\n",
      "Df Residuals:                     713   BIC:                         1.115e+04\n",
      "Df Model:                           1                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const        618.8046     24.954     24.798      0.000     569.813     667.796\n",
      "Likes          0.5321      0.084      6.369      0.000       0.368       0.696\n",
      "==============================================================================\n",
      "Omnibus:                      456.035   Durbin-Watson:                   1.635\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):             5831.785\n",
      "Skew:                           2.685   Prob(JB):                         0.00\n",
      "Kurtosis:                      15.920   Cond. No.                         342.\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
      "\n",
      "\n",
      "Regression Analysis for Edu:\n",
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                Friends   R-squared:                       0.002\n",
      "Model:                            OLS   Adj. R-squared:                  0.000\n",
      "Method:                 Least Squares   F-statistic:                     1.351\n",
      "Date:                Sun, 01 Oct 2023   Prob (F-statistic):              0.246\n",
      "Time:                        17:48:08   Log-Likelihood:                -5586.6\n",
      "No. Observations:                 715   AIC:                         1.118e+04\n",
      "Df Residuals:                     713   BIC:                         1.119e+04\n",
      "Df Model:                           1                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const        711.5821     26.184     27.176      0.000     660.175     762.989\n",
      "Edu          -58.8805     50.661     -1.162      0.246    -158.343      40.582\n",
      "==============================================================================\n",
      "Omnibus:                      497.249   Durbin-Watson:                   1.628\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):             7766.707\n",
      "Skew:                           2.949   Prob(JB):                         0.00\n",
      "Kurtosis:                      18.030   Cond. No.                         2.46\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
      "\n",
      "\n",
      "Regression Analysis for Events:\n",
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                Friends   R-squared:                       0.004\n",
      "Model:                            OLS   Adj. R-squared:                  0.003\n",
      "Method:                 Least Squares   F-statistic:                     3.057\n",
      "Date:                Sun, 01 Oct 2023   Prob (F-statistic):             0.0808\n",
      "Time:                        17:48:08   Log-Likelihood:                -5585.8\n",
      "No. Observations:                 715   AIC:                         1.118e+04\n",
      "Df Residuals:                     713   BIC:                         1.118e+04\n",
      "Df Model:                           1                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const        681.4055     23.865     28.552      0.000     634.551     728.260\n",
      "Events         1.6319      0.933      1.748      0.081      -0.201       3.465\n",
      "==============================================================================\n",
      "Omnibus:                      491.715   Durbin-Watson:                   1.621\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):             7522.138\n",
      "Skew:                           2.910   Prob(JB):                         0.00\n",
      "Kurtosis:                      17.785   Cond. No.                         27.3\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
      "\n",
      "\n",
      "Regression Analysis for Friends:\n",
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                Friends   R-squared:                       1.000\n",
      "Model:                            OLS   Adj. R-squared:                  1.000\n",
      "Method:                 Least Squares   F-statistic:                 2.299e+33\n",
      "Date:                Sun, 01 Oct 2023   Prob (F-statistic):               0.00\n",
      "Time:                        17:48:08   Log-Likelihood:                 19526.\n",
      "No. Observations:                 715   AIC:                        -3.905e+04\n",
      "Df Residuals:                     713   BIC:                        -3.904e+04\n",
      "Df Model:                           1                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const      -2.132e-14   1.92e-14     -1.113      0.266   -5.89e-14    1.63e-14\n",
      "Friends        1.0000   2.09e-17   4.79e+16      0.000       1.000       1.000\n",
      "==============================================================================\n",
      "Omnibus:                      522.883   Durbin-Watson:                   0.689\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):             9335.266\n",
      "Skew:                           3.117   Prob(JB):                         0.00\n",
      "Kurtosis:                      19.568   Cond. No.                     1.41e+03\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
      "[2] The condition number is large, 1.41e+03. This might indicate that there are\n",
      "strong multicollinearity or other numerical problems.\n",
      "\n",
      "\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import statsmodels.api as sm\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Create a DataFrame from the provided Excel file\n",
    "df = pd.read_excel(\"Facebook Friends.xlsx\")\n",
    "\n",
    "# Create a subset DataFrame with non-binary numerical variables\n",
    "subset_df = df[['Age', 'Photos', '# of Tags', 'Albums', 'Posts', 'Replies', 'Children', 'Likes', 'Edu', 'Events', 'Friends']]\n",
    "\n",
    "# Calculate the correlation matrix\n",
    "correlation_matrix = subset_df.corr()\n",
    "\n",
    "# Create a heatmap of the correlation matrix\n",
    "plt.figure(figsize=(10, 8))\n",
    "sns.heatmap(correlation_matrix, annot=True, cmap=\"coolwarm\", linewidths=.5)\n",
    "plt.title(\"Correlation Heatmap\")\n",
    "plt.show()\n",
    "\n",
    "# Perform single-variable linear regression analysis for each variable\n",
    "for column in subset_df.columns:\n",
    "    X = sm.add_constant(df[column])\n",
    "    y = df['Friends']  # Friends as the independent variable\n",
    "    model = sm.OLS(y, X).fit()\n",
    "    print(f\"Regression Analysis for {column}:\")\n",
    "    print(model.summary())\n",
    "    print(\"\\n\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "e4b8f090",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                Friends   R-squared:                       0.145\n",
      "Model:                            OLS   Adj. R-squared:                  0.133\n",
      "Method:                 Least Squares   F-statistic:                     11.99\n",
      "Date:                Sun, 01 Oct 2023   Prob (F-statistic):           2.90e-19\n",
      "Time:                        17:51:38   Log-Likelihood:                -5531.1\n",
      "No. Observations:                 715   AIC:                         1.108e+04\n",
      "Df Residuals:                     704   BIC:                         1.113e+04\n",
      "Df Model:                          10                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const        782.3715     94.103      8.314      0.000     597.616     967.127\n",
      "Age           -9.5473      3.719     -2.567      0.010     -16.849      -2.245\n",
      "Photos         0.0559      0.028      2.008      0.045       0.001       0.111\n",
      "# of Tags      0.1037      0.036      2.908      0.004       0.034       0.174\n",
      "Albums         0.8066      1.604      0.503      0.615      -2.343       3.956\n",
      "Posts          1.0858      0.617      1.759      0.079      -0.126       2.298\n",
      "Replies       -1.1618      0.670     -1.735      0.083      -2.476       0.153\n",
      "Children     -51.3321     39.267     -1.307      0.192    -128.426      25.762\n",
      "Likes          0.4073      0.082      4.944      0.000       0.246       0.569\n",
      "Edu          -53.9129     47.731     -1.130      0.259    -147.625      39.799\n",
      "Events         1.0351      0.876      1.182      0.238      -0.684       2.754\n",
      "==============================================================================\n",
      "Omnibus:                      517.634   Durbin-Watson:                   1.687\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):             9446.379\n",
      "Skew:                           3.060   Prob(JB):                         0.00\n",
      "Kurtosis:                      19.722   Cond. No.                     7.31e+03\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
      "[2] The condition number is large, 7.31e+03. This might indicate that there are\n",
      "strong multicollinearity or other numerical problems.\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import statsmodels.api as sm\n",
    "\n",
    "# Create a DataFrame from the provided Excel file\n",
    "df = pd.read_excel(\"Facebook Friends.xlsx\")\n",
    "\n",
    "# Define the dependent variable and independent variables\n",
    "dependent_variable = df['Friends']\n",
    "independent_variables = df[['Age', 'Photos', '# of Tags', 'Albums', 'Posts', 'Replies', 'Children', 'Likes', 'Edu', 'Events']]\n",
    "\n",
    "# Add a constant (intercept) to the independent variables\n",
    "independent_variables = sm.add_constant(independent_variables)\n",
    "\n",
    "# Perform multivariate linear regression\n",
    "model = sm.OLS(dependent_variable, independent_variables).fit()\n",
    "\n",
    "# Print the regression summary\n",
    "print(model.summary())\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "19be0e7d",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a4a273e0",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c6f8ca91",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}