From 3f216816132af4b7f084ee1dd93111c27cfc58eb Mon Sep 17 00:00:00 2001 From: Jeremie Date: Sun, 28 Apr 2019 22:18:32 +0100 Subject: [PATCH] add: minor: nb of rows before after dropping rows with missing data --- ...ta_Preparation_(Do_we_know_our_data).ipynb | 52 +++++++++++-------- 1 file changed, 31 insertions(+), 21 deletions(-) diff --git a/notebooks/jupyter/data/02_Data_Preparation_(Do_we_know_our_data).ipynb b/notebooks/jupyter/data/02_Data_Preparation_(Do_we_know_our_data).ipynb index 860e00b5..1cc611b8 100644 --- a/notebooks/jupyter/data/02_Data_Preparation_(Do_we_know_our_data).ipynb +++ b/notebooks/jupyter/data/02_Data_Preparation_(Do_we_know_our_data).ipynb @@ -79,7 +79,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 92, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -134,7 +134,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 93, "metadata": {}, "outputs": [], "source": [ @@ -172,7 +172,7 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 94, "metadata": {}, "outputs": [ { @@ -268,7 +268,7 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 95, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -283,7 +283,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Dataset rows count before dropping duplicates: 606\n", + "Dataset rows count BEFORE dropping duplicates: 606\n", "Duplicated rows count: 50\n", "% of duplicated rows to total rows in the dataset: 8.25082508250825\n", "\n" @@ -304,13 +304,13 @@ "output_type": "stream", "text": [ "50 rows deleted\n", - "Dataset rows count after dropping duplicates: 556\n" + "Dataset rows count AFTER dropping duplicates: 556\n" ] } ], "source": [ "total_rows_count = data.shape[0]\n", - "print(\"Dataset rows count before dropping duplicates:\", total_rows_count)\n", + "print(\"Dataset rows count BEFORE dropping duplicates:\", total_rows_count)\n", "\n", "duplicated_rows_count = data[data.duplicated()].shape[0]\n", "print(\"Duplicated rows count:\", duplicated_rows_count)\n", @@ -330,7 +330,7 @@ " print(duplicated_rows_count, \"rows deleted\")\n", "\n", "# Check the dataset after deletion\n", - "print(\"Dataset rows count after dropping duplicates:\", data.shape[0])" + "print(\"Dataset rows count AFTER dropping duplicates:\", data.shape[0])" ] }, { @@ -352,7 +352,7 @@ }, { "cell_type": "code", - "execution_count": 58, + "execution_count": 96, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -368,16 +368,16 @@ "output_type": "stream", "text": [ "\n", - "count 506.000000\n", - "mean 6.284634\n", - "std 0.702617\n", + "count 556.000000\n", + "mean 6.291450\n", + "std 0.708056\n", "min 3.561000\n", - "25% 5.885500\n", - "50% 6.208500\n", - "75% 6.623500\n", + "25% 5.887750\n", + "50% 6.211000\n", + "75% 6.630250\n", "max 8.780000\n", "Name: rm, dtype: float64\n", - "Number of outliers in the Room column (< mean - 2 std dev OR > mean + 2 std dev): 31\n" + "Number of outliers in the Room column (< mean - 2 std dev OR > mean + 2 std dev): 34\n" ] } ], @@ -392,7 +392,7 @@ }, { "cell_type": "code", - "execution_count": 59, + "execution_count": 97, "metadata": {}, "outputs": [ { @@ -404,7 +404,7 @@ }, { "data": { - "image/png": "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\n", + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAEBCAYAAAB2RW6SAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvnQurowAAFT1JREFUeJzt3X9MVff9x/HXvRe5/ih4vVfUK7piyWxu16xGSUy2NSa4TbOgLusfZaRrsrVptm6GpsXKbAcMq+aC7UpnXbvMLHExNTNWGbSRbqFbommcpmULZVsXxjoar4CXMoEK6L33+4dfWX8o9wf3cC6f+3z8Jfdwz31/7o8Xx/c9n89xxGKxmAAAxnLaXQAAwFoEPQAYjqAHAMMR9ABgOIIeAAxH0AOA4Qh6ADAcQQ8AhiPoAcBwBD0AGI6gBwDD5STyS+Pj49q7d6/eeustud1urVmzRrt371ZPT4+qq6s1NDQkj8ejYDCooqIii0sGACTDkciiZs8884ycTqd+/OMfy+Fw6NKlS1q8eLEefPBB3Xfffdq2bZuam5t1/PhxHT58eCbqBgAkKG7Qj46OasOGDfrTn/6kBQsWTN4eDoe1adMmnT17Vi6XS5FIROvXr9cbb7whr9ebcAEffjiqaDRzF9D0+W5TODxidxmWY5xmyZZxStkz1hvjdDodWrRoQfw7fEzc1k1vb688Ho8OHDigs2fPasGCBaqsrNTcuXO1dOlSuVwuSZLL5dKSJUsUCoWSCvpoNJbRQS8p4+tLF8ZplmwZp5Q9Y011nHGDPhKJqLe3V3fddZd27typv/zlL/r+97+vpqamlB7w03y+29KyHysVFOTZXcKMYJxmyZZxStkz1lTHGTfo/X6/cnJyVFZWJkm65557tGjRIs2dO1d9fX2KRCKTrZv+/n75/f6kCgiHRzL6r3FBQZ4GBobtLsNyjNMs2TJOKXvGemOcTqcj6QPkuKdXer1erV+/XmfOnJEk9fT0KBwOq6ioSIFAQK2trZKk1tZWBQKBpNo2AADrJXTWTW9vr3bt2qWhoSHl5OToscce04YNG9Td3a3q6mpdvnxZ+fn5CgaDuuOOO5IqgCP6zMA4zZIt45SyZ6zTOaJP6Dz6lStX6je/+c1nbi8uLtaxY8eSekAAwMxiZiwAGI6gBwDDJdS6AWajvPx5muv+7Fu8oCBPY+PXNHz5ig1VATOPoIex5rpztOWJ5ptua3l2m8z/+g64jtYNABiOoAcAw9G6QVaauBqZcjo5PXyYhKBHVsqd47pl/16ihw+z0LoBAMMR9ABgOIIeAAxH0AOA4Qh6ADAcQQ8AhiPoAcBwBD0AGI4JU0AKbrUypsSsWmQegh5IAStjYjahdQMAhiPoAcBwtG4wa03VJwfwP3xKMGtN1SeXrvfKAdC6AQDjEfQAYDiCHgAMR9ADgOEIegAwXEJn3ZSWlio3N1dut1uSVFVVpXvvvVcdHR2qqanR+Pi4CgsL1djYKJ/PZ2nBAIDkJHx65QsvvKDVq1dP/hyNRrVjxw7t27dPJSUlOnjwoPbv3699+/ZZUigAIDUpt246OzvldrtVUlIiSSovL9epU6fSVhgAID0SPqKvqqpSLBbTunXr9PjjjysUCmn58uWT271er6LRqIaGhuTxeCwpFgCQvISC/siRI/L7/ZqYmNCePXtUX1+vr33ta2kpwOe7LS37sVJBQZ7dJcyIbBlnoqbzfGTCc5kJNcyUbBlrquNMKOj9fr8kKTc3VxUVFfrBD36gBx98UBcuXJj8ncHBQTmdzqSP5sPhEUWjsaTuM5MKCvI0MGD+orOzcZxWf7inej7iPbbdz+VsfD1TlS1jvTFOp9OR9AFy3B79Rx99pOHh609iLBbT66+/rkAgoLvvvltjY2M6f/68JOno0aPavHlzCuUDAKwU94g+HA5r+/btikQiikajKi4uVm1trZxOpxoaGlRbW/uJ0ysBAJklbtCvXLlSJ0+evOm2tWvXqqWlJe1FAQDSh5mxAGA4gh4ADEfQA4DhCHoAMBxBDwCGI+gBwHAEPQAYjqAHAMMR9ABgOIIeAAxH0AOA4Qh6ADAcQQ8Ahkv4UoJANpm4GsmaqxbBfAQ9cBO5c1za8kTzLbe3PLttBqsBpofWDQAYjqAHAMMR9ABgOIIeAAxH0AOA4Qh6ADAcQQ8AhiPoAcBwBD0AGI6gBwDDEfQAYDiCHgAMl1TQHzhwQHfeeafee+89SVJHR4e2bt2qTZs26Xvf+57C4bAlRQIAUpdw0L/77rvq6OhQYWGhJCkajWrHjh2qqalRW1ubSkpKtH//fssKBQCkJqGgn5iYUH19verq6iZv6+zslNvtVklJiSSpvLxcp06dsqRIAEDqElqPvqmpSVu3btWKFSsmbwuFQlq+fPnkz16vV9FoVENDQ/J4PAkX4PPdlkS59siWC1BkyzhnQiY8l5lQw0zJlrGmOs64Qf/OO++os7NTVVVVKT1APOHwiKLRmCX7ToeCgjwNDAzbXYblZuM4M/nDbfdzORtfz1Rly1hvjNPpdCR9gBw36M+dO6fu7m5t3LhRknTx4kU99NBD+s53vqMLFy5M/t7g4KCcTmdSR/MAAOvF7dE/8sgjOn36tNrb29Xe3q5ly5bp0KFDevjhhzU2Nqbz589Lko4eParNmzdbXjAAIDkpXzPW6XSqoaFBtbW1Gh8fV2FhoRobG9NZGwAgDZIO+vb29sl/r127Vi0tLWktCACQXsyMBQDDEfQAYDiCHgAMR9ADgOEIegAwXMqnVwK4uYmrkSln7Y6NX9Pw5SszWBGyHUEPpFnuHJe2PNF8y+0tz26T+RP2kUlo3QCA4Qh6ADAcQQ8AhiPoAcBwBD0AGI6gBwDDEfQAYDiCHgAMR9ADgOEIegAwHEEPAIYj6AHAcAQ9ABiOoAcAwxH0AGA4gh4ADEfQA4DhCHoAMBxBDwCGI+gBwHAJXRz80Ucf1QcffCCn06n58+frJz/5iQKBgHp6elRdXa2hoSF5PB4Fg0EVFRVZXDIAIBkJBX0wGFReXp4k6Q9/+IN27dqlEydOqLa2VhUVFdq2bZuam5tVU1Ojw4cPW1owACA5CbVuboS8JI2MjMjhcCgcDqurq0tlZWWSpLKyMnV1dWlwcNCaSgEAKUnoiF6SnnrqKZ05c0axWEy/+tWvFAqFtHTpUrlcLkmSy+XSkiVLFAqF5PV6Ey7A57st+apnWEFBXvxfMkC2jDMTzMRznU2vZ7aMNdVxJhz0e/bskSSdPHlSDQ0NqqysTOkBPy0cHlE0GkvLvqxQUJCngYFhu8uw3Gwc52z+cFv9XM/G1zNV2TLWG+N0Oh1JHyAnfdbNN7/5TZ09e1bLli1TX1+fIpGIJCkSiai/v19+vz/ZXQIALBQ36EdHRxUKhSZ/bm9v18KFC+Xz+RQIBNTa2ipJam1tVSAQSKptAwCwXtzWzZUrV1RZWakrV67I6XRq4cKFeumll+RwOFRXV6fq6modPHhQ+fn5CgaDM1EzMKtNXI1M2XYaG7+m4ctXZrAimC5u0C9evFi//e1vb7qtuLhYx44dS3tRgMly57i05YnmW25veXabzO84YyYxMxYADEfQA4DhCHoAMBxBDwCGI+gBwHAJz4wFrJCXP09z3bd+G3KqITB9BD1sNdedw6mGgMVo3QCA4TiiBzLMVDNnaWUhFQQ9kGGmmjlLKwupoHUDAIYj6AHAcAQ9ABiOoAcAwxH0AGA4gh4ADEfQA4DhCHoAMBxBDwCGY2YsMlq8C2kDiI+gR0aLtxwAgPho3QCA4Qh6ADAcQQ8AhiPoAcBwBD0AGC7uWTcffvihnnzySf3nP/9Rbm6ubr/9dtXX18vr9aqjo0M1NTUaHx9XYWGhGhsb5fP5ZqJuAECC4h7ROxwOPfzww2pra1NLS4tWrlyp/fv3KxqNaseOHaqpqVFbW5tKSkq0f//+magZAJCEuEHv8Xi0fv36yZ/XrFmjCxcuqLOzU263WyUlJZKk8vJynTp1yrpKAQApSapHH41G9corr6i0tFShUEjLly+f3Ob1ehWNRjU0NJT2IgEAqUtqZuzu3bs1f/58PfDAA/r973+flgJ8vtvSsh8rZcsU/GwZ52w31es0cTWi3Dmum/7ex7eZJlveu6mOM+GgDwaDev/99/XSSy/J6XTK7/frwoULk9sHBwfldDrl8XiSKiAcHlE0GkvqPjOpoCBPAwPDdpdhObvGmS0f0HSa6nUqKMibcskIE9/L2fYZdTodSR8gJ9S6ee6559TZ2akXX3xRubm5kqS7775bY2NjOn/+vCTp6NGj2rx5c5KlAwCsFveI/p///KdefvllFRUVqby8XJK0YsUKvfjii2poaFBtbe0nTq8EAGSWuEH/+c9/Xv/4xz9uum3t2rVqaWlJe1EAgPRhZiwAGI6gBwDDEfQAYDiCHgAMR9ADgOEIegAwHBcHB2aRiasRZhMjaQQ9MIvkznHdcokD6foyB8Cn0boBAMNxRA9kiXhtn7Hxaxq+fGUGK8JMIeiBLJFI28f8NSCzE60bADAcQQ8AhiPoAcBwBD0AGI6gBwDDcdYNLJWXP09z3bzNADvxCYSl5rpzmMkJ2IzWDQAYjqAHAMMR9ABgOIIeAAxH0AOA4Qh6ADAcQQ8AhiPoAcBwBD0AGC5u0AeDQZWWlurOO+/Ue++9N3l7T0+P7r//fm3atEn333+//v3vf1tZJwAgRXGDfuPGjTpy5IgKCws/cXttba0qKirU1tamiooK1dTUWFYkACB1cYO+pKREfr//E7eFw2F1dXWprKxMklRWVqauri4NDg5aUyUAIGUp9ehDoZCWLl0ql8slSXK5XFqyZIlCoVBaiwMATJ/tq1f6fLfZXUJcBQV5dpcwI7JlnLi12foemK11JyvVcaYU9H6/X319fYpEInK5XIpEIurv7/9MiycR4fCIotFYKmXMiIKCPA0MDNtdhuWsGme2fABNMRvf69n2GXU6HUkfIKfUuvH5fAoEAmptbZUktba2KhAIyOv1prI7AICF4h7RP/PMM3rjjTd06dIlffe735XH49Frr72muro6VVdX6+DBg8rPz1cwGJyJegFYZOJqZMr/gY1PROTOdd1029j4NQ1fvmJVaZimuEH/9NNP6+mnn/7M7cXFxTp27JglRQGYeblzXHGvBnar7S3PbpP5zZPZi5mxAGA4gh4ADGf76ZWY/fLy52mum7cSkKn4dGLa5rpzpuzdArAXrRsAMBxH9FkiXntl4mpkBqsBMJMI+iwxVXtFosUCmIzWDQAYjqAHAMPRugFgq3jfH1m5vMJUj23Ssg4EPQBbJfL9kVXLK8Q7NdiUZR1o3QCA4Tiih6SpVy406b+wsAezp+3FMw9JU69caNJ/YWEPZk/bi9YNABiOoAcAw9G6AZDR4l35iuU74iPoAWS0RK58hanRugEAwxH0AGA4WjcAZrVMnQOSScsrEPQAZrVMnQOSScsr0LoBAMPN2iN6u1a8y8aV9uKd3gbwHslsszbo7VrxLhtX2uP0NsTDeySz0boBAMMR9ABguGm3bnp6elRdXa2hoSF5PB4Fg0EVFRWloTTrZGqffXwiIneuy5LHBbLRdL47iHff2bR897SDvra2VhUVFdq2bZuam5tVU1Ojw4cPp6M2y2Ryn50+J5A+0/nuIJH7zpblu6cV9OFwWF1dXfr1r38tSSorK9Pu3bs1ODgor9eb0D6cTkfKj79k0byU953MfT+9n+k8brz7x9v3VNun87hW1jWd+2ZjXVbum7rSe9/pfOZSyT6n05HS/RyxWCyW9L3+X2dnp3bu3KnXXntt8rZvfOMbamxs1Be+8IVUdwsASCO+jAUAw00r6P1+v/r6+hSJXF8POhKJqL+/X36/Py3FAQCmb1pB7/P5FAgE1NraKklqbW1VIBBIuD8PALDetHr0ktTd3a3q6mpdvnxZ+fn5CgaDuuOOO9JVHwBgmqYd9ACAzMaXsQBgOIIeAAxH0AOA4Qh6ADDcrF2PfqYcOHBAP//5z9XS0qLVq1fbXU7alZaWKjc3V263W5JUVVWle++91+aq0m98fFx79+7VW2+9JbfbrTVr1mj37t12l5V2H3zwgX74wx9O/jw8PKyRkRH9+c9/trEqa7z55ptqampSLBZTLBbTj370I33961+3u6y0++Mf/6impiZdu3ZNCxcu1L59+7Ry5cqk9kHQT+Hdd99VR0eHCgsL7S7FUi+88IKRf8Q+rrGxUW63W21tbXI4HLp06ZLdJVlixYoVam7+30Jce/bsmZzQaJJYLKYnn3xSR44c0erVq/X3v/9d3/72t/XVr35VTqc5jYr//ve/2rlzp44ePapVq1apublZdXV1OnToUFL7MecZSbOJiQnV19errq7O7lIwTaOjozp58qQqKyvlcFxfEGrx4sU2V2W9iYkJtbS06L777rO7FEs4nU4ND19fP3J4eFhLliwxKuQl6f3339fixYu1atUqSdKGDRt0+vRpDQ4OJrUfjuhvoampSVu3btWKFSvsLsVyVVVVisViWrdunR5//HHl5+fbXVJa9fb2yuPx6MCBAzp79qwWLFigyspKlZSU2F2apdrb27V06VIjFxh0OBx6/vnn9eijj2r+/PkaHR3VL3/5S7vLSrtVq1bp0qVL+utf/6ovfvGLamlpkSSFQqGkViAw689fmrzzzjvq7OxURUWF3aVY7siRI/rd736n48ePKxaLqb6+3u6S0i4Siai3t1d33XWXXn31VVVVVWn79u0aGRmxuzRLHT9+3Nij+WvXrunll1/WwYMH9eabb+oXv/iFHnvsMY2OjtpdWlrl5eXpZz/7mfbt26dvfetbCofDys/Pl8uV3AWKCPqbOHfunLq7u7Vx40aVlpbq4sWLeuihh3T69Gm7S0u7GwvQ5ebmqqKiQm+//bbNFaWf3+9XTk6OysrKJEn33HOPFi1apJ6eHpsrs05fX5/OnTunLVu22F2KJf72t7+pv79f69atkyStW7dO8+bNU3d3t82Vpd+XvvQlvfLKK3r11Vf1wAMPaGxsTJ/73OeS2gdBfxOPPPKITp8+rfb2drW3t2vZsmU6dOiQvvKVr9hdWlp99NFHkz3OWCym119/XYFAwOaq0s/r9Wr9+vU6c+aMpOuXvwyHw7r99tttrsw6J06c0IYNG7Ro0SK7S7HEsmXLdPHiRf3rX/+SdH3NrXA4nHQAzgYDAwOSpGg0queee07l5eWaP39+UvugR5/FwuGwtm/frkgkomg0quLiYtXW1tpdliV++tOfateuXQoGg8rJyVFDQ4Nx30V83IkTJ/TUU0/ZXYZlCgoKVFdX94kv2Pfu3SuPx2NzZen3/PPP6+2339bVq1f15S9/WVVVVUnvg0XNAMBwtG4AwHAEPQAYjqAHAMMR9ABgOIIeAAxH0AOA4Qh6ADAcQQ8Ahvs/fht5KhHVOQ8AAAAASUVORK5CYII=\n", "text/plain": [ "
" ] @@ -422,7 +422,7 @@ }, { "data": { - "image/png": "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\n", + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAEBCAYAAAB2RW6SAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvnQurowAAFR5JREFUeJzt3X9sE/f9x/GX7RCnhaTBxgQnoGZDa+UOqYhFQtNUTYMOos4hUacqWUY1rUVoY0LR1lCyrnMyKK2c0EntKOqkVZU6sbGhrjAHRqCLtnWs2ooK29JMa4XCoI0J4BCRAEnAvu8fFflCgfq3HX94Pv7C9p3v/eZzfnH+4LuzWZZlCQBgLHu+CwAAZBdBDwCGI+gBwHAEPQAYjqAHAMMR9ABgOIIeAAxH0AOA4Qh6ADAcQQ8AhiPoAcBwBD0AGI6gBwDDFeW7gHPnLigWy+4FNN3uWYpExrK6jXwwtS/J3N5M7Usyt7fp1pfdbtPs2TOTWifvQR+LWVkP+qvbMZGpfUnm9mZqX5K5vRV6X0zdAIDhCHoAMBxBDwCGI+gBwHAEPQAYjqAHAMMR9ABguLz/jh5mKy27QyXO1HYzj6dU4xNXNHr+UoarAm4vBD2yqsRZpLon9qS8fuj5eo1msB7gdsTUDQAYLqEj+omJCT377LN6++235XQ6tXjxYm3evFkDAwNqa2vTyMiIysvLFQwGVV1dneWSAQDJSCjou7q65HQ61dPTI5vNprNnz0qS2tvb1dzcrPr6eu3Zs0eBQECvvfZaVgsGACQn7tTNhQsXtHv3brW0tMhms0mS5syZo0gkov7+fvn9fkmS3+9Xf3+/hoeHs1sxACApcY/oT548qfLycm3btk1///vfNXPmTLW0tKikpEQVFRVyOBySJIfDoblz5yocDsvlcmW9cABAYuIGfTQa1cmTJ3Xfffdp48aN+uc//6nvfOc7euGFFzJSgNs9KyPvE4/HU5qT7eSaqX1dy7QeTevnWqb2Vuh9xQ16r9eroqKiqSma+++/X7Nnz1ZJSYmGhoYUjUblcDgUjUZ1+vRpeb3epAqIRMayfq1nj6dUZ86Y9yO9QugrEx+Q6d5jMgphzFJlam/TrS+73Zb0AXLcOXqXy6WlS5fq0KFDkqSBgQFFIhFVV1fL5/Opu7tbktTd3S2fz8e0DQBMMwn96uYnP/mJnnrqKQWDQRUVFamzs1NlZWXq6OhQW1ubtm/frrKyMgWDwWzXi9vM5OVoyt8K0jmrNp0zejmbF9NNQnvyggUL9Mtf/vKG5xcuXKhdu3ZlvCjgquIZjpTPrE3nrNp0zujlbF5MN5wZCwCGI+gBwHAEPQAYjqAHAMMR9ABgOIIeAAxH0AOA4Qh6ADAcQQ8AhiPoAcBwBD0AGI6gBwDDEfQAYDiCHgAMR9ADgOEIegAwHEEPAIYj6AHAcAQ9ABiOoAcAwxH0AGA4gh4ADEfQA4DhCHoAMBxBDwCGK0pkoWXLlqm4uFhOp1OS1NraqgceeEBHjx5VIBDQxMSEqqqq1NXVJbfbndWCgURNXo7K4ynNdxlA3iUU9JL04osv6p577pl6HIvFtGHDBj333HOqqanR9u3btXXrVj333HNZKRRIVvEMh+qe2JPSuqHn6zNcDZA/KU/d9PX1yel0qqamRpLU1NSk/fv3Z6wwAEBmJHxE39raKsuy9IUvfEE/+MEPFA6HVVlZOfW6y+VSLBbTyMiIysvLEy7A7Z6VXMUpMvUrvKl9FbpPGxeTx8zU3gq9r4SCfseOHfJ6vZqcnNSWLVu0adMmffWrX81IAZHImGIxKyPvdSseT6nOnBnN6jbyoRD6KvQPSKpuNS6FMGapMrW36daX3W5L+gA5oakbr9crSSouLlZzc7Peffddeb1eDQ4OTi0zPDwsu92e1NE8ACD74gb9xYsXNTr68b9mlmVp37598vl8WrRokcbHx3X48GFJ0s6dO1VbW5vdagEASYs7dROJRLR+/XpFo1HFYjEtXLhQ7e3tstvt6uzsVHt7+3U/rwQATC9xg37BggXavXv3TV9bsmSJQqFQxosCAGQOZ8YCgOEIegAwHEEPAIYj6AHAcAQ9ABiOoAcAwxH0AGA4gh4ADJfw1Stx+yotu0MlTnYVoFDx6UVcJc4ibuABFDCmbgDAcAQ9ABiOoAcAwxH0AGA4gh4ADEfQA4DhCHoAMBxBDwCGI+gBwHAEPQAYjqAHAMMR9ABgOIIeAAxH0AOA4ZIK+m3btunee+/V+++/L0k6evSoVq1apZUrV+qxxx5TJBLJSpEAgNQlHPTvvfeejh49qqqqKklSLBbThg0bFAgE1NPTo5qaGm3dujVrhQIAUpNQ0E9OTmrTpk3q6OiYeq6vr09Op1M1NTWSpKamJu3fvz8rRQIAUpdQ0L/wwgtatWqV5s+fP/VcOBxWZWXl1GOXy6VYLKaRkZHMVwkASFncWwkeOXJEfX19am1tzUoBbvesrLzvJ3k8pTnZTq6Z2leh+7RxMXnMTO2t0PuKG/TvvPOOjh07puXLl0uSTp06pccff1yPPvqoBgcHp5YbHh6W3W5XeXl5UgVEImOKxawky06Ox1OqM2dGs7qNfMhVX4W+k+fDrcbF1H1RMre36daX3W5L+gA57tTN2rVr9de//lW9vb3q7e3VvHnz9Morr2jNmjUaHx/X4cOHJUk7d+5UbW1tapUDALIm7hH9rdjtdnV2dqq9vV0TExOqqqpSV1dXJmsDCtLk5WhaUzfjE1c0ev5SpsvCbSzpoO/t7Z3685IlSxQKhTJaEFDoimc4VPfEnpTXDz1fr+kzUQATcGYsABiOoAcAwxH0AGA4gh4ADEfQA4DhCHoAMBxBDwCGI+gBwHAEPQAYjqAHAMMR9ABgOIIeAAxH0AOA4Qh6ADAcQQ8AhiPoAcBwBD0AGI6gBwDDEfQAYDiCHgAMR9ADgOEIegAwHEEPAIYj6AHAcEWJLLRu3Tp9+OGHstvtuvPOO/XjH/9YPp9PAwMDamtr08jIiMrLyxUMBlVdXZ3lkgEAyUgo6IPBoEpLSyVJb775pp566im98cYbam9vV3Nzs+rr67Vnzx4FAgG99tprWS0YAJCchKZuroa8JI2NjclmsykSiai/v19+v1+S5Pf71d/fr+Hh4exUCgBISUJH9JL0ox/9SIcOHZJlWfrFL36hcDisiooKORwOSZLD4dDcuXMVDoflcrmyVjAAIDkJB/2WLVskSbt371ZnZ6daWloyUoDbPSsj7xOPx1Maf6ECZGpft7tUx3XyclTFMxw5X/cqU/fHQu8r4aC/qqGhQYFAQPPmzdPQ0JCi0agcDoei0ahOnz4tr9eb1PtFImOKxaxky0iKx1OqM2dGs7qNfMhVX4W+kxeiVMfV4ylV3RN7Ulo39Hx9WvsTn7PcsNttSR8gx52jv3DhgsLh8NTj3t5e3XXXXXK73fL5fOru7pYkdXd3y+fzMW0DANNM3CP6S5cuqaWlRZcuXZLdbtddd92ll19+WTabTR0dHWpra9P27dtVVlamYDCYi5qRgtKyO1TiTPoLHAADxP3kz5kzR7/97W9v+trChQu1a9eujBeFzCtxFqX1lR5A4eLMWAAwHEEPAIYj6AHAcAQ9ABiOoAcAw/F7O2Cambwc5SQ1ZBRBD0wzxTMc/BQWGcXUDQAYjqAHAMMR9ABgOIIeAAxH0AOA4Qh6ADAcQQ8AhiPoAcBwBD0AGI6gBwDDEfQAYDiCHgAMR9ADgOEIegAwHEEPAIYj6AHAcAQ9ABiOoAcAw8W9leC5c+f05JNP6sSJEyouLtbdd9+tTZs2yeVy6ejRowoEApqYmFBVVZW6urrkdrtzUTcAIEFxj+htNpvWrFmjnp4ehUIhLViwQFu3blUsFtOGDRsUCATU09Ojmpoabd26NRc1AwCSEDfoy8vLtXTp0qnHixcv1uDgoPr6+uR0OlVTUyNJampq0v79+7NXKQAgJXGnbq4Vi8X061//WsuWLVM4HFZlZeXUay6XS7FYTCMjIyovL0/4Pd3uWcmUkDKPpzQn28k1U/tCfqS7P5m6PxZ6X0kF/ebNm3XnnXdq9erVOnjwYEYKiETGFItZGXmvW/F4SnXmzGhWt5EPyfRV6DsqciOdzwmfs9yw221JHyAnHPTBYFD/+9//9PLLL8tut8vr9WpwcHDq9eHhYdnt9qSO5gEA2ZfQzyt/+tOfqq+vTy+99JKKi4slSYsWLdL4+LgOHz4sSdq5c6dqa2uzVykAICVxj+g/+OAD/fznP1d1dbWampokSfPnz9dLL72kzs5Otbe3X/fzSgCFafJyNOUpvvGJKxmuBpkUN+g/97nP6b///e9NX1uyZIlCoVDGiwKQe8UzHKp7Yk9K64aer89wNcgkzowFAMMR9ABgOIIeAAxH0AOA4Qh6ADAcQQ8AhiPoAcBwBD0AGC6pi5ohfaVld6jEmdpf+/jEFY2ev5ThioD8SuczIfG5SARBn2MlzqK0zj6cPtfQAzIjnc+ExOciEUzdAIDhOKIvIDe76BTXmcd0MHk5quIZDvbHaYqgLyBcdArTFfvm9MbUDQAYjqAHAMMR9ABgOIIeAAxH0AOA4Qh6ADAcQQ8AhiPoAcBwBD0AGI6gBwDDEfQAYLi4QR8MBrVs2TLde++9ev/996eeHxgYUGNjo1auXKnGxkYdP348m3UCAFIUN+iXL1+uHTt2qKqq6rrn29vb1dzcrJ6eHjU3NysQCGStSABA6uIGfU1Njbxe73XPRSIR9ff3y+/3S5L8fr/6+/s1PDycnSoBAClLaY4+HA6roqJCDodDkuRwODR37lyFw+GMFgcASF/er0fvds9Kab2rNzpI1LU3REh2XQDT181uyJPMuolkQaHfUCWloPd6vRoaGlI0GpXD4VA0GtXp06dvmOJJRCQypljMSno9j6c0rRsdnDmTn7tMFvoOA0w36d70JF4WeDylecuLm7HbbUkfIKc0deN2u+Xz+dTd3S1J6u7uls/nk8vlSuXtAABZFPeI/plnntGBAwd09uxZffvb31Z5ebn27t2rjo4OtbW1afv27SorK1MwGMxFvQCAJMUN+qefflpPP/30Dc8vXLhQu3btykpRAIDM4cxYADAcQQ8AhiPoAcBwBD0AGI6gBwDDEfQAYDiCHgAMR9ADgOHyflGzQlNadodKnPy1ASZI9IJoN1tmfOKKRs9fykZZGUdiJanEWZTyBZSkjy+iBGB6SPeCaNPnUmefjqkbADAcQQ8AhmPqBgBSkM4NT3I9v0/QA0AKCml+n6kbADAcQQ8AhiPoAcBwBD0AGI6gBwDDEfQAYDiCHgAMR9ADgOFuyxOm0jmjDQAKzW0Z9Ome0QYAhYSpGwAwXNpBPzAwoMbGRq1cuVKNjY06fvx4BsoCAGRK2kHf3t6u5uZm9fT0qLm5WYFAIBN1AQAyJK05+kgkov7+fr366quSJL/fr82bN2t4eFgulyuh97DbbSlvf+7sOwpu3XxuuxDXzee26bkw1s3nttNZN9XsS2U9m2VZVkpbk9TX16eNGzdq7969U8899NBD6urq0uc///lU3xYAkEH8ZywAGC6toPd6vRoaGlI0GpUkRaNRnT59Wl6vNyPFAQDSl1bQu91u+Xw+dXd3S5K6u7vl8/kSnp8HAGRfWnP0knTs2DG1tbXp/PnzKisrUzAY1Gc/+9lM1QcASFPaQQ8AmN74z1gAMBxBDwCGI+gBwHAEPQAYzpjLFC9btkzFxcVyOp2SpNbWVj3wwAPXLXPp0iX98Ic/1HvvvSeHw6GNGzfqK1/5Sj7KTVgifbW1telvf/ubZs+eLUmqra3Vd7/73ZzXmqyJiQk9++yzevvtt+V0OrV48WJt3rz5umWi0aieeeYZvfXWW7LZbFq7dq0eeeSRPFWcmET6+tnPfqZf/epXmjt3riRpyZIlam9vz0e5Cfvwww/1ve99b+rx6OioxsbG9I9//OO65QpxzBLtrRDHTTIo6CXpxRdf1D333HPL11955RXNmjVLBw8e1PHjx/XNb35TBw4c0MyZM3NYZfLi9SVJa9eu1erVq3NUUWZ0dXXJ6XSqp6dHNptNZ8+evWGZUCikEydO6MCBAxoZGVFDQ4O++MUvav78+XmoODGJ9CVJDQ0N2rhxY46rS938+fO1Z8//38dhy5YtUydLXqsQxyzR3qTCGzfpNpu6+cMf/qDGxkZJUnV1tRYtWqS//OUvea7q9nThwgXt3r1bLS0tstk+vkjTnDlzblhu3759euSRR2S32+VyufTggw9q//79uS43YYn2VegmJycVCoX09a9//YbXCm3MPunTeitURgV9a2ur6urq1NHRofPnz9/w+uDgoKqqqqYee71enTp1KpclpiReX5L06quvqq6uTuvWrdOxY8dyXGHyTp48qfLycm3btk0PP/ywHn30UR0+fPiG5cLhsCorK6ceT/cxS7QvSdq7d6/q6ur02GOP6ciRIzmuND29vb2qqKi46cULC23MPunTepMKc9yMCfodO3bo97//vV5//XVZlqVNmzblu6SMSKSv73//+zp48KBCoZBWrFihNWvW3PJr53QRjUZ18uRJ3Xffffrd736n1tZWrV+/XmNjY/kuLS2J9tXU1KQ//vGPCoVCevzxx7Vu3TqdO3cuT1Un7/XXXzfqiPdan9ZboY6bMUF/9UJqxcXFam5u1rvvvnvDMpWVlfroo4+mHofDYc2bNy9nNaYikb4qKipkt388lA0NDbp48eK0P4Lyer0qKiqS3++XJN1///2aPXu2BgYGblhucHBw6vF0H7NE+/J4PJoxY4Yk6Utf+pK8Xq8++OCDnNebiqGhIb3zzjuqq6u76euFNmbXitdboY6bEUF/8eJFjY6OSpIsy9K+ffvk8/luWK62tla/+c1vJEnHjx/Xv//97xt+wTKdJNrX0NDQ1J/feust2e12VVRU5KzOVLhcLi1dulSHDh2S9PEtKSORiO6+++7rlqutrdWuXbsUi8U0PDysN998UytXrsxHyQlJtK9rx+w///mPPvroI33mM5/Jaa2peuONN/TlL3956lden1RoY3ateL0V7LhZBjhx4oRVX19v+f1+66GHHrLWr19vDQ0NWZZlWatWrbJOnTplWZZlXbhwwVq/fr314IMPWitWrLAOHjyYz7LjSrSvb33rW5bf77fq6uqsb3zjG9aRI0fyWXbCTpw4Ya1evdry+/1WQ0OD9ac//cmyLMtas2aN9a9//cuyLMu6cuWKFQgErOXLl1vLly+3du7cmc+SE5JIX08++aT1ta99zaqrq7MefvjhqWUKwYoVK6w///nP1z1X6GN2VbzeCnXcuKgZABjOiKkbAMCtEfQAYDiCHgAMR9ADgOEIegAwHEEPAIYj6AHAcAQ9ABju/wCSBeI2SfOROAAAAABJRU5ErkJggg==\n", "text/plain": [ "
" ] @@ -468,7 +468,7 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": 98, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -493,6 +493,7 @@ "name": "stdout", "output_type": "stream", "text": [ + "Dataset rows count BEFORE dropping rows with missing values: 556\n", "\n" ] }, @@ -505,6 +506,13 @@ }, "metadata": {}, "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Dataset rows count AFTER dropping rows with missing values: 506\n" + ] } ], "source": [ @@ -515,6 +523,7 @@ "plt.title(\"Dataset values count before removing missing values\")\n", "plt.show()\n", "\n", + "print(\"Dataset rows count BEFORE dropping rows with missing values:\", data.shape[0])\n", "# Remove rows with columns missing data \n", "if sum(missing_values_count) > 0:\n", " data = data.dropna()\n", @@ -527,7 +536,8 @@ "missing_values_count=(total_rows - total_rows_without_missing_values)\n", "plt.barh(data.columns, missing_values_count)\n", "plt.title(\"Dataset values count after removing missing values\")\n", - "plt.show()" + "plt.show()\n", + "print(\"Dataset rows count AFTER dropping rows with missing values:\", data.shape[0])\n" ] }, {