diff --git a/ceva.json b/ceva.json
new file mode 100644
index 0000000..daa0212
--- /dev/null
+++ b/ceva.json
@@ -0,0 +1 @@
+{"9": "JxdI", "0": "WqAfKV", "7": "Qbuqd"}
\ No newline at end of file
diff --git a/data-science/data-science-7.ipynb/data-science.ipynb b/data-science/data-science-7.ipynb/data-science.ipynb
new file mode 100644
index 0000000..853422d
--- /dev/null
+++ b/data-science/data-science-7.ipynb/data-science.ipynb
@@ -0,0 +1,428 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from sklearn.datasets import load_wine\n",
+ "from sklearn.datasets import load_breast_cancer\n",
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "import matplotlib.pyplot as plt\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 22,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "data = load_wine()\n",
+ "X, y = data.data, data.target"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 23,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " alcohol | \n",
+ " malic_acid | \n",
+ " ash | \n",
+ " alcalinity_of_ash | \n",
+ " magnesium | \n",
+ " total_phenols | \n",
+ " flavanoids | \n",
+ " nonflavanoid_phenols | \n",
+ " proanthocyanins | \n",
+ " color_intensity | \n",
+ " hue | \n",
+ " od280/od315_of_diluted_wines | \n",
+ " proline | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | count | \n",
+ " 1.780000e+02 | \n",
+ " 1.780000e+02 | \n",
+ " 1.780000e+02 | \n",
+ " 1.780000e+02 | \n",
+ " 1.780000e+02 | \n",
+ " 1.780000e+02 | \n",
+ " 1.780000e+02 | \n",
+ " 1.780000e+02 | \n",
+ " 1.780000e+02 | \n",
+ " 1.780000e+02 | \n",
+ " 1.780000e+02 | \n",
+ " 1.780000e+02 | \n",
+ " 1.780000e+02 | \n",
+ "
\n",
+ " \n",
+ " | mean | \n",
+ " 7.841418e-15 | \n",
+ " 2.444986e-16 | \n",
+ " -4.059175e-15 | \n",
+ " -7.110417e-17 | \n",
+ " -2.494883e-17 | \n",
+ " -1.955365e-16 | \n",
+ " 9.443133e-16 | \n",
+ " -4.178929e-16 | \n",
+ " -1.540590e-15 | \n",
+ " -4.129032e-16 | \n",
+ " 1.398382e-15 | \n",
+ " 2.126888e-15 | \n",
+ " -6.985673e-17 | \n",
+ "
\n",
+ " \n",
+ " | std | \n",
+ " 1.002821e+00 | \n",
+ " 1.002821e+00 | \n",
+ " 1.002821e+00 | \n",
+ " 1.002821e+00 | \n",
+ " 1.002821e+00 | \n",
+ " 1.002821e+00 | \n",
+ " 1.002821e+00 | \n",
+ " 1.002821e+00 | \n",
+ " 1.002821e+00 | \n",
+ " 1.002821e+00 | \n",
+ " 1.002821e+00 | \n",
+ " 1.002821e+00 | \n",
+ " 1.002821e+00 | \n",
+ "
\n",
+ " \n",
+ " | min | \n",
+ " -2.434235e+00 | \n",
+ " -1.432983e+00 | \n",
+ " -3.679162e+00 | \n",
+ " -2.671018e+00 | \n",
+ " -2.088255e+00 | \n",
+ " -2.107246e+00 | \n",
+ " -1.695971e+00 | \n",
+ " -1.868234e+00 | \n",
+ " -2.069034e+00 | \n",
+ " -1.634288e+00 | \n",
+ " -2.094732e+00 | \n",
+ " -1.895054e+00 | \n",
+ " -1.493188e+00 | \n",
+ "
\n",
+ " \n",
+ " | 25% | \n",
+ " -7.882448e-01 | \n",
+ " -6.587486e-01 | \n",
+ " -5.721225e-01 | \n",
+ " -6.891372e-01 | \n",
+ " -8.244151e-01 | \n",
+ " -8.854682e-01 | \n",
+ " -8.275393e-01 | \n",
+ " -7.401412e-01 | \n",
+ " -5.972835e-01 | \n",
+ " -7.951025e-01 | \n",
+ " -7.675624e-01 | \n",
+ " -9.522483e-01 | \n",
+ " -7.846378e-01 | \n",
+ "
\n",
+ " \n",
+ " | 50% | \n",
+ " 6.099988e-02 | \n",
+ " -4.231120e-01 | \n",
+ " -2.382132e-02 | \n",
+ " 1.518295e-03 | \n",
+ " -1.222817e-01 | \n",
+ " 9.595986e-02 | \n",
+ " 1.061497e-01 | \n",
+ " -1.760948e-01 | \n",
+ " -6.289785e-02 | \n",
+ " -1.592246e-01 | \n",
+ " 3.312687e-02 | \n",
+ " 2.377348e-01 | \n",
+ " -2.337204e-01 | \n",
+ "
\n",
+ " \n",
+ " | 75% | \n",
+ " 8.361286e-01 | \n",
+ " 6.697929e-01 | \n",
+ " 6.981085e-01 | \n",
+ " 6.020883e-01 | \n",
+ " 5.096384e-01 | \n",
+ " 8.089974e-01 | \n",
+ " 8.490851e-01 | \n",
+ " 6.095413e-01 | \n",
+ " 6.291754e-01 | \n",
+ " 4.939560e-01 | \n",
+ " 7.131644e-01 | \n",
+ " 7.885875e-01 | \n",
+ " 7.582494e-01 | \n",
+ "
\n",
+ " \n",
+ " | max | \n",
+ " 2.259772e+00 | \n",
+ " 3.109192e+00 | \n",
+ " 3.156325e+00 | \n",
+ " 3.154511e+00 | \n",
+ " 4.371372e+00 | \n",
+ " 2.539515e+00 | \n",
+ " 3.062832e+00 | \n",
+ " 2.402403e+00 | \n",
+ " 3.485073e+00 | \n",
+ " 3.435432e+00 | \n",
+ " 3.301694e+00 | \n",
+ " 1.960915e+00 | \n",
+ " 2.971473e+00 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
"
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "df2 = df[['alcohol', \"color_intensity\"]]\n",
+ "colors = []\n",
+ "for ci in y:\n",
+ " if ci == 0:\n",
+ " colors.append('blue')\n",
+ " elif ci ==1:\n",
+ " colors.append(\"red\")\n",
+ " elif ci == 2:\n",
+ " colors.append(\"magenta\")\n",
+ "#_ = plt.figure(figsize=(20,20))\n",
+ "df.plot.scatter(\"alcohol\", \"color_intensity\", c = colors)\n",
+ "plt.show()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 25,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from sklearn.cluster import KMeans\n",
+ "\n",
+ "clf = KMeans(n_clusters=3)\n",
+ "clf=clf.fit(df2)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 26,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([[-0.99779866, -0.8442919 ],\n",
+ " [ 0.40313085, 1.65389899],\n",
+ " [ 0.75390118, 0.06029021]])"
+ ]
+ },
+ "execution_count": 26,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "clf.cluster_centers_"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 27,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "cluster_colors=[]\n",
+ "for ci in clf.labels_:\n",
+ " if ci == 0:\n",
+ " cluster_colors.append(\"blue\")\n",
+ " elif ci ==1:\n",
+ " cluster_colors.append(\"red\")\n",
+ " elif ci == 2:\n",
+ " cluster_colors.append(\"magenta\")\n",
+ " "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 28,
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "KeyError",
+ "evalue": "\"None of [Float64Index([ 1.5186125409891542, 0.24628962701506343, 0.19687902841412896,\\n 1.6915496360924271, 0.29570022561600007, 1.4815545920384512,\\n 1.7162549353928964, 1.3086174969351785, 2.2597715200031865,\\n 1.0615645039304995,\\n ...\\n 0.7156903137239518, 0.49334262001974233, -0.9889753380083244,\\n -0.28487430794499297, 1.4321439934375169, 0.8762747591769932,\\n 0.49334262001974233, 0.3327581745667009, 0.2092316780643626,\\n 1.395086044486816],\\n dtype='float64', length=178)] are in the [columns]\"",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)",
+ "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[0m_\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfigure\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfigsize\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m20\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;36m20\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mplot\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mscatter\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m\"alcohol\"\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdf\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m\"color_intensity\"\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mc\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcolors\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 3\u001b[0m \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mscatter\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'alcohol'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdf\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'color_intensity'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mc\u001b[0m\u001b[1;33m=\u001b[0m \u001b[0mcluster_colors\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0malpha\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0.3\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0ms\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m150\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[1;31m#plt.scatter(df['alcohol'], df['color_intensity'], c= cluster_colors, alpha=0.3, s=150)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshow\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mD:\\AppliedDataScience\\Anaconda\\lib\\site-packages\\pandas\\plotting\\_core.py\u001b[0m in \u001b[0;36mscatter\u001b[1;34m(self, x, y, s, c, **kwargs)\u001b[0m\n\u001b[0;32m 1617\u001b[0m ... colormap='viridis')\n\u001b[0;32m 1618\u001b[0m \"\"\"\n\u001b[1;32m-> 1619\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkind\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m\"scatter\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mx\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0my\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0ms\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0ms\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mc\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1620\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1621\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mhexbin\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mx\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mC\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mreduce_C_function\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mgridsize\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mD:\\AppliedDataScience\\Anaconda\\lib\\site-packages\\pandas\\plotting\\_core.py\u001b[0m in \u001b[0;36m__call__\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 898\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mkind\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_dataframe_kinds\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 899\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mABCDataFrame\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 900\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mplot_backend\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mplot\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mx\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0my\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkind\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mkind\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 901\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 902\u001b[0m \u001b[1;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34mf\"plot kind {kind} can only be used for data frames\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mD:\\AppliedDataScience\\Anaconda\\lib\\site-packages\\pandas\\plotting\\_matplotlib\\__init__.py\u001b[0m in \u001b[0;36mplot\u001b[1;34m(data, kind, **kwargs)\u001b[0m\n\u001b[0;32m 59\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m\"ax\"\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0max\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m\"left_ax\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0max\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 60\u001b[0m \u001b[0mplot_obj\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mPLOT_CLASSES\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mkind\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 61\u001b[1;33m \u001b[0mplot_obj\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mgenerate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 62\u001b[0m \u001b[0mplot_obj\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdraw\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 63\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mplot_obj\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresult\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mD:\\AppliedDataScience\\Anaconda\\lib\\site-packages\\pandas\\plotting\\_matplotlib\\core.py\u001b[0m in \u001b[0;36mgenerate\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 278\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_compute_plot_data\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 279\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_setup_subplots\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 280\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_make_plot\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 281\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_add_table\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 282\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_make_legend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mD:\\AppliedDataScience\\Anaconda\\lib\\site-packages\\pandas\\plotting\\_matplotlib\\core.py\u001b[0m in \u001b[0;36m_make_plot\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 1040\u001b[0m \u001b[0mlabel\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1041\u001b[0m scatter = ax.scatter(\n\u001b[1;32m-> 1042\u001b[1;33m \u001b[0mdata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1043\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0my\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1044\u001b[0m \u001b[0mc\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mc_values\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mD:\\AppliedDataScience\\Anaconda\\lib\\site-packages\\pandas\\core\\frame.py\u001b[0m in \u001b[0;36m__getitem__\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 3028\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mis_iterator\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3029\u001b[0m \u001b[0mkey\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlist\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 3030\u001b[1;33m \u001b[0mindexer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mloc\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_get_listlike_indexer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mraise_missing\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 3031\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3032\u001b[0m \u001b[1;31m# take() does not accept boolean indexers\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mD:\\AppliedDataScience\\Anaconda\\lib\\site-packages\\pandas\\core\\indexing.py\u001b[0m in \u001b[0;36m_get_listlike_indexer\u001b[1;34m(self, key, axis, raise_missing)\u001b[0m\n\u001b[0;32m 1264\u001b[0m \u001b[0mkeyarr\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindexer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnew_indexer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0max\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_reindex_non_unique\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkeyarr\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1265\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1266\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_validate_read_indexer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkeyarr\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindexer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mraise_missing\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mraise_missing\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1267\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mkeyarr\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindexer\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1268\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mD:\\AppliedDataScience\\Anaconda\\lib\\site-packages\\pandas\\core\\indexing.py\u001b[0m in \u001b[0;36m_validate_read_indexer\u001b[1;34m(self, key, indexer, axis, raise_missing)\u001b[0m\n\u001b[0;32m 1306\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mmissing\u001b[0m \u001b[1;33m==\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mindexer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1307\u001b[0m \u001b[0maxis_name\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_get_axis_name\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1308\u001b[1;33m \u001b[1;32mraise\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34mf\"None of [{key}] are in the [{axis_name}]\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1309\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1310\u001b[0m \u001b[0max\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_get_axis\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;31mKeyError\u001b[0m: \"None of [Float64Index([ 1.5186125409891542, 0.24628962701506343, 0.19687902841412896,\\n 1.6915496360924271, 0.29570022561600007, 1.4815545920384512,\\n 1.7162549353928964, 1.3086174969351785, 2.2597715200031865,\\n 1.0615645039304995,\\n ...\\n 0.7156903137239518, 0.49334262001974233, -0.9889753380083244,\\n -0.28487430794499297, 1.4321439934375169, 0.8762747591769932,\\n 0.49334262001974233, 0.3327581745667009, 0.2092316780643626,\\n 1.395086044486816],\\n dtype='float64', length=178)] are in the [columns]\""
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "_ = plt.figure(figsize=(20,20))\n",
+ "df.plot.scatter(df[\"alcohol\"], df[\"color_intensity\"], c = colors)\n",
+ "plt.scatter(df['alcohol'], df['color_intensity'], c= cluster_colors, alpha=0.3, s=150)\n",
+ "#plt.scatter(df['alcohol'], df['color_intensity'], c= cluster_colors, alpha=0.3, s=150)\n",
+ "plt.show()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "interpreter": {
+ "hash": "70755f98cf1e97b7faee6dc1f70869fe24a8420130d344886bc04d616b8b3bed"
+ },
+ "kernelspec": {
+ "display_name": "Python 3.8.8 64-bit ('base': conda)",
+ "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": "3.8.8"
+ },
+ "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/homework3-oop/ex1.py b/homework3-oop/ex1.py
index 5a3ca06..65549c6 100644
--- a/homework3-oop/ex1.py
+++ b/homework3-oop/ex1.py
@@ -27,4 +27,10 @@
functionality in it (besides all_implemented()).
The explanations for what the methods should do are mainly for the classes
that will extend the Animal class.
-"""
\ No newline at end of file
+"""
+
+
+from abc import ABC
+
+class Animal(ABC):
+ pass
\ No newline at end of file
diff --git a/homework4-ds/homework4.ipynb b/homework4-ds/homework4.ipynb
index a20871b..7d256bb 100644
--- a/homework4-ds/homework4.ipynb
+++ b/homework4-ds/homework4.ipynb
@@ -21,11 +21,19 @@
},
{
"cell_type": "code",
+<<<<<<< HEAD
+ "execution_count": 2,
+=======
"execution_count": 36,
+>>>>>>> 5f2dd86669233d319ebe9f0f010a6cd6905ddf12
"metadata": {},
"outputs": [],
"source": [
"# Your code goes here\n",
+<<<<<<< HEAD
+ "\n",
+=======
+>>>>>>> 5f2dd86669233d319ebe9f0f010a6cd6905ddf12
"import sqlite3\n",
"conn = sqlite3.connect(\"homework4.db\")"
]
@@ -45,8 +53,14 @@
"outputs": [],
"source": [
"# Your code goes here\n",
+<<<<<<< HEAD
+ "\n",
+ "import pandas as pd\n",
+ "data=pd.read_sql(\"SELECT * FROM homework4;\", conn)"
+=======
"import pandas as pd\n",
"df = pd.read_sql(\"select * from homework4\", conn)"
+>>>>>>> 5f2dd86669233d319ebe9f0f010a6cd6905ddf12
]
},
{
@@ -66,10 +80,185 @@
},
{
"cell_type": "code",
+<<<<<<< HEAD
+ "execution_count": 4,
+=======
"execution_count": 38,
+>>>>>>> 5f2dd86669233d319ebe9f0f010a6cd6905ddf12
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\n",
+ "RangeIndex: 884 entries, 0 to 883\n",
+ "Data columns (total 12 columns):\n",
+ " # Column Non-Null Count Dtype \n",
+ "--- ------ -------------- ----- \n",
+ " 0 id 884 non-null int64 \n",
+ " 1 age 884 non-null float64\n",
+ " 2 sex 884 non-null float64\n",
+ " 3 bmi 884 non-null float64\n",
+ " 4 bp 884 non-null float64\n",
+ " 5 s1 884 non-null float64\n",
+ " 6 s2 884 non-null float64\n",
+ " 7 s3 884 non-null float64\n",
+ " 8 s4 884 non-null float64\n",
+ " 9 s5 884 non-null float64\n",
+ " 10 s6 884 non-null float64\n",
+ " 11 target 884 non-null float64\n",
+ "dtypes: float64(11), int64(1)\n",
+ "memory usage: 83.0 KB\n"
+ ]
+ }
+ ],
+ "source": [
+<<<<<<< HEAD
+ "data.info()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\n",
+ "RangeIndex: 884 entries, 0 to 883\n",
+ "Data columns (total 12 columns):\n",
+ " # Column Non-Null Count Dtype \n",
+ "--- ------ -------------- ----- \n",
+ " 0 id 884 non-null int64 \n",
+ " 1 age 884 non-null float64\n",
+ " 2 sex 884 non-null float64\n",
+ " 3 bmi 884 non-null float64\n",
+ " 4 bp 884 non-null float64\n",
+ " 5 s1 884 non-null float64\n",
+ " 6 s2 884 non-null float64\n",
+ " 7 s3 884 non-null float64\n",
+ " 8 s4 884 non-null float64\n",
+ " 9 s5 884 non-null float64\n",
+ " 10 s6 884 non-null float64\n",
+ " 11 target 884 non-null float64\n",
+ "dtypes: float64(11), int64(1)\n",
+ "memory usage: 83.0 KB\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Your code goes here\n",
+ "data.info()\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "id 0\n",
+ "age 0\n",
+ "sex 0\n",
+ "bmi 0\n",
+ "bp 0\n",
+ "s1 0\n",
+ "s2 0\n",
+ "s3 0\n",
+ "s4 0\n",
+ "s5 0\n",
+ "s6 0\n",
+ "target 0\n",
+ "dtype: int64\n"
+ ]
+ }
+ ],
+ "source": [
+ "nulls_number = data.isnull().sum()\n",
+ "print(nulls_number)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "id 0\n",
+ "age 0\n",
+ "sex 0\n",
+ "bmi 0\n",
+ "bp 0\n",
+ "s1 0\n",
+ "s2 0\n",
+ "s3 0\n",
+ "s4 0\n",
+ "s5 0\n",
+ "s6 0\n",
+ "target 0\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "data.isna().sum()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ " id age sex bmi bp s1 s2 \\\n",
+ "442 443 0.038076 0.050680 0.061696 0.021872 -0.044223 -0.034821 \n",
+ "443 444 -0.001882 -0.044642 -0.051474 -0.026328 -0.008449 -0.019163 \n",
+ "444 445 0.085299 0.050680 0.044451 -0.005671 -0.045599 -0.034194 \n",
+ "445 446 -0.089063 -0.044642 -0.011595 -0.036656 0.012191 0.024991 \n",
+ "446 447 0.005383 -0.044642 -0.036385 0.021872 0.003935 0.015596 \n",
+ ".. ... ... ... ... ... ... ... \n",
+ "879 880 0.041708 0.050680 0.019662 0.059744 -0.005697 -0.002566 \n",
+ "880 881 -0.005515 0.050680 -0.015906 -0.067642 0.049341 0.079165 \n",
+ "881 882 0.041708 0.050680 -0.015906 0.017282 -0.037344 -0.013840 \n",
+ "882 883 -0.045472 -0.044642 0.039062 0.001215 0.016318 0.015283 \n",
+ "883 884 -0.045472 -0.044642 -0.073030 -0.081414 0.083740 0.027809 \n",
+ "\n",
+ " s3 s4 s5 s6 target \n",
+ "442 -0.043401 -0.002592 0.019908 -0.017646 151.0 \n",
+ "443 0.074412 -0.039493 -0.068330 -0.092204 75.0 \n",
+ "444 -0.032356 -0.002592 0.002864 -0.025930 141.0 \n",
+ "445 -0.036038 0.034309 0.022692 -0.009362 206.0 \n",
+ "446 0.008142 -0.002592 -0.031991 -0.046641 135.0 \n",
+ ".. ... ... ... ... ... \n",
+ "879 -0.028674 -0.002592 0.031193 0.007207 178.0 \n",
+ "880 -0.028674 0.034309 -0.018118 0.044485 104.0 \n",
+ "881 -0.024993 -0.011080 -0.046879 0.015491 132.0 \n",
+ "882 -0.028674 0.026560 0.044528 -0.025930 220.0 \n",
+ "883 0.173816 -0.039493 -0.004220 0.003064 57.0 \n",
+ "\n",
+ "[442 rows x 12 columns]\n"
+ ]
+ }
+ ],
"source": [
+ "duplicates = data[data.duplicated(['age', 'sex', 'bmi', 'bp', 's1', \"s2\", \"s3\", \"s4\", \"s5\", \"s6\", \"target\"])]\n",
+ "print(duplicates)"
+=======
"# Your code goes here\n",
"run = True \n",
"if run:\n",
@@ -77,6 +266,7 @@
" df = df.set_index(ids)\n",
" df.drop(columns=['id'], axis=1, inplace=True)\n",
" df.head()"
+>>>>>>> 5f2dd86669233d319ebe9f0f010a6cd6905ddf12
]
},
{
@@ -89,50 +279,1705 @@
]
},
{
- "cell_type": "markdown",
+ "cell_type": "code",
+ "execution_count": 9,
"metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "442\n"
+ ]
+ }
+ ],
"source": [
- "#### Step 4 - Clean your data\n",
+ "#Your code goes here:\n",
"\n",
- "* Remove null or missing values\n",
- "* Clean data types\n",
- "* Remove outliers"
+ "new_data = data.drop_duplicates(subset=[\"age\", \"sex\", \"bmi\", \"bp\", \"s1\", \"s2\", \"s3\", \"s4\", \"s5\", \"s6\", \"target\"])\n",
+ "print(len(new_data))"
]
},
{
"cell_type": "code",
- "execution_count": 39,
+ "execution_count": 10,
"metadata": {},
"outputs": [
{
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "Initial number of obs: 884\nRemoved duplicates number of obs: 442\n"
- ]
+ "data": {
+ "text/plain": [
+ "array([[,\n",
+ " ,\n",
+ " ],\n",
+ " [,\n",
+ " ,\n",
+ " ],\n",
+ " [,\n",
+ " ,\n",
+ " ],\n",
+ " [,\n",
+ " ,\n",
+ " ]], dtype=object)"
+ ]
+ },
+ "execution_count": 10,
+ "metadata": {},
+ "output_type": "execute_result"
+ },
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
}
],
"source": [
- "# Your code goes here\n",
- "print(f\"Initial number of obs: {len(df)}\")\n",
- "df = df.drop_duplicates()\n",
- "print(f\"Removed duplicates number of obs: {len(df)}\")"
+ "import numpy as np\n",
+ "%matplotlib inline\n",
+ "new_data.hist()"
]
},
{
- "cell_type": "markdown",
+ "cell_type": "code",
+ "execution_count": 11,
"metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " id | \n",
+ " age | \n",
+ " sex | \n",
+ " bmi | \n",
+ " bp | \n",
+ " s1 | \n",
+ " s2 | \n",
+ " s3 | \n",
+ " s4 | \n",
+ " s5 | \n",
+ " s6 | \n",
+ " target | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | count | \n",
+ " 442.000000 | \n",
+ " 4.420000e+02 | \n",
+ " 4.420000e+02 | \n",
+ " 4.420000e+02 | \n",
+ " 4.420000e+02 | \n",
+ " 4.420000e+02 | \n",
+ " 4.420000e+02 | \n",
+ " 4.420000e+02 | \n",
+ " 4.420000e+02 | \n",
+ " 4.420000e+02 | \n",
+ " 4.420000e+02 | \n",
+ " 442.000000 | \n",
+ "
\n",
+ " \n",
+ " | mean | \n",
+ " 221.500000 | \n",
+ " -3.634285e-16 | \n",
+ " 1.308343e-16 | \n",
+ " -8.045349e-16 | \n",
+ " 1.281655e-16 | \n",
+ " -8.835316e-17 | \n",
+ " 1.327024e-16 | \n",
+ " -4.574646e-16 | \n",
+ " 3.777301e-16 | \n",
+ " -3.830854e-16 | \n",
+ " -3.412882e-16 | \n",
+ " 152.133484 | \n",
+ "
\n",
+ " \n",
+ " | std | \n",
+ " 127.738666 | \n",
+ " 4.761905e-02 | \n",
+ " 4.761905e-02 | \n",
+ " 4.761905e-02 | \n",
+ " 4.761905e-02 | \n",
+ " 4.761905e-02 | \n",
+ " 4.761905e-02 | \n",
+ " 4.761905e-02 | \n",
+ " 4.761905e-02 | \n",
+ " 4.761905e-02 | \n",
+ " 4.761905e-02 | \n",
+ " 77.093005 | \n",
+ "
\n",
+ " \n",
+ " | min | \n",
+ " 1.000000 | \n",
+ " -1.072256e-01 | \n",
+ " -4.464164e-02 | \n",
+ " -9.027530e-02 | \n",
+ " -1.123996e-01 | \n",
+ " -1.267807e-01 | \n",
+ " -1.156131e-01 | \n",
+ " -1.023071e-01 | \n",
+ " -7.639450e-02 | \n",
+ " -1.260974e-01 | \n",
+ " -1.377672e-01 | \n",
+ " 25.000000 | \n",
+ "
\n",
+ " \n",
+ " | 25% | \n",
+ " 111.250000 | \n",
+ " -3.729927e-02 | \n",
+ " -4.464164e-02 | \n",
+ " -3.422907e-02 | \n",
+ " -3.665645e-02 | \n",
+ " -3.424784e-02 | \n",
+ " -3.035840e-02 | \n",
+ " -3.511716e-02 | \n",
+ " -3.949338e-02 | \n",
+ " -3.324879e-02 | \n",
+ " -3.317903e-02 | \n",
+ " 87.000000 | \n",
+ "
\n",
+ " \n",
+ " | 50% | \n",
+ " 221.500000 | \n",
+ " 5.383060e-03 | \n",
+ " -4.464164e-02 | \n",
+ " -7.283766e-03 | \n",
+ " -5.670611e-03 | \n",
+ " -4.320866e-03 | \n",
+ " -3.819065e-03 | \n",
+ " -6.584468e-03 | \n",
+ " -2.592262e-03 | \n",
+ " -1.947634e-03 | \n",
+ " -1.077698e-03 | \n",
+ " 140.500000 | \n",
+ "
\n",
+ " \n",
+ " | 75% | \n",
+ " 331.750000 | \n",
+ " 3.807591e-02 | \n",
+ " 5.068012e-02 | \n",
+ " 3.124802e-02 | \n",
+ " 3.564384e-02 | \n",
+ " 2.835801e-02 | \n",
+ " 2.984439e-02 | \n",
+ " 2.931150e-02 | \n",
+ " 3.430886e-02 | \n",
+ " 3.243323e-02 | \n",
+ " 2.791705e-02 | \n",
+ " 211.500000 | \n",
+ "
\n",
+ " \n",
+ " | max | \n",
+ " 442.000000 | \n",
+ " 1.107267e-01 | \n",
+ " 5.068012e-02 | \n",
+ " 1.705552e-01 | \n",
+ " 1.320442e-01 | \n",
+ " 1.539137e-01 | \n",
+ " 1.987880e-01 | \n",
+ " 1.811791e-01 | \n",
+ " 1.852344e-01 | \n",
+ " 1.335990e-01 | \n",
+ " 1.356118e-01 | \n",
+ " 346.000000 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
"
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "import matplotlib.pyplot as plt\n",
+ "%matplotlib inline\n",
+ "\n",
+ "fig = new_data.boxplot(column=[\"bmi\"]) \n",
+ "\n",
+ "\n",
+ " "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "fig2 = new_data.boxplot(column=[\"s1\"])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "fig2 = new_data.boxplot(column=[\"sex\"])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "fig2 = new_data.boxplot(column=[\"bp\"])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "fig2 = new_data.boxplot(column=[\"s2\"])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "fig2 = new_data.boxplot(column=[\"s3\"])"
]
},
{
"cell_type": "code",
+ "execution_count": 20,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "fig2 = new_data.boxplot(column=[\"s4\"])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "fig2 = new_data.boxplot(column=[\"s5\"])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 22,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "fig2 = new_data.boxplot(column=[\"s6\"])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 23,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAD4CAYAAAAXUaZHAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8QVMy6AAAACXBIWXMAAAsTAAALEwEAmpwYAAAQEUlEQVR4nO3df6zddX3H8ecLaACBKAS4qaWxZKuL4EbJbpgby3IVI0yyFGNYaow0k6wuYqIJWVbMEjWkC0v88ZeYXKOxWZxdt0noqBKx4cSwDGrLQCk/Qjcq1jZ0KgplppH63h/3i57Re3vPveeee+nnPh/Jyfmez/fz+X7fJ/ne1/3mcz7n3lQVkqS2nLbUBUiSFp7hLkkNMtwlqUGGuyQ1yHCXpAadsdQFAFx44YW1Zs2apS5DmtZLL73EOeecs9RlSCfYu3fvj6vqoun2vSbCfc2aNezZs2epy5Cm1ev1mJiYWOoypBMk+cFM+5yWkaQGGe6S1CDDXZIaNGu4Jzkrye4kjybZl+RTXfsnk/woySPd4919Y25Lsj/JU0muHeUbkCSdaJAPVI8B76iqo0lWAA8k+Wa373NV9en+zkkuAzYAlwNvBL6d5M1VdXwhC5ckzWzWO/eacrR7uaJ7nOyvja0HtlXVsap6BtgPXDV0pZKkgQ20FDLJ6cBe4LeBz1fVQ0n+FPhIkpuAPcCtVfU8sAp4sG/4wa7t1cfcBGwCGBsbo9frDfM+pJE5evSo16dOOQOFezelsi7JG4C7krwV+AJwO1N38bcDnwE+CGS6Q0xzzElgEmB8fLxcR6zXKte561Q0py8xVdXPkvSA6/rn2pN8Ebine3kQWN037BLg0JB1Sgsime7eY+H5fxK01AZZLXNRd8dOkrOBdwJPJlnZ1+09wGPd9g5gQ5Izk1wKrAV2L2jV0jxV1Zwfb/qbe+Y8Rlpqg9y5rwS2dvPupwHbq+qeJP+QZB1TUy4HgA8BVNW+JNuBx4GXgVtcKSNJi2vWcK+q7wFXTtP+gZOM2QJsGa40SdJ8+Q1VSWqQ4S5JDTLcJalBhrskNchwl6QGGe6S1CDDXZIaZLhLUoMMd0lqkOEuSQ0y3CWpQYa7JDXIcJekBhnuktQgw12SGmS4S1KDDHdJapDhLkkNMtwlqUGGuyQ1yHCXpAbNGu5JzkqyO8mjSfYl+VTXfkGS+5I83T2f3zfmtiT7kzyV5NpRvgFJ0okGuXM/Bryjqq4A1gHXJXkbsBnYVVVrgV3da5JcBmwALgeuA+5McvoIapckzWDWcK8pR7uXK7pHAeuBrV37VuCGbns9sK2qjlXVM8B+4KqFLFqSdHIDzbknOT3JI8AR4L6qeggYq6rDAN3zxV33VcAP+4Yf7NokSYvkjEE6VdVxYF2SNwB3JXnrSbpnukOc0CnZBGwCGBsbo9frDVKKtCS8PnWqGSjcX1FVP0vSY2ou/bkkK6vqcJKVTN3Vw9Sd+uq+YZcAh6Y51iQwCTA+Pl4TExNzr15aDPfuxOtTp5pBVstc1N2xk+Rs4J3Ak8AOYGPXbSNwd7e9A9iQ5MwklwJrgd0LXLck6SQGuXNfCWztVrycBmyvqnuS/AewPcnNwLPAjQBVtS/JduBx4GXglm5aR5K0SGYN96r6HnDlNO0/Aa6ZYcwWYMvQ1UmS5sVvqEpSgwx3SWqQ4S5JDTLcJalBhrskNchwl6QGGe6S1CDDXZIaZLhLUoMMd0lqkOEuSQ0y3CWpQYa7JDXIcJekBhnuktQgw12SGmS4S1KDDHdJapDhLkkNMtwlqUGGuyQ1yHCXpAbNGu5JVie5P8kTSfYl+WjX/skkP0rySPd4d9+Y25LsT/JUkmtH+QYkSSc6Y4A+LwO3VtXDSc4D9ia5r9v3uar6dH/nJJcBG4DLgTcC307y5qo6vpCFS5JmNuude1UdrqqHu+0XgSeAVScZsh7YVlXHquoZYD9w1UIUK0kazCB37r+WZA1wJfAQcDXwkSQ3AXuYurt/nqngf7Bv2EGm+WWQZBOwCWBsbIxerzeP8qXF4fWpU83A4Z7kXOBfgY9V1QtJvgDcDlT3/Bngg0CmGV4nNFRNApMA4+PjNTExMefipUVx7068PnWqGWi1TJIVTAX7V6vq6wBV9VxVHa+qXwFf5DdTLweB1X3DLwEOLVzJkqTZDLJaJsCXgCeq6rN97Sv7ur0HeKzb3gFsSHJmkkuBtcDuhStZkjSbQaZlrgY+AHw/ySNd28eB9yVZx9SUywHgQwBVtS/JduBxplba3OJKGUlaXLOGe1U9wPTz6N84yZgtwJYh6pIkDcFvqEpSgwx3SWqQ4S5JDTLcJalBhrskNchwl6QGGe6S1CDDXZIaZLhLUoMMd0lqkOEuSQ0y3CWpQYa7JDXIcJekBhnuktQgw12SGmS4S1KDDHdJatAg/0NVes264lPf4ue/+OXIz7Nm886RHv/1Z6/g0U+8a6Tn0PJiuOuU9vNf/JIDd1w/0nP0ej0mJiZGeo5R//LQ8uO0jCQ1yHCXpAbNGu5JVie5P8kTSfYl+WjXfkGS+5I83T2f3zfmtiT7kzyV5NpRvgFJ0okGuXN/Gbi1qt4CvA24JcllwGZgV1WtBXZ1r+n2bQAuB64D7kxy+iiKlyRNb9Zwr6rDVfVwt/0i8ASwClgPbO26bQVu6LbXA9uq6lhVPQPsB65a4LolSScxp9UySdYAVwIPAWNVdRimfgEkubjrtgp4sG/Ywa7t1cfaBGwCGBsbo9frzbV2CWDk187Ro0cX5fr0Z0ALaeBwT3Iu8K/Ax6rqhSQzdp2mrU5oqJoEJgHGx8dr1EvN1Kh7d458meJiLIVcjPeh5WWg1TJJVjAV7F+tqq93zc8lWdntXwkc6doPAqv7hl8CHFqYciVJgxhktUyALwFPVNVn+3btADZ22xuBu/vaNyQ5M8mlwFpg98KVLEmazSDTMlcDHwC+n+SRru3jwB3A9iQ3A88CNwJU1b4k24HHmVppc0tVHV/owiVJM5s13KvqAaafRwe4ZoYxW4AtQ9QlSRqC31CVpAYZ7pLUIMNdkhpkuEtSgwx3SWqQ4S5JDTLcJalBhrskNchwl6QGGe6S1CDDXZIaZLhLUoMMd0lqkOEuSQ0y3CWpQYa7JDXIcJekBhnuktQgw12SGmS4S1KDDHdJapDhLkkNmjXck3w5yZEkj/W1fTLJj5I80j3e3bfvtiT7kzyV5NpRFS5Jmtkgd+5fAa6bpv1zVbWue3wDIMllwAbg8m7MnUlOX6hiJUmDmTXcq+o7wE8HPN56YFtVHauqZ4D9wFVD1CdJmoczhhj7kSQ3AXuAW6vqeWAV8GBfn4Nd2wmSbAI2AYyNjdHr9YYoRcvZqK+do0ePLsr16c+AFtJ8w/0LwO1Adc+fAT4IZJq+Nd0BqmoSmAQYHx+viYmJeZaiZe3enYz62un1eiM/x2K8Dy0v81otU1XPVdXxqvoV8EV+M/VyEFjd1/US4NBwJUqS5mpe4Z5kZd/L9wCvrKTZAWxIcmaSS4G1wO7hSpQkzdWs0zJJvgZMABcmOQh8AphIso6pKZcDwIcAqmpfku3A48DLwC1VdXwklUuSZjRruFfV+6Zp/tJJ+m8BtgxTlCRpOMOslpGW3Hlv2czvbt08+hNtHe3hz3sLwPWjPYmWFcNdp7QXn7iDA3eMNhQXY7XMms07R3p8LT/+bRlJapDhLkkNMtwlqUGGuyQ1yHCXpAYZ7pLUIMNdkhpkuEtSgwx3SWqQ4S5JDTLcJalBhrskNchwl6QGGe6S1CDDXZIaZLhLUoMMd0lqkOEuSQ0y3CWpQYa7JDVo1nBP8uUkR5I81td2QZL7kjzdPZ/ft++2JPuTPJXk2lEVLkma2SB37l8BrntV22ZgV1WtBXZ1r0lyGbABuLwbc2eS0xesWknSQGYN96r6DvDTVzWvB7Z221uBG/rat1XVsap6BtgPXLUwpUqSBnXGPMeNVdVhgKo6nOTirn0V8GBfv4Nd2wmSbAI2AYyNjdHr9eZZipa7UV87R48eXZTr058BLaT5hvtMMk1bTdexqiaBSYDx8fGamJhY4FK0LNy7k1FfO71eb+TnWIz3oeVlvqtlnkuyEqB7PtK1HwRW9/W7BDg0//IkSfMx33DfAWzstjcCd/e1b0hyZpJLgbXA7uFKlCTN1azTMkm+BkwAFyY5CHwCuAPYnuRm4FngRoCq2pdkO/A48DJwS1UdH1HtkqQZzBruVfW+GXZdM0P/LcCWYYqSJA3Hb6hKUoMMd0lq0EIvhZQW3ZrNO0d/kntHe47Xn71ipMfX8mO465R24I7rR36ONZt3Lsp5pIXktIwkNchwl6QGGe6S1CDDXZIaZLhLUoMMd0lqkOEuSQ0y3CWpQYa7JDXIcJekBhnuktQgw12SGmS4S1KDDHdJapDhLkkNMtwlqUGGuyQ1aKj/xJTkAPAicBx4uarGk1wA/BOwBjgA/HlVPT9cmZKkuViIO/e3V9W6qhrvXm8GdlXVWmBX91qStIhGMS2zHtjabW8FbhjBOSRJJzFsuBfwrSR7k2zq2saq6jBA93zxkOeQJM3RUHPuwNVVdSjJxcB9SZ4cdGD3y2ATwNjYGL1eb8hSpNHx+tSpZqhwr6pD3fORJHcBVwHPJVlZVYeTrASOzDB2EpgEGB8fr4mJiWFKkUbn3p14fepUM+9pmSTnJDnvlW3gXcBjwA5gY9dtI3D3sEVKkuZmmDv3MeCuJK8c5x+r6t4k3wW2J7kZeBa4cfgyJUlzMe9wr6r/Bq6Ypv0nwDXDFCVJGo7fUJWkBhnuktQgw12SGmS4S1KDDHdJapDhLkkNMtwlqUGGuyQ1yHCXpAYZ7pLUoGH/5K90Sun+FtLcx/393PpX1bzOIy0U79y1rFTVnB/333//nMdIS81wl6QGGe6S1CDDXZIaZLhLUoMMd0lqkOEuSQ0y3CWpQYa7JDUor4UvXCT5H+AHS12HNIMLgR8vdRHSNN5UVRdNt+M1Ee7Sa1mSPVU1vtR1SHPhtIwkNchwl6QGGe7S7CaXugBprpxzl6QGeecuSQ0y3CWpQYa7loUkb0jy4UU4zw1JLhv1eaTZGO5aLt4ADBzumTKfn48bAMNdS84PVLUsJNkGrAeeAu4Hfg84H1gB/G1V3Z1kDfDNbv8fMhXUNwHvB37I1LdU91bVp5P8FvB54CLgf4G/BC4A7gF+3j3eW1X/tUhvUfp//AfZWi42A2+tqnVJzgBeV1UvJLkQeDDJjq7f7wB/UVUfTjIOvBe4kqmflYeBvV2/SeCvqurpJH8A3FlV7+iOc09V/ctivjnp1Qx3LUcB/i7JnwC/AlYBY92+H1TVg932HwN3V9UvAJL8W/d8LvBHwD8neeWYZy5S7dJADHctR+9najrl96vql0kOAGd1+17q65dXD+ycBvysqtaNrEJpSH6gquXiReC8bvv1wJEu2N8OvGmGMQ8Af5bkrO5u/XqAqnoBeCbJjfDrD1+vmOY80pIx3LUsVNVPgH9P8hiwDhhPsoepu/gnZxjzXWAH8CjwdWAPUx+U0o27OcmjwD6mPqwF2Ab8dZL/7D50lZaEq2Wkk0hyblUdTfI64DvApqp6eKnrkmbjnLt0cpPdl5LOArYa7DpVeOcuSQ1yzl2SGmS4S1KDDHdJapDhLkkNMtwlqUH/BxZouziTmHJTAAAAAElFTkSuQmCC",
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "fig2 = new_data.boxplot(column=[\"target\"])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 24,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "fig2 = new_data.boxplot(column=[\"age\"])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "\"\"\"id 662.500000\n",
+ "age 0.151139\n",
+ "sex 0.193663\n",
+ "bmi 0.129464\n",
+ "bp 0.144094\n",
+ "s1 0.122267\n",
+ "s2 0.120149\n",
+ "s3 0.125954\n",
+ "s4 0.145012\n",
+ "s5 0.130956\n",
+ "s6 0.119561\n",
+ "target 398.250000\n",
+ "dtype: float64\"\"\"\n",
+ "\n",
+ "\"\"\"id -219.500000\n",
+ "age -0.150362\n",
+ "sex -0.187624\n",
+ "bmi -0.132445\n",
+ "bp -0.145107\n",
+ "s1 -0.128157\n",
+ "s2 -0.120663\n",
+ "s3 -0.131760\n",
+ "s4 -0.150197\n",
+ "s5 -0.131772\n",
+ "s6 -0.124823\n",
+ "target -99.750000\n",
+ "dtype: float64\"\"\""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Step 4 - Clean your data\n",
+ "\n",
+ "* Remove null or missing values\n",
+ "* Clean data types\n",
+ "* Remove outliers"
+ ]
+ },
+ {
+ "cell_type": "code",
+<<<<<<< HEAD
+ "execution_count": 32,
+=======
+ "execution_count": 39,
+>>>>>>> 5f2dd86669233d319ebe9f0f010a6cd6905ddf12
+ "metadata": {},
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Initial number of obs: 884\nRemoved duplicates number of obs: 442\n"
+ ]
+ }
+ ],
+ "source": [
+<<<<<<< HEAD
+ "new_data = new_data.drop(new_data.index[new_data[\"bmi\"] >= 0.129464])\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 33,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "new_data = new_data.drop(new_data.index[new_data[\"bmi\"] <= -0.132445])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 34,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "new_data = new_data.drop(new_data.index[new_data[\"s1\"] >= 0.122267])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 35,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "new_data = new_data.drop(new_data.index[new_data[\"s1\"] <= -0.128157])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 36,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "new_data = new_data.drop(new_data.index[new_data[\"s2\"] >= 0.120149])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 37,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "new_data = new_data.drop(new_data.index[new_data[\"s2\"] <= -0.120663])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 38,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "new_data = new_data.drop(new_data.index[new_data[\"s3\"] >= 0.125954])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 39,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "new_data = new_data.drop(new_data.index[new_data[\"s4\"] >= 0.145012])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 60,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "new_data = new_data.drop(new_data.index[new_data[\"s5\"] >= 0.130956])\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 59,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "new_data = new_data.drop(new_data.index[new_data[\"s6\"] >= 0.119561])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 61,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "new_data = new_data.drop(new_data.index[new_data[\"s6\"] <= -0.124823])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 62,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " id | \n",
+ " age | \n",
+ " sex | \n",
+ " bmi | \n",
+ " bp | \n",
+ " s1 | \n",
+ " s2 | \n",
+ " s3 | \n",
+ " s4 | \n",
+ " s5 | \n",
+ " s6 | \n",
+ " target | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 1 | \n",
+ " 0.038076 | \n",
+ " 0.050680 | \n",
+ " 0.061696 | \n",
+ " 0.021872 | \n",
+ " -0.044223 | \n",
+ " -0.034821 | \n",
+ " -0.043401 | \n",
+ " -0.002592 | \n",
+ " 0.019908 | \n",
+ " -0.017646 | \n",
+ " 151.0 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 2 | \n",
+ " -0.001882 | \n",
+ " -0.044642 | \n",
+ " -0.051474 | \n",
+ " -0.026328 | \n",
+ " -0.008449 | \n",
+ " -0.019163 | \n",
+ " 0.074412 | \n",
+ " -0.039493 | \n",
+ " -0.068330 | \n",
+ " -0.092204 | \n",
+ " 75.0 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 3 | \n",
+ " 0.085299 | \n",
+ " 0.050680 | \n",
+ " 0.044451 | \n",
+ " -0.005671 | \n",
+ " -0.045599 | \n",
+ " -0.034194 | \n",
+ " -0.032356 | \n",
+ " -0.002592 | \n",
+ " 0.002864 | \n",
+ " -0.025930 | \n",
+ " 141.0 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 4 | \n",
+ " -0.089063 | \n",
+ " -0.044642 | \n",
+ " -0.011595 | \n",
+ " -0.036656 | \n",
+ " 0.012191 | \n",
+ " 0.024991 | \n",
+ " -0.036038 | \n",
+ " 0.034309 | \n",
+ " 0.022692 | \n",
+ " -0.009362 | \n",
+ " 206.0 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 5 | \n",
+ " 0.005383 | \n",
+ " -0.044642 | \n",
+ " -0.036385 | \n",
+ " 0.021872 | \n",
+ " 0.003935 | \n",
+ " 0.015596 | \n",
+ " 0.008142 | \n",
+ " -0.002592 | \n",
+ " -0.031991 | \n",
+ " -0.046641 | \n",
+ " 135.0 | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 436 | \n",
+ " 437 | \n",
+ " -0.056370 | \n",
+ " -0.044642 | \n",
+ " -0.074108 | \n",
+ " -0.050428 | \n",
+ " -0.024960 | \n",
+ " -0.047034 | \n",
+ " 0.092820 | \n",
+ " -0.076395 | \n",
+ " -0.061177 | \n",
+ " -0.046641 | \n",
+ " 48.0 | \n",
+ "
\n",
+ " \n",
+ " | 437 | \n",
+ " 438 | \n",
+ " 0.041708 | \n",
+ " 0.050680 | \n",
+ " 0.019662 | \n",
+ " 0.059744 | \n",
+ " -0.005697 | \n",
+ " -0.002566 | \n",
+ " -0.028674 | \n",
+ " -0.002592 | \n",
+ " 0.031193 | \n",
+ " 0.007207 | \n",
+ " 178.0 | \n",
+ "
\n",
+ " \n",
+ " | 438 | \n",
+ " 439 | \n",
+ " -0.005515 | \n",
+ " 0.050680 | \n",
+ " -0.015906 | \n",
+ " -0.067642 | \n",
+ " 0.049341 | \n",
+ " 0.079165 | \n",
+ " -0.028674 | \n",
+ " 0.034309 | \n",
+ " -0.018118 | \n",
+ " 0.044485 | \n",
+ " 104.0 | \n",
+ "
\n",
+ " \n",
+ " | 439 | \n",
+ " 440 | \n",
+ " 0.041708 | \n",
+ " 0.050680 | \n",
+ " -0.015906 | \n",
+ " 0.017282 | \n",
+ " -0.037344 | \n",
+ " -0.013840 | \n",
+ " -0.024993 | \n",
+ " -0.011080 | \n",
+ " -0.046879 | \n",
+ " 0.015491 | \n",
+ " 132.0 | \n",
+ "
\n",
+ " \n",
+ " | 440 | \n",
+ " 441 | \n",
+ " -0.045472 | \n",
+ " -0.044642 | \n",
+ " 0.039062 | \n",
+ " 0.001215 | \n",
+ " 0.016318 | \n",
+ " 0.015283 | \n",
+ " -0.028674 | \n",
+ " 0.026560 | \n",
+ " 0.044528 | \n",
+ " -0.025930 | \n",
+ " 220.0 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
405 rows × 12 columns
\n",
+ "
"
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "new_data[\"s4\"].hist()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 71,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "fig=new_data.boxplot(column=[\"s6\"])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 72,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "id 604.988885\n",
+ "age 0.144483\n",
+ "sex 0.142964\n",
+ "bmi 0.134793\n",
+ "bp 0.138984\n",
+ "s1 0.126069\n",
+ "s2 0.129446\n",
+ "s3 0.128641\n",
+ "s4 0.124469\n",
+ "s5 0.127318\n",
+ "s6 0.129779\n",
+ "target 373.231272\n",
+ "dtype: float64"
+ ]
+ },
+ "execution_count": 72,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "#another way for detecting outliers:\n",
+ "\n",
+ "standard_deviation = new_data.std()\n",
+ "mean = new_data.mean()\n",
+ "upper_limit2 = mean + 3 * standard_deviation\n",
+ "upper_limit2"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 73,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "id -167.561725\n",
+ "age -0.145395\n",
+ "sex -0.142809\n",
+ "bmi -0.138566\n",
+ "bp -0.140351\n",
+ "s1 -0.135533\n",
+ "s2 -0.134468\n",
+ "s3 -0.130547\n",
+ "s4 -0.131420\n",
+ "s5 -0.135127\n",
+ "s6 -0.134819\n",
+ "target -76.199174\n",
+ "dtype: float64"
+ ]
+ },
+ "execution_count": 73,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "lower_limit2 = mean - 3 * standard_deviation\n",
+ "lower_limit2"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " id | \n",
+ " age | \n",
+ " sex | \n",
+ " bmi | \n",
+ " bp | \n",
+ " s1 | \n",
+ " s2 | \n",
+ " s3 | \n",
+ " s4 | \n",
+ " s5 | \n",
+ " s6 | \n",
+ " target | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 1 | \n",
+ " 0.038076 | \n",
+ " 0.050680 | \n",
+ " 0.061696 | \n",
+ " 0.021872 | \n",
+ " -0.044223 | \n",
+ " -0.034821 | \n",
+ " -0.043401 | \n",
+ " -0.002592 | \n",
+ " 0.019908 | \n",
+ " -0.017646 | \n",
+ " 151.0 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 2 | \n",
+ " -0.001882 | \n",
+ " -0.044642 | \n",
+ " -0.051474 | \n",
+ " -0.026328 | \n",
+ " -0.008449 | \n",
+ " -0.019163 | \n",
+ " 0.074412 | \n",
+ " -0.039493 | \n",
+ " -0.068330 | \n",
+ " -0.092204 | \n",
+ " 75.0 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 3 | \n",
+ " 0.085299 | \n",
+ " 0.050680 | \n",
+ " 0.044451 | \n",
+ " -0.005671 | \n",
+ " -0.045599 | \n",
+ " -0.034194 | \n",
+ " -0.032356 | \n",
+ " -0.002592 | \n",
+ " 0.002864 | \n",
+ " -0.025930 | \n",
+ " 141.0 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 4 | \n",
+ " -0.089063 | \n",
+ " -0.044642 | \n",
+ " -0.011595 | \n",
+ " -0.036656 | \n",
+ " 0.012191 | \n",
+ " 0.024991 | \n",
+ " -0.036038 | \n",
+ " 0.034309 | \n",
+ " 0.022692 | \n",
+ " -0.009362 | \n",
+ " 206.0 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 5 | \n",
+ " 0.005383 | \n",
+ " -0.044642 | \n",
+ " -0.036385 | \n",
+ " 0.021872 | \n",
+ " 0.003935 | \n",
+ " 0.015596 | \n",
+ " 0.008142 | \n",
+ " -0.002592 | \n",
+ " -0.031991 | \n",
+ " -0.046641 | \n",
+ " 135.0 | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 436 | \n",
+ " 437 | \n",
+ " -0.056370 | \n",
+ " -0.044642 | \n",
+ " -0.074108 | \n",
+ " -0.050428 | \n",
+ " -0.024960 | \n",
+ " -0.047034 | \n",
+ " 0.092820 | \n",
+ " -0.076395 | \n",
+ " -0.061177 | \n",
+ " -0.046641 | \n",
+ " 48.0 | \n",
+ "
\n",
+ " \n",
+ " | 437 | \n",
+ " 438 | \n",
+ " 0.041708 | \n",
+ " 0.050680 | \n",
+ " 0.019662 | \n",
+ " 0.059744 | \n",
+ " -0.005697 | \n",
+ " -0.002566 | \n",
+ " -0.028674 | \n",
+ " -0.002592 | \n",
+ " 0.031193 | \n",
+ " 0.007207 | \n",
+ " 178.0 | \n",
+ "
\n",
+ " \n",
+ " | 438 | \n",
+ " 439 | \n",
+ " -0.005515 | \n",
+ " 0.050680 | \n",
+ " -0.015906 | \n",
+ " -0.067642 | \n",
+ " 0.049341 | \n",
+ " 0.079165 | \n",
+ " -0.028674 | \n",
+ " 0.034309 | \n",
+ " -0.018118 | \n",
+ " 0.044485 | \n",
+ " 104.0 | \n",
+ "
\n",
+ " \n",
+ " | 439 | \n",
+ " 440 | \n",
+ " 0.041708 | \n",
+ " 0.050680 | \n",
+ " -0.015906 | \n",
+ " 0.017282 | \n",
+ " -0.037344 | \n",
+ " -0.013840 | \n",
+ " -0.024993 | \n",
+ " -0.011080 | \n",
+ " -0.046879 | \n",
+ " 0.015491 | \n",
+ " 132.0 | \n",
+ "
\n",
+ " \n",
+ " | 440 | \n",
+ " 441 | \n",
+ " -0.045472 | \n",
+ " -0.044642 | \n",
+ " 0.039062 | \n",
+ " 0.001215 | \n",
+ " 0.016318 | \n",
+ " 0.015283 | \n",
+ " -0.028674 | \n",
+ " 0.026560 | \n",
+ " 0.044528 | \n",
+ " -0.025930 | \n",
+ " 220.0 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
409 rows × 12 columns
\n",
+ "
"
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "fig=new_data.boxplot(column=[\"s6\"])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ ":3: FutureWarning: Automatic reindexing on DataFrame vs Series comparisons is deprecated and will raise ValueError in a future version. Do `left, right = left.align(right, axis=1, copy=False)` before e.g. `left == right`\n",
+ " new_data = new_data[~((new_data[cols] < (Q1 - 1.5 * IQR)) |(new_data[cols] > (Q3 + 1.5 * IQR))).any(axis=1)]\n",
+ ":3: FutureWarning: Automatic reindexing on DataFrame vs Series comparisons is deprecated and will raise ValueError in a future version. Do `left, right = left.align(right, axis=1, copy=False)` before e.g. `left == right`\n",
+ " new_data = new_data[~((new_data[cols] < (Q1 - 1.5 * IQR)) |(new_data[cols] > (Q3 + 1.5 * IQR))).any(axis=1)]\n"
+ ]
+ }
+ ],
+ "source": [
+ "#Another round of data cleaning\n",
+ "cols=[\"age\", \"sex\", \"bmi\", \"bp\", \"s1\", \"s2\", \"s3\", \"s4\", \"s5\", \"s6\", \"target\"]\n",
+ "new_data = new_data[~((new_data[cols] < (Q1 - 1.5 * IQR)) |(new_data[cols] > (Q3 + 1.5 * IQR))).any(axis=1)]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " id | \n",
+ " age | \n",
+ " sex | \n",
+ " bmi | \n",
+ " bp | \n",
+ " s1 | \n",
+ " s2 | \n",
+ " s3 | \n",
+ " s4 | \n",
+ " s5 | \n",
+ " s6 | \n",
+ " target | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 1 | \n",
+ " 0.038076 | \n",
+ " 0.050680 | \n",
+ " 0.061696 | \n",
+ " 0.021872 | \n",
+ " -0.044223 | \n",
+ " -0.034821 | \n",
+ " -0.043401 | \n",
+ " -0.002592 | \n",
+ " 0.019908 | \n",
+ " -0.017646 | \n",
+ " 151.0 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 2 | \n",
+ " -0.001882 | \n",
+ " -0.044642 | \n",
+ " -0.051474 | \n",
+ " -0.026328 | \n",
+ " -0.008449 | \n",
+ " -0.019163 | \n",
+ " 0.074412 | \n",
+ " -0.039493 | \n",
+ " -0.068330 | \n",
+ " -0.092204 | \n",
+ " 75.0 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 3 | \n",
+ " 0.085299 | \n",
+ " 0.050680 | \n",
+ " 0.044451 | \n",
+ " -0.005671 | \n",
+ " -0.045599 | \n",
+ " -0.034194 | \n",
+ " -0.032356 | \n",
+ " -0.002592 | \n",
+ " 0.002864 | \n",
+ " -0.025930 | \n",
+ " 141.0 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 4 | \n",
+ " -0.089063 | \n",
+ " -0.044642 | \n",
+ " -0.011595 | \n",
+ " -0.036656 | \n",
+ " 0.012191 | \n",
+ " 0.024991 | \n",
+ " -0.036038 | \n",
+ " 0.034309 | \n",
+ " 0.022692 | \n",
+ " -0.009362 | \n",
+ " 206.0 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 5 | \n",
+ " 0.005383 | \n",
+ " -0.044642 | \n",
+ " -0.036385 | \n",
+ " 0.021872 | \n",
+ " 0.003935 | \n",
+ " 0.015596 | \n",
+ " 0.008142 | \n",
+ " -0.002592 | \n",
+ " -0.031991 | \n",
+ " -0.046641 | \n",
+ " 135.0 | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 436 | \n",
+ " 437 | \n",
+ " -0.056370 | \n",
+ " -0.044642 | \n",
+ " -0.074108 | \n",
+ " -0.050428 | \n",
+ " -0.024960 | \n",
+ " -0.047034 | \n",
+ " 0.092820 | \n",
+ " -0.076395 | \n",
+ " -0.061177 | \n",
+ " -0.046641 | \n",
+ " 48.0 | \n",
+ "
\n",
+ " \n",
+ " | 437 | \n",
+ " 438 | \n",
+ " 0.041708 | \n",
+ " 0.050680 | \n",
+ " 0.019662 | \n",
+ " 0.059744 | \n",
+ " -0.005697 | \n",
+ " -0.002566 | \n",
+ " -0.028674 | \n",
+ " -0.002592 | \n",
+ " 0.031193 | \n",
+ " 0.007207 | \n",
+ " 178.0 | \n",
+ "
\n",
+ " \n",
+ " | 438 | \n",
+ " 439 | \n",
+ " -0.005515 | \n",
+ " 0.050680 | \n",
+ " -0.015906 | \n",
+ " -0.067642 | \n",
+ " 0.049341 | \n",
+ " 0.079165 | \n",
+ " -0.028674 | \n",
+ " 0.034309 | \n",
+ " -0.018118 | \n",
+ " 0.044485 | \n",
+ " 104.0 | \n",
+ "
\n",
+ " \n",
+ " | 439 | \n",
+ " 440 | \n",
+ " 0.041708 | \n",
+ " 0.050680 | \n",
+ " -0.015906 | \n",
+ " 0.017282 | \n",
+ " -0.037344 | \n",
+ " -0.013840 | \n",
+ " -0.024993 | \n",
+ " -0.011080 | \n",
+ " -0.046879 | \n",
+ " 0.015491 | \n",
+ " 132.0 | \n",
+ "
\n",
+ " \n",
+ " | 440 | \n",
+ " 441 | \n",
+ " -0.045472 | \n",
+ " -0.044642 | \n",
+ " 0.039062 | \n",
+ " 0.001215 | \n",
+ " 0.016318 | \n",
+ " 0.015283 | \n",
+ " -0.028674 | \n",
+ " 0.026560 | \n",
+ " 0.044528 | \n",
+ " -0.025930 | \n",
+ " 220.0 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
409 rows × 12 columns
\n",
+ "