From 1e937297e7b240855b32c95c87a8b6990ccc9403 Mon Sep 17 00:00:00 2001 From: Nawaz Sk Date: Fri, 18 Jan 2019 22:21:44 +0530 Subject: [PATCH 1/3] Created using Colaboratory --- Exercise.ipynb | 977 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 977 insertions(+) create mode 100644 Exercise.ipynb diff --git a/Exercise.ipynb b/Exercise.ipynb new file mode 100644 index 0000000..d67b524 --- /dev/null +++ b/Exercise.ipynb @@ -0,0 +1,977 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "name": "Exercise.ipynb", + "version": "0.3.2", + "provenance": [], + "collapsed_sections": [] + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + } + }, + "cells": [ + { + "metadata": { + "id": "2LTtpUJEibjg", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "# Pandas Exercise :\n", + "\n", + "\n", + "#### import necessary modules" + ] + }, + { + "metadata": { + "id": "c3_UBbMRhiKx", + "colab_type": "code", + "colab": {} + }, + "cell_type": "code", + "source": [ + "import numpy as np\n", + "import pandas as pd" + ], + "execution_count": 0, + "outputs": [] + }, + { + "metadata": { + "id": "tp-cTCyWi8mR", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Load url = \"https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data\" to a dataframe named wine_df\n", + "\n", + "This is a wine dataset\n", + "\n" + ] + }, + { + "metadata": { + "id": "DMojQY3thrRi", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 2176 + }, + "outputId": "3cf51cac-e1ca-4211-bf4f-3b0b97482866" + }, + "cell_type": "code", + "source": [ + "url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data'\n", + "wine_df = pd.read_csv(url)\n", + "print(wine_df)" + ], + "execution_count": 68, + "outputs": [ + { + "output_type": "stream", + "text": [ + " 1 14.23 1.71 2.43 15.6 127 2.8 3.06 .28 2.29 5.64 1.04 \\\n", + "0 1 13.20 1.78 2.14 11.2 100 2.65 2.76 0.26 1.28 4.380000 1.05 \n", + "1 1 13.16 2.36 2.67 18.6 101 2.80 3.24 0.30 2.81 5.680000 1.03 \n", + "2 1 14.37 1.95 2.50 16.8 113 3.85 3.49 0.24 2.18 7.800000 0.86 \n", + "3 1 13.24 2.59 2.87 21.0 118 2.80 2.69 0.39 1.82 4.320000 1.04 \n", + "4 1 14.20 1.76 2.45 15.2 112 3.27 3.39 0.34 1.97 6.750000 1.05 \n", + "5 1 14.39 1.87 2.45 14.6 96 2.50 2.52 0.30 1.98 5.250000 1.02 \n", + "6 1 14.06 2.15 2.61 17.6 121 2.60 2.51 0.31 1.25 5.050000 1.06 \n", + "7 1 14.83 1.64 2.17 14.0 97 2.80 2.98 0.29 1.98 5.200000 1.08 \n", + "8 1 13.86 1.35 2.27 16.0 98 2.98 3.15 0.22 1.85 7.220000 1.01 \n", + "9 1 14.10 2.16 2.30 18.0 105 2.95 3.32 0.22 2.38 5.750000 1.25 \n", + "10 1 14.12 1.48 2.32 16.8 95 2.20 2.43 0.26 1.57 5.000000 1.17 \n", + "11 1 13.75 1.73 2.41 16.0 89 2.60 2.76 0.29 1.81 5.600000 1.15 \n", + "12 1 14.75 1.73 2.39 11.4 91 3.10 3.69 0.43 2.81 5.400000 1.25 \n", + "13 1 14.38 1.87 2.38 12.0 102 3.30 3.64 0.29 2.96 7.500000 1.20 \n", + "14 1 13.63 1.81 2.70 17.2 112 2.85 2.91 0.30 1.46 7.300000 1.28 \n", + "15 1 14.30 1.92 2.72 20.0 120 2.80 3.14 0.33 1.97 6.200000 1.07 \n", + "16 1 13.83 1.57 2.62 20.0 115 2.95 3.40 0.40 1.72 6.600000 1.13 \n", + "17 1 14.19 1.59 2.48 16.5 108 3.30 3.93 0.32 1.86 8.700000 1.23 \n", + "18 1 13.64 3.10 2.56 15.2 116 2.70 3.03 0.17 1.66 5.100000 0.96 \n", + "19 1 14.06 1.63 2.28 16.0 126 3.00 3.17 0.24 2.10 5.650000 1.09 \n", + "20 1 12.93 3.80 2.65 18.6 102 2.41 2.41 0.25 1.98 4.500000 1.03 \n", + "21 1 13.71 1.86 2.36 16.6 101 2.61 2.88 0.27 1.69 3.800000 1.11 \n", + "22 1 12.85 1.60 2.52 17.8 95 2.48 2.37 0.26 1.46 3.930000 1.09 \n", + "23 1 13.50 1.81 2.61 20.0 96 2.53 2.61 0.28 1.66 3.520000 1.12 \n", + "24 1 13.05 2.05 3.22 25.0 124 2.63 2.68 0.47 1.92 3.580000 1.13 \n", + "25 1 13.39 1.77 2.62 16.1 93 2.85 2.94 0.34 1.45 4.800000 0.92 \n", + "26 1 13.30 1.72 2.14 17.0 94 2.40 2.19 0.27 1.35 3.950000 1.02 \n", + "27 1 13.87 1.90 2.80 19.4 107 2.95 2.97 0.37 1.76 4.500000 1.25 \n", + "28 1 14.02 1.68 2.21 16.0 96 2.65 2.33 0.26 1.98 4.700000 1.04 \n", + "29 1 13.73 1.50 2.70 22.5 101 3.00 3.25 0.29 2.38 5.700000 1.19 \n", + ".. .. ... ... ... ... ... ... ... ... ... ... ... \n", + "147 3 13.32 3.24 2.38 21.5 92 1.93 0.76 0.45 1.25 8.420000 0.55 \n", + "148 3 13.08 3.90 2.36 21.5 113 1.41 1.39 0.34 1.14 9.400000 0.57 \n", + "149 3 13.50 3.12 2.62 24.0 123 1.40 1.57 0.22 1.25 8.600000 0.59 \n", + "150 3 12.79 2.67 2.48 22.0 112 1.48 1.36 0.24 1.26 10.800000 0.48 \n", + "151 3 13.11 1.90 2.75 25.5 116 2.20 1.28 0.26 1.56 7.100000 0.61 \n", + "152 3 13.23 3.30 2.28 18.5 98 1.80 0.83 0.61 1.87 10.520000 0.56 \n", + "153 3 12.58 1.29 2.10 20.0 103 1.48 0.58 0.53 1.40 7.600000 0.58 \n", + "154 3 13.17 5.19 2.32 22.0 93 1.74 0.63 0.61 1.55 7.900000 0.60 \n", + "155 3 13.84 4.12 2.38 19.5 89 1.80 0.83 0.48 1.56 9.010000 0.57 \n", + "156 3 12.45 3.03 2.64 27.0 97 1.90 0.58 0.63 1.14 7.500000 0.67 \n", + "157 3 14.34 1.68 2.70 25.0 98 2.80 1.31 0.53 2.70 13.000000 0.57 \n", + "158 3 13.48 1.67 2.64 22.5 89 2.60 1.10 0.52 2.29 11.750000 0.57 \n", + "159 3 12.36 3.83 2.38 21.0 88 2.30 0.92 0.50 1.04 7.650000 0.56 \n", + "160 3 13.69 3.26 2.54 20.0 107 1.83 0.56 0.50 0.80 5.880000 0.96 \n", + "161 3 12.85 3.27 2.58 22.0 106 1.65 0.60 0.60 0.96 5.580000 0.87 \n", + "162 3 12.96 3.45 2.35 18.5 106 1.39 0.70 0.40 0.94 5.280000 0.68 \n", + "163 3 13.78 2.76 2.30 22.0 90 1.35 0.68 0.41 1.03 9.580000 0.70 \n", + "164 3 13.73 4.36 2.26 22.5 88 1.28 0.47 0.52 1.15 6.620000 0.78 \n", + "165 3 13.45 3.70 2.60 23.0 111 1.70 0.92 0.43 1.46 10.680000 0.85 \n", + "166 3 12.82 3.37 2.30 19.5 88 1.48 0.66 0.40 0.97 10.260000 0.72 \n", + "167 3 13.58 2.58 2.69 24.5 105 1.55 0.84 0.39 1.54 8.660000 0.74 \n", + "168 3 13.40 4.60 2.86 25.0 112 1.98 0.96 0.27 1.11 8.500000 0.67 \n", + "169 3 12.20 3.03 2.32 19.0 96 1.25 0.49 0.40 0.73 5.500000 0.66 \n", + "170 3 12.77 2.39 2.28 19.5 86 1.39 0.51 0.48 0.64 9.899999 0.57 \n", + "171 3 14.16 2.51 2.48 20.0 91 1.68 0.70 0.44 1.24 9.700000 0.62 \n", + "172 3 13.71 5.65 2.45 20.5 95 1.68 0.61 0.52 1.06 7.700000 0.64 \n", + "173 3 13.40 3.91 2.48 23.0 102 1.80 0.75 0.43 1.41 7.300000 0.70 \n", + "174 3 13.27 4.28 2.26 20.0 120 1.59 0.69 0.43 1.35 10.200000 0.59 \n", + "175 3 13.17 2.59 2.37 20.0 120 1.65 0.68 0.53 1.46 9.300000 0.60 \n", + "176 3 14.13 4.10 2.74 24.5 96 2.05 0.76 0.56 1.35 9.200000 0.61 \n", + "\n", + " 3.92 1065 \n", + "0 3.40 1050 \n", + "1 3.17 1185 \n", + "2 3.45 1480 \n", + "3 2.93 735 \n", + "4 2.85 1450 \n", + "5 3.58 1290 \n", + "6 3.58 1295 \n", + "7 2.85 1045 \n", + "8 3.55 1045 \n", + "9 3.17 1510 \n", + "10 2.82 1280 \n", + "11 2.90 1320 \n", + "12 2.73 1150 \n", + "13 3.00 1547 \n", + "14 2.88 1310 \n", + "15 2.65 1280 \n", + "16 2.57 1130 \n", + "17 2.82 1680 \n", + "18 3.36 845 \n", + "19 3.71 780 \n", + "20 3.52 770 \n", + "21 4.00 1035 \n", + "22 3.63 1015 \n", + "23 3.82 845 \n", + "24 3.20 830 \n", + "25 3.22 1195 \n", + "26 2.77 1285 \n", + "27 3.40 915 \n", + "28 3.59 1035 \n", + "29 2.71 1285 \n", + ".. ... ... \n", + "147 1.62 650 \n", + "148 1.33 550 \n", + "149 1.30 500 \n", + "150 1.47 480 \n", + "151 1.33 425 \n", + "152 1.51 675 \n", + "153 1.55 640 \n", + "154 1.48 725 \n", + "155 1.64 480 \n", + "156 1.73 880 \n", + "157 1.96 660 \n", + "158 1.78 620 \n", + "159 1.58 520 \n", + "160 1.82 680 \n", + "161 2.11 570 \n", + "162 1.75 675 \n", + "163 1.68 615 \n", + "164 1.75 520 \n", + "165 1.56 695 \n", + "166 1.75 685 \n", + "167 1.80 750 \n", + "168 1.92 630 \n", + "169 1.83 510 \n", + "170 1.63 470 \n", + "171 1.71 660 \n", + "172 1.74 740 \n", + "173 1.56 750 \n", + "174 1.56 835 \n", + "175 1.62 840 \n", + "176 1.60 560 \n", + "\n", + "[177 rows x 14 columns]\n" + ], + "name": "stdout" + } + ] + }, + { + "metadata": { + "id": "BF9MMjoZjSlg", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### print first five rows" + ] + }, + { + "metadata": { + "id": "1vSMQdnHjYNU", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 204 + }, + "outputId": "e2da40ba-9b64-4ee2-cdcf-e6a19ed962ff" + }, + "cell_type": "code", + "source": [ + "wine_df.head(5)" + ], + "execution_count": 69, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
114.231.712.4315.61272.83.06.282.295.641.043.921065
0113.201.782.1411.21002.652.760.261.284.381.053.401050
1113.162.362.6718.61012.803.240.302.815.681.033.171185
2114.371.952.5016.81133.853.490.242.187.800.863.451480
3113.242.592.8721.01182.802.690.391.824.321.042.93735
4114.201.762.4515.21123.273.390.341.976.751.052.851450
\n", + "
" + ], + "text/plain": [ + " 1 14.23 1.71 2.43 15.6 127 2.8 3.06 .28 2.29 5.64 1.04 3.92 \\\n", + "0 1 13.20 1.78 2.14 11.2 100 2.65 2.76 0.26 1.28 4.38 1.05 3.40 \n", + "1 1 13.16 2.36 2.67 18.6 101 2.80 3.24 0.30 2.81 5.68 1.03 3.17 \n", + "2 1 14.37 1.95 2.50 16.8 113 3.85 3.49 0.24 2.18 7.80 0.86 3.45 \n", + "3 1 13.24 2.59 2.87 21.0 118 2.80 2.69 0.39 1.82 4.32 1.04 2.93 \n", + "4 1 14.20 1.76 2.45 15.2 112 3.27 3.39 0.34 1.97 6.75 1.05 2.85 \n", + "\n", + " 1065 \n", + "0 1050 \n", + "1 1185 \n", + "2 1480 \n", + "3 735 \n", + "4 1450 " + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 69 + } + ] + }, + { + "metadata": { + "id": "Tet6P2DvjY3T", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### assign wine_df to a different variable wine_df_copy and then delete all odd rows of wine_df_copy\n", + "\n", + "[Hint](https://pandas.pydata.org/pandas-docs/stable/generated/pandas.DataFrame.drop.html)" + ] + }, + { + "metadata": { + "id": "CMj3qSdJjx0u", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 2176 + }, + "outputId": "1f9337b1-d130-43c9-cbb9-ae76dd486e0c" + }, + "cell_type": "code", + "source": [ + "wine_df_copy = wine_df\n", + "wine_df_copy = wine_df_copy[wine_df_copy.index%2 == 0]\n", + "print(wine_df_copy)" + ], + "execution_count": 70, + "outputs": [ + { + "output_type": "stream", + "text": [ + " 1 14.23 1.71 2.43 15.6 127 2.8 3.06 .28 2.29 5.64 1.04 \\\n", + "0 1 13.20 1.78 2.14 11.2 100 2.65 2.76 0.26 1.28 4.380000 1.05 \n", + "2 1 14.37 1.95 2.50 16.8 113 3.85 3.49 0.24 2.18 7.800000 0.86 \n", + "4 1 14.20 1.76 2.45 15.2 112 3.27 3.39 0.34 1.97 6.750000 1.05 \n", + "6 1 14.06 2.15 2.61 17.6 121 2.60 2.51 0.31 1.25 5.050000 1.06 \n", + "8 1 13.86 1.35 2.27 16.0 98 2.98 3.15 0.22 1.85 7.220000 1.01 \n", + "10 1 14.12 1.48 2.32 16.8 95 2.20 2.43 0.26 1.57 5.000000 1.17 \n", + "12 1 14.75 1.73 2.39 11.4 91 3.10 3.69 0.43 2.81 5.400000 1.25 \n", + "14 1 13.63 1.81 2.70 17.2 112 2.85 2.91 0.30 1.46 7.300000 1.28 \n", + "16 1 13.83 1.57 2.62 20.0 115 2.95 3.40 0.40 1.72 6.600000 1.13 \n", + "18 1 13.64 3.10 2.56 15.2 116 2.70 3.03 0.17 1.66 5.100000 0.96 \n", + "20 1 12.93 3.80 2.65 18.6 102 2.41 2.41 0.25 1.98 4.500000 1.03 \n", + "22 1 12.85 1.60 2.52 17.8 95 2.48 2.37 0.26 1.46 3.930000 1.09 \n", + "24 1 13.05 2.05 3.22 25.0 124 2.63 2.68 0.47 1.92 3.580000 1.13 \n", + "26 1 13.30 1.72 2.14 17.0 94 2.40 2.19 0.27 1.35 3.950000 1.02 \n", + "28 1 14.02 1.68 2.21 16.0 96 2.65 2.33 0.26 1.98 4.700000 1.04 \n", + "30 1 13.58 1.66 2.36 19.1 106 2.86 3.19 0.22 1.95 6.900000 1.09 \n", + "32 1 13.76 1.53 2.70 19.5 132 2.95 2.74 0.50 1.35 5.400000 1.25 \n", + "34 1 13.48 1.81 2.41 20.5 100 2.70 2.98 0.26 1.86 5.100000 1.04 \n", + "36 1 13.05 1.65 2.55 18.0 98 2.45 2.43 0.29 1.44 4.250000 1.12 \n", + "38 1 14.22 3.99 2.51 13.2 128 3.00 3.04 0.20 2.08 5.100000 0.89 \n", + "40 1 13.41 3.84 2.12 18.8 90 2.45 2.68 0.27 1.48 4.280000 0.91 \n", + "42 1 13.24 3.98 2.29 17.5 103 2.64 2.63 0.32 1.66 4.360000 0.82 \n", + "44 1 14.21 4.04 2.44 18.9 111 2.85 2.65 0.30 1.25 5.240000 0.87 \n", + "46 1 13.90 1.68 2.12 16.0 101 3.10 3.39 0.21 2.14 6.100000 0.91 \n", + "48 1 13.94 1.73 2.27 17.4 108 2.88 3.54 0.32 2.08 8.900000 1.12 \n", + "50 1 13.83 1.65 2.60 17.2 94 2.45 2.99 0.22 2.29 5.600000 1.24 \n", + "52 1 13.77 1.90 2.68 17.1 115 3.00 2.79 0.39 1.68 6.300000 1.13 \n", + "54 1 13.56 1.73 2.46 20.5 116 2.96 2.78 0.20 2.45 6.250000 0.98 \n", + "56 1 13.29 1.97 2.68 16.8 102 3.00 3.23 0.31 1.66 6.000000 1.07 \n", + "58 2 12.37 0.94 1.36 10.6 88 1.98 0.57 0.28 0.42 1.950000 1.05 \n", + ".. .. ... ... ... ... ... ... ... ... ... ... ... \n", + "118 2 12.00 3.43 2.00 19.0 87 2.00 1.64 0.37 1.87 1.280000 0.93 \n", + "120 2 11.56 2.05 3.23 28.5 119 3.18 5.08 0.47 1.87 6.000000 0.93 \n", + "122 2 13.05 5.80 2.13 21.5 86 2.62 2.65 0.30 2.01 2.600000 0.73 \n", + "124 2 12.07 2.16 2.17 21.0 85 2.60 2.65 0.37 1.35 2.760000 0.86 \n", + "126 2 11.79 2.13 2.78 28.5 92 2.13 2.24 0.58 1.76 3.000000 0.97 \n", + "128 2 12.04 4.30 2.38 22.0 80 2.10 1.75 0.42 1.35 2.600000 0.79 \n", + "130 3 12.88 2.99 2.40 20.0 104 1.30 1.22 0.24 0.83 5.400000 0.74 \n", + "132 3 12.70 3.55 2.36 21.5 106 1.70 1.20 0.17 0.84 5.000000 0.78 \n", + "134 3 12.60 2.46 2.20 18.5 94 1.62 0.66 0.63 0.94 7.100000 0.73 \n", + "136 3 12.53 5.51 2.64 25.0 96 1.79 0.60 0.63 1.10 5.000000 0.82 \n", + "138 3 12.84 2.96 2.61 24.0 101 2.32 0.60 0.53 0.81 4.920000 0.89 \n", + "140 3 13.36 2.56 2.35 20.0 89 1.40 0.50 0.37 0.64 5.600000 0.70 \n", + "142 3 13.62 4.95 2.35 20.0 92 2.00 0.80 0.47 1.02 4.400000 0.91 \n", + "144 3 13.16 3.57 2.15 21.0 102 1.50 0.55 0.43 1.30 4.000000 0.60 \n", + "146 3 12.87 4.61 2.48 21.5 86 1.70 0.65 0.47 0.86 7.650000 0.54 \n", + "148 3 13.08 3.90 2.36 21.5 113 1.41 1.39 0.34 1.14 9.400000 0.57 \n", + "150 3 12.79 2.67 2.48 22.0 112 1.48 1.36 0.24 1.26 10.800000 0.48 \n", + "152 3 13.23 3.30 2.28 18.5 98 1.80 0.83 0.61 1.87 10.520000 0.56 \n", + "154 3 13.17 5.19 2.32 22.0 93 1.74 0.63 0.61 1.55 7.900000 0.60 \n", + "156 3 12.45 3.03 2.64 27.0 97 1.90 0.58 0.63 1.14 7.500000 0.67 \n", + "158 3 13.48 1.67 2.64 22.5 89 2.60 1.10 0.52 2.29 11.750000 0.57 \n", + "160 3 13.69 3.26 2.54 20.0 107 1.83 0.56 0.50 0.80 5.880000 0.96 \n", + "162 3 12.96 3.45 2.35 18.5 106 1.39 0.70 0.40 0.94 5.280000 0.68 \n", + "164 3 13.73 4.36 2.26 22.5 88 1.28 0.47 0.52 1.15 6.620000 0.78 \n", + "166 3 12.82 3.37 2.30 19.5 88 1.48 0.66 0.40 0.97 10.260000 0.72 \n", + "168 3 13.40 4.60 2.86 25.0 112 1.98 0.96 0.27 1.11 8.500000 0.67 \n", + "170 3 12.77 2.39 2.28 19.5 86 1.39 0.51 0.48 0.64 9.899999 0.57 \n", + "172 3 13.71 5.65 2.45 20.5 95 1.68 0.61 0.52 1.06 7.700000 0.64 \n", + "174 3 13.27 4.28 2.26 20.0 120 1.59 0.69 0.43 1.35 10.200000 0.59 \n", + "176 3 14.13 4.10 2.74 24.5 96 2.05 0.76 0.56 1.35 9.200000 0.61 \n", + "\n", + " 3.92 1065 \n", + "0 3.40 1050 \n", + "2 3.45 1480 \n", + "4 2.85 1450 \n", + "6 3.58 1295 \n", + "8 3.55 1045 \n", + "10 2.82 1280 \n", + "12 2.73 1150 \n", + "14 2.88 1310 \n", + "16 2.57 1130 \n", + "18 3.36 845 \n", + "20 3.52 770 \n", + "22 3.63 1015 \n", + "24 3.20 830 \n", + "26 2.77 1285 \n", + "28 3.59 1035 \n", + "30 2.88 1515 \n", + "32 3.00 1235 \n", + "34 3.47 920 \n", + "36 2.51 1105 \n", + "38 3.53 760 \n", + "40 3.00 1035 \n", + "42 3.00 680 \n", + "44 3.33 1080 \n", + "46 3.33 985 \n", + "48 3.10 1260 \n", + "50 3.37 1265 \n", + "52 2.93 1375 \n", + "54 3.03 1120 \n", + "56 2.84 1270 \n", + "58 1.82 520 \n", + ".. ... ... \n", + "118 3.05 564 \n", + "120 3.69 465 \n", + "122 3.10 380 \n", + "124 3.28 378 \n", + "126 2.44 466 \n", + "128 2.57 580 \n", + "130 1.42 530 \n", + "132 1.29 600 \n", + "134 1.58 695 \n", + "136 1.69 515 \n", + "138 2.15 590 \n", + "140 2.47 780 \n", + "142 2.05 550 \n", + "144 1.68 830 \n", + "146 1.86 625 \n", + "148 1.33 550 \n", + "150 1.47 480 \n", + "152 1.51 675 \n", + "154 1.48 725 \n", + "156 1.73 880 \n", + "158 1.78 620 \n", + "160 1.82 680 \n", + "162 1.75 675 \n", + "164 1.75 520 \n", + "166 1.75 685 \n", + "168 1.92 630 \n", + "170 1.63 470 \n", + "172 1.74 740 \n", + "174 1.56 835 \n", + "176 1.60 560 \n", + "\n", + "[89 rows x 14 columns]\n" + ], + "name": "stdout" + } + ] + }, + { + "metadata": { + "id": "o6Cs6T1Rjz71", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Assign the columns as below:\n", + "\n", + "The attributes are (dontated by Riccardo Leardi, riclea '@' anchem.unige.it): \n", + "1) Alcohol \n", + "2) Malic acid \n", + "3) Ash \n", + "4) Alcalinity of ash \n", + "5) Magnesium \n", + "6) Total phenols \n", + "7) Flavanoids \n", + "8) Nonflavanoid phenols \n", + "9) Proanthocyanins \n", + "10)Color intensity \n", + "11)Hue \n", + "12)OD280/OD315 of diluted wines \n", + "13)Proline " + ] + }, + { + "metadata": { + "id": "my8HB4V4j779", + "colab_type": "code", + "colab": {} + }, + "cell_type": "code", + "source": [ + "wine_df.columns = ['Alcohol','Malic acid','Ash','Alcalinity of ash','Magnesium','Total phenols','Flavanoids','Nonflavanoid phenols','Proanthocyanins','Color intensity','Hue','OD280/OD315 of diluted wines','Proline','Col-14']\n", + "wine_df" + ], + "execution_count": 0, + "outputs": [] + }, + { + "metadata": { + "id": "Zqi7hwWpkNbH", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Set the values of the first 3 rows from alcohol as NaN\n", + "\n", + "Hint- Use iloc to select 3 rows of wine_df" + ] + }, + { + "metadata": { + "id": "buyT4vX4kPMl", + "colab_type": "code", + "colab": {} + }, + "cell_type": "code", + "source": [ + "wine_df.Alcohol.iloc[:3] = np.nan\n", + "print(wine_df)" + ], + "execution_count": 0, + "outputs": [] + }, + { + "metadata": { + "id": "RQMNI2UHkP3o", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Create an array of 10 random numbers uptill 10 and assign it to a variable named `random`" + ] + }, + { + "metadata": { + "id": "xunmCjaEmDwZ", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 34 + }, + "outputId": "bf4a4f50-e894-4f9d-8b62-70db9fa219ff" + }, + "cell_type": "code", + "source": [ + "random = np.random.randint(1,10,10)\n", + "print(random)" + ], + "execution_count": 73, + "outputs": [ + { + "output_type": "stream", + "text": [ + "[5 8 7 2 1 8 4 1 2 6]\n" + ], + "name": "stdout" + } + ] + }, + { + "metadata": { + "id": "hELUakyXmFSu", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Use random numbers you generated as an index and assign NaN value to each of cell of the column alcohol" + ] + }, + { + "metadata": { + "id": "zMgaNnNHmP01", + "colab_type": "code", + "colab": {} + }, + "cell_type": "code", + "source": [ + "wine_df.Alcohol.iloc[random] = np.nan\n", + "print(wine_df)" + ], + "execution_count": 0, + "outputs": [] + }, + { + "metadata": { + "id": "PHyK_vRsmRwV", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### How many missing values do we have? \n", + "\n", + "Hint: you can use isnull() and sum()" + ] + }, + { + "metadata": { + "id": "EnOYhmEqmfKp", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 272 + }, + "outputId": "97ba5773-5ea6-40ef-fb6b-6a69ad34af75" + }, + "cell_type": "code", + "source": [ + "print((wine_df.isnull()).sum())" + ], + "execution_count": 77, + "outputs": [ + { + "output_type": "stream", + "text": [ + "Alcohol 8\n", + "Malic acid 0\n", + "Ash 0\n", + "Alcalinity of ash 0\n", + "Magnesium 0\n", + "Total phenols 0\n", + "Flavanoids 0\n", + "Nonflavanoid phenols 0\n", + "Proanthocyanins 0\n", + "Color intensity 0\n", + "Hue 0\n", + "OD280/OD315 of diluted wines 0\n", + "Proline 0\n", + "Col-14 0\n", + "dtype: int64\n" + ], + "name": "stdout" + } + ] + }, + { + "metadata": { + "id": "-Fd4WBklmf1_", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Delete the rows that contain missing values " + ] + }, + { + "metadata": { + "id": "As7IC6Ktms8-", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 3247 + }, + "outputId": "3f232de0-741e-4300-b54e-c845433492b7" + }, + "cell_type": "code", + "source": [ + "wine_df = wine_df.dropna(how='any',axis=0)\n", + "print(wine_df)" + ], + "execution_count": 84, + "outputs": [ + { + "output_type": "stream", + "text": [ + " Alcohol Malic acid Ash Alcalinity of ash Magnesium Total phenols \\\n", + "3 1.0 13.24 2.59 2.87 21.0 118 \n", + "9 1.0 14.10 2.16 2.30 18.0 105 \n", + "10 1.0 14.12 1.48 2.32 16.8 95 \n", + "11 1.0 13.75 1.73 2.41 16.0 89 \n", + "12 1.0 14.75 1.73 2.39 11.4 91 \n", + "13 1.0 14.38 1.87 2.38 12.0 102 \n", + "14 1.0 13.63 1.81 2.70 17.2 112 \n", + "15 1.0 14.30 1.92 2.72 20.0 120 \n", + "16 1.0 13.83 1.57 2.62 20.0 115 \n", + "17 1.0 14.19 1.59 2.48 16.5 108 \n", + "18 1.0 13.64 3.10 2.56 15.2 116 \n", + "19 1.0 14.06 1.63 2.28 16.0 126 \n", + "20 1.0 12.93 3.80 2.65 18.6 102 \n", + "21 1.0 13.71 1.86 2.36 16.6 101 \n", + "22 1.0 12.85 1.60 2.52 17.8 95 \n", + "23 1.0 13.50 1.81 2.61 20.0 96 \n", + "24 1.0 13.05 2.05 3.22 25.0 124 \n", + "25 1.0 13.39 1.77 2.62 16.1 93 \n", + "26 1.0 13.30 1.72 2.14 17.0 94 \n", + "27 1.0 13.87 1.90 2.80 19.4 107 \n", + "28 1.0 14.02 1.68 2.21 16.0 96 \n", + "29 1.0 13.73 1.50 2.70 22.5 101 \n", + "30 1.0 13.58 1.66 2.36 19.1 106 \n", + "31 1.0 13.68 1.83 2.36 17.2 104 \n", + "32 1.0 13.76 1.53 2.70 19.5 132 \n", + "33 1.0 13.51 1.80 2.65 19.0 110 \n", + "34 1.0 13.48 1.81 2.41 20.5 100 \n", + "35 1.0 13.28 1.64 2.84 15.5 110 \n", + "36 1.0 13.05 1.65 2.55 18.0 98 \n", + "37 1.0 13.07 1.50 2.10 15.5 98 \n", + ".. ... ... ... ... ... ... \n", + "147 3.0 13.32 3.24 2.38 21.5 92 \n", + "148 3.0 13.08 3.90 2.36 21.5 113 \n", + "149 3.0 13.50 3.12 2.62 24.0 123 \n", + "150 3.0 12.79 2.67 2.48 22.0 112 \n", + "151 3.0 13.11 1.90 2.75 25.5 116 \n", + "152 3.0 13.23 3.30 2.28 18.5 98 \n", + "153 3.0 12.58 1.29 2.10 20.0 103 \n", + "154 3.0 13.17 5.19 2.32 22.0 93 \n", + "155 3.0 13.84 4.12 2.38 19.5 89 \n", + "156 3.0 12.45 3.03 2.64 27.0 97 \n", + "157 3.0 14.34 1.68 2.70 25.0 98 \n", + "158 3.0 13.48 1.67 2.64 22.5 89 \n", + "159 3.0 12.36 3.83 2.38 21.0 88 \n", + "160 3.0 13.69 3.26 2.54 20.0 107 \n", + "161 3.0 12.85 3.27 2.58 22.0 106 \n", + "162 3.0 12.96 3.45 2.35 18.5 106 \n", + "163 3.0 13.78 2.76 2.30 22.0 90 \n", + "164 3.0 13.73 4.36 2.26 22.5 88 \n", + "165 3.0 13.45 3.70 2.60 23.0 111 \n", + "166 3.0 12.82 3.37 2.30 19.5 88 \n", + "167 3.0 13.58 2.58 2.69 24.5 105 \n", + "168 3.0 13.40 4.60 2.86 25.0 112 \n", + "169 3.0 12.20 3.03 2.32 19.0 96 \n", + "170 3.0 12.77 2.39 2.28 19.5 86 \n", + "171 3.0 14.16 2.51 2.48 20.0 91 \n", + "172 3.0 13.71 5.65 2.45 20.5 95 \n", + "173 3.0 13.40 3.91 2.48 23.0 102 \n", + "174 3.0 13.27 4.28 2.26 20.0 120 \n", + "175 3.0 13.17 2.59 2.37 20.0 120 \n", + "176 3.0 14.13 4.10 2.74 24.5 96 \n", + "\n", + " Flavanoids Nonflavanoid phenols Proanthocyanins Color intensity \\\n", + "3 2.80 2.69 0.39 1.82 \n", + "9 2.95 3.32 0.22 2.38 \n", + "10 2.20 2.43 0.26 1.57 \n", + "11 2.60 2.76 0.29 1.81 \n", + "12 3.10 3.69 0.43 2.81 \n", + "13 3.30 3.64 0.29 2.96 \n", + "14 2.85 2.91 0.30 1.46 \n", + "15 2.80 3.14 0.33 1.97 \n", + "16 2.95 3.40 0.40 1.72 \n", + "17 3.30 3.93 0.32 1.86 \n", + "18 2.70 3.03 0.17 1.66 \n", + "19 3.00 3.17 0.24 2.10 \n", + "20 2.41 2.41 0.25 1.98 \n", + "21 2.61 2.88 0.27 1.69 \n", + "22 2.48 2.37 0.26 1.46 \n", + "23 2.53 2.61 0.28 1.66 \n", + "24 2.63 2.68 0.47 1.92 \n", + "25 2.85 2.94 0.34 1.45 \n", + "26 2.40 2.19 0.27 1.35 \n", + "27 2.95 2.97 0.37 1.76 \n", + "28 2.65 2.33 0.26 1.98 \n", + "29 3.00 3.25 0.29 2.38 \n", + "30 2.86 3.19 0.22 1.95 \n", + "31 2.42 2.69 0.42 1.97 \n", + "32 2.95 2.74 0.50 1.35 \n", + "33 2.35 2.53 0.29 1.54 \n", + "34 2.70 2.98 0.26 1.86 \n", + "35 2.60 2.68 0.34 1.36 \n", + "36 2.45 2.43 0.29 1.44 \n", + "37 2.40 2.64 0.28 1.37 \n", + ".. ... ... ... ... \n", + "147 1.93 0.76 0.45 1.25 \n", + "148 1.41 1.39 0.34 1.14 \n", + "149 1.40 1.57 0.22 1.25 \n", + "150 1.48 1.36 0.24 1.26 \n", + "151 2.20 1.28 0.26 1.56 \n", + "152 1.80 0.83 0.61 1.87 \n", + "153 1.48 0.58 0.53 1.40 \n", + "154 1.74 0.63 0.61 1.55 \n", + "155 1.80 0.83 0.48 1.56 \n", + "156 1.90 0.58 0.63 1.14 \n", + "157 2.80 1.31 0.53 2.70 \n", + "158 2.60 1.10 0.52 2.29 \n", + "159 2.30 0.92 0.50 1.04 \n", + "160 1.83 0.56 0.50 0.80 \n", + "161 1.65 0.60 0.60 0.96 \n", + "162 1.39 0.70 0.40 0.94 \n", + "163 1.35 0.68 0.41 1.03 \n", + "164 1.28 0.47 0.52 1.15 \n", + "165 1.70 0.92 0.43 1.46 \n", + "166 1.48 0.66 0.40 0.97 \n", + "167 1.55 0.84 0.39 1.54 \n", + "168 1.98 0.96 0.27 1.11 \n", + "169 1.25 0.49 0.40 0.73 \n", + "170 1.39 0.51 0.48 0.64 \n", + "171 1.68 0.70 0.44 1.24 \n", + "172 1.68 0.61 0.52 1.06 \n", + "173 1.80 0.75 0.43 1.41 \n", + "174 1.59 0.69 0.43 1.35 \n", + "175 1.65 0.68 0.53 1.46 \n", + "176 2.05 0.76 0.56 1.35 \n", + "\n", + " Hue OD280/OD315 of diluted wines Proline Col-14 \n", + "3 4.320000 1.04 2.93 735 \n", + "9 5.750000 1.25 3.17 1510 \n", + "10 5.000000 1.17 2.82 1280 \n", + "11 5.600000 1.15 2.90 1320 \n", + "12 5.400000 1.25 2.73 1150 \n", + "13 7.500000 1.20 3.00 1547 \n", + "14 7.300000 1.28 2.88 1310 \n", + "15 6.200000 1.07 2.65 1280 \n", + "16 6.600000 1.13 2.57 1130 \n", + "17 8.700000 1.23 2.82 1680 \n", + "18 5.100000 0.96 3.36 845 \n", + "19 5.650000 1.09 3.71 780 \n", + "20 4.500000 1.03 3.52 770 \n", + "21 3.800000 1.11 4.00 1035 \n", + "22 3.930000 1.09 3.63 1015 \n", + "23 3.520000 1.12 3.82 845 \n", + "24 3.580000 1.13 3.20 830 \n", + "25 4.800000 0.92 3.22 1195 \n", + "26 3.950000 1.02 2.77 1285 \n", + "27 4.500000 1.25 3.40 915 \n", + "28 4.700000 1.04 3.59 1035 \n", + "29 5.700000 1.19 2.71 1285 \n", + "30 6.900000 1.09 2.88 1515 \n", + "31 3.840000 1.23 2.87 990 \n", + "32 5.400000 1.25 3.00 1235 \n", + "33 4.200000 1.10 2.87 1095 \n", + "34 5.100000 1.04 3.47 920 \n", + "35 4.600000 1.09 2.78 880 \n", + "36 4.250000 1.12 2.51 1105 \n", + "37 3.700000 1.18 2.69 1020 \n", + ".. ... ... ... ... \n", + "147 8.420000 0.55 1.62 650 \n", + "148 9.400000 0.57 1.33 550 \n", + "149 8.600000 0.59 1.30 500 \n", + "150 10.800000 0.48 1.47 480 \n", + "151 7.100000 0.61 1.33 425 \n", + "152 10.520000 0.56 1.51 675 \n", + "153 7.600000 0.58 1.55 640 \n", + "154 7.900000 0.60 1.48 725 \n", + "155 9.010000 0.57 1.64 480 \n", + "156 7.500000 0.67 1.73 880 \n", + "157 13.000000 0.57 1.96 660 \n", + "158 11.750000 0.57 1.78 620 \n", + "159 7.650000 0.56 1.58 520 \n", + "160 5.880000 0.96 1.82 680 \n", + "161 5.580000 0.87 2.11 570 \n", + "162 5.280000 0.68 1.75 675 \n", + "163 9.580000 0.70 1.68 615 \n", + "164 6.620000 0.78 1.75 520 \n", + "165 10.680000 0.85 1.56 695 \n", + "166 10.260000 0.72 1.75 685 \n", + "167 8.660000 0.74 1.80 750 \n", + "168 8.500000 0.67 1.92 630 \n", + "169 5.500000 0.66 1.83 510 \n", + "170 9.899999 0.57 1.63 470 \n", + "171 9.700000 0.62 1.71 660 \n", + "172 7.700000 0.64 1.74 740 \n", + "173 7.300000 0.70 1.56 750 \n", + "174 10.200000 0.59 1.56 835 \n", + "175 9.300000 0.60 1.62 840 \n", + "176 9.200000 0.61 1.60 560 \n", + "\n", + "[169 rows x 14 columns]\n" + ], + "name": "stdout" + } + ] + }, + { + "metadata": { + "id": "DlpG8drhmz7W", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "### BONUS: Play with the data set below" + ] + }, + { + "metadata": { + "id": "mD40T0Cnm5SA", + "colab_type": "code", + "colab": {} + }, + "cell_type": "code", + "source": [ + "#exam next week, will play later :-P" + ], + "execution_count": 0, + "outputs": [] + } + ] +} \ No newline at end of file From 6bcc2f215157e60cbfed34c8ffc4887f542a15a8 Mon Sep 17 00:00:00 2001 From: Nawaz Sk Date: Fri, 18 Jan 2019 22:28:13 +0530 Subject: [PATCH 2/3] Delete Exercise.ipynb --- Exercise.ipynb | 977 ------------------------------------------------- 1 file changed, 977 deletions(-) delete mode 100644 Exercise.ipynb diff --git a/Exercise.ipynb b/Exercise.ipynb deleted file mode 100644 index d67b524..0000000 --- a/Exercise.ipynb +++ /dev/null @@ -1,977 +0,0 @@ -{ - "nbformat": 4, - "nbformat_minor": 0, - "metadata": { - "colab": { - "name": "Exercise.ipynb", - "version": "0.3.2", - "provenance": [], - "collapsed_sections": [] - }, - "kernelspec": { - "name": "python3", - "display_name": "Python 3" - } - }, - "cells": [ - { - "metadata": { - "id": "2LTtpUJEibjg", - "colab_type": "text" - }, - "cell_type": "markdown", - "source": [ - "# Pandas Exercise :\n", - "\n", - "\n", - "#### import necessary modules" - ] - }, - { - "metadata": { - "id": "c3_UBbMRhiKx", - "colab_type": "code", - "colab": {} - }, - "cell_type": "code", - "source": [ - "import numpy as np\n", - "import pandas as pd" - ], - "execution_count": 0, - "outputs": [] - }, - { - "metadata": { - "id": "tp-cTCyWi8mR", - "colab_type": "text" - }, - "cell_type": "markdown", - "source": [ - "#### Load url = \"https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data\" to a dataframe named wine_df\n", - "\n", - "This is a wine dataset\n", - "\n" - ] - }, - { - "metadata": { - "id": "DMojQY3thrRi", - "colab_type": "code", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 2176 - }, - "outputId": "3cf51cac-e1ca-4211-bf4f-3b0b97482866" - }, - "cell_type": "code", - "source": [ - "url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data'\n", - "wine_df = pd.read_csv(url)\n", - "print(wine_df)" - ], - "execution_count": 68, - "outputs": [ - { - "output_type": "stream", - "text": [ - " 1 14.23 1.71 2.43 15.6 127 2.8 3.06 .28 2.29 5.64 1.04 \\\n", - "0 1 13.20 1.78 2.14 11.2 100 2.65 2.76 0.26 1.28 4.380000 1.05 \n", - "1 1 13.16 2.36 2.67 18.6 101 2.80 3.24 0.30 2.81 5.680000 1.03 \n", - "2 1 14.37 1.95 2.50 16.8 113 3.85 3.49 0.24 2.18 7.800000 0.86 \n", - "3 1 13.24 2.59 2.87 21.0 118 2.80 2.69 0.39 1.82 4.320000 1.04 \n", - "4 1 14.20 1.76 2.45 15.2 112 3.27 3.39 0.34 1.97 6.750000 1.05 \n", - "5 1 14.39 1.87 2.45 14.6 96 2.50 2.52 0.30 1.98 5.250000 1.02 \n", - "6 1 14.06 2.15 2.61 17.6 121 2.60 2.51 0.31 1.25 5.050000 1.06 \n", - "7 1 14.83 1.64 2.17 14.0 97 2.80 2.98 0.29 1.98 5.200000 1.08 \n", - "8 1 13.86 1.35 2.27 16.0 98 2.98 3.15 0.22 1.85 7.220000 1.01 \n", - "9 1 14.10 2.16 2.30 18.0 105 2.95 3.32 0.22 2.38 5.750000 1.25 \n", - "10 1 14.12 1.48 2.32 16.8 95 2.20 2.43 0.26 1.57 5.000000 1.17 \n", - "11 1 13.75 1.73 2.41 16.0 89 2.60 2.76 0.29 1.81 5.600000 1.15 \n", - "12 1 14.75 1.73 2.39 11.4 91 3.10 3.69 0.43 2.81 5.400000 1.25 \n", - "13 1 14.38 1.87 2.38 12.0 102 3.30 3.64 0.29 2.96 7.500000 1.20 \n", - "14 1 13.63 1.81 2.70 17.2 112 2.85 2.91 0.30 1.46 7.300000 1.28 \n", - "15 1 14.30 1.92 2.72 20.0 120 2.80 3.14 0.33 1.97 6.200000 1.07 \n", - "16 1 13.83 1.57 2.62 20.0 115 2.95 3.40 0.40 1.72 6.600000 1.13 \n", - "17 1 14.19 1.59 2.48 16.5 108 3.30 3.93 0.32 1.86 8.700000 1.23 \n", - "18 1 13.64 3.10 2.56 15.2 116 2.70 3.03 0.17 1.66 5.100000 0.96 \n", - "19 1 14.06 1.63 2.28 16.0 126 3.00 3.17 0.24 2.10 5.650000 1.09 \n", - "20 1 12.93 3.80 2.65 18.6 102 2.41 2.41 0.25 1.98 4.500000 1.03 \n", - "21 1 13.71 1.86 2.36 16.6 101 2.61 2.88 0.27 1.69 3.800000 1.11 \n", - "22 1 12.85 1.60 2.52 17.8 95 2.48 2.37 0.26 1.46 3.930000 1.09 \n", - "23 1 13.50 1.81 2.61 20.0 96 2.53 2.61 0.28 1.66 3.520000 1.12 \n", - "24 1 13.05 2.05 3.22 25.0 124 2.63 2.68 0.47 1.92 3.580000 1.13 \n", - "25 1 13.39 1.77 2.62 16.1 93 2.85 2.94 0.34 1.45 4.800000 0.92 \n", - "26 1 13.30 1.72 2.14 17.0 94 2.40 2.19 0.27 1.35 3.950000 1.02 \n", - "27 1 13.87 1.90 2.80 19.4 107 2.95 2.97 0.37 1.76 4.500000 1.25 \n", - "28 1 14.02 1.68 2.21 16.0 96 2.65 2.33 0.26 1.98 4.700000 1.04 \n", - "29 1 13.73 1.50 2.70 22.5 101 3.00 3.25 0.29 2.38 5.700000 1.19 \n", - ".. .. ... ... ... ... ... ... ... ... ... ... ... \n", - "147 3 13.32 3.24 2.38 21.5 92 1.93 0.76 0.45 1.25 8.420000 0.55 \n", - "148 3 13.08 3.90 2.36 21.5 113 1.41 1.39 0.34 1.14 9.400000 0.57 \n", - "149 3 13.50 3.12 2.62 24.0 123 1.40 1.57 0.22 1.25 8.600000 0.59 \n", - "150 3 12.79 2.67 2.48 22.0 112 1.48 1.36 0.24 1.26 10.800000 0.48 \n", - "151 3 13.11 1.90 2.75 25.5 116 2.20 1.28 0.26 1.56 7.100000 0.61 \n", - "152 3 13.23 3.30 2.28 18.5 98 1.80 0.83 0.61 1.87 10.520000 0.56 \n", - "153 3 12.58 1.29 2.10 20.0 103 1.48 0.58 0.53 1.40 7.600000 0.58 \n", - "154 3 13.17 5.19 2.32 22.0 93 1.74 0.63 0.61 1.55 7.900000 0.60 \n", - "155 3 13.84 4.12 2.38 19.5 89 1.80 0.83 0.48 1.56 9.010000 0.57 \n", - "156 3 12.45 3.03 2.64 27.0 97 1.90 0.58 0.63 1.14 7.500000 0.67 \n", - "157 3 14.34 1.68 2.70 25.0 98 2.80 1.31 0.53 2.70 13.000000 0.57 \n", - "158 3 13.48 1.67 2.64 22.5 89 2.60 1.10 0.52 2.29 11.750000 0.57 \n", - "159 3 12.36 3.83 2.38 21.0 88 2.30 0.92 0.50 1.04 7.650000 0.56 \n", - "160 3 13.69 3.26 2.54 20.0 107 1.83 0.56 0.50 0.80 5.880000 0.96 \n", - "161 3 12.85 3.27 2.58 22.0 106 1.65 0.60 0.60 0.96 5.580000 0.87 \n", - "162 3 12.96 3.45 2.35 18.5 106 1.39 0.70 0.40 0.94 5.280000 0.68 \n", - "163 3 13.78 2.76 2.30 22.0 90 1.35 0.68 0.41 1.03 9.580000 0.70 \n", - "164 3 13.73 4.36 2.26 22.5 88 1.28 0.47 0.52 1.15 6.620000 0.78 \n", - "165 3 13.45 3.70 2.60 23.0 111 1.70 0.92 0.43 1.46 10.680000 0.85 \n", - "166 3 12.82 3.37 2.30 19.5 88 1.48 0.66 0.40 0.97 10.260000 0.72 \n", - "167 3 13.58 2.58 2.69 24.5 105 1.55 0.84 0.39 1.54 8.660000 0.74 \n", - "168 3 13.40 4.60 2.86 25.0 112 1.98 0.96 0.27 1.11 8.500000 0.67 \n", - "169 3 12.20 3.03 2.32 19.0 96 1.25 0.49 0.40 0.73 5.500000 0.66 \n", - "170 3 12.77 2.39 2.28 19.5 86 1.39 0.51 0.48 0.64 9.899999 0.57 \n", - "171 3 14.16 2.51 2.48 20.0 91 1.68 0.70 0.44 1.24 9.700000 0.62 \n", - "172 3 13.71 5.65 2.45 20.5 95 1.68 0.61 0.52 1.06 7.700000 0.64 \n", - "173 3 13.40 3.91 2.48 23.0 102 1.80 0.75 0.43 1.41 7.300000 0.70 \n", - "174 3 13.27 4.28 2.26 20.0 120 1.59 0.69 0.43 1.35 10.200000 0.59 \n", - "175 3 13.17 2.59 2.37 20.0 120 1.65 0.68 0.53 1.46 9.300000 0.60 \n", - "176 3 14.13 4.10 2.74 24.5 96 2.05 0.76 0.56 1.35 9.200000 0.61 \n", - "\n", - " 3.92 1065 \n", - "0 3.40 1050 \n", - "1 3.17 1185 \n", - "2 3.45 1480 \n", - "3 2.93 735 \n", - "4 2.85 1450 \n", - "5 3.58 1290 \n", - "6 3.58 1295 \n", - "7 2.85 1045 \n", - "8 3.55 1045 \n", - "9 3.17 1510 \n", - "10 2.82 1280 \n", - "11 2.90 1320 \n", - "12 2.73 1150 \n", - "13 3.00 1547 \n", - "14 2.88 1310 \n", - "15 2.65 1280 \n", - "16 2.57 1130 \n", - "17 2.82 1680 \n", - "18 3.36 845 \n", - "19 3.71 780 \n", - "20 3.52 770 \n", - "21 4.00 1035 \n", - "22 3.63 1015 \n", - "23 3.82 845 \n", - "24 3.20 830 \n", - "25 3.22 1195 \n", - "26 2.77 1285 \n", - "27 3.40 915 \n", - "28 3.59 1035 \n", - "29 2.71 1285 \n", - ".. ... ... \n", - "147 1.62 650 \n", - "148 1.33 550 \n", - "149 1.30 500 \n", - "150 1.47 480 \n", - "151 1.33 425 \n", - "152 1.51 675 \n", - "153 1.55 640 \n", - "154 1.48 725 \n", - "155 1.64 480 \n", - "156 1.73 880 \n", - "157 1.96 660 \n", - "158 1.78 620 \n", - "159 1.58 520 \n", - "160 1.82 680 \n", - "161 2.11 570 \n", - "162 1.75 675 \n", - "163 1.68 615 \n", - "164 1.75 520 \n", - "165 1.56 695 \n", - "166 1.75 685 \n", - "167 1.80 750 \n", - "168 1.92 630 \n", - "169 1.83 510 \n", - "170 1.63 470 \n", - "171 1.71 660 \n", - "172 1.74 740 \n", - "173 1.56 750 \n", - "174 1.56 835 \n", - "175 1.62 840 \n", - "176 1.60 560 \n", - "\n", - "[177 rows x 14 columns]\n" - ], - "name": "stdout" - } - ] - }, - { - "metadata": { - "id": "BF9MMjoZjSlg", - "colab_type": "text" - }, - "cell_type": "markdown", - "source": [ - "#### print first five rows" - ] - }, - { - "metadata": { - "id": "1vSMQdnHjYNU", - "colab_type": "code", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 204 - }, - "outputId": "e2da40ba-9b64-4ee2-cdcf-e6a19ed962ff" - }, - "cell_type": "code", - "source": [ - "wine_df.head(5)" - ], - "execution_count": 69, - "outputs": [ - { - "output_type": "execute_result", - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
114.231.712.4315.61272.83.06.282.295.641.043.921065
0113.201.782.1411.21002.652.760.261.284.381.053.401050
1113.162.362.6718.61012.803.240.302.815.681.033.171185
2114.371.952.5016.81133.853.490.242.187.800.863.451480
3113.242.592.8721.01182.802.690.391.824.321.042.93735
4114.201.762.4515.21123.273.390.341.976.751.052.851450
\n", - "
" - ], - "text/plain": [ - " 1 14.23 1.71 2.43 15.6 127 2.8 3.06 .28 2.29 5.64 1.04 3.92 \\\n", - "0 1 13.20 1.78 2.14 11.2 100 2.65 2.76 0.26 1.28 4.38 1.05 3.40 \n", - "1 1 13.16 2.36 2.67 18.6 101 2.80 3.24 0.30 2.81 5.68 1.03 3.17 \n", - "2 1 14.37 1.95 2.50 16.8 113 3.85 3.49 0.24 2.18 7.80 0.86 3.45 \n", - "3 1 13.24 2.59 2.87 21.0 118 2.80 2.69 0.39 1.82 4.32 1.04 2.93 \n", - "4 1 14.20 1.76 2.45 15.2 112 3.27 3.39 0.34 1.97 6.75 1.05 2.85 \n", - "\n", - " 1065 \n", - "0 1050 \n", - "1 1185 \n", - "2 1480 \n", - "3 735 \n", - "4 1450 " - ] - }, - "metadata": { - "tags": [] - }, - "execution_count": 69 - } - ] - }, - { - "metadata": { - "id": "Tet6P2DvjY3T", - "colab_type": "text" - }, - "cell_type": "markdown", - "source": [ - "#### assign wine_df to a different variable wine_df_copy and then delete all odd rows of wine_df_copy\n", - "\n", - "[Hint](https://pandas.pydata.org/pandas-docs/stable/generated/pandas.DataFrame.drop.html)" - ] - }, - { - "metadata": { - "id": "CMj3qSdJjx0u", - "colab_type": "code", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 2176 - }, - "outputId": "1f9337b1-d130-43c9-cbb9-ae76dd486e0c" - }, - "cell_type": "code", - "source": [ - "wine_df_copy = wine_df\n", - "wine_df_copy = wine_df_copy[wine_df_copy.index%2 == 0]\n", - "print(wine_df_copy)" - ], - "execution_count": 70, - "outputs": [ - { - "output_type": "stream", - "text": [ - " 1 14.23 1.71 2.43 15.6 127 2.8 3.06 .28 2.29 5.64 1.04 \\\n", - "0 1 13.20 1.78 2.14 11.2 100 2.65 2.76 0.26 1.28 4.380000 1.05 \n", - "2 1 14.37 1.95 2.50 16.8 113 3.85 3.49 0.24 2.18 7.800000 0.86 \n", - "4 1 14.20 1.76 2.45 15.2 112 3.27 3.39 0.34 1.97 6.750000 1.05 \n", - "6 1 14.06 2.15 2.61 17.6 121 2.60 2.51 0.31 1.25 5.050000 1.06 \n", - "8 1 13.86 1.35 2.27 16.0 98 2.98 3.15 0.22 1.85 7.220000 1.01 \n", - "10 1 14.12 1.48 2.32 16.8 95 2.20 2.43 0.26 1.57 5.000000 1.17 \n", - "12 1 14.75 1.73 2.39 11.4 91 3.10 3.69 0.43 2.81 5.400000 1.25 \n", - "14 1 13.63 1.81 2.70 17.2 112 2.85 2.91 0.30 1.46 7.300000 1.28 \n", - "16 1 13.83 1.57 2.62 20.0 115 2.95 3.40 0.40 1.72 6.600000 1.13 \n", - "18 1 13.64 3.10 2.56 15.2 116 2.70 3.03 0.17 1.66 5.100000 0.96 \n", - "20 1 12.93 3.80 2.65 18.6 102 2.41 2.41 0.25 1.98 4.500000 1.03 \n", - "22 1 12.85 1.60 2.52 17.8 95 2.48 2.37 0.26 1.46 3.930000 1.09 \n", - "24 1 13.05 2.05 3.22 25.0 124 2.63 2.68 0.47 1.92 3.580000 1.13 \n", - "26 1 13.30 1.72 2.14 17.0 94 2.40 2.19 0.27 1.35 3.950000 1.02 \n", - "28 1 14.02 1.68 2.21 16.0 96 2.65 2.33 0.26 1.98 4.700000 1.04 \n", - "30 1 13.58 1.66 2.36 19.1 106 2.86 3.19 0.22 1.95 6.900000 1.09 \n", - "32 1 13.76 1.53 2.70 19.5 132 2.95 2.74 0.50 1.35 5.400000 1.25 \n", - "34 1 13.48 1.81 2.41 20.5 100 2.70 2.98 0.26 1.86 5.100000 1.04 \n", - "36 1 13.05 1.65 2.55 18.0 98 2.45 2.43 0.29 1.44 4.250000 1.12 \n", - "38 1 14.22 3.99 2.51 13.2 128 3.00 3.04 0.20 2.08 5.100000 0.89 \n", - "40 1 13.41 3.84 2.12 18.8 90 2.45 2.68 0.27 1.48 4.280000 0.91 \n", - "42 1 13.24 3.98 2.29 17.5 103 2.64 2.63 0.32 1.66 4.360000 0.82 \n", - "44 1 14.21 4.04 2.44 18.9 111 2.85 2.65 0.30 1.25 5.240000 0.87 \n", - "46 1 13.90 1.68 2.12 16.0 101 3.10 3.39 0.21 2.14 6.100000 0.91 \n", - "48 1 13.94 1.73 2.27 17.4 108 2.88 3.54 0.32 2.08 8.900000 1.12 \n", - "50 1 13.83 1.65 2.60 17.2 94 2.45 2.99 0.22 2.29 5.600000 1.24 \n", - "52 1 13.77 1.90 2.68 17.1 115 3.00 2.79 0.39 1.68 6.300000 1.13 \n", - "54 1 13.56 1.73 2.46 20.5 116 2.96 2.78 0.20 2.45 6.250000 0.98 \n", - "56 1 13.29 1.97 2.68 16.8 102 3.00 3.23 0.31 1.66 6.000000 1.07 \n", - "58 2 12.37 0.94 1.36 10.6 88 1.98 0.57 0.28 0.42 1.950000 1.05 \n", - ".. .. ... ... ... ... ... ... ... ... ... ... ... \n", - "118 2 12.00 3.43 2.00 19.0 87 2.00 1.64 0.37 1.87 1.280000 0.93 \n", - "120 2 11.56 2.05 3.23 28.5 119 3.18 5.08 0.47 1.87 6.000000 0.93 \n", - "122 2 13.05 5.80 2.13 21.5 86 2.62 2.65 0.30 2.01 2.600000 0.73 \n", - "124 2 12.07 2.16 2.17 21.0 85 2.60 2.65 0.37 1.35 2.760000 0.86 \n", - "126 2 11.79 2.13 2.78 28.5 92 2.13 2.24 0.58 1.76 3.000000 0.97 \n", - "128 2 12.04 4.30 2.38 22.0 80 2.10 1.75 0.42 1.35 2.600000 0.79 \n", - "130 3 12.88 2.99 2.40 20.0 104 1.30 1.22 0.24 0.83 5.400000 0.74 \n", - "132 3 12.70 3.55 2.36 21.5 106 1.70 1.20 0.17 0.84 5.000000 0.78 \n", - "134 3 12.60 2.46 2.20 18.5 94 1.62 0.66 0.63 0.94 7.100000 0.73 \n", - "136 3 12.53 5.51 2.64 25.0 96 1.79 0.60 0.63 1.10 5.000000 0.82 \n", - "138 3 12.84 2.96 2.61 24.0 101 2.32 0.60 0.53 0.81 4.920000 0.89 \n", - "140 3 13.36 2.56 2.35 20.0 89 1.40 0.50 0.37 0.64 5.600000 0.70 \n", - "142 3 13.62 4.95 2.35 20.0 92 2.00 0.80 0.47 1.02 4.400000 0.91 \n", - "144 3 13.16 3.57 2.15 21.0 102 1.50 0.55 0.43 1.30 4.000000 0.60 \n", - "146 3 12.87 4.61 2.48 21.5 86 1.70 0.65 0.47 0.86 7.650000 0.54 \n", - "148 3 13.08 3.90 2.36 21.5 113 1.41 1.39 0.34 1.14 9.400000 0.57 \n", - "150 3 12.79 2.67 2.48 22.0 112 1.48 1.36 0.24 1.26 10.800000 0.48 \n", - "152 3 13.23 3.30 2.28 18.5 98 1.80 0.83 0.61 1.87 10.520000 0.56 \n", - "154 3 13.17 5.19 2.32 22.0 93 1.74 0.63 0.61 1.55 7.900000 0.60 \n", - "156 3 12.45 3.03 2.64 27.0 97 1.90 0.58 0.63 1.14 7.500000 0.67 \n", - "158 3 13.48 1.67 2.64 22.5 89 2.60 1.10 0.52 2.29 11.750000 0.57 \n", - "160 3 13.69 3.26 2.54 20.0 107 1.83 0.56 0.50 0.80 5.880000 0.96 \n", - "162 3 12.96 3.45 2.35 18.5 106 1.39 0.70 0.40 0.94 5.280000 0.68 \n", - "164 3 13.73 4.36 2.26 22.5 88 1.28 0.47 0.52 1.15 6.620000 0.78 \n", - "166 3 12.82 3.37 2.30 19.5 88 1.48 0.66 0.40 0.97 10.260000 0.72 \n", - "168 3 13.40 4.60 2.86 25.0 112 1.98 0.96 0.27 1.11 8.500000 0.67 \n", - "170 3 12.77 2.39 2.28 19.5 86 1.39 0.51 0.48 0.64 9.899999 0.57 \n", - "172 3 13.71 5.65 2.45 20.5 95 1.68 0.61 0.52 1.06 7.700000 0.64 \n", - "174 3 13.27 4.28 2.26 20.0 120 1.59 0.69 0.43 1.35 10.200000 0.59 \n", - "176 3 14.13 4.10 2.74 24.5 96 2.05 0.76 0.56 1.35 9.200000 0.61 \n", - "\n", - " 3.92 1065 \n", - "0 3.40 1050 \n", - "2 3.45 1480 \n", - "4 2.85 1450 \n", - "6 3.58 1295 \n", - "8 3.55 1045 \n", - "10 2.82 1280 \n", - "12 2.73 1150 \n", - "14 2.88 1310 \n", - "16 2.57 1130 \n", - "18 3.36 845 \n", - "20 3.52 770 \n", - "22 3.63 1015 \n", - "24 3.20 830 \n", - "26 2.77 1285 \n", - "28 3.59 1035 \n", - "30 2.88 1515 \n", - "32 3.00 1235 \n", - "34 3.47 920 \n", - "36 2.51 1105 \n", - "38 3.53 760 \n", - "40 3.00 1035 \n", - "42 3.00 680 \n", - "44 3.33 1080 \n", - "46 3.33 985 \n", - "48 3.10 1260 \n", - "50 3.37 1265 \n", - "52 2.93 1375 \n", - "54 3.03 1120 \n", - "56 2.84 1270 \n", - "58 1.82 520 \n", - ".. ... ... \n", - "118 3.05 564 \n", - "120 3.69 465 \n", - "122 3.10 380 \n", - "124 3.28 378 \n", - "126 2.44 466 \n", - "128 2.57 580 \n", - "130 1.42 530 \n", - "132 1.29 600 \n", - "134 1.58 695 \n", - "136 1.69 515 \n", - "138 2.15 590 \n", - "140 2.47 780 \n", - "142 2.05 550 \n", - "144 1.68 830 \n", - "146 1.86 625 \n", - "148 1.33 550 \n", - "150 1.47 480 \n", - "152 1.51 675 \n", - "154 1.48 725 \n", - "156 1.73 880 \n", - "158 1.78 620 \n", - "160 1.82 680 \n", - "162 1.75 675 \n", - "164 1.75 520 \n", - "166 1.75 685 \n", - "168 1.92 630 \n", - "170 1.63 470 \n", - "172 1.74 740 \n", - "174 1.56 835 \n", - "176 1.60 560 \n", - "\n", - "[89 rows x 14 columns]\n" - ], - "name": "stdout" - } - ] - }, - { - "metadata": { - "id": "o6Cs6T1Rjz71", - "colab_type": "text" - }, - "cell_type": "markdown", - "source": [ - "#### Assign the columns as below:\n", - "\n", - "The attributes are (dontated by Riccardo Leardi, riclea '@' anchem.unige.it): \n", - "1) Alcohol \n", - "2) Malic acid \n", - "3) Ash \n", - "4) Alcalinity of ash \n", - "5) Magnesium \n", - "6) Total phenols \n", - "7) Flavanoids \n", - "8) Nonflavanoid phenols \n", - "9) Proanthocyanins \n", - "10)Color intensity \n", - "11)Hue \n", - "12)OD280/OD315 of diluted wines \n", - "13)Proline " - ] - }, - { - "metadata": { - "id": "my8HB4V4j779", - "colab_type": "code", - "colab": {} - }, - "cell_type": "code", - "source": [ - "wine_df.columns = ['Alcohol','Malic acid','Ash','Alcalinity of ash','Magnesium','Total phenols','Flavanoids','Nonflavanoid phenols','Proanthocyanins','Color intensity','Hue','OD280/OD315 of diluted wines','Proline','Col-14']\n", - "wine_df" - ], - "execution_count": 0, - "outputs": [] - }, - { - "metadata": { - "id": "Zqi7hwWpkNbH", - "colab_type": "text" - }, - "cell_type": "markdown", - "source": [ - "#### Set the values of the first 3 rows from alcohol as NaN\n", - "\n", - "Hint- Use iloc to select 3 rows of wine_df" - ] - }, - { - "metadata": { - "id": "buyT4vX4kPMl", - "colab_type": "code", - "colab": {} - }, - "cell_type": "code", - "source": [ - "wine_df.Alcohol.iloc[:3] = np.nan\n", - "print(wine_df)" - ], - "execution_count": 0, - "outputs": [] - }, - { - "metadata": { - "id": "RQMNI2UHkP3o", - "colab_type": "text" - }, - "cell_type": "markdown", - "source": [ - "#### Create an array of 10 random numbers uptill 10 and assign it to a variable named `random`" - ] - }, - { - "metadata": { - "id": "xunmCjaEmDwZ", - "colab_type": "code", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 34 - }, - "outputId": "bf4a4f50-e894-4f9d-8b62-70db9fa219ff" - }, - "cell_type": "code", - "source": [ - "random = np.random.randint(1,10,10)\n", - "print(random)" - ], - "execution_count": 73, - "outputs": [ - { - "output_type": "stream", - "text": [ - "[5 8 7 2 1 8 4 1 2 6]\n" - ], - "name": "stdout" - } - ] - }, - { - "metadata": { - "id": "hELUakyXmFSu", - "colab_type": "text" - }, - "cell_type": "markdown", - "source": [ - "#### Use random numbers you generated as an index and assign NaN value to each of cell of the column alcohol" - ] - }, - { - "metadata": { - "id": "zMgaNnNHmP01", - "colab_type": "code", - "colab": {} - }, - "cell_type": "code", - "source": [ - "wine_df.Alcohol.iloc[random] = np.nan\n", - "print(wine_df)" - ], - "execution_count": 0, - "outputs": [] - }, - { - "metadata": { - "id": "PHyK_vRsmRwV", - "colab_type": "text" - }, - "cell_type": "markdown", - "source": [ - "#### How many missing values do we have? \n", - "\n", - "Hint: you can use isnull() and sum()" - ] - }, - { - "metadata": { - "id": "EnOYhmEqmfKp", - "colab_type": "code", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 272 - }, - "outputId": "97ba5773-5ea6-40ef-fb6b-6a69ad34af75" - }, - "cell_type": "code", - "source": [ - "print((wine_df.isnull()).sum())" - ], - "execution_count": 77, - "outputs": [ - { - "output_type": "stream", - "text": [ - "Alcohol 8\n", - "Malic acid 0\n", - "Ash 0\n", - "Alcalinity of ash 0\n", - "Magnesium 0\n", - "Total phenols 0\n", - "Flavanoids 0\n", - "Nonflavanoid phenols 0\n", - "Proanthocyanins 0\n", - "Color intensity 0\n", - "Hue 0\n", - "OD280/OD315 of diluted wines 0\n", - "Proline 0\n", - "Col-14 0\n", - "dtype: int64\n" - ], - "name": "stdout" - } - ] - }, - { - "metadata": { - "id": "-Fd4WBklmf1_", - "colab_type": "text" - }, - "cell_type": "markdown", - "source": [ - "#### Delete the rows that contain missing values " - ] - }, - { - "metadata": { - "id": "As7IC6Ktms8-", - "colab_type": "code", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 3247 - }, - "outputId": "3f232de0-741e-4300-b54e-c845433492b7" - }, - "cell_type": "code", - "source": [ - "wine_df = wine_df.dropna(how='any',axis=0)\n", - "print(wine_df)" - ], - "execution_count": 84, - "outputs": [ - { - "output_type": "stream", - "text": [ - " Alcohol Malic acid Ash Alcalinity of ash Magnesium Total phenols \\\n", - "3 1.0 13.24 2.59 2.87 21.0 118 \n", - "9 1.0 14.10 2.16 2.30 18.0 105 \n", - "10 1.0 14.12 1.48 2.32 16.8 95 \n", - "11 1.0 13.75 1.73 2.41 16.0 89 \n", - "12 1.0 14.75 1.73 2.39 11.4 91 \n", - "13 1.0 14.38 1.87 2.38 12.0 102 \n", - "14 1.0 13.63 1.81 2.70 17.2 112 \n", - "15 1.0 14.30 1.92 2.72 20.0 120 \n", - "16 1.0 13.83 1.57 2.62 20.0 115 \n", - "17 1.0 14.19 1.59 2.48 16.5 108 \n", - "18 1.0 13.64 3.10 2.56 15.2 116 \n", - "19 1.0 14.06 1.63 2.28 16.0 126 \n", - "20 1.0 12.93 3.80 2.65 18.6 102 \n", - "21 1.0 13.71 1.86 2.36 16.6 101 \n", - "22 1.0 12.85 1.60 2.52 17.8 95 \n", - "23 1.0 13.50 1.81 2.61 20.0 96 \n", - "24 1.0 13.05 2.05 3.22 25.0 124 \n", - "25 1.0 13.39 1.77 2.62 16.1 93 \n", - "26 1.0 13.30 1.72 2.14 17.0 94 \n", - "27 1.0 13.87 1.90 2.80 19.4 107 \n", - "28 1.0 14.02 1.68 2.21 16.0 96 \n", - "29 1.0 13.73 1.50 2.70 22.5 101 \n", - "30 1.0 13.58 1.66 2.36 19.1 106 \n", - "31 1.0 13.68 1.83 2.36 17.2 104 \n", - "32 1.0 13.76 1.53 2.70 19.5 132 \n", - "33 1.0 13.51 1.80 2.65 19.0 110 \n", - "34 1.0 13.48 1.81 2.41 20.5 100 \n", - "35 1.0 13.28 1.64 2.84 15.5 110 \n", - "36 1.0 13.05 1.65 2.55 18.0 98 \n", - "37 1.0 13.07 1.50 2.10 15.5 98 \n", - ".. ... ... ... ... ... ... \n", - "147 3.0 13.32 3.24 2.38 21.5 92 \n", - "148 3.0 13.08 3.90 2.36 21.5 113 \n", - "149 3.0 13.50 3.12 2.62 24.0 123 \n", - "150 3.0 12.79 2.67 2.48 22.0 112 \n", - "151 3.0 13.11 1.90 2.75 25.5 116 \n", - "152 3.0 13.23 3.30 2.28 18.5 98 \n", - "153 3.0 12.58 1.29 2.10 20.0 103 \n", - "154 3.0 13.17 5.19 2.32 22.0 93 \n", - "155 3.0 13.84 4.12 2.38 19.5 89 \n", - "156 3.0 12.45 3.03 2.64 27.0 97 \n", - "157 3.0 14.34 1.68 2.70 25.0 98 \n", - "158 3.0 13.48 1.67 2.64 22.5 89 \n", - "159 3.0 12.36 3.83 2.38 21.0 88 \n", - "160 3.0 13.69 3.26 2.54 20.0 107 \n", - "161 3.0 12.85 3.27 2.58 22.0 106 \n", - "162 3.0 12.96 3.45 2.35 18.5 106 \n", - "163 3.0 13.78 2.76 2.30 22.0 90 \n", - "164 3.0 13.73 4.36 2.26 22.5 88 \n", - "165 3.0 13.45 3.70 2.60 23.0 111 \n", - "166 3.0 12.82 3.37 2.30 19.5 88 \n", - "167 3.0 13.58 2.58 2.69 24.5 105 \n", - "168 3.0 13.40 4.60 2.86 25.0 112 \n", - "169 3.0 12.20 3.03 2.32 19.0 96 \n", - "170 3.0 12.77 2.39 2.28 19.5 86 \n", - "171 3.0 14.16 2.51 2.48 20.0 91 \n", - "172 3.0 13.71 5.65 2.45 20.5 95 \n", - "173 3.0 13.40 3.91 2.48 23.0 102 \n", - "174 3.0 13.27 4.28 2.26 20.0 120 \n", - "175 3.0 13.17 2.59 2.37 20.0 120 \n", - "176 3.0 14.13 4.10 2.74 24.5 96 \n", - "\n", - " Flavanoids Nonflavanoid phenols Proanthocyanins Color intensity \\\n", - "3 2.80 2.69 0.39 1.82 \n", - "9 2.95 3.32 0.22 2.38 \n", - "10 2.20 2.43 0.26 1.57 \n", - "11 2.60 2.76 0.29 1.81 \n", - "12 3.10 3.69 0.43 2.81 \n", - "13 3.30 3.64 0.29 2.96 \n", - "14 2.85 2.91 0.30 1.46 \n", - "15 2.80 3.14 0.33 1.97 \n", - "16 2.95 3.40 0.40 1.72 \n", - "17 3.30 3.93 0.32 1.86 \n", - "18 2.70 3.03 0.17 1.66 \n", - "19 3.00 3.17 0.24 2.10 \n", - "20 2.41 2.41 0.25 1.98 \n", - "21 2.61 2.88 0.27 1.69 \n", - "22 2.48 2.37 0.26 1.46 \n", - "23 2.53 2.61 0.28 1.66 \n", - "24 2.63 2.68 0.47 1.92 \n", - "25 2.85 2.94 0.34 1.45 \n", - "26 2.40 2.19 0.27 1.35 \n", - "27 2.95 2.97 0.37 1.76 \n", - "28 2.65 2.33 0.26 1.98 \n", - "29 3.00 3.25 0.29 2.38 \n", - "30 2.86 3.19 0.22 1.95 \n", - "31 2.42 2.69 0.42 1.97 \n", - "32 2.95 2.74 0.50 1.35 \n", - "33 2.35 2.53 0.29 1.54 \n", - "34 2.70 2.98 0.26 1.86 \n", - "35 2.60 2.68 0.34 1.36 \n", - "36 2.45 2.43 0.29 1.44 \n", - "37 2.40 2.64 0.28 1.37 \n", - ".. ... ... ... ... \n", - "147 1.93 0.76 0.45 1.25 \n", - "148 1.41 1.39 0.34 1.14 \n", - "149 1.40 1.57 0.22 1.25 \n", - "150 1.48 1.36 0.24 1.26 \n", - "151 2.20 1.28 0.26 1.56 \n", - "152 1.80 0.83 0.61 1.87 \n", - "153 1.48 0.58 0.53 1.40 \n", - "154 1.74 0.63 0.61 1.55 \n", - "155 1.80 0.83 0.48 1.56 \n", - "156 1.90 0.58 0.63 1.14 \n", - "157 2.80 1.31 0.53 2.70 \n", - "158 2.60 1.10 0.52 2.29 \n", - "159 2.30 0.92 0.50 1.04 \n", - "160 1.83 0.56 0.50 0.80 \n", - "161 1.65 0.60 0.60 0.96 \n", - "162 1.39 0.70 0.40 0.94 \n", - "163 1.35 0.68 0.41 1.03 \n", - "164 1.28 0.47 0.52 1.15 \n", - "165 1.70 0.92 0.43 1.46 \n", - "166 1.48 0.66 0.40 0.97 \n", - "167 1.55 0.84 0.39 1.54 \n", - "168 1.98 0.96 0.27 1.11 \n", - "169 1.25 0.49 0.40 0.73 \n", - "170 1.39 0.51 0.48 0.64 \n", - "171 1.68 0.70 0.44 1.24 \n", - "172 1.68 0.61 0.52 1.06 \n", - "173 1.80 0.75 0.43 1.41 \n", - "174 1.59 0.69 0.43 1.35 \n", - "175 1.65 0.68 0.53 1.46 \n", - "176 2.05 0.76 0.56 1.35 \n", - "\n", - " Hue OD280/OD315 of diluted wines Proline Col-14 \n", - "3 4.320000 1.04 2.93 735 \n", - "9 5.750000 1.25 3.17 1510 \n", - "10 5.000000 1.17 2.82 1280 \n", - "11 5.600000 1.15 2.90 1320 \n", - "12 5.400000 1.25 2.73 1150 \n", - "13 7.500000 1.20 3.00 1547 \n", - "14 7.300000 1.28 2.88 1310 \n", - "15 6.200000 1.07 2.65 1280 \n", - "16 6.600000 1.13 2.57 1130 \n", - "17 8.700000 1.23 2.82 1680 \n", - "18 5.100000 0.96 3.36 845 \n", - "19 5.650000 1.09 3.71 780 \n", - "20 4.500000 1.03 3.52 770 \n", - "21 3.800000 1.11 4.00 1035 \n", - "22 3.930000 1.09 3.63 1015 \n", - "23 3.520000 1.12 3.82 845 \n", - "24 3.580000 1.13 3.20 830 \n", - "25 4.800000 0.92 3.22 1195 \n", - "26 3.950000 1.02 2.77 1285 \n", - "27 4.500000 1.25 3.40 915 \n", - "28 4.700000 1.04 3.59 1035 \n", - "29 5.700000 1.19 2.71 1285 \n", - "30 6.900000 1.09 2.88 1515 \n", - "31 3.840000 1.23 2.87 990 \n", - "32 5.400000 1.25 3.00 1235 \n", - "33 4.200000 1.10 2.87 1095 \n", - "34 5.100000 1.04 3.47 920 \n", - "35 4.600000 1.09 2.78 880 \n", - "36 4.250000 1.12 2.51 1105 \n", - "37 3.700000 1.18 2.69 1020 \n", - ".. ... ... ... ... \n", - "147 8.420000 0.55 1.62 650 \n", - "148 9.400000 0.57 1.33 550 \n", - "149 8.600000 0.59 1.30 500 \n", - "150 10.800000 0.48 1.47 480 \n", - "151 7.100000 0.61 1.33 425 \n", - "152 10.520000 0.56 1.51 675 \n", - "153 7.600000 0.58 1.55 640 \n", - "154 7.900000 0.60 1.48 725 \n", - "155 9.010000 0.57 1.64 480 \n", - "156 7.500000 0.67 1.73 880 \n", - "157 13.000000 0.57 1.96 660 \n", - "158 11.750000 0.57 1.78 620 \n", - "159 7.650000 0.56 1.58 520 \n", - "160 5.880000 0.96 1.82 680 \n", - "161 5.580000 0.87 2.11 570 \n", - "162 5.280000 0.68 1.75 675 \n", - "163 9.580000 0.70 1.68 615 \n", - "164 6.620000 0.78 1.75 520 \n", - "165 10.680000 0.85 1.56 695 \n", - "166 10.260000 0.72 1.75 685 \n", - "167 8.660000 0.74 1.80 750 \n", - "168 8.500000 0.67 1.92 630 \n", - "169 5.500000 0.66 1.83 510 \n", - "170 9.899999 0.57 1.63 470 \n", - "171 9.700000 0.62 1.71 660 \n", - "172 7.700000 0.64 1.74 740 \n", - "173 7.300000 0.70 1.56 750 \n", - "174 10.200000 0.59 1.56 835 \n", - "175 9.300000 0.60 1.62 840 \n", - "176 9.200000 0.61 1.60 560 \n", - "\n", - "[169 rows x 14 columns]\n" - ], - "name": "stdout" - } - ] - }, - { - "metadata": { - "id": "DlpG8drhmz7W", - "colab_type": "text" - }, - "cell_type": "markdown", - "source": [ - "### BONUS: Play with the data set below" - ] - }, - { - "metadata": { - "id": "mD40T0Cnm5SA", - "colab_type": "code", - "colab": {} - }, - "cell_type": "code", - "source": [ - "#exam next week, will play later :-P" - ], - "execution_count": 0, - "outputs": [] - } - ] -} \ No newline at end of file From b07625be5ecdcf4e8c9e3a388765027509b5c3fe Mon Sep 17 00:00:00 2001 From: Nawaz Sk Date: Fri, 18 Jan 2019 22:29:34 +0530 Subject: [PATCH 3/3] Created using Colaboratory --- Exercise.ipynb | 2053 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 2053 insertions(+) create mode 100644 Exercise.ipynb diff --git a/Exercise.ipynb b/Exercise.ipynb new file mode 100644 index 0000000..580f7b3 --- /dev/null +++ b/Exercise.ipynb @@ -0,0 +1,2053 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "name": "Exercise.ipynb", + "version": "0.3.2", + "provenance": [], + "collapsed_sections": [] + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + } + }, + "cells": [ + { + "metadata": { + "id": "2LTtpUJEibjg", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "# Pandas Exercise :\n", + "\n", + "\n", + "#### import necessary modules" + ] + }, + { + "metadata": { + "id": "c3_UBbMRhiKx", + "colab_type": "code", + "colab": {} + }, + "cell_type": "code", + "source": [ + "import numpy as np\n", + "import pandas as pd" + ], + "execution_count": 0, + "outputs": [] + }, + { + "metadata": { + "id": "tp-cTCyWi8mR", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Load url = \"https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data\" to a dataframe named wine_df\n", + "\n", + "This is a wine dataset\n", + "\n" + ] + }, + { + "metadata": { + "id": "DMojQY3thrRi", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 359 + }, + "outputId": "75935be6-1816-4db5-c0c7-4016595f14a0" + }, + "cell_type": "code", + "source": [ + "url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data'\n", + "wine_df = pd.read_csv(url)\n", + "wine_df.head(10)" + ], + "execution_count": 108, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
114.231.712.4315.61272.83.06.282.295.641.043.921065
0113.201.782.1411.21002.652.760.261.284.381.053.401050
1113.162.362.6718.61012.803.240.302.815.681.033.171185
2114.371.952.5016.81133.853.490.242.187.800.863.451480
3113.242.592.8721.01182.802.690.391.824.321.042.93735
4114.201.762.4515.21123.273.390.341.976.751.052.851450
5114.391.872.4514.6962.502.520.301.985.251.023.581290
6114.062.152.6117.61212.602.510.311.255.051.063.581295
7114.831.642.1714.0972.802.980.291.985.201.082.851045
8113.861.352.2716.0982.983.150.221.857.221.013.551045
9114.102.162.3018.01052.953.320.222.385.751.253.171510
\n", + "
" + ], + "text/plain": [ + " 1 14.23 1.71 2.43 15.6 127 2.8 3.06 .28 2.29 5.64 1.04 3.92 \\\n", + "0 1 13.20 1.78 2.14 11.2 100 2.65 2.76 0.26 1.28 4.38 1.05 3.40 \n", + "1 1 13.16 2.36 2.67 18.6 101 2.80 3.24 0.30 2.81 5.68 1.03 3.17 \n", + "2 1 14.37 1.95 2.50 16.8 113 3.85 3.49 0.24 2.18 7.80 0.86 3.45 \n", + "3 1 13.24 2.59 2.87 21.0 118 2.80 2.69 0.39 1.82 4.32 1.04 2.93 \n", + "4 1 14.20 1.76 2.45 15.2 112 3.27 3.39 0.34 1.97 6.75 1.05 2.85 \n", + "5 1 14.39 1.87 2.45 14.6 96 2.50 2.52 0.30 1.98 5.25 1.02 3.58 \n", + "6 1 14.06 2.15 2.61 17.6 121 2.60 2.51 0.31 1.25 5.05 1.06 3.58 \n", + "7 1 14.83 1.64 2.17 14.0 97 2.80 2.98 0.29 1.98 5.20 1.08 2.85 \n", + "8 1 13.86 1.35 2.27 16.0 98 2.98 3.15 0.22 1.85 7.22 1.01 3.55 \n", + "9 1 14.10 2.16 2.30 18.0 105 2.95 3.32 0.22 2.38 5.75 1.25 3.17 \n", + "\n", + " 1065 \n", + "0 1050 \n", + "1 1185 \n", + "2 1480 \n", + "3 735 \n", + "4 1450 \n", + "5 1290 \n", + "6 1295 \n", + "7 1045 \n", + "8 1045 \n", + "9 1510 " + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 108 + } + ] + }, + { + "metadata": { + "id": "BF9MMjoZjSlg", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### print first five rows" + ] + }, + { + "metadata": { + "id": "1vSMQdnHjYNU", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 204 + }, + "outputId": "c13d7565-8120-42d0-bda7-b60b1ca628b6" + }, + "cell_type": "code", + "source": [ + "wine_df.head(5)" + ], + "execution_count": 109, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
114.231.712.4315.61272.83.06.282.295.641.043.921065
0113.201.782.1411.21002.652.760.261.284.381.053.401050
1113.162.362.6718.61012.803.240.302.815.681.033.171185
2114.371.952.5016.81133.853.490.242.187.800.863.451480
3113.242.592.8721.01182.802.690.391.824.321.042.93735
4114.201.762.4515.21123.273.390.341.976.751.052.851450
\n", + "
" + ], + "text/plain": [ + " 1 14.23 1.71 2.43 15.6 127 2.8 3.06 .28 2.29 5.64 1.04 3.92 \\\n", + "0 1 13.20 1.78 2.14 11.2 100 2.65 2.76 0.26 1.28 4.38 1.05 3.40 \n", + "1 1 13.16 2.36 2.67 18.6 101 2.80 3.24 0.30 2.81 5.68 1.03 3.17 \n", + "2 1 14.37 1.95 2.50 16.8 113 3.85 3.49 0.24 2.18 7.80 0.86 3.45 \n", + "3 1 13.24 2.59 2.87 21.0 118 2.80 2.69 0.39 1.82 4.32 1.04 2.93 \n", + "4 1 14.20 1.76 2.45 15.2 112 3.27 3.39 0.34 1.97 6.75 1.05 2.85 \n", + "\n", + " 1065 \n", + "0 1050 \n", + "1 1185 \n", + "2 1480 \n", + "3 735 \n", + "4 1450 " + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 109 + } + ] + }, + { + "metadata": { + "id": "Tet6P2DvjY3T", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### assign wine_df to a different variable wine_df_copy and then delete all odd rows of wine_df_copy\n", + "\n", + "[Hint](https://pandas.pydata.org/pandas-docs/stable/generated/pandas.DataFrame.drop.html)" + ] + }, + { + "metadata": { + "id": "CMj3qSdJjx0u", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 359 + }, + "outputId": "a6676447-dd0c-4866-9df4-34f02706caf0" + }, + "cell_type": "code", + "source": [ + "wine_df_copy = wine_df\n", + "wine_df_copy = wine_df_copy[wine_df_copy.index%2 == 0]\n", + "wine_df_copy.head(10)" + ], + "execution_count": 110, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
114.231.712.4315.61272.83.06.282.295.641.043.921065
0113.201.782.1411.21002.652.760.261.284.381.053.401050
2114.371.952.5016.81133.853.490.242.187.800.863.451480
4114.201.762.4515.21123.273.390.341.976.751.052.851450
6114.062.152.6117.61212.602.510.311.255.051.063.581295
8113.861.352.2716.0982.983.150.221.857.221.013.551045
10114.121.482.3216.8952.202.430.261.575.001.172.821280
12114.751.732.3911.4913.103.690.432.815.401.252.731150
14113.631.812.7017.21122.852.910.301.467.301.282.881310
16113.831.572.6220.01152.953.400.401.726.601.132.571130
18113.643.102.5615.21162.703.030.171.665.100.963.36845
\n", + "
" + ], + "text/plain": [ + " 1 14.23 1.71 2.43 15.6 127 2.8 3.06 .28 2.29 5.64 1.04 3.92 \\\n", + "0 1 13.20 1.78 2.14 11.2 100 2.65 2.76 0.26 1.28 4.38 1.05 3.40 \n", + "2 1 14.37 1.95 2.50 16.8 113 3.85 3.49 0.24 2.18 7.80 0.86 3.45 \n", + "4 1 14.20 1.76 2.45 15.2 112 3.27 3.39 0.34 1.97 6.75 1.05 2.85 \n", + "6 1 14.06 2.15 2.61 17.6 121 2.60 2.51 0.31 1.25 5.05 1.06 3.58 \n", + "8 1 13.86 1.35 2.27 16.0 98 2.98 3.15 0.22 1.85 7.22 1.01 3.55 \n", + "10 1 14.12 1.48 2.32 16.8 95 2.20 2.43 0.26 1.57 5.00 1.17 2.82 \n", + "12 1 14.75 1.73 2.39 11.4 91 3.10 3.69 0.43 2.81 5.40 1.25 2.73 \n", + "14 1 13.63 1.81 2.70 17.2 112 2.85 2.91 0.30 1.46 7.30 1.28 2.88 \n", + "16 1 13.83 1.57 2.62 20.0 115 2.95 3.40 0.40 1.72 6.60 1.13 2.57 \n", + "18 1 13.64 3.10 2.56 15.2 116 2.70 3.03 0.17 1.66 5.10 0.96 3.36 \n", + "\n", + " 1065 \n", + "0 1050 \n", + "2 1480 \n", + "4 1450 \n", + "6 1295 \n", + "8 1045 \n", + "10 1280 \n", + "12 1150 \n", + "14 1310 \n", + "16 1130 \n", + "18 845 " + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 110 + } + ] + }, + { + "metadata": { + "id": "o6Cs6T1Rjz71", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Assign the columns as below:\n", + "\n", + "The attributes are (dontated by Riccardo Leardi, riclea '@' anchem.unige.it): \n", + "1) Alcohol \n", + "2) Malic acid \n", + "3) Ash \n", + "4) Alcalinity of ash \n", + "5) Magnesium \n", + "6) Total phenols \n", + "7) Flavanoids \n", + "8) Nonflavanoid phenols \n", + "9) Proanthocyanins \n", + "10)Color intensity \n", + "11)Hue \n", + "12)OD280/OD315 of diluted wines \n", + "13)Proline " + ] + }, + { + "metadata": { + "id": "my8HB4V4j779", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 359 + }, + "outputId": "cf250a08-a1a8-43b2-8955-752f3c512750" + }, + "cell_type": "code", + "source": [ + "wine_df.columns = ['Alcohol','Malic acid','Ash','Alcalinity of ash','Magnesium','Total phenols','Flavanoids','Nonflavanoid phenols','Proanthocyanins','Color intensity','Hue','OD280/OD315 of diluted wines','Proline','Col-14']\n", + "wine_df.head(10)" + ], + "execution_count": 111, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
AlcoholMalic acidAshAlcalinity of ashMagnesiumTotal phenolsFlavanoidsNonflavanoid phenolsProanthocyaninsColor intensityHueOD280/OD315 of diluted winesProlineCol-14
0113.201.782.1411.21002.652.760.261.284.381.053.401050
1113.162.362.6718.61012.803.240.302.815.681.033.171185
2114.371.952.5016.81133.853.490.242.187.800.863.451480
3113.242.592.8721.01182.802.690.391.824.321.042.93735
4114.201.762.4515.21123.273.390.341.976.751.052.851450
5114.391.872.4514.6962.502.520.301.985.251.023.581290
6114.062.152.6117.61212.602.510.311.255.051.063.581295
7114.831.642.1714.0972.802.980.291.985.201.082.851045
8113.861.352.2716.0982.983.150.221.857.221.013.551045
9114.102.162.3018.01052.953.320.222.385.751.253.171510
\n", + "
" + ], + "text/plain": [ + " Alcohol Malic acid Ash Alcalinity of ash Magnesium Total phenols \\\n", + "0 1 13.20 1.78 2.14 11.2 100 \n", + "1 1 13.16 2.36 2.67 18.6 101 \n", + "2 1 14.37 1.95 2.50 16.8 113 \n", + "3 1 13.24 2.59 2.87 21.0 118 \n", + "4 1 14.20 1.76 2.45 15.2 112 \n", + "5 1 14.39 1.87 2.45 14.6 96 \n", + "6 1 14.06 2.15 2.61 17.6 121 \n", + "7 1 14.83 1.64 2.17 14.0 97 \n", + "8 1 13.86 1.35 2.27 16.0 98 \n", + "9 1 14.10 2.16 2.30 18.0 105 \n", + "\n", + " Flavanoids Nonflavanoid phenols Proanthocyanins Color intensity Hue \\\n", + "0 2.65 2.76 0.26 1.28 4.38 \n", + "1 2.80 3.24 0.30 2.81 5.68 \n", + "2 3.85 3.49 0.24 2.18 7.80 \n", + "3 2.80 2.69 0.39 1.82 4.32 \n", + "4 3.27 3.39 0.34 1.97 6.75 \n", + "5 2.50 2.52 0.30 1.98 5.25 \n", + "6 2.60 2.51 0.31 1.25 5.05 \n", + "7 2.80 2.98 0.29 1.98 5.20 \n", + "8 2.98 3.15 0.22 1.85 7.22 \n", + "9 2.95 3.32 0.22 2.38 5.75 \n", + "\n", + " OD280/OD315 of diluted wines Proline Col-14 \n", + "0 1.05 3.40 1050 \n", + "1 1.03 3.17 1185 \n", + "2 0.86 3.45 1480 \n", + "3 1.04 2.93 735 \n", + "4 1.05 2.85 1450 \n", + "5 1.02 3.58 1290 \n", + "6 1.06 3.58 1295 \n", + "7 1.08 2.85 1045 \n", + "8 1.01 3.55 1045 \n", + "9 1.25 3.17 1510 " + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 111 + } + ] + }, + { + "metadata": { + "id": "Zqi7hwWpkNbH", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Set the values of the first 3 rows from alcohol as NaN\n", + "\n", + "Hint- Use iloc to select 3 rows of wine_df" + ] + }, + { + "metadata": { + "id": "buyT4vX4kPMl", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 444 + }, + "outputId": "75d93567-4646-4ab4-bea1-fd067d881dcf" + }, + "cell_type": "code", + "source": [ + "wine_df.Alcohol.iloc[:3] = np.nan\n", + "wine_df.head(10)" + ], + "execution_count": 112, + "outputs": [ + { + "output_type": "stream", + "text": [ + "/usr/local/lib/python3.6/dist-packages/pandas/core/indexing.py:194: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame\n", + "\n", + "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n", + " self._setitem_with_indexer(indexer, value)\n" + ], + "name": "stderr" + }, + { + "output_type": "execute_result", + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
AlcoholMalic acidAshAlcalinity of ashMagnesiumTotal phenolsFlavanoidsNonflavanoid phenolsProanthocyaninsColor intensityHueOD280/OD315 of diluted winesProlineCol-14
0NaN13.201.782.1411.21002.652.760.261.284.381.053.401050
1NaN13.162.362.6718.61012.803.240.302.815.681.033.171185
2NaN14.371.952.5016.81133.853.490.242.187.800.863.451480
31.013.242.592.8721.01182.802.690.391.824.321.042.93735
41.014.201.762.4515.21123.273.390.341.976.751.052.851450
51.014.391.872.4514.6962.502.520.301.985.251.023.581290
61.014.062.152.6117.61212.602.510.311.255.051.063.581295
71.014.831.642.1714.0972.802.980.291.985.201.082.851045
81.013.861.352.2716.0982.983.150.221.857.221.013.551045
91.014.102.162.3018.01052.953.320.222.385.751.253.171510
\n", + "
" + ], + "text/plain": [ + " Alcohol Malic acid Ash Alcalinity of ash Magnesium Total phenols \\\n", + "0 NaN 13.20 1.78 2.14 11.2 100 \n", + "1 NaN 13.16 2.36 2.67 18.6 101 \n", + "2 NaN 14.37 1.95 2.50 16.8 113 \n", + "3 1.0 13.24 2.59 2.87 21.0 118 \n", + "4 1.0 14.20 1.76 2.45 15.2 112 \n", + "5 1.0 14.39 1.87 2.45 14.6 96 \n", + "6 1.0 14.06 2.15 2.61 17.6 121 \n", + "7 1.0 14.83 1.64 2.17 14.0 97 \n", + "8 1.0 13.86 1.35 2.27 16.0 98 \n", + "9 1.0 14.10 2.16 2.30 18.0 105 \n", + "\n", + " Flavanoids Nonflavanoid phenols Proanthocyanins Color intensity Hue \\\n", + "0 2.65 2.76 0.26 1.28 4.38 \n", + "1 2.80 3.24 0.30 2.81 5.68 \n", + "2 3.85 3.49 0.24 2.18 7.80 \n", + "3 2.80 2.69 0.39 1.82 4.32 \n", + "4 3.27 3.39 0.34 1.97 6.75 \n", + "5 2.50 2.52 0.30 1.98 5.25 \n", + "6 2.60 2.51 0.31 1.25 5.05 \n", + "7 2.80 2.98 0.29 1.98 5.20 \n", + "8 2.98 3.15 0.22 1.85 7.22 \n", + "9 2.95 3.32 0.22 2.38 5.75 \n", + "\n", + " OD280/OD315 of diluted wines Proline Col-14 \n", + "0 1.05 3.40 1050 \n", + "1 1.03 3.17 1185 \n", + "2 0.86 3.45 1480 \n", + "3 1.04 2.93 735 \n", + "4 1.05 2.85 1450 \n", + "5 1.02 3.58 1290 \n", + "6 1.06 3.58 1295 \n", + "7 1.08 2.85 1045 \n", + "8 1.01 3.55 1045 \n", + "9 1.25 3.17 1510 " + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 112 + } + ] + }, + { + "metadata": { + "id": "RQMNI2UHkP3o", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Create an array of 10 random numbers uptill 10 and assign it to a variable named `random`" + ] + }, + { + "metadata": { + "id": "xunmCjaEmDwZ", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 34 + }, + "outputId": "eff253d6-a5ef-425f-fc8e-abb78c499c9f" + }, + "cell_type": "code", + "source": [ + "random = np.random.randint(1,10,10)\n", + "print(random)" + ], + "execution_count": 113, + "outputs": [ + { + "output_type": "stream", + "text": [ + "[8 2 1 9 6 6 9 2 9 2]\n" + ], + "name": "stdout" + } + ] + }, + { + "metadata": { + "id": "hELUakyXmFSu", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Use random numbers you generated as an index and assign NaN value to each of cell of the column alcohol" + ] + }, + { + "metadata": { + "id": "zMgaNnNHmP01", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 359 + }, + "outputId": "a9f82ab3-b77d-47e2-fec3-d12bf130fc86" + }, + "cell_type": "code", + "source": [ + "wine_df.Alcohol.iloc[random] = np.nan\n", + "wine_df.head(10)" + ], + "execution_count": 114, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
AlcoholMalic acidAshAlcalinity of ashMagnesiumTotal phenolsFlavanoidsNonflavanoid phenolsProanthocyaninsColor intensityHueOD280/OD315 of diluted winesProlineCol-14
0NaN13.201.782.1411.21002.652.760.261.284.381.053.401050
1NaN13.162.362.6718.61012.803.240.302.815.681.033.171185
2NaN14.371.952.5016.81133.853.490.242.187.800.863.451480
31.013.242.592.8721.01182.802.690.391.824.321.042.93735
41.014.201.762.4515.21123.273.390.341.976.751.052.851450
51.014.391.872.4514.6962.502.520.301.985.251.023.581290
6NaN14.062.152.6117.61212.602.510.311.255.051.063.581295
71.014.831.642.1714.0972.802.980.291.985.201.082.851045
8NaN13.861.352.2716.0982.983.150.221.857.221.013.551045
9NaN14.102.162.3018.01052.953.320.222.385.751.253.171510
\n", + "
" + ], + "text/plain": [ + " Alcohol Malic acid Ash Alcalinity of ash Magnesium Total phenols \\\n", + "0 NaN 13.20 1.78 2.14 11.2 100 \n", + "1 NaN 13.16 2.36 2.67 18.6 101 \n", + "2 NaN 14.37 1.95 2.50 16.8 113 \n", + "3 1.0 13.24 2.59 2.87 21.0 118 \n", + "4 1.0 14.20 1.76 2.45 15.2 112 \n", + "5 1.0 14.39 1.87 2.45 14.6 96 \n", + "6 NaN 14.06 2.15 2.61 17.6 121 \n", + "7 1.0 14.83 1.64 2.17 14.0 97 \n", + "8 NaN 13.86 1.35 2.27 16.0 98 \n", + "9 NaN 14.10 2.16 2.30 18.0 105 \n", + "\n", + " Flavanoids Nonflavanoid phenols Proanthocyanins Color intensity Hue \\\n", + "0 2.65 2.76 0.26 1.28 4.38 \n", + "1 2.80 3.24 0.30 2.81 5.68 \n", + "2 3.85 3.49 0.24 2.18 7.80 \n", + "3 2.80 2.69 0.39 1.82 4.32 \n", + "4 3.27 3.39 0.34 1.97 6.75 \n", + "5 2.50 2.52 0.30 1.98 5.25 \n", + "6 2.60 2.51 0.31 1.25 5.05 \n", + "7 2.80 2.98 0.29 1.98 5.20 \n", + "8 2.98 3.15 0.22 1.85 7.22 \n", + "9 2.95 3.32 0.22 2.38 5.75 \n", + "\n", + " OD280/OD315 of diluted wines Proline Col-14 \n", + "0 1.05 3.40 1050 \n", + "1 1.03 3.17 1185 \n", + "2 0.86 3.45 1480 \n", + "3 1.04 2.93 735 \n", + "4 1.05 2.85 1450 \n", + "5 1.02 3.58 1290 \n", + "6 1.06 3.58 1295 \n", + "7 1.08 2.85 1045 \n", + "8 1.01 3.55 1045 \n", + "9 1.25 3.17 1510 " + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 114 + } + ] + }, + { + "metadata": { + "id": "PHyK_vRsmRwV", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### How many missing values do we have? \n", + "\n", + "Hint: you can use isnull() and sum()" + ] + }, + { + "metadata": { + "id": "EnOYhmEqmfKp", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 272 + }, + "outputId": "409c61b1-0d47-416d-adcf-07e3c452ba94" + }, + "cell_type": "code", + "source": [ + "print((wine_df.isnull()).sum())" + ], + "execution_count": 115, + "outputs": [ + { + "output_type": "stream", + "text": [ + "Alcohol 6\n", + "Malic acid 0\n", + "Ash 0\n", + "Alcalinity of ash 0\n", + "Magnesium 0\n", + "Total phenols 0\n", + "Flavanoids 0\n", + "Nonflavanoid phenols 0\n", + "Proanthocyanins 0\n", + "Color intensity 0\n", + "Hue 0\n", + "OD280/OD315 of diluted wines 0\n", + "Proline 0\n", + "Col-14 0\n", + "dtype: int64\n" + ], + "name": "stdout" + } + ] + }, + { + "metadata": { + "id": "-Fd4WBklmf1_", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Delete the rows that contain missing values " + ] + }, + { + "metadata": { + "id": "As7IC6Ktms8-", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 359 + }, + "outputId": "a79d4627-4676-45e1-8ebf-24b64f5b9a99" + }, + "cell_type": "code", + "source": [ + "wine_df = wine_df.dropna(how='any',axis=0)\n", + "wine_df.head(10)" + ], + "execution_count": 116, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
AlcoholMalic acidAshAlcalinity of ashMagnesiumTotal phenolsFlavanoidsNonflavanoid phenolsProanthocyaninsColor intensityHueOD280/OD315 of diluted winesProlineCol-14
31.013.242.592.8721.01182.802.690.391.824.321.042.93735
41.014.201.762.4515.21123.273.390.341.976.751.052.851450
51.014.391.872.4514.6962.502.520.301.985.251.023.581290
71.014.831.642.1714.0972.802.980.291.985.201.082.851045
101.014.121.482.3216.8952.202.430.261.575.001.172.821280
111.013.751.732.4116.0892.602.760.291.815.601.152.901320
121.014.751.732.3911.4913.103.690.432.815.401.252.731150
131.014.381.872.3812.01023.303.640.292.967.501.203.001547
141.013.631.812.7017.21122.852.910.301.467.301.282.881310
151.014.301.922.7220.01202.803.140.331.976.201.072.651280
\n", + "
" + ], + "text/plain": [ + " Alcohol Malic acid Ash Alcalinity of ash Magnesium Total phenols \\\n", + "3 1.0 13.24 2.59 2.87 21.0 118 \n", + "4 1.0 14.20 1.76 2.45 15.2 112 \n", + "5 1.0 14.39 1.87 2.45 14.6 96 \n", + "7 1.0 14.83 1.64 2.17 14.0 97 \n", + "10 1.0 14.12 1.48 2.32 16.8 95 \n", + "11 1.0 13.75 1.73 2.41 16.0 89 \n", + "12 1.0 14.75 1.73 2.39 11.4 91 \n", + "13 1.0 14.38 1.87 2.38 12.0 102 \n", + "14 1.0 13.63 1.81 2.70 17.2 112 \n", + "15 1.0 14.30 1.92 2.72 20.0 120 \n", + "\n", + " Flavanoids Nonflavanoid phenols Proanthocyanins Color intensity Hue \\\n", + "3 2.80 2.69 0.39 1.82 4.32 \n", + "4 3.27 3.39 0.34 1.97 6.75 \n", + "5 2.50 2.52 0.30 1.98 5.25 \n", + "7 2.80 2.98 0.29 1.98 5.20 \n", + "10 2.20 2.43 0.26 1.57 5.00 \n", + "11 2.60 2.76 0.29 1.81 5.60 \n", + "12 3.10 3.69 0.43 2.81 5.40 \n", + "13 3.30 3.64 0.29 2.96 7.50 \n", + "14 2.85 2.91 0.30 1.46 7.30 \n", + "15 2.80 3.14 0.33 1.97 6.20 \n", + "\n", + " OD280/OD315 of diluted wines Proline Col-14 \n", + "3 1.04 2.93 735 \n", + "4 1.05 2.85 1450 \n", + "5 1.02 3.58 1290 \n", + "7 1.08 2.85 1045 \n", + "10 1.17 2.82 1280 \n", + "11 1.15 2.90 1320 \n", + "12 1.25 2.73 1150 \n", + "13 1.20 3.00 1547 \n", + "14 1.28 2.88 1310 \n", + "15 1.07 2.65 1280 " + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 116 + } + ] + }, + { + "metadata": { + "id": "DlpG8drhmz7W", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "### BONUS: Play with the data set below" + ] + }, + { + "metadata": { + "id": "mD40T0Cnm5SA", + "colab_type": "code", + "colab": {} + }, + "cell_type": "code", + "source": [ + "#exam next week, will play later :-P" + ], + "execution_count": 0, + "outputs": [] + } + ] +} \ No newline at end of file