{ "cells": [ { "cell_type": "code", "execution_count": 68, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "donner = pd.read_csv('donner.csv')\n", "\n", "\n" ] }, { "cell_type": "code", "execution_count": 69, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "slope: -0.01335811360204437\n", "intercept: 0.8692324569894554\n", "R: -0.332573571747557\n", "SE(slope): 0.005776575683969789\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "import matplotlib.pyplot as plt\n", "plt.rcParams.update({'font.size': 22})\n", "\n", "plt.scatter(donner.AGE, donner.FEMALE)\n", "\n", "import scipy.stats as stats\n", "\n", "slope, intercept, r_value, p_value, std_err = stats.linregress(donner.AGE, donner.SURVIVED)\n", "\n", "print('slope:', slope)\n", "print('intercept:', intercept)\n", "print('R:', r_value)\n", "print('SE(slope):', std_err)\n", "\n", "yhat = [slope*x+intercept for x in donner.AGE]\n", "\n", "plt.plot(donner.AGE, yhat)\n", "plt.xlabel('Age')\n", "plt.ylabel('Survived')\n", "#plt.show()\n", "plt.savefig('C:/Users/sofia/Dropbox/Apps/Overleaf/Applied Statistics Course/figures/log_res_age.png') \n" ] }, { "cell_type": "code", "execution_count": 70, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[]" ] }, "execution_count": 70, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# logit, inverse logit function \n", "import numpy as np\n", "\n", "x = np.linspace(0.001, 0.999, 100).tolist()\n", "y = [np.log(p/(1-p)) for p in x]\n", "\n", "\n", "plt.plot(x, y)" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[]" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAD8CAYAAACMwORRAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMS4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvNQv5yAAAH7pJREFUeJzt3Xl8VfWd//HXJ/vCkkAISyAEZBFEQYmo1bqioq3YTcWp/nTqSO3ULtNOp7adtjO2j7bTdqb196id1l+1dasIbqWK1WqttVYwQRBkk8iWEJawJSEhy7338/sjFxtjIBe4ybn35v18PPLIPed+k7yVy5tvzj3nfM3dERGR1JIWdAAREYk/lbuISApSuYuIpCCVu4hIClK5i4ikIJW7iEgKUrmLiKQglbuISApSuYuIpKCMoH5wUVGRl5WVBfXjRUSS0vLly/e4+7CexgVW7mVlZVRWVgb140VEkpKZbY1lnA7LiIikIJW7iEgKUrmLiKQglbuISApSuYuIpKAey93M7jOz3Wb21hGeNzP7v2ZWZWarzOyM+McUEZFjEcvM/TfAnKM8fwUwMfoxH/jfE48lIiInosfz3N39L2ZWdpQhVwMPeMd6fUvNrMDMRrr7jjhlFBGJWSTitIUjtLZHaA2FaQ1FaAtHCEecUNiJuBOKOOFIhFDYO/ZHOn+O/H07+nzEnYiDE/3sjjtEOn0G/j6u877Ie78Wdy6ZMpzpYwp69f9DPC5iKgGqO23XRPe9r9zNbD4ds3tKS0vj8KNFJNlFIk79oXb2Nbexv6mNfU1tNLSEONjSTlNbmIOtIZpaQxxsCXU8bgtxsDVMa3tHcbe2hzuVeUeRJzIzGD44JynK3brZ1+2q2+5+D3APQHl5uVbmFklh7k7dwVZ2HGhhR30LO+sPsaM++rihhX3RIj/Q3NYxoz2CzHQjPzuD/KwMBmRnkJ+dzqCcDHIHZpOdmU52Rlr0I53szL8/znp3fxqZ6WlkpBsZaUZ6Wlr0s/39c/oR9qelkZYG6WmGYaQZmBlmkGaG0fEZg7TD+6KfiT53+GsOf+4r8Sj3GmBMp+3RQG0cvq+IJIG2UIS3dzVStfsgm/Y0sXlPE5v3HGRzXRNNbeH3jM1KT2PE4BxGDM5h0vABDMnPYkheFoX5WQzJz6Iwr+NjcG4m+dnpDMjJIDsjPaD/suQWj3JfDNxuZguAs4B6HW8XSU3hiLNuRwMrtu1nTW0Db9XWs2FnI+3hjql3msHowjzGFeVTPnYIZUPzKCnMY+TgHEYOzmFIflafzl77sx7L3cweAS4EisysBvg2kAng7r8AlgBXAlVAM/CPvRVWRPpWJOKs2l7Pa+/s5fXNe6ncsp/G1hAAhXmZTCsZzKfOG8e0UYOZPGIgY4fmaaadIGI5W+b6Hp534LNxSyQigWpqDfHKxj28uG4XL23YzZ6DbQBMKB7A3BmjmDVuCDPHFlJSkKtZeAIL7Ja/IpI42sMR/rpxD0+u2M7za3fS0h5hYE4GF04uZvaUYs6dUETRgOygY8oxULmL9GPV+5p5aOlWHltew96mNgryMvnEzNF86NRRlJcVkpmuO5QkK5W7SD+0bNNe7v3rZl5YtwszY/aUYj5+xmgunFxMVoYKPRWo3EX6kdfe2ctPX3ibZZv3UZiXyW0XnMQNZ49lVEFu0NEkzlTuIv3A6pp6vvvMWpZt3kfxwGy+fdVUrp9VSk6mzmxJVSp3kRRW19jKj55bz6LlNQzNz1Kp9yMqd5EU5O488no131+yjpZQmFs/OJ7bL57AoJzMoKNJH1G5i6SY7QcOccfjq3hl4x4+cNJQvvuRaYwfNiDoWNLHVO4iKWTxm7V8/YnVRNz5zkem8clZpaSl6UKj/kjlLpICWkNhvvfMOu5/bStnlBZw17zTGTMkL+hYEiCVu0iS21F/iNseeoM3qw/wT+eN46tXnKyLj0TlLpLM1tTW86nfVNDUGuYXN5zBnGkjg44kCULlLpKkXn67jn9+aDkDczJZdNs5TBk5KOhIkkBU7iJJ6OlVtXxhwUomDR/Ir28+kxGDc4KOJAlG5S6SZJ5cUcOXF77JzLGF3HfzmQzUuevSDZW7SBJZVFnNvz2+irPHDeXem8vJy9JfYemeXhkiSeLZ1Tv46uOrOG9CEffcWE5ulm4hIEem86VEksDfqvbwhQUrOb20UMUuMVG5iyS41TX13PpAJeOK8rnvpjNV7BITlbtIAtvV0MI/PVBBQV4W939qFoPz9OapxEbH3EUSVEt7mPkPLqexJcTjn/mATneUY6JyF0lA7s4dj6/izeoD/PLGmbpASY6ZDsuIJKBfv7qFp1bW8q+XTeLyU0YEHUeSkMpdJMGsqjnA959dx+wpxXz2oglBx5EkpXIXSSANLe3c/tsVDBuQzY+vmY6Z7sUux0fH3EUShLvztSdWs/3AIRZ++mwK8rKCjiRJTDN3kQTx1MrtPLNqB1+6dBIzxw4JOo4kOZW7SALYWd/Ct3+3hpljC7ntgpOCjiMpQOUuErCOwzGraAtH+PE100nXmqcSByp3kYAtqqzhpQ11fHXOyYwryg86jqSImMrdzOaY2QYzqzKzO7p5vtTMXjKzFWa2ysyujH9UkdRT19jKd55Zy6xxQ7jpnLKg40gK6bHczSwduBu4ApgKXG9mU7sM+3dgobufDswDfh7voCKp6PtL1tHSHuZ7Hz2VNB2OkTiKZeY+C6hy903u3gYsAK7uMsaBw9dHDwZq4xdRJDW99s5enlixnU+ffxITigcEHUdSTCznuZcA1Z22a4Czuoz5D+B5M/sckA/Mjks6kRTVForwzd+9xZghudx+sa5ClfiLZebe3e+K3mX7euA37j4auBJ40Mze973NbL6ZVZpZZV1d3bGnFUkR/++VTVTtPsidc6eRk6n7s0v8xVLuNcCYTtujef9hl1uAhQDu/hqQAxR1/Ubufo+7l7t7+bBhw44vsUiS29XQws/+VMXlpwznopOLg44jKSqWcq8AJprZODPLouMN08VdxmwDLgEwsyl0lLum5iLd+O/nNxCKRPj6lVOCjiIprMdyd/cQcDvwHLCOjrNi1pjZnWY2Nzrsy8CtZvYm8Ahws7t3PXQj0u+t29HAouU13HROGWOH6px26T0x3TjM3ZcAS7rs+1anx2uBc+MbTSS1uDvfW7KOQTmZfO7iiUHHkRSnK1RF+sif367jlY17+PwlE7UWqvQ6lbtIHwhHnB8sWU/Z0DxuPHts0HGkH1C5i/SBp1fVsmFXI1++bDJZGfprJ71PrzKRXhYKR/jpCxs5ecRAPnTqyKDjSD+hchfpZU+u2M7mPU38y6WTdP8Y6TMqd5Fe1BaKcNeLGzm1ZDCXTR0edBzpR1TuIr1o0fJqavYf4kuXTtJi19KnVO4ivaQtFOHuP1VxemkBF07W7Takb6ncRXrJUyu2U1vfwhcumahZu/Q5lbtILwhHnP99+R1OGTWICyZp1i59T+Uu0gv+8NZONu9p4p8vnKBZuwRC5S4SZ+7Oz/9cxfiifOZMGxF0HOmnVO4icfaXjXtYU9vAbRecRLrOa5eAqNxF4uznL1UxcnAOHzm9JOgo0o+p3EXiaPnW/SzbvI9bPzhe95CRQOnVJxJH9/11M4NyMrjuzDE9DxbpRSp3kTip2d/Ms2/t4PqzSsnPjmkdHJFeo3IXiZP7/7YFM+Omc8qCjiKicheJh4OtIRa8Xs2Vp45kVEFu0HFEVO4i8bCosprG1hC3nDcu6CgigMpd5ISFI86vX93CGaUFzBhTEHQcEUDlLnLCXly3i237mrnlvPFBRxF5l8pd5ATd+9fNlBTkcvkpWoxDEofKXeQErN/ZwLLN+/g/54wlI11/nSRx6NUocgIeWrqVrIw0ri3XRUuSWFTuIsfpYGuIJ9/YzlWnjaIwPyvoOCLvoXIXOU5PrthOU1uYG88ZG3QUkfdRuYscB3fnode2Mq1kENNHDw46jsj7qNxFjkPFlv1s2NXIjWeP1UpLkpBU7iLH4cGlWxmYk8Hc6bpnuyQmlbvIMdrd2MIf3trBNTPHkJuVHnQckW7FVO5mNsfMNphZlZndcYQx15rZWjNbY2a/jW9MkcSxsKKa9rDzybNLg44ickQ93nTazNKBu4FLgRqgwswWu/vaTmMmAl8DznX3/WZW3FuBRYIUCkf47bJtnDehiJOGDQg6jsgRxTJznwVUufsmd28DFgBXdxlzK3C3u+8HcPfd8Y0pkhhefruO2voWbtCsXRJcLOVeAlR32q6J7utsEjDJzF41s6VmNqe7b2Rm882s0swq6+rqji+xSIAWVFRTNCCbS6boPjKS2GIp9+7O8/Iu2xnAROBC4HrgV2b2vnufuvs97l7u7uXDhg071qwigdrd0MKf1u/m4zNLyNR9ZCTBxfIKrQE63zhjNFDbzZjfuXu7u28GNtBR9iIp47E3aghHnOt0HxlJArGUewUw0czGmVkWMA9Y3GXMU8BFAGZWRMdhmk3xDCoSJHfn0YpqZo0bwni9kSpJoMdyd/cQcDvwHLAOWOjua8zsTjObGx32HLDXzNYCLwFfcfe9vRVapK8t3bSPrXubmXemZu2SHHo8FRLA3ZcAS7rs+1anxw58KfohknIerdjGwJwMrpg2MugoIjHRu0IiPahvbmfJWzv5yIwSXZEqSUPlLtKDp1Zupy0U4TodkpEkonIXOQp3Z0FFNdNKBjGtRLf2leShchc5ire2N7BuRwPXnakrUiW5qNxFjmJBxTayM9KYO31U0FFEjonKXeQImttCLF5Zy4dOHcng3Myg44gcE5W7yBEsWb2TxtaQ3kiVpKRyFzmCRyu2Ma4on1njhgQdReSYqdxFulG1+yAVW/Zz3ZljtEaqJCWVu0g3FlZWk5FmfOwMrZEqyUnlLtJFWyjC48truGRKMcUDc4KOI3JcVO4iXby4bhd7m9qYp3PbJYmp3EW6eLSymhGDcjh/khaUkeSlchfppPbAIV5+u45ry0eTnqY3UiV5qdxFOllUWYM7XKPVliTJqdxFoiIRZ2FlNedNKGLMkLyg44icEJW7SNSr7+xh+4FDXKsrUiUFqNxFohZUVFOQl8llU4cHHUXkhKncRYB9TW38cc0uPjKjhJxMrbYkyU/lLgI8uWI7bWGttiSpQ+Uu/Z67s7CimuljCpgyclDQcUTiQuUu/d7K6gNs2NXIdTr9UVKIyl36vYWV1eRmpnPV9JFBRxGJG5W79GtNrdHVlk4bycAcrbYkqUPlLv3aM6t30NQWZp7eSJUUo3KXfu3RimrGD8tn5tjCoKOIxJXKXfqtqt2NLN+6n3labUlSkMpd+q1HKw6vtjQ66Cgicadyl36pLRThiTe2M3vKcIoGZAcdRyTuVO7SLx1ebUlXpEqqiqnczWyOmW0wsyozu+Mo4z5hZm5m5fGLKBJ/Wm1JUl2P5W5m6cDdwBXAVOB6M5vazbiBwOeBZfEOKRJP1fuatdqSpLxYZu6zgCp33+TubcAC4Opuxn0H+CHQEsd8InG3oGIbBsybpQWwJXXFUu4lQHWn7ZrovneZ2enAGHd/Oo7ZROKuPRzh0YoaLj65mFEFuUHHEek1sZR7d7+3+rtPmqUBPwG+3OM3MptvZpVmVllXVxd7SpE4+ePaXew52MonzxobdBSRXhVLudcAnU8pGA3UdtoeCEwD/mxmW4CzgcXdvanq7ve4e7m7lw8bpjeypO89vGwrJQW5eiNVUl4s5V4BTDSzcWaWBcwDFh9+0t3r3b3I3cvcvQxYCsx198peSSxynDbvaeLVqr38w1mleiNVUl6P5e7uIeB24DlgHbDQ3deY2Z1mNre3A4rEyyOvbyMjzbimXFekSurLiGWQuy8BlnTZ960jjL3wxGOJxFdLe5hFldVcdspwigfmBB1HpNfpClXpF/7w1k72N7frjVTpN1Tu0i88vGwr44ryOWf80KCjiPQJlbukvPU7G6jYsp/rZ40hTW+kSj+hcpeUd//ftpCTmca1WgBb+hGVu6S0/U1tPLliOx89fTQFeVlBxxHpMyp3SWmPVlbT0h7h5g+UBR1FpE+p3CVlhcIRHnxtK+eMH8rkEQODjiPSp1TukrJeWLeL7QcOcfO5ZUFHEelzKndJWb9+dQslBbnMnjI86CgifU7lLilpbW0Dyzbv46YPjNV9ZKRfUrlLSrr/b1vIzUznunItyCH9k8pdUs7uxhaeXLGdj51RwuC8zKDjiARC5S4p5/6/baE9EuGfPjg+6CgigVG5S0o52Briwde2MueUEYwryg86jkhgVO6SUh6tqKahJcT88zVrl/5N5S4poz0c4d5XNjGrbAinlxYGHUckUCp3SRnPrNpBbX0Ln75As3YRlbukBHfnl3/ZxITiAVw0uTjoOCKBU7lLSvjzhjrW7Whg/vnjdc92EVTukgLcnbte3EhJQS4fPb0k6DgiCUHlLknvlY17WFl9gM9eNIHMdL2kRUDlLknu8Kx91OAcPj5Ts3aRw1TuktT+9s5elm/dz2cuPInsjPSg44gkDJW7JLW7XtzI8EHZXKP1UUXeQ+UuSevVqj28vnkft11wEjmZmrWLdKZyl6Tk7vzXH9ZTUpDL9bN0W1+RrlTukpSWrN7Jqpp6vjh7ombtIt1QuUvSaQ9H+PHzG5g0fAAfO2N00HFEEpLKXZLOosoaNu9p4iuXn6wl9ESOQOUuSeVQW5i7XnybmWMLmT1F95ARORKVuySVX7z8DrsaWrnjipMx06xd5EhiKnczm2NmG8ysyszu6Ob5L5nZWjNbZWYvmtnY+EeV/q5mfzO/ePkdPnzaSM4sGxJ0HJGE1mO5m1k6cDdwBTAVuN7MpnYZtgIod/fTgMeAH8Y7qMj3n12PGXztyilBRxFJeLHM3GcBVe6+yd3bgAXA1Z0HuPtL7t4c3VwK6BQGiaulm/byzKod3HbBSZQU5AYdRyThxVLuJUB1p+2a6L4juQV4trsnzGy+mVWaWWVdXV3sKaVfC4Uj/Ofv11JSkMunzz8p6DgiSSGWcu/uXSvvdqDZDUA58KPunnf3e9y93N3Lhw0bFntK6dfu/etm1u1o4JsfnkJuli5YEolFRgxjaoDOd2UaDdR2HWRms4FvABe4e2t84kl/t21vMz954W0unTqcy08ZEXQckaQRy8y9AphoZuPMLAuYByzuPMDMTgd+Ccx1993xjyn9kbvzjadWk5GWxp1Xn6JTH0WOQY/l7u4h4HbgOWAdsNDd15jZnWY2NzrsR8AAYJGZrTSzxUf4diIxe2rldl7ZuId/mzOZkYP1JqrIsYjlsAzuvgRY0mXftzo9nh3nXNLP7axv4du/W8MZpQV88ixdNiFyrHSFqiScSMT5ymNv0h52/vvaGbp/jMhxULlLwnngtS28snEP//7hKYwryg86jkhSUrlLQtm4q5HvP7uei08u5h+0CIfIcVO5S8Joag3xmYffYEB2Bj/4+Kk6O0bkBMT0hqpIb3N3vv7kajbVHeTBW86ieGBO0JFEkppm7pIQHlq6ld+trOVLl07i3AlFQccRSXoqdwlcxZZ93Pn0Wi4+uZh/vnBC0HFEUoLKXQK1dW8T8x+oZExhHv9z7XTSdNqjSFyo3CUw9c3t/ONvKnDgvpvPpCAvK+hIIilD5S6BaGkP8+mHKqne18w9N5ZTpvPZReJKZ8tIn2sPR/jsw2+wbPM+fnrdDGaN05J5IvGmmbv0qXDE+eKjK3lx/W6++5FpXD3jaOu+iMjx0sxd+kwoHOErj63imVU7+MaVU3RDMJFepHKXPtHSHubzj6zg+bW7+Mrlk7n1/PFBRxJJaSp36XVNrSHmP1jJq1V7+c+5p3DTB8qCjiSS8lTu0qu2HzjELb+p4O1djfz4mul8YubooCOJ9Asqd+k1y7fu59MPVtLaHuG+m8/kwsnFQUcS6TdU7hJ37s6DS7fy3afXMbIghwXzy5lQPDDoWCL9ispd4qr+UDtffWwVf1izk4smD+N/rp1BYb6uPBXpayp3iZuXNuzmG0+sZndjK//+oSl86txxuleMSEBU7nLC9je18Z2n1/LEiu1MLB7AYzfMZMaYgqBjifRrKnc5bqFwhEde38ZPXthIw6F2Pn/xBD578QSyM9KDjibS76nc5Zi5Oy9t2M33lqynavdBzh4/hG9fdQpTRg4KOpqIRKncJWbuzh/X7uJnL1WxqqaesqF5/PLGmVw2dbjWOxVJMCp36dGhtjC/f7OW+17dzPqdjZQOyeMHHzuVj50xmqwM3XtOJBGp3OWIqnYf5LfLtvHY8moaWkJMGj6An1w3natOG0VGukpdJJGp3OU9avY38/SqHfz+zVrW1DaQmW7MmTaSG84qZda4ITr8IpIkVO79XDjirKw+wJ837ObPG+pYvb0egBljCvjmh6cyd/oohg3MDjiliBwrlXs/0xaK8FZtPcu37Kdy6z6Wbd7HgeZ20gxOLy3kK5dP5qrTRlE6NC/oqCJyAlTuKexQW5gNuxpZv6OB9TsbWVNbz6qaelpDEQBKh+Qxe8pwLpg0jA9OLNIC1SIpJKZyN7M5wF1AOvArd/9Bl+ezgQeAmcBe4Dp33xLfqNKdlvYwNfub2bavma17Oz627Wtm854mtuxtwr1jXH5WOpNHDOSGs8dSPraQmWMLKR6UE2x4Eek1PZa7maUDdwOXAjVAhZktdve1nYbdAux39wlmNg/4L+C63gic6iIRp7ElxIFDbdQfaqf+UDsHmtvZe7CVXY2t7G5oZXdjy7uf9ze3v+fr87PSKR2az8kjBnL1jFGcPGIQU0cOYnRhru7zItKPxDJznwVUufsmADNbAFwNdC73q4H/iD5+DPiZmZn74Xlj4nN33MGBiDuR6HYo4oTCEdrCEUJhpz0coT36ORT26P7ovkiE9lCEUKTj+db2CM1tIZrbw7S0hWluC3f/uD1Ew6EQB5rbaGwNcaT/axlpxrCB2RQPyqF0aB7lZYUMH5TDmCG5lA7JZ+zQPIbmZ+mMFhGJqdxLgOpO2zXAWUca4+4hM6sHhgJ74hGys4UV1dzzyqZ3y/dwEUciHQUdeXff4e2/73vPeH/v+N7+Z8gMcjPTOz6y0snL+vvj4oE5nDQsg4LcTAbnZjIoN5OCvCwGR7cH52YydEAWQ/KyNPsWkZjEUu7dtUnXKoxlDGY2H5gPUFpaGsOPfr/C/CwmDx+IGaSZkRb9bJ0ep6Xx3m2zo483oMu2Rb8uPQ0y09PISE8jK93ISEsjMyONzDSL7jeyos9npnfsO7w/OyONvKwMcjPTyclM04xaRPpMLOVeA4zptD0aqD3CmBozywAGA/u6fiN3vwe4B6C8vPy45sqXTh3OpVOHH8+Xioj0G7FcQ14BTDSzcWaWBcwDFncZsxi4Kfr4E8Cfkul4u4hIqulx5h49hn478Bwdp0Le5+5rzOxOoNLdFwP3Ag+aWRUdM/Z5vRlaRESOLqbz3N19CbCky75vdXrcAlwT32giInK8dGs/EZEUpHIXEUlBKncRkRSkchcRSUEqdxGRFGRBnY5uZnXA1uP88iJ64dYGcaBcx0a5jl2iZlOuY3Miuca6+7CeBgVW7ifCzCrdvTzoHF0p17FRrmOXqNmU69j0RS4dlhERSUEqdxGRFJSs5X5P0AGOQLmOjXIdu0TNplzHptdzJeUxdxERObpknbmLiMhRJG25m9kMM1tqZivNrNLMZgWd6TAz+5yZbTCzNWb2w6DzdGZm/2pmbmZFQWcBMLMfmdl6M1tlZk+aWUHAeeZE/+yqzOyOILMcZmZjzOwlM1sXfU19IehMnZlZupmtMLOng85ymJkVmNlj0dfWOjM7J+hMAGb2L9E/w7fM7BEz67VV6pO23IEfAv/p7jOAb0W3A2dmF9Gxpuxp7n4K8OOAI73LzMbQsdD5tqCzdPJHYJq7nwa8DXwtqCCdFoO/ApgKXG9mU4PK00kI+LK7TwHOBj6bILkO+wKwLugQXdwF/MHdTwamkwD5zKwE+DxQ7u7T6LiFeq/dHj2Zy92BQdHHg3n/6lBB+QzwA3dvBXD33QHn6ewnwL/RzRKIQXH35909FN1cSsdKX0F5dzF4d28DDi8GHyh33+Hub0QfN9JRVCXBpupgZqOBDwG/CjrLYWY2CDifjnUmcPc2dz8QbKp3ZQC50RXr8ujF3krmcv8i8CMzq6ZjdhzYjK+LScAHzWyZmb1sZmcGHQjAzOYC2939zaCzHMWngGcD/PndLQafECV6mJmVAacDy4JN8q6f0jFhiAQdpJPxQB3w6+jhol+ZWX7Qodx9Ox1dtQ3YAdS7+/O99fNiWqwjKGb2AjCim6e+AVwC/Iu7P25m19Lxr/TsBMiVARTS8evzmcBCMxvfF8sO9pDr68BlvZ2hO0fL5e6/i475Bh2HHx7uy2xdxLTQe1DMbADwOPBFd29IgDwfBna7+3IzuzDoPJ1kAGcAn3P3ZWZ2F3AH8M0gQ5lZIR2/CY4DDgCLzOwGd3+oN35eQpe7ux+xrM3sATqO9QEsog9/Lewh12eAJ6Jl/rqZRei4j0RdULnM7FQ6XlBvmhl0HPp4w8xmufvOoHJ1yncT8GHgkoDX3o1lMfhAmFkmHcX+sLs/EXSeqHOBuWZ2JZADDDKzh9z9hoBz1QA17n74t5vH6Cj3oM0GNrt7HYCZPQF8AOiVck/mwzK1wAXRxxcDGwPM0tlTdOTBzCYBWQR84yJ3X+3uxe5e5u5ldLz4z+iLYu+Jmc0BvgrMdffmgOPEshh8n7OOf5HvBda5+/8Enecwd/+au4+OvqbmAX9KgGIn+rquNrPJ0V2XAGsDjHTYNuBsM8uL/pleQi++0ZvQM/ce3ArcFX1jogWYH3Cew+4D7jOzt4A24KaAZ6OJ7mdANvDH6G8VS939tiCCHGkx+CCydHEucCOw2sxWRvd9Pbq2sXTvc8DD0X+kNwH/GHAeooeIHgPeoOMQ5Ap68UpVXaEqIpKCkvmwjIiIHIHKXUQkBancRURSkMpdRCQFqdxFRFKQyl1EJAWp3EVEUpDKXUQkBf1/mr+PvACpVBMAAAAASUVORK5CYII=\n", "text/plain": [ "" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "#inverse logit\n", "\n", "x = np.linspace(-8, 8, 1000).tolist()\n", "y = [1/(1+np.exp(-p)) for p in x]\n", "\n", "\n", "plt.plot(x, y)" ] }, { "cell_type": "code", "execution_count": 91, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Optimization terminated successfully.\n", " Current function value: 0.625452\n", " Iterations 6\n", " Results: Logit\n", "==============================================================\n", "Model: Logit No. Iterations: 6.0000 \n", "Dependent Variable: SURVIVED Pseudo R-squared: 0.090 \n", "Date: 2022-05-26 12:47 AIC: 60.2907\n", "No. Observations: 45 BIC: 63.9040\n", "Df Model: 1 Log-Likelihood: -28.145\n", "Df Residuals: 43 LL-Null: -30.913\n", "Converged: 1.0000 Scale: 1.0000 \n", "---------------------------------------------------------------\n", " Coef. Std.Err. z P>|z| [0.025 0.975]\n", "---------------------------------------------------------------\n", "const 1.8185 0.9994 1.8197 0.0688 -0.1402 3.7773\n", "AGE -0.0665 0.0322 -2.0630 0.0391 -0.1296 -0.0033\n", "==============================================================\n", "\n" ] } ], "source": [ "import statsmodels.api as sm\n", "from statsmodels.tools import add_constant\n", "\n", "X = donner.AGE\n", "X= add_constant(X)\n", "Y = donner.SURVIVED\n", "# building the model and fitting the data\n", "log_reg = sm.Logit(Y, X).fit()\n", "\n", "print(log_reg.summary2())\n" ] }, { "cell_type": "code", "execution_count": 92, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[ 0.62072939 -0.04909915]]\n", "[0.62072939]\n" ] } ], "source": [ "from sklearn import linear_model as lr\n", "clf = lr.LogisticRegression().fit(X, Y)\n", "\n", "print(clf.coef_)\n", "print(clf.intercept_)" ] }, { "cell_type": "code", "execution_count": 93, "metadata": {}, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAaIAAAEeCAYAAADIAxFhAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMS4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvNQv5yAAAIABJREFUeJzt3XuYFNWd//H3d2a4TbjIHQQZNCIqxNsMKt4QwRX3pwQVRMSEmKw8gkY3JmLUJ4mbLF5WV2NWNJKNoELUeENdw5osEW/ByxCMiriIioyCLhGUmwjMfH9/VDXM9HTPdPfUUN0zn9fz1FPTp06d/lZXz3ynqk6dMndHREQkLkVxByAiIq2bEpGIiMRKiUhERGKlRCQiIrFSIhIRkVgpEYmISKyUiEREJFZKRCIiEislIhERiVVJ3AEUgh49evjAgQPjDkNEpKAsXbr07+7es7F6SkQZGDhwIJWVlXGHISJSUMzsw0zq6dSciIjESolIRERipUQkIiKxUiISEZFY5U0iMrPBZna5mc0zs3fMrMbM3MzGN7Hd883sBTP7wsy2mFmlmV1iZnmz7SIirVk+9ZqbBlweZYNmNguYDmwHFgE7gVHAHcAoM5vg7tVRvqeIiGQnn44K3gJuBiYCBwLPNaUxMzuHIAl9Ahzm7me4+1nAIGAFcBZwaZMiFhGRJsubIyJ3/8/ar82sqU1eHc6vcvd3a73Pp2Y2DVgM/NjM/sPda5r6ZiIikpt8OiKKjJn1B8qBHcDDycvd/TngY6APcGyzBzR/PgwcCEVFwXz+/L3SzPzpLzKw5COKrIaBJR8xf/qLDTeUpjzbdtLWz9L06VBSAmbBfPr0RrY3289n9D0MtA+DOO1D5o++J6c44xLV5xxZPNF8zaU1cve8nAiOWBwYn8O6Z4br/rWBOo+HdS5prL3y8nLP2bx57qWl7rBnKi0NypuxmXnTXvBSttStzxafN+q3qRuaNi1l+bxRv82qnbT1p72Q1fZOm1a36cQ0bVpEn09D21UA0u7fLD/nyOKJ5msuLQxQ6Zn8zc6kUhxTExPRZeG6jzdQ5/awzi2NtdekRFRWlvovallZszZTVlyVuj6rUzdUXJyyvIzVWbWTtn5xVVbbmyYcLy6O6PNpaLsKQNr9m+XnHFk8ZZF8zaWFyTQRtchTc0DHcL61gTpbwnmnVAvNbGrY1bty/fr1uUeyZk125RE1s6Z639Tl7Jd6herUnQfT1c+6PE086aQJJ2151p9PlvHnm7T7N8vPOSoRfc2llWqpiSjR08FzbcDdZ7t7hbtX9OzZ6OCx6Q0YkF15RM0MKF6bupyq1CsUF2dVP+vyNPGkkyactOVZfz5Zxp9v0u7fLD/nqET0NZdWqqUmos3hvGMDdRLLNjdQp+lmzoTS0rplpaVBeTM2M3PqakqTDghL2crMUYtSNzR1asrymaMWZdVO2vpTVze0efVMnZpdedafT0PbVQDS7t8sP+fI4onmay6tVSbn7+KYaNo1orE03lnhsbDOpY2116RrRO7BFduyMnezYJ7jFdxsm5k37QUvK65yo9rLiqv2XMhO11Ca8mzbSVs/S9Om7blWVFycvqPC7u3N9vMZ9VsvY3UQJ6sLpqNCQlSfc2TxRPM1lxaEDK8RWVA3/5jZYmAEMMHdH8ly3f2ANQTdt/dx9y9T1KkC+gMnuPtLDbVXUVHheh6RiEh2zGypu1c0Vq9Fnppz9yrgr0BbYELycjMbQZCEPgGW7N3oRESktoJORGZ2QzhA6g0pFifKbjKzA2ut0wu4M3x5o2tUBRGRWOXNED9mdhR7EgTAoeH8ejP7UaLQ3WuPhNAXGBzO63D3R8zsLoLBVN80s/9hz6CnnYEFBIOfiohIjPImEREkh2NSlA/KtUF3n25mLwKXEFxvKgbeAe4B7tLRkIhI/PK2s0I+UWcFEZHsterOCiIiUjiUiEREJFZKRCIiEislIhERiZUSkYiIxEqJSEREYqVEJCIisVIiEhGRWCkRiYhIrJSIREQkVkpEIiISKyUiERGJlRKRiIjESolIRERipUQkIiKxUiISEZFYKRGJiEislIhERCRWSkQiIhIrJSIREYmVEpGIiMRKiUhERGKlRCQiIrFSIhIRkVgpEYmISKyUiEREJFZKRCIiEislIhERiZUSkYiIxEqJSEREYqVEJCIisVIiEhGRWCkRiYhIrJSIREQkVkpEIiISKyUiERGJlRKRiIjESolIRERipUQkIiKxUiISEZFYKRGJiEislIhERCRWSkQiIhKrksYqmNn7TWjf3f3rTVhfRERauEYTETAwTbkD1sgyzyEmERFpRTI5Nbd/iuk2giTzGHAWcGQ4nQU8Gi67FTgg+pBFRKQlafSIyN0/rP3azMYB/wyc5+4PJ1X/G/CEmY0HHgJeAj5EREQkjVw6K/wIeDVFEtrN3R8BXgnrioiIpJVLIjoMeC+Deh8AQ3NoX0REWpFcEpEDB2dQb3AObYuISCuTSyJ6FTjSzC5KV8HM/gk4iuD0nIiISFqZdN9O9nNgJPBrMzsPmE9wGg6Crt6Tw+XVwL9GEKOIiLRgWScid3/BzC4AZhMknJOTqhiwFbjY3Z9vcoQikpGamho2btzIli1b2L59OzU1NXGHJC1EcXExnTp1olu3brRr1y7y9nM5IsLdHzSz54B/Ak4C+oeLPgaeA37r7mujCVFEGrNr1y6qqqooKSmhW7dulJaWUlRUhFm6e85FMuPu7Ny5k02bNrFmzRoGDBgQeTLKKREBuPs64BcRxiIiOdqwYQPt2rWjb9++Sj4SKTOjbdu29OjRAwi+a3379o30PTToqUgL8MUXX9C9e3clIWlWnTt3ZvPmzZG3m/MRkZl1AS4AhgM9gUXu/m/hssFAGfCCu38ZRaAikt6uXbto27Zt3GFIC9emTRuqq6sjbzenRGRmYwh6y+3DnsFNP65V5chw+fkEQ/2ISDPT0ZA0t+b6jmV9as7MhhIMdtoJuBOYSP1RuJ8EvgS+2dQARUSkZcvliOgaoB1wlrs/CWBmdY563H2bmb0DHN70EEVEpCXLpbPCycCyRBJqQBUQbdcKERFpcXJJRN2BVRnUqwE65NC+iEizeOKJJzj++OPp3LkzZoaZ8frrr8cdVpOdfPLJmBmLFy+OO5Sc5HJqbiN7bmBtyNeBT3NoX0QkcsuWLWP8+PEAnHLKKbvvhenWrVucYQm5JaJXgdPMbJC7v5uqgpkNI3hcxANNCU5EJCoLFixg165dXHPNNcycOTPucKSWXE7NzQLaAI+E9wvVYWYHAPcQdOm+q2nhiYhEo6qqCoBBgwbFHIkkyzoRufszwH8A3wDeNrM3CJLOaDN7BXgHGALc5u4vRhmsiEi2rrvuOsyMOXPmAHDhhRfuvj70ne98Z3e9qqoqLr/8cgYPHkyHDh3o3Lkzxx9/PHPnzsXd67Vb+7rMSy+9xJgxY+jatStdunThtNNOq3Pt6b777mPYsGF07NiRbt26ccEFF/DJJ5/Ua3Pnzp3cf//9TJo0icGDB9OpUydKS0s59NBDueqqq9iwYUNOn8EzzzzD2LFj6d27N23btqVv375MmjSJN998M6f2IufuOU3AxcBagk4Jtaf1wGW5tpuPU3l5uYvks7fffjvuEPLW448/7lOmTPGvf/3rDvjxxx/vU6ZM8SlTpvhvfvMbd3f/85//7F26dHHADzzwQB83bpyPHj3aO3bs6IB/61vfqtfuiBEjHPArrrjCi4uL/eijj/aJEyf6wQcf7IB37tzZV65c6T/84Q+9TZs2Pnr0aD/77LO9d+/eDviQIUP8q6++qtNmVVWVA961a1cfPny4n3vuuT5mzBjv0aOHA37AAQf4+vXr08by7LPP1lt22WWXOeAlJSU+fPhwnzBhgh955JEOePv27f3pp5/O6vPM5rsGVHom+SSTSmlXDo6ojgLGE9zYehxQ0pQ283FSIpJ8p0TUuClTpjjgc+bMqVO+du1a79q1qxcXF/vcuXO9pqZm97I1a9b4EUcckXK9xB9/M/OHH354d3l1dbVPmjTJAR86dKj37t3bly9fvnv5Z5995gcddJADft9999Vpc9OmTf7kk0/6jh076pRv27bNL7zwQgf84osvrrdt6RLRXXfdtTvprVixos6yxx9/3EtKSnyfffbxDRs2pP3ckuVdImotkxKR5LtYEtG8ee5lZe5mwXzevL0fQxbSJaIZM2Y44DNmzEi53muvveaAH3XUUXXKE3/8J02aVG+dZcuWOcElC7/77rvrLb/11lsd8AsvvDDj+Ldu3eolJSXes2fPestSJaJdu3Z53759HaiTCGu75JJLHPBf/epXGcfRHIko615zZnYTMMfd38l2XRFpIebPh6lTYdu24PWHHwavASZPji+uHPzhD38AYMKECSmXl5eX07FjR15//XW2b99O+/bt6ywfM2ZMvXUOPPDABpcnOkysXZv6sW3Lli1j0aJFrF69mq1btwZHDUDbtm1Zv349GzdupGvXrg1u1+uvv866desYMmQIhx56aMo6I0aMYNasWSxZsoTvf//7DbbXnHLpvn0l8CMzew2YCzzo7p9HGpWI5Ldrr92ThBK2bQvKCywRvf/++wAMGzas0bqfffYZ/fr1q1PWv3/92yo7duyY0fLt27fXKd+yZQuTJ0/myScbHrhm06ZNjSaixHYtX7680cFK169f3+Dy5pZLIrqVYFTto4FhwG1m9gRBUnrGE6lbRFquNWuyK89jiccaTJw4sd7RTrJUTyYtKmq483Fjy2u7+uqrefLJJzn00EO58cYbqaiooEePHrRp0waAfffdl3Xr1pHJn9nEdvXr14/Ro0c3WPfggw/OOMbmkHUicvcfmdkM4DTgQuBM4FxgAvCJmd0P3OvuKyKNVETyx4ABwem4VOUFZr/99mPVqlX85Cc/YciQIbHG8vDDDwPw0EMPMXTo0DrLtm7dmrLLdzr77bcfAH379mXu3LmRxdgccnpCq7vXuPtCdz8X6ANMJxhxoS8wA3jLzF4xs4ujC1VE8sbMmVBaWrestDQoLzCnn346sCcJxClxn1AiidT2u9/9LqMjoYSjjz6a7t27s2zZMlatymR40Pg0+VHh7v6Fu//a3YcDBwM3Ah8RnLab1dT2RSQPTZ4Ms2dDWRmYBfPZswvu+hDAlVdeSefOnbn++uuZNWsWu3btqlfn5Zdf3iuJKnGKbNasun86Kysrufrqq7Nqq02bNvzkJz+hurqacePG8eqrr9ars3XrVh544AFWrIj3BFaTE1GSVcCLQGXE7YpIvpk8GVavhpqaYF6ASQiCo48FCxbQqVMnLr30UgYMGMCpp57Keeedx0knnUS/fv0YPnw4jz76aLPH8tOf/hSAa6+9liOOOIJJkyYxYsQIjjnmGE477TTKysqyau/yyy/nBz/4AcuXL+eYY47h8MMP5+yzz2bcuHGUl5fTq1cvzj//fD5MdZp1L4okEZnZEDO7meBI6CngLIIntM6Pon0RkeY0cuRIli9fzjXXXEOvXr14+eWXWbBgAWvWrGHQoEHccMMNe2Wg1PHjx/Pss88ycuRIqqqqeOqpp9i0aRO//OUvuf/++3Nq89Zbb+W5557jvPPOY+PGjTz99NMsXryYbdu2ceaZZzJ//nxOPPHEiLckO5ZrJzcz60bQe+47wJHseVz4EmAO8JC7b44gxthVVFR4ZaUO8iR/rVixgkMOOSTuMKQVyOa7ZmZL3b2isXpZHxGZ2Zlm9ijBOHO3Ewzxsxa4ARjs7se7+3/mmoTM7Hwze8HMvjCzLWZWaWaXmFlWsZrZdWbmDUzbG29FRESaWy73ET0RzrcDDxHcP/SnKO4fMrNZBD3wtgOLgJ3AKOAOYJSZTXD36iyb/RuQ6hGMO5sSq4iIRCPXB+PNIRhR4YuoAjGzcwiS0CfASR4+dM/MegPPElx3upTgKCwbC9z9uqjiFBGRaOXyPKJj3f3uKJNQKNE38Sqv9eRXd/8UmBa+/HG2p+hERCS/5cUfdTPrD5QDO4B6nfXd/TngY4KbZ4/du9GJiEhzavTUnJmdFP74qrtvr/U6I+7+fAbVjgzny939yzR1XgP6hXX/kkUIR4UjhncFNgCvAE+7+44s2hARkWaSyTWixQTP1TgEWFnrdSY8w/fYP5w3dFdVYjTF/Ruok8qZ4VTbR2Z2QXikJSIiMcokSTxPkFC2Jb2OUmLM9K0N1NkSzjtl2OZ7BNedFgIfAG2BbwA/A0YAfzCz49z9b9mHKyIiUWk0Ebn7yQ29jkjiZtjIEpy7p7oN+VngWTN7BDgHmAmckTIgs6nAVIABBTiisIhIociLzgpA4ubXjg3USSyLYrSGn4fzU82sTaoK7j7b3SvcvaJnz54RvKWIiKSSy8gKp1tjj/vL3upw3tCIfolx0Vc3UCdTicectwV6RNCeiIjkKJcjoqeBKjO70cyiGtxqWTgfYmYd0tQZllS3KbrX+nlL2loiItLscklEfwX2Zc8D8F42s4vNbJ9cg3D3qrDdtgRPeq3DzEYA/QlGXViS6/vUcm44/9+WMjCriEihymVkhQpgKHALQWI4muABeOvM7EEzG5PjqbsbwvlNZnZgotDMegF3hi9vdPeaWssuNbN3zOy+2g2Z2YBw8NR2SeVmZt+q9V635RCniIhEKNdHhb/t7jMIrtv8I8FoCE5wpPE0wX06WZ26c/dHgLsIRk9408yeMrPHgHeBQ4EFBIOf1tYDGAwkd2vrRvAspPVm9pqZPWpmTxF06b4P6ADc4e53Z7PdIiJRMDOiv9ReuJrUa87da9z9v939PIIEMo1g5IK+wJXAm1m2Nx2YTHCabgRwGsFTXy8Fzsli5O0q4GZgaRjX6cCpBNv7EDDK3b+fTWwiItI8chl9OyV33wTcbWa/J7hp9LIc2/kd8LsM614HXJei/DOCa1giIpLnIklE4YjYpxM8rfUMgk4HEByZiIiIpNWkU3NmNtTMbiEYGftJgtEKaoAHgH8g+3HhRESaRe3rMnPnzqWiooKvfe1r9OnTh+9973usX78egO3bt/Ozn/2Mgw46iPbt2zNgwACuvfZadu6s/yzN9evXc/vttzNmzBj2339/2rdvT5cuXTj22GOZNWsW1dXZPscTdu7cya9//WtOPPFEunbtSvv27Rk0aBBXXHHF7hhbHHfPaiLoCPB9oBKoJkg8NcBLwEVAp2zbzPepvLzcRfLZ22+/HXcIeY+gQ5XPmDHD27Zt66eeeqqfffbZ3qdPHwf8sMMO882bN/txxx3nXbt29XHjxvnpp5/upaWlDvhFF11Ur83777/fAe/fv7+ffPLJPnHiRD/55JO9Xbt2Dvg3v/lNr6mpSRtLsi+++MJPOOEEB7xLly5+yimn+Nlnn+0DBw50wAcMGOAffPBBc3w8GcvmuwZUeiZ5JZNKdVYIHuOdSEBVwPXAQdm2U0iTEpHkOyWixiX++Pfu3bvO57VhwwYfPHiwAz506FA/4YQT/PPPP9+9fNmyZV5SUuJm5qtXr67T5ttvv+0vv/xyvfdau3atH3HEEQ74gw8+mDaWZBMnTnTAx48f7xs2bNhdvmvXLp8xY4YDPmLEiFw2PzL5koi+JDj1dhpg2a5fiJMSkeS7OBLRvHnuZWXuZsF83ry9HkJWEn/877777nrLbrvtNge8qKgo5Wc5duxYB/zee+/N+P3++Mc/7k4q6WKpbfny5Q54WVmZb9u2rd461dXVfthhhzngb7zxRsZxRK05ElEunRX6ADWuEQlEWq3582HqVNgWPhzmww+D1wCTJ8cXVybGjBlTr+zAA4N76MvKyjjkkPq3Pw4aNAiAtWvX1lu2a9cu/vznP7NkyRI++eQTtm/fjruzeXPwJ3LlypUZxbVw4UIAzjjjDDp0qD/SWVFRESeccAJvvPEGS5Ys4Rvf+EZG7RaCXBLRBoLrQ8dEHIuIFIhrr92ThBK2bQvK8z0R9e/fv15Zx44d0y6rvXz79u11yleuXMm4ceNYsWJF2vfbtGlTRnG9//77AMyaNYtZs2Y1WLeldVrIJRFtIRjtQERaqTVrsivPJ0VF6TsLN7QslfHjx7NixQrGjh3LjBkzOOSQQ+jSpQvFxcWsXLmSwYMHJy5pNCrRw668vJyhQ4c2WHfIkCFZxZnvcklEKwgGIBWRVmrAgOB0XKry1uKdd97hzTffpFevXjz22GMUFxfXWb5q1aqs2ttvv+BJNyNHjuTmm2+OLM5CkMt9RL8BTjCz8qiDEZHCMHMmlJbWLSstDcpbiw0bNgCw77771ktCAPPnz8+qvdNPPx2ABQsWsGvXrqYHWEByGX37twSjYf/JzK4ys4OSR7kWkZZt8mSYPRvKysAsmM+enf/Xh6I0aNAgioqKeOutt3j++efrLJszZw4PPPBAVu0dddRRjBs3jlWrVnHuuefy0Ucf1auzbt06fvnLX7a4RJX1qTkzq32r8PXhlG4kWXf3yMazE5H8MXly60o8yXr27Mn06dO54447GDlyJCNGjKBPnz68+eabvPXWW1x99dXccMMNjTdUy7333svYsWN5/PHHWbhwIYcffjhlZWVs2rSJqqoqVqxYQU1NDRdffDElJS3nT2sup+Ysi6lJQwiJiOSz22+/ndmzZ3P44Yfz6quvsnDhQnr37s3ChQuZmujPnoXOnTuzaNEi7rvvPk466STee+89HnvsMZYuXUpJSQkXX3wxzzzzDO3bt2+GrYmPZdqjozWrqKjwysrKuMMQSWvFihUp738RiVo23zUzW+rBw1QbpCMWERGJlRKRiIjESolIRERi1dRec41RrzkREWlQLkkiZT/tCOqKiEgrlMsNrUWpJqAYOIDgoXkbgF+E5SIiImlFdtosfPbEamCWmf0NeNbMVrj7g1G9h4iItDzNcsTi7i8CfwX+uTnaF5H6dE+gNLfm+o4156mzD4GWNVa5SJ4qKSlhx44dcYchLdzOnTtTDvDaVM2ZiIYANc3YvoiEunTpwmeffaajImlWmzZtolOnTpG3G3kiMrPuZjYLOBh4Jer2RaS+bt268dVXX/HRRx+xefNmqqurlZQkEu7Ojh07+Pvf/87GjRvp1q1b5O+Ry31E7zewuCPQnaDb9g7gutzCEpFslJSUUFZWxsaNG9m4cSNr166lpkYnJCQaxcXFdOrUiQEDBtCuXfRP/cml19zARpbvAF4AfuruS3JoX0RyUFRURPfu3enevXvcoYhkJZdEtH8Dy3YA6929ZT21SUREmk3WicjdUzypXkREJDeR3NBqZucA44CewEfAQ+7+pyjaFhGRlq3RXnNmNtrMXjWzH6dZfg/we+B84B+A7wL/bWbXRxqpiIi0SJl03x4DlAMvJi8ws3OB7xD0klsG3EKQlBy4ysyOiyxSERFpkTI5NTcc+CwctifZZeH8GeD/uXsNgJldBNwNfA/4SxSBiohIy5TJEVF/gnHj6jCzzsCxBEc//5JIQqF7gLWAjohERKRBmSSinsD6FOUV4fob3f3l2gvcvRp4gyCJiYiIpJVJInKga4ry8nBe72gptAFok0tQIiLSemSSiKqAw8ws+WmrIwiSVLrx5LoB/9eE2EREpBXIJBEtBvoRPHkVADMbQtBVG+DpNOsdQXCdSEREJK1MEtFtwE7gNjN70cweI+gJVwxUJl8fAjCzYUAf4NUogxURkZan0UTk7v8LTAG+JOgFNw7oBKwDvp1mtWnh/H8iiFFERFqwjIb4cfeHzGwxcAbQC1gDPOHuW9KsUgn8DVgURZAiItJyZTzWnLt/Cvw2w7p35hyRiIi0Ks35qHAREZFGKRGJiEislIhERCRWSkQiIhIrJSIREYmVEpGIiMRKiUhERGKlRCQiIrFSIhIRkVgpEYmISKyUiEREJFZKRCIiEislIhERiZUSkYiIxEqJSEREYqVEJCIisVIiEhGRWCkRiYhIrJSIREQkVkpEIiISKyUiERGJlRKRiIjESolIRERipUQkIiKxUiISEZFYKRGJiEislIhERCRWSkQiIhIrJSIREYmVEpGIiMRKiUhERGKlRCQiIrFSIhIRkVgpEYmISKyUiEREJFZKRCIiEislIhERiVXeJSIzO9/MXjCzL8xsi5lVmtklZpZTrGY2xsz+aGYbzGybmb1lZteaWbuoYxcRkezlVSIys1nAfKACeAH4E3AQcAfwiJkVZ9neDGAhcArwV+BpoBfwr8BiMyuNLnoREclF3iQiMzsHmA58Ahzm7me4+1nAIGAFcBZwaRbtVQA3AtuA4919tLtPAA4AngeOBWZGuxUiIpKtvElEwNXh/Cp3fzdR6O6fAtPClz/O4hTdjwEDbnL3V2q1twW4EKgBppvZPk2OXEREcpYXicjM+gPlwA7g4eTl7v4c8DHQh+BIprH22gKnhy/np2jvfWAJ0Bb4x5wDFxGRJsuLRAQcGc6Xu/uXaeq8llS3IYOBUmCDu78XQXtNMn8+DBwIRUXBfH691Jjfpk+HkhIwC+bTpwfl6barX9ctmPnuqV/XLZG+bzqjRwd1E9Po0Tm9bdbi2r+xfa+y3TFRBVogv0hxbW5Bf8zuHvsEXAY48HgDdW4P69ySQXtjw7rLGqjzg7DOI421V15e7rmaN8+9tNQd9kylpUF5IZg2rW7siWnUqNTbtU+HLx1qkurX+L77bI7kfadNS11/1Kj0cTanuPZvbN+rbHdMVIEWyC9SXJubrx8zUOmZ5IBMKjX3BFwTJoV5DdSZGda5O4P2zg/rvthAnYvCOs801l5TElFZWerf27KynJvcq4qLU8effkpOQnvKo3jf4uLU9RuKqTnFtX9j+15lu2OiCrRAfpHi2tx8/ZgzTUT5cmrOwrnnS3tmNjW8h6ly/fr1OQeyZk125fmmujq/3jeueNKJa//G9r3KdsdEFWiB/CLFtbmF/jHnSyLaHM47NlAnsWxzA3Uia8/dZ7t7hbtX9OzZM4O3TG3AgOzK801xVnduNf/7xhVPOnHt39i+V9numKgCLZBfpLg2t9A/5nxJRKvDeVkDdfZLqptJew19fNm0l7OZM6E06bbZ0tKgvBBMnZq6fNSo1Nu1T4evqH8g6uy7z9ZI3reheLIpj0pc+ze271W2OyaqQAvkFykRDIvLAAALIElEQVSuzS34jzmT83fNPREkBQe+AjqkqVMV1jk+g/baEtzI6sDX09R5MVw+ubH2mnKNyD240FdW5m4WzPPs+mqjpk3bc2mguHjPdel027XvPpvDa0XBlG1HhcbeN53kDgvN3VEhIa79G9v3KtsdE1WgBfKLFNfm5uPHTIbXiCyoGz8zWwocBUxx9/uSlo0AFhOMutDP3WsyaO9R4GzgZ+7+86RlBwDvAruA3u7+eUNtVVRUeGVlZRZbIyIiZrbU3Ssaq5cvp+YAbgjnN5nZgYlCM+sF3Bm+vLF2EjKzS83sHTOrk7gSdQmOeK4ys6NrrdMRuIdg2+9sLAmJiEjzyptE5O6PAHcRjJ7wppk9ZWaPERy5HAosIBj8tLYeBDev1rsW5O6vEQzzUwr8JRyB+/fAe8AI4BXg2mbaHBERyVBJ3AHU5u7TzexF4BKCZFEMvENwBHNXJqfkktr7NzN7A/ghMAxoD7wP/IrgxtivooxfRESylzfXiPKZrhGJiGSvEK8RiYhIK6REJCIisVIiEhGRWCkRiYhIrNRZIQNmth74MO44mqAH8Pe4g5Bmo/3bshXy/i1z90YH61QiagXMrDKTnitSmLR/W7bWsH91ak5ERGKlRCQiIrFSImodZscdgDQr7d+WrcXvX10jEhGRWOmISEREYqVEVGDMrI2ZjTKzfzezl81snZntMLOPzewRMzu5kfXPN7MXzOwLM9tiZpVmdomZ6buQx8zsejPzcPpRA/W0fwuEmXUwsxlm9pqZfW5m28zsAzN72MyOT1G/KNyXleG+/SLc15PiiD9KOjVXYMxsNPCn8OUnwFJgK8GjMoaG5b9w95+mWHcWMB3YDiwCdgKjgE7A48AEd69u1g2QrJnZMGAJwT+OBlzp7rekqKf9WyDMbH/gj8CBwP8BLxM8oXogcATwc3f/11r1i4HHgLHAJoL9245g/7YD/sPdL9uLmxCtTB7jqil/JuAU4BHgxBTLJhI8ddaBkUnLzgnL1wGDapX3Bt4Ol10e9/ZpqrdP2wHLgY8JkokDP0pRT/u3QCbga8CqcJ/8HGiTtLw7cFBS2Q/D+ssJniqdKB9E8A+pA9+Me9ty/kziDkBTxDsU/jP8Uv42qbwyLP92inVG1PojVhT3Nmiqs29uCvfNmcDcBhKR9m+BTARPo3bg3gzrFwOfhuuclGL5lHDZq3FvW66Tzhu3PMvCef9EgZn1B8qBHcDDySu4+3ME/3H3AY7dCzFKBszsGIL/hH/n7k81UE/7t0CYWVvgovDljRmuNhzoBXzk7s+nWP4wwWnYYWbWr+lR7n1KRC3PoHC+rlbZkeF8ubt/mWa915LqSozMrD1wL7ABuLyR6tq/haOc4NRblbuvMLPjwo4od5vZv5jZ8BTrJPbZaymW4e7bCE7ZQXB9qeDk1aPCpWnMrA/wnfDlo7UW7R/OGxq4dU1SXYnXTGAwcJ67NzbgpfZv4fhGOH/XzOYSnFar7adm9ijwrVr/VGS6f4+gQPevjohaCDMrAeYBXYBFSadyOobzrQ00sSWcd2qG8CQLZnYc8M/AAnd/KINVtH8LR7dwfhLwbeAWgp5zXYFvEpxCPQeYVWudFr9/lYhajl8TdOWsAi5IWmbhXH3185yZdQDmEHTRnZ7pauFc+zf/Jf7mlhB0KLrS3d9z98/d/UlgHMF+nGJmB4R1W/z+VSJqAczsduB7BN04R7n7J0lVNofzjqSXWLa5gTrS/K4HDgKucPd1jVUOaf8Wjtqf/2+SF7p7JcG9gUXAyUnrtNj9q2tEBc7M/h24DFhPkITeTVFtdTgva6Cp/ZLqSjzOAmoI/iNOvn5wcDifZmZnAKvc/Z/Q/i0kq2v9/EGaOh8AFQS9HGuv02L3rxJRATOzfwOuAD4DTnX3t9NUTXTpHmJmHdL0rBqWVFfiU0Rw7086B4TTPuFr7d/C8ddaP3cn+AcyWY9wnrjuk1hnWIq6mFkpe0ZVKcj9q1NzBcrMbgSuBDYSJKG/pavr7lUEX+a2wIQUbY0guO/oE4KhZCQm7j7Q3S3VRNCdG4IhfszdjwjX0f4tEO7+MfBK+HJU8nIz6wocFb6sDOdLCIYB6m9mJ6VodgLQBngtbL/gKBEVIDP7BXAV8DlBEsrkv6AbwvlNZnZgrbZ6AXeGL29095pIg5W9Rfu3cMwM5z81s933/YT3jt1F0PN1KeE/DR6MD3hzWO2ucJ8m1hnEnhtjE+0WHA16WmDMbCzwRPiykj03siV7x93r3LltZncC0wgGxfwf9gyK2RlYAIx3DYqZt2rdd5Ju0FPt3wJhZjcDPyIYDeMVgtPrRwP7EnThHln7em846OnjBEM9JQY9bQOMBtpT4IOe6hpR4elW6+eKcErlOZKGEHH36Wb2InAJwTWIYuAd4B7gLv23XNi0fwuHu19pZn8Bvk8wckIpwU2ptxIcua5Pql9tZuMIuvRfCJwGVBMcOd3p7r/bm/FHTUdEIiISK10jEhGRWCkRiYhIrJSIREQkVkpEIiISKyUiERGJlRKRiIjESolIRERipUQkEjMzKzKzNWbmZvZ/ZtYm7phE9iYlIpH4/QN7hvHvSTCMi0iroUQkEr/vhvOPk16LtAoa4kckRmbWDVhL8AiHk4DF4aIB7r42rrhE9iYdEYnE6wKgHbDY3V8E/kgwWOm3061gZkeY2RNmtsHMtprZUjP7brjMzSzlf5dm9jUzm2Fmr5nZJjP70syWm9l1ZtbQY6hFmpUSkUi8Lgznc8P5nKTyOszsFILn1IwFPgWeJHgswOzw0QIpmVl/4FXgJoJHTi8hSHpdgZ8BL4UPZRPZ63RqTiQmZnYkwZNVNwN93H2bmbUlOFXXHTgxPEpK1C8FVgF9gZ8D13n4C2xmxwHPAB0Bwie6JtYz4CVgOHAHcJW7bwuXdQBmExyZ3evu32nObRZJRUdEIvH5Xjj/fSIxuPsOIPFsmeROC+MJktBK4F+81n+R7v4X9jyJNdkYgiT0MnB54r3C9b4ELiZ4FPVkHRVJHJSIRGJgZu2ASeHLOUmLE68nJF27GRHOH0rzkLt0D0f7x3D+aKr13H0rwdN+S4BhjcUuEjUlIpF4nEXwtN133f2l2gvcfRnwOsFptnNrLeoXzj9M02a68gPC+c2JzgzJE3uSVc9sN0SkqfSocJF4JE67dQkf752sd6169yQtS3dhN92jwIvD+XPA6kbiSpfMRJqNEpHIXmZm+wGjwpe9wimd483sIHdfSdCJAYJeb6kMTFNeFc4fdvdZ2cQqsjfo1JzI3nchwe/eIne3dBPwcFg/cfT0fDg/18xS/e5OSlEGsDCcT4gkepGIKRGJ7EVhV+op4cv7G6meWP5tMysmSEyfAgcD14ZtJdo9BrgkTTsLgKXACDP7dTiaQ3JcB5hZuvVFmpXuIxLZi8IbUhcB2wjuHdrcQN02BKfjegBnuvt/mdmpwFMEozGsIOjU0IdgeKBfAT8Adrp726S2+gN/AL5BcN/S34CPwrYHAAcBn7p7n+i2ViQzOiIS2bsSIyY80VASAnD3ncCD4cvvhmV/Ao4jSEZ9gXEEoyNcAtwW1v17irY+Ao4GLgWWAUOAc4ChBInpFuDsXDdKpCl0RCTSQpjZt4D7gP9ydz1KQgqGjohECoiZ9TKzer3mzOxYIDHW3Ny9GpRIE6n7tkhhOQz4k5m9BXwA7CC4YfXIcPn97v5oXMGJ5EKn5kQKSNjp4BqC4X76Ap0IRt9+neBIaJ7rl1oKjBKRiIjESteIREQkVkpEIiISKyUiERGJlRKRiIjESolIRERipUQkIiKx+v9txOKy6nrbewAAAABJRU5ErkJggg==\n", "text/plain": [ "" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "x = np.linspace(0, 100, 100)\n", "x = add_constant(x)\n", "female = (donner.FEMALE==1)\n", "plt.scatter(donner.AGE[female], donner.SURVIVED[female], c ='red',label ='female')\n", "plt.scatter(donner.AGE[~female], donner.SURVIVED[~female], c='blue', label ='male')\n", "\n", "plt.legend()\n", "\n", "# yhat = log_reg.predict(x)\n", "# x = np.linspace(0, 100, 100)\n", "# plt.plot(x, yhat)\n", "\n", "plt.xlabel('Age')\n", "plt.ylabel('Survived')\n", "plt.savefig('C:/Users/sofia/Dropbox/Apps/Overleaf/Applied Statistics Course/figures/log_res_age_fitted.png') \n" ] }, { "cell_type": "code", "execution_count": 94, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Optimization terminated successfully.\n", " Current function value: 0.569514\n", " Iterations 6\n", " Results: Logit\n", "==============================================================\n", "Model: Logit No. Iterations: 6.0000 \n", "Dependent Variable: SURVIVED Pseudo R-squared: 0.171 \n", "Date: 2022-05-26 12:48 AIC: 57.2563\n", "No. Observations: 45 BIC: 62.6763\n", "Df Model: 2 Log-Likelihood: -25.628\n", "Df Residuals: 42 LL-Null: -30.913\n", "Converged: 1.0000 Scale: 1.0000 \n", "---------------------------------------------------------------\n", " Coef. Std.Err. z P>|z| [0.025 0.975]\n", "---------------------------------------------------------------\n", "const 1.6331 1.1102 1.4710 0.1413 -0.5429 3.8092\n", "AGE -0.0782 0.0373 -2.0973 0.0360 -0.1513 -0.0051\n", "FEMALE 1.5973 0.7555 2.1142 0.0345 0.1165 3.0780\n", "==============================================================\n", "\n" ] } ], "source": [ "X = donner[['AGE', 'FEMALE']]\n", "X=add_constant(X)\n", "Y = donner.SURVIVED\n", "# building the model and fitting the data\n", "log_reg = sm.Logit(Y, X).fit()\n", "\n", "print(log_reg.summary2())\n", "lr =log_reg.summary2\n", "\n", "\n", "# import matplotlib.pyplot as plt\n", "# plt.rc('figure', figsize=(12, 7))\n", "# #plt.text(0.01, 0.05, str(model.summary()), {'fontsize': 12}) old approach\n", "# plt.text(0.01, 0.05, str(log_reg.summary2()), {'fontsize': 10}, fontproperties = 'monospace') # approach improved by OP -> monospace!\n", "# plt.axis('off')# plt.tight_layout()\n", "# plt.savefig('output.png')" ] }, { "cell_type": "code", "execution_count": 96, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[ 0.53118312 -0.05493944 1.06133315]]\n", "[0.53118312]\n" ] } ], "source": [ "from sklearn import linear_model as lr\n", "clf = lr.LogisticRegression().fit(X, Y)\n", "\n", "print(clf.coef_)\n", "print(clf.intercept_)" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
spamto_multiplefromccsent_emailimageattachdollarwinnerinheritviagrapasswordnum_charline_breaksformatre_subjexclaim_subjurgent_subjexclaim_mess
000100000000011.37020210000
100100000000010.50420210001
20010000401007.77319210006
300100000000013.256255100048
40010000000021.2312900001
50010000000021.0912500001
60110100000004.83719310001
70111111000007.421237100018
80010000000003.0516900001
90010000000002.6436810000
100010100000000.8692510002
110011000000004.0207901001
1200100000000010.45919110000
1300111000000015.075354110010
1400120002000019.69333011004
1500111000000018.380481110010
1600100005000118.037345101020
1700120000000013.89022511000
180010100000000.5963301002
190010000000004.5606410000
200010000000002.1928510003
2100100229000011.45334410004
22001000021000016.64756010003
230010100000000.2001001000
240010000000004.9386910000
250010000000002.2284501001
260011000000003.9598101001
270012000000004.5496701001
280010000000000.5061800000
290010000000002.2075710005
............................................................
38911010002000000.5372200003
389210100005000068.1371292100014
389310100003010010.58514210019
38941110002000000.4592100000
38951010000000000.031300000
38961010000000000.110710000
38971010001000000.198610011
38981010000000001.3621600000
38991010000010000.8194200001
39001010000000000.9992710002
39011010002000000.4592100000
39021010000000000.6502200000
390310100004000019.263472101010
39041010000000001.5354000000
39051010000400001.1072500000
39061010000100000.073500101
39071010000000000.015310000
39081010000001000.2491100000
39091110002000000.3411800000
39101010000000002.4025500000
39111010000000001.0552710001
39121010000000000.8191910002
39131010000200001.5974600103
39141010000100000.3331300000
391500100000000014.58423300001
39161010000000000.3321200000
39171010000100000.3231500000
39180110000000008.65620810005
391901100000000010.18513200000
39201010000210002.2256500101
\n", "

3921 rows × 19 columns

\n", "
" ], "text/plain": [ " spam to_multiple from cc sent_email image attach dollar winner \\\n", "0 0 0 1 0 0 0 0 0 0 \n", "1 0 0 1 0 0 0 0 0 0 \n", "2 0 0 1 0 0 0 0 4 0 \n", "3 0 0 1 0 0 0 0 0 0 \n", "4 0 0 1 0 0 0 0 0 0 \n", "5 0 0 1 0 0 0 0 0 0 \n", "6 0 1 1 0 1 0 0 0 0 \n", "7 0 1 1 1 1 1 1 0 0 \n", "8 0 0 1 0 0 0 0 0 0 \n", "9 0 0 1 0 0 0 0 0 0 \n", "10 0 0 1 0 1 0 0 0 0 \n", "11 0 0 1 1 0 0 0 0 0 \n", "12 0 0 1 0 0 0 0 0 0 \n", "13 0 0 1 1 1 0 0 0 0 \n", "14 0 0 1 2 0 0 0 2 0 \n", "15 0 0 1 1 1 0 0 0 0 \n", "16 0 0 1 0 0 0 0 5 0 \n", "17 0 0 1 2 0 0 0 0 0 \n", "18 0 0 1 0 1 0 0 0 0 \n", "19 0 0 1 0 0 0 0 0 0 \n", "20 0 0 1 0 0 0 0 0 0 \n", "21 0 0 1 0 0 2 2 9 0 \n", "22 0 0 1 0 0 0 0 21 0 \n", "23 0 0 1 0 1 0 0 0 0 \n", "24 0 0 1 0 0 0 0 0 0 \n", "25 0 0 1 0 0 0 0 0 0 \n", "26 0 0 1 1 0 0 0 0 0 \n", "27 0 0 1 2 0 0 0 0 0 \n", "28 0 0 1 0 0 0 0 0 0 \n", "29 0 0 1 0 0 0 0 0 0 \n", "... ... ... ... .. ... ... ... ... ... \n", "3891 1 0 1 0 0 0 2 0 0 \n", "3892 1 0 1 0 0 0 0 5 0 \n", "3893 1 0 1 0 0 0 0 3 0 \n", "3894 1 1 1 0 0 0 2 0 0 \n", "3895 1 0 1 0 0 0 0 0 0 \n", "3896 1 0 1 0 0 0 0 0 0 \n", "3897 1 0 1 0 0 0 1 0 0 \n", "3898 1 0 1 0 0 0 0 0 0 \n", "3899 1 0 1 0 0 0 0 0 1 \n", "3900 1 0 1 0 0 0 0 0 0 \n", "3901 1 0 1 0 0 0 2 0 0 \n", "3902 1 0 1 0 0 0 0 0 0 \n", "3903 1 0 1 0 0 0 0 4 0 \n", "3904 1 0 1 0 0 0 0 0 0 \n", "3905 1 0 1 0 0 0 0 4 0 \n", "3906 1 0 1 0 0 0 0 1 0 \n", "3907 1 0 1 0 0 0 0 0 0 \n", "3908 1 0 1 0 0 0 0 0 0 \n", "3909 1 1 1 0 0 0 2 0 0 \n", "3910 1 0 1 0 0 0 0 0 0 \n", "3911 1 0 1 0 0 0 0 0 0 \n", "3912 1 0 1 0 0 0 0 0 0 \n", "3913 1 0 1 0 0 0 0 2 0 \n", "3914 1 0 1 0 0 0 0 1 0 \n", "3915 0 0 1 0 0 0 0 0 0 \n", "3916 1 0 1 0 0 0 0 0 0 \n", "3917 1 0 1 0 0 0 0 1 0 \n", "3918 0 1 1 0 0 0 0 0 0 \n", "3919 0 1 1 0 0 0 0 0 0 \n", "3920 1 0 1 0 0 0 0 2 1 \n", "\n", " inherit viagra password num_char line_breaks format re_subj \\\n", "0 0 0 0 11.370 202 1 0 \n", "1 0 0 0 10.504 202 1 0 \n", "2 1 0 0 7.773 192 1 0 \n", "3 0 0 0 13.256 255 1 0 \n", "4 0 0 2 1.231 29 0 0 \n", "5 0 0 2 1.091 25 0 0 \n", "6 0 0 0 4.837 193 1 0 \n", "7 0 0 0 7.421 237 1 0 \n", "8 0 0 0 3.051 69 0 0 \n", "9 0 0 0 2.643 68 1 0 \n", "10 0 0 0 0.869 25 1 0 \n", "11 0 0 0 4.020 79 0 1 \n", "12 0 0 0 10.459 191 1 0 \n", "13 0 0 0 15.075 354 1 1 \n", "14 0 0 0 19.693 330 1 1 \n", "15 0 0 0 18.380 481 1 1 \n", "16 0 0 1 18.037 345 1 0 \n", "17 0 0 0 13.890 225 1 1 \n", "18 0 0 0 0.596 33 0 1 \n", "19 0 0 0 4.560 64 1 0 \n", "20 0 0 0 2.192 85 1 0 \n", "21 0 0 0 11.453 344 1 0 \n", "22 0 0 0 16.647 560 1 0 \n", "23 0 0 0 0.200 10 0 1 \n", "24 0 0 0 4.938 69 1 0 \n", "25 0 0 0 2.228 45 0 1 \n", "26 0 0 0 3.959 81 0 1 \n", "27 0 0 0 4.549 67 0 1 \n", "28 0 0 0 0.506 18 0 0 \n", "29 0 0 0 2.207 57 1 0 \n", "... ... ... ... ... ... ... ... \n", "3891 0 0 0 0.537 22 0 0 \n", "3892 0 0 0 68.137 1292 1 0 \n", "3893 1 0 0 10.585 142 1 0 \n", "3894 0 0 0 0.459 21 0 0 \n", "3895 0 0 0 0.031 3 0 0 \n", "3896 0 0 0 0.110 7 1 0 \n", "3897 0 0 0 0.198 6 1 0 \n", "3898 0 0 0 1.362 16 0 0 \n", "3899 0 0 0 0.819 42 0 0 \n", "3900 0 0 0 0.999 27 1 0 \n", "3901 0 0 0 0.459 21 0 0 \n", "3902 0 0 0 0.650 22 0 0 \n", "3903 0 0 0 19.263 472 1 0 \n", "3904 0 0 0 1.535 40 0 0 \n", "3905 0 0 0 1.107 25 0 0 \n", "3906 0 0 0 0.073 5 0 0 \n", "3907 0 0 0 0.015 3 1 0 \n", "3908 1 0 0 0.249 11 0 0 \n", "3909 0 0 0 0.341 18 0 0 \n", "3910 0 0 0 2.402 55 0 0 \n", "3911 0 0 0 1.055 27 1 0 \n", "3912 0 0 0 0.819 19 1 0 \n", "3913 0 0 0 1.597 46 0 0 \n", "3914 0 0 0 0.333 13 0 0 \n", "3915 0 0 0 14.584 233 0 0 \n", "3916 0 0 0 0.332 12 0 0 \n", "3917 0 0 0 0.323 15 0 0 \n", "3918 0 0 0 8.656 208 1 0 \n", "3919 0 0 0 10.185 132 0 0 \n", "3920 0 0 0 2.225 65 0 0 \n", "\n", " exclaim_subj urgent_subj exclaim_mess \n", "0 0 0 0 \n", "1 0 0 1 \n", "2 0 0 6 \n", "3 0 0 48 \n", "4 0 0 1 \n", "5 0 0 1 \n", "6 0 0 1 \n", "7 0 0 18 \n", "8 0 0 1 \n", "9 0 0 0 \n", "10 0 0 2 \n", "11 0 0 1 \n", "12 0 0 0 \n", "13 0 0 10 \n", "14 0 0 4 \n", "15 0 0 10 \n", "16 1 0 20 \n", "17 0 0 0 \n", "18 0 0 2 \n", "19 0 0 0 \n", "20 0 0 3 \n", "21 0 0 4 \n", "22 0 0 3 \n", "23 0 0 0 \n", "24 0 0 0 \n", "25 0 0 1 \n", "26 0 0 1 \n", "27 0 0 1 \n", "28 0 0 0 \n", "29 0 0 5 \n", "... ... ... ... \n", "3891 0 0 3 \n", "3892 0 0 14 \n", "3893 0 1 9 \n", "3894 0 0 0 \n", "3895 0 0 0 \n", "3896 0 0 0 \n", "3897 0 1 1 \n", "3898 0 0 0 \n", "3899 0 0 1 \n", "3900 0 0 2 \n", "3901 0 0 0 \n", "3902 0 0 0 \n", "3903 1 0 10 \n", "3904 0 0 0 \n", "3905 0 0 0 \n", "3906 1 0 1 \n", "3907 0 0 0 \n", "3908 0 0 0 \n", "3909 0 0 0 \n", "3910 0 0 0 \n", "3911 0 0 1 \n", "3912 0 0 2 \n", "3913 1 0 3 \n", "3914 0 0 0 \n", "3915 0 0 1 \n", "3916 0 0 0 \n", "3917 0 0 0 \n", "3918 0 0 5 \n", "3919 0 0 0 \n", "3920 1 0 1 \n", "\n", "[3921 rows x 19 columns]" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "emails = pd.read_csv('email.csv')\n", "\n", "\n", "# delete time column\n", "del emails['time']\n", "del emails['number']\n", "\n", "# convert winner to numerical\n", "level_mapping = {'no': 0, 'yes': 1}\n", "winner = emails['winner'].copy()\n", "winner = winner.replace(level_mapping)\n", "emails['winner'] = winner\n", "\n", "emails\n", "\n" ] }, { "cell_type": "code", "execution_count": 98, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Optimization terminated successfully.\n", " Current function value: 0.248912\n", " Iterations 10\n", " Results: Logit\n", "================================================================\n", "Model: Logit No. Iterations: 10.0000 \n", "Dependent Variable: spam Pseudo R-squared: 0.199 \n", "Date: 2022-05-26 12:48 AIC: 1965.9699\n", "No. Observations: 3921 BIC: 2009.8886\n", "Df Model: 6 Log-Likelihood: -975.98 \n", "Df Residuals: 3914 LL-Null: -1218.6 \n", "Converged: 1.0000 Scale: 1.0000 \n", "----------------------------------------------------------------\n", " Coef. Std.Err. z P>|z| [0.025 0.975]\n", "----------------------------------------------------------------\n", "const -0.8921 0.0892 -9.9985 0.0000 -1.0670 -0.7173\n", "to_multiple -2.6719 0.3073 -8.6936 0.0000 -3.2743 -2.0695\n", "image -2.4903 1.0228 -2.4346 0.0149 -4.4950 -0.4855\n", "attach 0.5356 0.1007 5.3205 0.0000 0.3383 0.7329\n", "winner 1.6606 0.3183 5.2178 0.0000 1.0368 2.2844\n", "format -1.5203 0.1209 -12.5735 0.0000 -1.7573 -1.2833\n", "re_subj -3.0881 0.3762 -8.2093 0.0000 -3.8254 -2.3508\n", "================================================================\n", "\n" ] } ], "source": [ "yheader =emails.columns[0]\n", "xheader = emails.columns[2:18]\n", "\n", "Y = emails[yheader]\n", "X = emails[['to_multiple', 'image', 'attach', 'winner', 'format','re_subj']]\n", "\n", "X = add_constant(X)\n", "\n", "log_reg = sm.Logit(Y, X).fit()\n", "\n", "print(log_reg.summary2())\n", "lr =log_reg.summary2\n" ] }, { "cell_type": "code", "execution_count": 108, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[-0.45564089 -2.43682052 -1.5202543 0.45503679 1.48901031 -1.49396259\n", " -2.7552273 ]]\n", "[-0.45564089]\n" ] }, { "data": { "text/plain": [ "array([[0.35945543, 0.64054457]])" ] }, "execution_count": 108, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn import linear_model as lr\n", "clf = lr.LogisticRegression().fit(X, Y)\n", "\n", "print(clf.coef_)\n", "print(clf.intercept_)\n", "yhat = clf.predict_proba([[1, 0, 0, 0, 1, 0, 0]])\n", "yhat" ] }, { "cell_type": "code", "execution_count": 109, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[0.68319075]\n", "[0.66445047]\n" ] } ], "source": [ "a = log_reg.predict([1, 0, 0, 0, 1, 0, 0])\n", "print(a)\n", "print(np.exp(a)/(1+np.exp(a)))\n" ] }, { "cell_type": "code", "execution_count": 66, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "4.4816890703380645" ] }, "execution_count": 66, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np.exp(1.5)" ] } ], "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": "3.6.13" } }, "nbformat": 4, "nbformat_minor": 2 }