You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
195 lines
22 KiB
195 lines
22 KiB
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Simple example of logistic regression with scikit-learn"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import numpy as np\n",
|
|
"import pandas as pd\n",
|
|
"import matplotlib.pyplot as plt"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Read data \n",
|
|
"Data are from the [wikipedia article on logistic regression](https://en.wikipedia.org/wiki/Logistic_regression)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# data: 1. hours studies, 2. passed (0/1) \n",
|
|
"filename = \"https://www.physi.uni-heidelberg.de/~reygers/lectures/2021/ml/data/exam.txt\"\n",
|
|
"df = pd.read_csv(filename, engine='python', sep='\\s+')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"x_tmp = df['hours_studied'].values\n",
|
|
"x = np.reshape(x_tmp, (-1, 1))\n",
|
|
"y = df['passed'].values"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Fit the model"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from sklearn.linear_model import LogisticRegression\n",
|
|
"clf = LogisticRegression(penalty='none', fit_intercept=True)\n",
|
|
"clf.fit(x, y);"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Calculate predictions"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"hours_studied_tmp = np.linspace(0., 6., 1000)\n",
|
|
"hours_studied = np.reshape(hours_studied_tmp, (-1, 1))\n",
|
|
"y_pred = clf.predict_proba(hours_studied)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Plot result"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAYYAAAEKCAYAAAAW8vJGAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy86wFpkAAAACXBIWXMAAAsTAAALEwEAmpwYAAAzgUlEQVR4nO3dd3gVZfbA8e9JBxJ6qKELSBEpodjAumJZy2LvBVF/Yllsa9nVZYuCruu66+7asFJEwd57YQUJvfcWaoAQEkLqPb8/ZqI3MQmTcGtyPs9zn9w7d2beM5eQc+etoqoYY4wxZWLCHYAxxpjIYonBGGNMOZYYjDHGlGOJwRhjTDmWGIwxxpQTF+4ADlfLli21c+fO4Q7DGGOiyrx583arampl70V9YujcuTMZGRnhDsMYY6KKiGyq6j2rSjLGGFOOJQZjjDHlWGIwxhhTjiUGY4wx5VhiMMYYU07IEoOITBKRXSKytIr3RUSeEpG1IrJYRAaGKjYTHHvyClm0ZR978gqjuoxQlROqa6mp2sQVimNCFVdNReq/Y02EsrvqS8C/gFeqeP8MoLv7GAr8x/1potA7C7dy74zFxMfEUOzzMXFUP87p3z7qyghVOaG6llDEFYpjQhVXTUXqv2NNheyOQVW/BfZWs8u5wCvqmA00FZG2oYnOBNKevELunbGYgmIfuYUlFBT7uGfG4oB+gwpFGaEqJ1TXEoq4QnFMqOKqqUj9d6yNSGpjaA9s8Xud6W77BREZIyIZIpKRlZUVkuCMd5nZB4mPKf+rFR8TQ2b2wagqI1TlhOpaaqo2cYXimFDFVVOhKENVKSwpZV9+Edv2HSS3oDhg5/YXlSOfVfVZ4FmA9PR0W2kowqQ1a0Cxz1duW7HPR1qzBlFVRqjKCdW11FRt4grFMaGKq6YOVYaqkl9USnZ+Efvyi8nOLyLnYDF5BSXkFZaQ6/786XVhCXkFxT9tyy0sIb+olFLfz3/y/nJ+Xy4f2ilg11AmkhLDVqCD3+s0d5uJMi2SE5k4qh/3VKhrbZGcGFVlhKqcUF1LKOIKxTGhisuLwpJSsnIL2ZVbyK79hfy6XztmLsgkBqFUlbSmDbjsuTk/JYOiUl+152uUEEtyUhzJiXEkJ8WTkhhHq5Skn7Y1TIilUWIcDeJjaZgQS3rn5ocVf1UklEt7ikhn4H1V7VvJe2cBY4EzcRqdn1LVIYc6Z3p6utpcSZFpT14hmdkHSWvWIGh/5EJRRqjKCdW11FRt4grFMcEuo9Sn7NhfQObefLbuO0hm9kEys/PZtq+AXbkF7MotZF/+L6tyYgRSkuJp3iiBlskJNGvoPJo2inefx9PU3dakQTwpSXEkJ8XRKCGO2BjxdB2BICLzVDW90ve8JgYROR84CWhFhbYJVb3Iw/FTgROBlsBO4CEg3j3+vyIiOL2WRgL5wLWqesi/+JYYjDG1VVLqIzP7IOt357E+6wDrsg6wcfcBMvfls31fASW+8n8fW6Uk0rZpA1qnJNKqcSKtUpJoVeF5i+TEkP6Br63qEoOnqiQR+RtwKzAL5496aU2DUNVLD/G+ArfU9LzGGHMoqkpm9kGWbdvP8u37Wb0jl3VZeWzak1+ueqdpw3i6tGzEgA7N+HW/BqQ1a0haswakNWtAu6YNSIqPDeNVhI7XNoargQtV9Z1gBmOMMYfL51PWZuWxcPM+lm3LYcX2XFZs309uYQkAItClRSO6piZz8pGt6JaaTNdU53XzRglhjj4yeE0M+cDKYAZijDG1kZNfzIIt2czfvI8Fm7NZuHnfT0mgYUIsvdo25twB7ejdtgm92zWmZ+sUGiTUj2/+teU1MTwK3CMiN6pqSTADMsaY6hwoLOHHjXv539rdzFq7hxU79qPqNPr2aJ3Cr/u3Y0CHpgzo2IyuLRsREwX1/ZHGa2J4Dvg1sFVEVgPlmuJV9eRAB2aMMeBUDS3dlsMXK3Yxa+1uFm7ZR4lPSYiNYWCnptxxSg8Gd25Gvw5NSU6MpB740cvrp/hf4HjgY5zGZxtUZowJmoLiUmat3c3nK3bxxYqd7MotJEbgqLSm3DC8K8d1a8mgTs2sSihIvCaGi4HzVfWzYAZjjKm/CopL+XrVLt5dtI0vV+6ioNhHo4RYRvRM5ZQjW3PSka2scThEvCaGLGwUsjEmwEpKfcxat4d3F27j02U7yC0soWVyAhcMSuNXvdswtGtzEuPsriDUvCaGh4DxInKNquYFMyBjTN23eU8+r2ds5o2MTHblFpKSFMfIvm04p387junagrjYSJrfs/7xmhjuBjoDO0VkM79sfO4X4LiMMXVMUYmPT5fvYNqPW/h+7W5iBE7q2YoL0ztwYs/UejN4LBp4TQxvBjUKY0ydlX2giCk/bubl/21kV24h7Zs2YNxpPbgwPY22TcI7g6ypnKfEoKp/DHYgxpi6ZX1WHpNmbeDNeZkUFPs4oXtLJozqx/AeqVExl1B9Zp1+jTEBtXpnLk99sYYPlmwnPiaG8wa04/rju9KzTUq4QzMeeZ1ELwF4ALgU6Ig7K2oZVbXKQWPquVU7cnnqyzV8uGQ7DeNjuWlEN647rgupKZEzhbjxxusdw59wxjI8AvydnxujLwF+H5TIjDFRYcvefB77ZBXvLd5Gw/hYbh7RjdEndLUxB1HMa2K4CLhJVT8WkceBd1R1nYisAE4DnglahMaYiJSTX8zTX6/lpVkbiYmBm0d044YTutLMEkLU85oYWgPL3ed5QFP3+cfAhADHZIyJYMWlPl79YRNPfbmGnIPFXDAwjTt/1ZM2TZLCHZoJEK+JYTPQzv25FjgdmAccAxwMTmjGmEjz44a9PPj2ElbvzOP4I1py/5m96N2ucbjDMgHmNTG8BZwCzAb+AUwVkRuA9sBjQYrNGBMh9uQV8shHK3lzXibtmzbguavSObVXK5wVeU1d43Ucw31+z98UkS3AccBqVX0/WMEZY8JLVZkxfyt//mA5eQUl3DSiG7edcgQNE6yne11Wq39dVZ0DzAEQkXhVLT7EIcaYKLNrfwH3zVzCFyt3MbhzM/5y/lH0aG1jEeoDr+MY3gWuVdU9Fbb3AqYAA4IQmzEmDFSVdxdt4w/vLKOguJQHz+rFdcd1sZXQ6hGvUxg2A5aIyK/KNojIWJwG6MXBCMwYE3o5B4sZO2UBt09bSJeWjfjw9hMYfUJXSwr1jNeqpBHAg8B7IvIs0A2nR9L1qjo1WMEZY0JnweZsbp26gB05Bdx9ek9uHN7Vpr+up7w2Pvtw1mOIxRnpXAIMV9XZwQzOGBN8Pp/y/PfrmfjxKto0SWL6TccwsGOzcIdlwshrG0Mi8DhwA/AwcALO3cNoVX0neOEZY4JpX34Rv319IV+tyuKMvm14dFQ/mjSIP/SBpk7zWpU0z933eFXNABCRO4FpIvKaqt4QrACNMcGxakcuY17NYPu+Av50bh+uGNbJxiUYwHtimA3cpqr5ZRtU9W8i8jnwWlAiM8YEzcdLtzNu+iKSE+OYOmYYgzpZ1ZH5mdc2htFVbF8kIumBDckYEyw+n/L3z1fzzy/X0r9DU565chCtG9scR6Y8z10OROQMEXlfRJaLSAd322jg+KBFZ4wJmILiUm6ZMp9/frmWi9LTeP3GYZYUTKU8JQYRuRyYDqwBuvDzQj2xwD3BCc0YEyh7DxRx+fNz+GjpDh44sxcTRvUjMc7W1zKV83rHcA9wg6r+FqerapnZQP9AB2WMCZxNew4w6j//Y8nWHP59+UBuGN7VGplNtbwmhu7AD5VszwM8z7krIiNFZJWIrBWR31XyfkcR+UpEFojIYhE50+u5jTG/tHDLPn7z7/+RnV/ElNFDOfOotuEOyUQBr4lhG9Cjku3DgXVeTuAOjnsaOAPoDVwqIr0r7PYgMF1VB+AsG/pvj/EZYyr437rdXPbcbBomxjLz5mNJ79w83CGZKOE1MTwLPCUix7mvO4jI1cBE4D8ezzEEWKuq61W1CJgGnFthH+XnO5AmOAnJGFNDX67cybUvziWtWQNm3HQsXVOTwx2SiSJeu6tOFJEmwGdAEvAVUAg8rqpPeyyrPbDF73UmMLTCPg8Dn4rIrUAj4NTKTiQiY4AxAB07dvRYvDH1w/uLt3HHtIX0atuYl68bQnNbg9nUkOfuqqr6ANAS55v/MCBVVX8f4HguBV5S1TTgTOBVEflFjKr6rKqmq2p6ampqgEMwJnpNz9jCbVMXMKBjUybfMNSSgqmVGi3U4458zqhlWVuBDn6v09xt/q4HRrpl/SAiSTjJaFctyzSm3piesYV7Zyzm+CNa8uyV6TRIsO6opnZCOafuXKC7iHQRkQScxuV3K+yzGWdt6bJFgJKArBDGaExUmjk/86ek8NxVlhTM4QlZYlDVEmAs8AmwAqf30TIRGS8i57i73QncICKLgKnANaqqoYrRmGj0zsKt3PXGIo7t1oLnrkonKd6Sgjk8IV3RW1U/BD6ssO0Pfs+XA8dVPM4YU7n3F2/jt68vZEiX5jx/1WBLCiYgbHkmY6LUFyt2cvu0haR3as4LVw+26iMTMF4X6hlexVsKFADrVHVvwKIyxlRr7sa9/N/k+fRp15hJ1w6mUWJIb/5NHef1t+lrnCQAUDbJiv9rn4i8C1ypqgcCF54xpqKVO/Zz/Utzad+sAS9eM5hkSwomwLxWJZ2F02B8BXCE+7gCWAaMch/9gUcDH6IxpsyWvflc9cKPNEyI45XrhtAiOTHcIZk6yOtXjT8Dt6vqF37b1otIFjBBVQeJSCnwT+DWQAdpjIGs3EKufGEOhSU+3rjpGNKaNQx3SKaO8nrH0JtfDkbD3VY2Ed4SoE0ggjLGlJdfVMJ1L81l5/5CJl0zmB6tU8IdkqnDvCaG5cADIvLTfav7/H73PXBGNe8IbHjGmFKfcvu0hSzblsO/Lhtg6zOboPNalfR/wHvAVhFZ6m7rC/iAs93XXbFpso0JuEc+XMFny3fy8K97c0qv1uEOx9QDXmdXnSMiXXAanHu6m6cAU1Q1z93nleCEaEz99ersTTz//QauObYz1xzXJdzhmHrCcz83txvqM0GMxRjj56tVu3jonaWc2qsVvz+74ppWxgSP58QgImk4K7a1okLbhKo+EeC4jKnXVmzfz9jJ8+nVtjH/uGQAsTG2RrMJHa8jny8HJgElOLOd+k9sp4AlBmMCZO+BIka/nEFKUjwvXG2jmk3oef2NGw/8Dfi9qpYGMR5j6rWSUh+3TJ5PVl4hb9x4DG2aJIU7JFMPee2u2hp43pKCMcH11w9X8sP6PTxy/lEc3aFpuMMx9ZTXxPAhv1yf2RgTQDPmZTJp1gauPa4zowalhTscU495rUr6DJggIn1wRjgX+7+pqjMDHZgx9cnizH3c99YSjunagvvP7BXucEw95zUxlHVTvb+S9xSwieCNqaWs3EJufHUeqcmJ/OuyAcTH2jIpJry8DnCz31RjgqCk1MctU+aTnV/Emzcda7Olmohg/eCMCaPHPl3Fjxv28veLj6Zv+ybhDscYoJrEICLjgH+raoH7vEo2wM2Ymvts+U6e+WY9lw7pyPkDrLHZRI7q7hhuBV7GWbqzujUWbICbMTW0ZW8+d05fSJ92jXno1zbdhYksVSYGVe1S2XNjzOEpLCnllinzUeDflw8kKd76bpjIUutGZRGJD2QgxtQXf/lgBYszc3jsgqPp1KJRuMMx5hc8JQYRuU1ERvm9ngQcFJFVItKzmkONMX7eW7SNV37YxOjjuzCyry14aCKT1zuG23Amz0NEhgMXApcBC3HmUDLGHML6rDx+N2Mxgzo1494zjgx3OMZUyWt31fbABvf5r4E3VHW6iCwBvgtKZMbUIYUlpdw6dQHxcTH881IbxGYim9ffzv046zAAnAZ84T4vBmz6R2MO4bGPV7Fs234mjupHu6YNwh2OMdXyesfwKfCciMwHjgA+crf34ec7CWNMJb5etYvnv9/AlcM68as+1q5gIp/XO4ZbgFlAKnCBqu51tw8EpgYjMGPqgqzcQu56YxE9W6fwwFk2OZ6JDl7nStpPJYPcVPWhgEdkTB3h8yl3vrGI3IISptwwzMYrmKjhtbtqb/9uqSJymoi8JiL3iYjn33YRGel2cV0rIr+rYp+LRGS5iCwTkSlez21MpJk0awPfrs7i92f3pkfrlHCHY4xnXquSJgEDAESkA/AO0ByniunPXk7gJpCngTOA3sClItK7wj7dgfuA41S1D3CHx/iMiShLMnOY8PFKTu/TmsuHdgx3OMbUiNfEcCQw331+ATBHVc8ErgQu9XiOIcBaVV2vqkXANODcCvvcADytqtkAqrrL47mNiRgHCku4bdoCWiYnMmFUP0Qk3CEZUyNeE0MsUOQ+PwVnqU+AdTjrQXvRHtji9zrT3eavB9BDRGaJyGwRGVnZiURkjIhkiEhGVlaWx+KNCY3x7y1n054D/P3i/jRtmBDucIypMa+JYSlws4icgJMYPna3twd2BzCeOKA7cCLOnchzItK04k6q+qyqpqtqempqagCLN+bwfLZ8J69nbOHmE7sxrGuLcIdjTK14TQz34lTzfA1MVdUl7vZzgB89nmMr0MHvdZq7zV8m8K6qFqvqBmA1TqIwJuLtySvkvpmL6d22Mbef0iPc4RhTa167q34rIqlA47L6f9czQL7HsuYC3UWkC05CuARnviV/b+PcKbwoIi1xqpbWezy/MWGjqtz/1hL2Hyxh8uj+JMTZlBcmenn+7VXV0gpJAVXd6LWBWFVLgLHAJ8AKYLqqLhOR8SJyjrvbJ8AeEVkOfAXcrap7vMZoTLjMmL+VT5bt5O7Te9KzjXVNNdFNVNXbjiIn4Xyb7wiUa1FT1ZMDH5o36enpmpGREa7ijSEzO58znvyOXu0aM/WGYcTGWC8kE/lEZJ6qplf2ntcBbtfgzI+UgtMwnAU0w5kSY3lAojQmCvl8yt1vLManyt8uPNqSgqkTvFYl3QWMVdVLcWZUvU9VBwCvAXnBCs6YSPfi/zbyw/o9PPTrPnRo3jDc4RgTEF4TQ1fgc/d5IZDsPv8XcE2AYzImKqzZmcuEj1dyaq/WXJieFu5wjAkYr4lhD041Ejg9ivq6z1sANrm8qXeKS338dvpCkhPjeOQ3R9noZlOneF2P4TvgV8ASYDrwlIichjPY7bMgxWZMxPrnF2tYunU//71iEKkpieEOx5iA8poYxvLzSm2PACXAcThJwtMkesbUFQs2Z/P01+sYNTCNkX1t4R1T93gd4LbX77kPmBC0iIyJYAeLSrlz+iLaNE7ioXN6H/oAY6KQ1zsGRCQJZ6Ry2f+G5TjTYxwMRmDGRKJHP1rB+t0HmHLDUBonxYc7HGOCwus4hoE4M6n+DWf67CHA48B69z1j6rzv1mTx8g+buO64LhzbrWW4wzEmaLz2SnoWZ83nNFUdrqrDcSbE+9Z9z5g6LSe/mLvfWMwRrZK5Z2TPQx9gTBTzWpXUB7hKVQ+UbVDVAyIyHrD5KEyd99C7S9mdV8hzV6Xb2s2mzvN6x7ASaFfJ9rY4U2MbU2d9sHg7by/cxm2ndOeotCbhDseYoPN6x/AgztiF8cBsd9swd/vvRKR52Y7+PZiMiXa79hfwwNtLOLpDU/7vxG7hDseYkPCaGN5zf04ByqZjLRvq+Y7fa8VZBtSYqKeq3DNjMQXFpTxx0dHExdoaC6Z+8JoYTgpqFMZEoKk/buHrVVn88Zw+dEtNPvQBxtQRXge4fRPsQIyJJJv2HODPHyzn+CNacuWwTuEOx5iQsntjYyoo9Snjpi8iNkZ47MJ+xNgaC6ae8Tzy2Zj64plv1zFvUzZPXtyftk1s8mBT/9gdgzF+lm/bz98/W81ZR7Xl3P6V9dA2pu6rMjGIyHARsTsKU28UlpQybvpCmjZM4E/n9bU1Fky9Vd0dw1dAcwARWS8iLUITkjHh8cSnq1m5I5eJo/rRvFFCuMMxJmyqSwzZQBf3eedD7GtMVJu9fg/Pfreey4Z25KQjW4U7HGPCqrqqohnANyKyHWfgWoaIlFa2o6p2DUZwxoRCbkExd05fRMfmDXngzF7hDseYsKsuMdwEvAt0B54AXgRyQxGUMaE0/r3lbM85yBs3HUujRGtWM6bK/wWqqsAHACJyNPA3VbXEYOqUT5bt4I15mdxyUjcGdWoW7nCMiQheRz5fCz+t4nYETtXSOlUtCGJsxgRVVm4h981cQp92jbn9lB7hDseYiOF1Bbc4EXkMp0F6EbAEyBaRiSJi6xuaqKOq3DdzMXmFJTx5cX8S4qxvhTFlvFaoTgQuxWl3+N7ddgLwCE5yuSvwoRkTPNMztvD5il08eFYvurdOCXc4xkQUr4nhMuA6Vf3Qb9s6EckCnscSg4kim/fkM/695RzTtQXXHdfl0AcYU894vX9uAqyrZPs6oGnAojEmyJwJ8hYSI8LjFx1tE+QZUwmviWERcFsl228HFgYsGmOC7Nlv15OxKZs/ntuH9k1tgjxjKuM1MdwDXC0iq0TkZfexCrgCuNtrYSIy0j3HWhH5XTX7jRIRFZF0r+c25lCWbs3hic9WcUbfNpw/oH24wzEmYnlKDKr6LdADeBNIdh9vAD1V9fvqji0jIrHA08AZQG/gUhHpXcl+KTh3InO8nNcYL/KLSrht6gJaNErkr+cfZRPkGVMNz8M8VXUb8MBhlDUEWKuq6wFEZBpwLrC8wn5/AiZQgzsRYw5l/HvL2bDnAJNHD6WZTZBnTLVC2Xm7PbDF73Wmu+0nIjIQ6KCqH1R3IhEZIyIZIpKRlZUV+EhNnfLRku1Mm7uFm0Z049huLcMdjjERL2JG9YhIDM6cTHceal9VfVZV01U1PTU1NfjBmai1bd9BfjdzCUenNWHcaTa62RgvQpkYtgId/F6nudvKpAB9ga9FZCMwDHjXGqBNbZX6lN++vpDiUh//uGQA8bER8z3ImIgWyv8pc4HuItJFRBKAS3BmbwVAVXNUtaWqdlbVzsBs4BxVzQhhjKYO+e8365izYS9/PKcPnVs2Cnc4xkQNr3Ml3SEizQ+nIFUtAcYCnwArgOmqukxExovIOYdzbmMqWrA5myc+W83Z/dpywaC0cIdjTFQRZ3btQ+wksglojfMN/3lV/TTYgXmVnp6uGRl2U2F+lldYwpn/+I5Sn/Lh7SfQpIHN82hMRSIyT1Urrar3WpXUGadrqQ94R0Q2ud/0OwcmRGMCQ1W5f+YSMrPzefKS/pYUjKkFrwPcVFU/UdVLcLqYPg6cDawVkc9E5BJ3AJsxYTX1xy28u2gb407rweDOh1X7aUy9VePGZ1XdC8wDFgAlQBecEc0bReSUwIZnjHfLtuXw8HvLOKF7S/7vxCPCHY4xUctzYhCR1iJyj4isAD4HEoGRqnoEzl3EK8Ck4IRpTPVyC4oZO2UBzRrG8+TF/W3WVGMOg9deSe/hjFq+EvgP0F5Vr1DVrwHcJT7/QflxCsaEhLMa2xI27TnAPy8dSIvkxHCHZExU8zpX0i5guKrOrmafLJxqJWNCavKczby/eDt3n96TIV2sXcGYw+W1KukbnDaFckQkQUSugp8aqDcFMjhjDmXp1hzGv7+cET1SuXlEt3CHY0yd4DUxvIiziltFKe57xoRcTn4xt0yZT/OGCTxhq7EZEzBeq5IEqGwkXEcgJ3DhGOONz6fc8foCtu07yLQxw6xdwZgAqjYxiMgSnISgwDciUuL3dizQCfgweOEZU7knP1/NV6uy+NN5fRnUydoVjAmkQ90xvOn+7At8AOT5vVcEbARmBD4sY6r22fKdPPXlWi4YlMYVQzuGOxxj6pxqE4Oq/hHAnQb7dbdbqjFhsy4rj3GvL+So9k3483l9bYlOY4LAUxuDqr4c7ECMOZS8whJuenUe8XEx/PfKQSTF2ywsxgRDlYlBRPYDXVV1t4jkUnnjMwCq2jgYwRlTxudT7pq+iHVZebx2/VDaN20Q7pCMqbOqu2O4Fcj1e37o+bmNCZInPlvNx8t28OBZvTj2CFu32ZhgqjIx+FcfqepLIYnGmEq8vWAr//pqLZcM7sD1x9vgemOCzRbBNRFt3qZs7pmxmKFdmjP+XGtsNiYUqmtjqLZdwZ+1MZhgyMzO58ZXM2jbJIn/XjGIhDj7HmNMKFTXxjA2ZFEYU0FeYQmjX86gsMTHtDHpNGuUEO6QjKk3PLUxGBNKxaU+bn5tHmt25THpmsEc0Sol3CEZU6/YvbmJKKrKvTMW892a3fz1/L6M6JEa7pCMqXdsHIOJKI9/uoqZ87fy21N7cPFgm+7CmHDwOo7B2htM0L36w0ae/modlw7pwG2n2JrNxoSL13EM1t5ggurjpTv4w7vLOOXIVvzJuqUaE1Ze12MAQEROBnq7L5er6peBD8nUN7PW7ua2aQs4Oq0p/7xsAHGx1vRlTDh5Sgwi0gVneu1+wDZ3czt3vYZRqro+SPGZOi5j415Gv5xB15aNeOnawTRMqNF3FWNMEHj9avYCTntDV1XtqKodga7APuD5IMVm6rilW3O49sW5tGmSxKvXD6VpQxurYEwk8Pr17BhgmKpuLtugqptF5LfAD0GJzNRpq3fmcuULc2jcIJ7Jo4eSmmJLcxoTKbzeMWwGKpvnOAnYErhwTH2wLiuPK56fQ1xsDJNHD6WdTaFtTETxmhjuBJ4SkWEiEisiMSIyDHjSfc8YT9bszOXiZ2bjU2Xy6KF0btko3CEZYyqoySR6ScAswOe+jgFKgcmApwFuIjIS+AcQCzyvqo9WeH8cMBooAbKA61R1k6crMRFv5Y79XP7cHGJihKk3DLOpLoyJUCGbRE9EYoGngdOATGCuiLyrqsv9dlsApKtqvojcDEwELg5kHCY8lm3L4Yrn55AYF8uUG4bSNTU53CEZY6oQykn0hgBry7q2isg04Fzgp8Sgql/57T8buCLAMZgwWLhlH1dP+pHkxDim3DCUTi2s+siYSFbjTuMi0gYo16/Qv7dSNdpTvqE6Exhazf7XAx9VEcMYYAxAx442n04k+2Z1Fje/No+WyYlMHj2UDs0bhjskY8wheB3g1gR4CriICknBFRvIoETkCiAdGFHZ+6r6LPAsQHp6uq1FHaHeXrCVu95YRI/WKbx03WBapSSFOyRjjAdeeyU9DhwNnAcUAJcBd+N86/faBrAV6OD3Os3dVo6InAo8AJyjqoUez20izAvfb+CO1xeS3rkZ024cZknBmCjitSrpDOBSVf1OREqBear6uohsB24E3vRwjrlAd3d6ja3AJTgJ5iciMgB4Bhipqru8XoSJHKU+5dGPVvDcdxs4o28b/n5xf5LiA3pDaYwJMq93DE2Bsm6jOUAL9/kPwLFeTqCqJTg9nT4BVgDTVXWZiIwXkXPc3R4DkoE3RGShiLzrMT4TAfIKS7jx1Xk8990GrjqmE/+6bKAlBWOikNc7hnU4cyNtxvmjfomI/Aj8BtjrtTBV/RD4sMK2P/g9P9XruUxkyczOZ/TLGazZlcf4c/tw1TGdwx2SMaaWvCaGl3BmVv0aeBR4H+fbfwxwezACM9Fj/uZsxrySQWGxjxevGcxwW47TmKjmKTGo6t/9nn8pIr2AQcAaVV0SrOBMZFNVXpuzmT+9t5w2TZKYNibdRjMbUwfUavJ7d5oKm6qiHssvKuH+mUt4e+E2RvRI5cmL+9OskU2bbUxd4DkxiMh5wDh+XsFtBfCEqr4VhLhMBFuXlcfNr81jza48xp3Wg7EnHUFMjC3FaUxd4XWA253AX4FXcNobwFmjYYqI/F5VHw9OeCaSqCoz5m/loXeWkhAXwyvXDeGE7taeYExd4/WO4S5grKo+57dtktszaTzOADhTh+3LL+L+t5bw4ZIdDOncnCcv6W/rKBhTR3lNDMnAV5Vs/8p9z9Rh36/ZzZ1vLGRPXhH3jOzJjcO7EWtVR8bUWV4Tw9vABThdVf2NAmwQWh2VV1jCYx+v5OUfNtE1tREvXD2Yvu2bhDssY0yQVbdQzzi/l2uB34nISfy8xvMw9/FE8MIz4fLlyp088NZSduwv4JpjO3PvyCNpkGCjmI2pD6q7Y7i1wutsoIf78N92DU47g6kDducV8sf3lvPeom30aJ3M05cfy8COzcIdljEmhKpbqKdLKAMx4VVc6uOVHzbx5OerKSz2Me60Htw0ohsJcV6n0zLG1BW1WagnGVBVPRCEeEwYfLs6i/HvL2ftrjyG90jlD2f35ohW1qfAmPqqJgPcbgHuxVmJDRHJBCao6r+DFJsJstU7c5n48So+X7GTTi0a8vxV6ZzSqxUi1uPImPrM6wC3+4H7cMYrfO9uPgF4VEQaq2rF3komgm3ek8+Tn6/mrYVbSU6I456RPbn++C4kxlnjsjHG+x3DTcAYVZ3qt+0LEVmDMyLaEkMU2JFTwNNfrWXa3M3EiDDmhK7cNKKbzXFkjCnHa2JohbMCW0U/Aq0DF44JhvVZeTzzzXpmLshEFS4Z0oFbT+5O68a23KYx5pe8JobVOMtwVuyWehmwKqARmYBZkpnDf75Zy0dLd5AQG8MlgzsyZnhXOjRvGO7QjDERzGtieBiYLiLDgVnutuOAEcCFQYjL1FJRiY+Plm7nlR82MW9TNimJcdw8ohvXHteF1JTEcIdnjIkCXhfqmSkiQ3Cm3T7b3bwCGKKqC4IVnPFue85BpszZzNQft7A7r5DOLRry4Fm9uGhwBxonxYc7PGNMFDlkYhCReOA14H5VvSL4IRmvDhaV8smyHcyYn8mstbtR4OSerbjymE4M755qayQYY2rlkIlBVYtF5Fc43VVNmJX6lB837GXm/Ew+XLKdA0WltG/agLEnHcEFgzrQsYW1HxhjDo/XNoaZwG+wdRfCorjUxw/r9vDR0h18tnwHu/OKaJQQy5lHtWXUoDSGdG5udwfGmIDxmhg2Aw+KyAlABlBuOgxVtRlWA2xffhHfr93Nlyt38fnynewvKKFhQiwnHdmKkX3acGqv1jbbqTEmKLwmhmtwZlLt5z78KTb19mEr9SmLM/fxzeosvlmdxaIt+/ApNGkQz6m9W3NG37ac0L0lSfGWDIwxweW1V5LNtBpghSWlLMnM4ceNe5m7YS8Zm7LJLShBBPqlNWXsyd0Z0SOVo9OaEBdrM5waY0KntrOroqp5gQ+nblJVtucUsGRrDosz95GxMZuFW/ZRWOIDoFtqI87u145hXZszvHuqTVFhjAmrmsyuegfOOIay2VW34VQhPamqGpToopDPp2zdd5CVO3JZsjWHJZn7WLI1h915RQDExgi92zbmimGdGNy5OYM7N6NFsg08M8ZEDq+zq04ExgCP8fPSnscAfwDaAvcEJboI5vMp23IOsmZnHqt35rJ6Zx5rduWydlce+UWlAMQIdG+Vwok9W3FU+yYcldaE3m0bWzuBMSaieb1jGA2MVtU3/bZ9KSKrgGeoo4mhoLiUzOx8Nu1xHpv35rNpzwE27c0nc+9Bikp9P+3bKiWRHq1TuHhwB7q3SqFnm2R6tW1Mw4Qa19YZY0xY1eSv1uIqtkVly+jBolK27jvIjpwCtue4P/cXsCPHfewvYO+BonLHNEqIpWOLRvRolcJpvVrTqUUjurdOpnurZJo2tHYBY0zd4DUxvALcAtxeYfvNwKsBjShEJs3awGOflJ8YtnmjBNo0TqJtkyQGdGxKm8ZJdGjekA7NG9KpRUNaNEqw1c2MMXWe18SQCFwmIqcDs91tQ4F2wGQReapsR1W9raqTiMhI4B9ALPB8xZXfRCQRJwkNAvYAF6vqRo8x1sipvVqT1qyBmwga0KpxYlDq/vfkFZKZfZC0Zg08NTLXdP9QHROpcdVGXSkjlOWY+sVrYjgSmO8+7+T+3OE+evntV2XvJBGJBZ4GTgMygbki8q6qLvfb7XogW1WPEJFLgAnAxR5jrJGebVLo2SYlGKf+yTsLt3LvjMXEx8RQ7PMxcVQ/zunfPmD7h+qYSI2rNupKGaEsx9Q/EqqepiJyDPCwqp7uvr4PQFUf8dvnE3efH0QkDifxpFbXHTY9PV0zMjKCG3wt7Mkr5LgJX1JQ/HMDdVJ8DLPuPbnSb3Y13T9Ux0RqXLVRV8oIZTmm7hKReaqaXtl7oWw4bg9s8Xud6W6rdB9VLQFygBYVTyQiY0QkQ0QysrKyghTu4cnMPkh8TPmPNz4mhszsgwHZP1THRGpctVFXyghlOaZ+isoeRar6rKqmq2p6ampquMOpVFqzBhT7fOW2Fft8pDVrEJD9Q3VMpMZVG3WljFCWY+qnUCaGrUAHv9dp7rZK93GrkprgNEJHnRbJiUwc1Y+k+BhSEuNIio9h4qh+Vd7m13T/UB0TqXHVRl0pI5TlmPoplG0MccBq4BScBDAXuExVl/ntcwtwlKre5DY+/0ZVL6ruvJHaxlCmrvT+idS4aqOulBHKckzdU10bQ8gSgxvImcCTON1VJ6nqX0RkPJChqu+KSBLOuIgBwF7gElVdX905Iz0xGGNMJKouMYR0vgZV/RD4sMK2P/g9LwAuDGVMxhhjyovKxmdjjDHBY4nBGGNMOZYYjDHGlGOJwRhjTDkh7ZUUDCKSBWyq5eEtgd0BDCec7FoiT125DrBriVSHcy2dVLXSEcJRnxgOh4hkVNVdK9rYtUSeunIdYNcSqYJ1LVaVZIwxphxLDMYYY8qp74nh2XAHEEB2LZGnrlwH2LVEqqBcS71uYzDGGPNL9f2OwRhjTAWWGIwxxpRTbxODiIwUkVUislZEfhfueGpLRCaJyC4RWRruWA6HiHQQka9EZLmILBOR28MdU22JSJKI/Cgii9xr+WO4YzpcIhIrIgtE5P1wx3I4RGSjiCwRkYUiErXTMotIUxF5U0RWisgKd+nkwJ2/PrYxiEgsztoQp+EsMToXuFRVl4c1sFoQkeFAHvCKqvYNdzy1JSJtgbaqOl9EUoB5wHlR+m8iQCNVzROReOB74HZVnR3m0GpNRMYB6UBjVT073PHUlohsBNJVNaoHuInIy8B3qvq8iCQADVV1X6DOX1/vGIYAa1V1vaoWAdOAc8McU62o6rc4a1dENVXdrqrz3ee5wAp+uSZ4VFBHnvsy3n1E7TcwEUkDzgKeD3csBkSkCTAceAFAVYsCmRSg/iaG9sAWv9eZROkfobpIRDrjLNY0J8yh1Jpb9bIQ2AV8pqpRey04i2vdA/gOsV80UOBTEZknImPCHUwtdQGygBfd6r3nRaRRIAuor4nBRCgRSQZmAHeo6v5wx1Nbqlqqqv1x1jYfIiJRWc0nImcDu1R1XrhjCZDjVXUgcAZwi1sVG23igIHAf1R1AHAACGg7aX1NDFuBDn6v09xtJozc+vgZwGRVnRnueALBvcX/ChgZ5lBq6zjgHLdufhpwsoi8Ft6Qak9Vt7o/dwFv4VQrR5tMINPvLvRNnEQRMPU1McwFuotIF7fh5hLg3TDHVK+5DbYvACtU9Ylwx3M4RCRVRJq6zxvgdHJYGdagaklV71PVNFXtjPP/5EtVvSLMYdWKiDRyOzbgVr38Coi63nyqugPYIiI93U2nAAHtpBHSNZ8jhaqWiMhY4BMgFpikqsvCHFatiMhU4ESgpYhkAg+p6gvhjapWjgOuBJa4dfMA97vrhEebtsDLbu+3GGC6qkZ1N886ojXwlvMdhDhgiqp+HN6Qau1WYLL7xXY9cG0gT14vu6saY4ypWn2tSjLGGFMFSwzGGGPKscRgjDGmHEsMxhhjyrHEYIwxphxLDKbeEJETRURFpGWYyt8oIneFodzO7nUf1qLx4YrfhJ4lBlMnVfFH7H84Ywz2BLnsh6uYBn0w8O9gll2FLTjXvTAMZZsoVC8HuJnaE5EEd0bacJUfr6rFtTnWjXtHgEOqSflZYSq3lDBe9+ESkTigVG3QVcjYHUM9JiJfi8h/ReQfIpLtPh4TkRi/fTa634Anicg+YLK7/VgR+UZE8kVkq4j8R0Qa1/DcV4jIXBHJdRcbekNE2vu9X1b1c6a78E0RcLqIdBORd0Rkh4gcEJH57mRvP5UNdAIec4/XCudr6bfvb9yFWwpFZIuIPOBOz+F//Q+KyDMisl9EMkXk7mo+02uAh4A+ZWW7235xF+O+d7N7LfkislpEThKRNBH5xL22hSIysEIZ1X72lcRUrirJ73M4RUTmuOfJqFhOFZKq+yxEpKOIvOX+m+aKyExxpu0ue/8Xd1Mico2I5FXcx92+DigEGonIcBGZLSJ5IpLj/k5E5eSEkc4Sg7kc5/fgGOBGYAxwR4V9xuHM9ZMO3C8iRwGf4swvdTTwG6A/MKmG507A+SN6NHA20BKYWkmME4AHgSNxpuJOBj7CmYPoaJyJ92aKyJHu/r/BmWhsPE4VStvKLlxEBgFvADOBo3BmqLwPGFth198CS3AmKpsATJSqV8x6HfgbsMqv7Ner2Bf3uqa515HhPn8Bp8ppALANeMkvZq+fvReP4FzzQJzqtcn+SbEKVX4WbtJ/B2fqiZPcRzvgbQ/nragLcBlwIc51Frjn/t59PRRnOvDSGp7XeKGq9qinD+BrnJXsxG/bgzgzN5a93gi8V+G4V4AXKmzrjzPXfSuv564kniPdc6S5r090X4/ycC2zgQcrxH1XhX3KztfSfT0ZZ1I4/30eruT6p1bYZ41/WZXE8jCwtJLt5WJyY3nE73Vfd9u4amI+5GdfSbmd3ffTK5zzdL99jvP/7Ks4T7WfBU6iLgU6+73fFWcdh1Or+myAa4C8Cp9fMdDab1tzN74R4f5/Ux8edsdgZqv7P8/1A9C+QtVExbVxBwFXuLf0eW41wCz3vW5ezy0iA91qlE0ikutXTscK5ZUrX5xZMieKsz50tlt+eiXHHUovv7jLfM8vr39xhX22Aa1qWFZV/M+90/25pJJtZeV5/exrWva2CuV4OabsuLJjegHbVHVj2Zuqut7dp3cNY8tU1bJrR1X34tw5fSIiH4jIOBGp6b+38cgan40XByq8jsFZ5vHvlezraV0LcaY9/gT4HGdW1V04VUnf4VQxVVf+4zjrG9yF8401H+ebdMXjDod/QqvY2K0ErhrW/9xazbYYv5+H9dkfouxDXVdtP4uy8/uAitVK8ZXsX/HfHFW9VkSexPm3Pwf4i4icp6qfeCjf1IAlBjNURMTvm/0wnG991a2eNh/oo6pra3tut36/Jc7U2hvAaQj2GPPxwCuqOsM9Lgnn2/Jqv32KcKZUr84KnCqUiufOVGfd6dryUnZtef3sw2EF0E5EOpfdNYhIV5x2hrL1ArKA1hV+L/p7LUBVFwGLgAki8hFwNc4XDBNAVpVk2gFPikhPEbkAuJvKv436m4CzXOV/RWSAiBwhImeLyDM1OPdmnN4mY0Wkq4icBfzJY8yrgfPdqqijgNeApAr7bAROEJH2UvWAtr8BI9xeMD1E5HLgTmCixziqshHo5MbXUkQSD/N8/rx+9uHwOU5V02QRSXd7QU3GSWZfuvt8jdNecL84vcuuBy441InFWVTrUbdHVicROQnoR4AXqDEOSwxmMs632znAczg9YqpNDKq6GBiO06j5Dc43uEf4uT78kOdWp0//1cB5OP+5H8Lp/eTFOJyqp+9weifNdp/7+wPO8q3rcL6lVnYd83F6vYzCWcnrUffxL49xVGUG8CHwhVv2pYd5vp/U4LMPOfcO4Fyca/7KfewAziu7O1DVFcDNOD3UFuM0WP/Vw+nzgR44vchWAy/j/H5NCOxVGLCFeuo1cfr7L1XVit0zI/rcxpjgsjsGY4wx5VhiMMYYU45VJRljjCnH7hiMMcaUY4nBGGNMOZYYjDHGlGOJwRhjTDmWGIwxxpTz/1k1xTfrWV7oAAAAAElFTkSuQmCC\n",
|
|
"text/plain": [
|
|
"<Figure size 432x288 with 1 Axes>"
|
|
]
|
|
},
|
|
"metadata": {
|
|
"needs_background": "light"
|
|
},
|
|
"output_type": "display_data"
|
|
}
|
|
],
|
|
"source": [
|
|
"df.plot.scatter(x='hours_studied', y='passed')\n",
|
|
"plt.plot(hours_studied, y_pred[:,1])\n",
|
|
"plt.xlabel(\"preparation time in hours\", fontsize=14)\n",
|
|
"plt.ylabel(\"probability of passing exam\", fontsize=14)\n",
|
|
"plt.savefig(\"03_ml_basics_logistic_regression.pdf\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"{'C': 1.0,\n",
|
|
" 'class_weight': None,\n",
|
|
" 'dual': False,\n",
|
|
" 'fit_intercept': True,\n",
|
|
" 'intercept_scaling': 1,\n",
|
|
" 'l1_ratio': None,\n",
|
|
" 'max_iter': 100,\n",
|
|
" 'multi_class': 'auto',\n",
|
|
" 'n_jobs': None,\n",
|
|
" 'penalty': 'none',\n",
|
|
" 'random_state': None,\n",
|
|
" 'solver': 'lbfgs',\n",
|
|
" 'tol': 0.0001,\n",
|
|
" 'verbose': 0,\n",
|
|
" 'warm_start': False}"
|
|
]
|
|
},
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"clf.get_params()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Coefficient: [[1.50464522]]\n",
|
|
"Intercept: [-4.07771764]\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"print('Coefficient: ', clf.coef_)\n",
|
|
"print('Intercept: ', clf.intercept_)"
|
|
]
|
|
}
|
|
],
|
|
"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": "3.8.5"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 4
|
|
}
|