From dce2894f0c600ec58a422ffe2df9c4ac5f7f15b7 Mon Sep 17 00:00:00 2001 From: AGCreates <43198265+AGCreates@users.noreply.github.com> Date: Mon, 8 Oct 2018 13:55:36 +0530 Subject: [PATCH 1/4] Solved part 2 Assignment 3 get to know your your data --- AGCreates.ipynb | 3059 ++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 3029 insertions(+), 30 deletions(-) diff --git a/AGCreates.ipynb b/AGCreates.ipynb index 9e2543a..4f3c6b2 100644 --- a/AGCreates.ipynb +++ b/AGCreates.ipynb @@ -1,32 +1,3031 @@ { - "cells": [ - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3", - "language": "python", - "name": "python3" + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "name": "Get to know your Data.ipynb", + "version": "0.3.2", + "provenance": [], + "include_colab_link": true + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + } }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.5.2" - } - }, - "nbformat": 4, - "nbformat_minor": 2 -} + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "[View in Colaboratory](https://colab.research.google.com/github/AGCreates/Assignment-3/blob/AGCreates/AGCreates.ipynb)" + ] + }, + { + "metadata": { + "id": "J82LU53m_OU0", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "# Get to know your Data\n", + "\n", + "\n", + "#### Import necessary modules\n" + ] + }, + { + "metadata": { + "id": "ZyO1UXL8mtSj", + "colab_type": "code", + "colab": {} + }, + "cell_type": "code", + "source": [ + "import pandas as pd\n", + "import numpy as np\n" + ], + "execution_count": 0, + "outputs": [] + }, + { + "metadata": { + "id": "yXTzTowtnwGI", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Loading CSV Data to a DataFrame" + ] + }, + { + "metadata": { + "id": "H1Bjlb5wm9f-", + "colab_type": "code", + "colab": {} + }, + "cell_type": "code", + "source": [ + "iris_df = pd.read_csv('https://raw.githubusercontent.com/uiuc-cse/data-fa14/gh-pages/data/iris.csv')\n" + ], + "execution_count": 0, + "outputs": [] + }, + { + "metadata": { + "id": "KE-k7b_Mn5iN", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### See the top 10 rows\n" + ] + }, + { + "metadata": { + "id": "HY2Ps7xMn4ao", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 204 + }, + "outputId": "4cdfb127-21e6-4ef6-eb2d-ef20b0c19e86" + }, + "cell_type": "code", + "source": [ + "iris_df.head()Get to know your Data\n", + "Import necessary modules\n", + "[ ]\n", + "\n", + "import pandas as pd\n", + "import numpy as np\n", + "​\n", + "Loading CSV Data to a DataFrame\n", + "[ ]\n", + "\n", + "iris_df = pd.read_csv('https://raw.githubusercontent.com/uiuc-cse/data-fa14/gh-pages/data/iris.csv')\n", + "​\n", + "See the top 10 rows" + ], + "execution_count": 4, + "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", + "
sepal_lengthsepal_widthpetal_lengthpetal_widthspecies
05.13.51.40.2setosa
14.93.01.40.2setosa
24.73.21.30.2setosa
34.63.11.50.2setosa
45.03.61.40.2setosa
\n", + "
" + ], + "text/plain": [ + " sepal_length sepal_width petal_length petal_width species\n", + "0 5.1 3.5 1.4 0.2 setosa\n", + "1 4.9 3.0 1.4 0.2 setosa\n", + "2 4.7 3.2 1.3 0.2 setosa\n", + "3 4.6 3.1 1.5 0.2 setosa\n", + "4 5.0 3.6 1.4 0.2 setosa" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 4 + } + ] + }, + { + "metadata": { + "id": "ZQXekIodqOZu", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Find number of rows and columns\n" + ] + }, + { + "metadata": { + "id": "6Y-A-lbFqR82", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 68 + }, + "outputId": "a85add90-3697-4dce-b021-c94dcdd29b37" + }, + "cell_type": "code", + "source": [ + "print(iris_df.shape)\n", + "\n", + "#first is row and second is column\n", + "#select row by simple indexing\n", + "\n", + "print(iris_df.shape[0])\n", + "print(iris_df.shape[1])" + ], + "execution_count": 5, + "outputs": [ + { + "output_type": "stream", + "text": [ + "(150, 5)\n", + "150\n", + "5\n" + ], + "name": "stdout" + } + ] + }, + { + "metadata": { + "id": "4ckCiGPhrC_t", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Print all columns" + ] + }, + { + "metadata": { + "id": "S6jgMyRDrF2a", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 68 + }, + "outputId": "21690248-dc53-4fa3-b40f-24b1a33c5276" + }, + "cell_type": "code", + "source": [ + "print(iris_df.columns)" + ], + "execution_count": 6, + "outputs": [ + { + "output_type": "stream", + "text": [ + "Index(['sepal_length', 'sepal_width', 'petal_length', 'petal_width',\n", + " 'species'],\n", + " dtype='object')\n" + ], + "name": "stdout" + } + ] + }, + { + "metadata": { + "id": "kVav5-ACtIqS", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Check Index\n" + ] + }, + { + "metadata": { + "id": "iu3I9zIGtLDX", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 34 + }, + "outputId": "b2c51f4c-2376-4485-8bd8-bc4d58039e2b" + }, + "cell_type": "code", + "source": [ + "print(iris_df.index)" + ], + "execution_count": 7, + "outputs": [ + { + "output_type": "stream", + "text": [ + "RangeIndex(start=0, stop=150, step=1)\n" + ], + "name": "stdout" + } + ] + }, + { + "metadata": { + "id": "psCc7PborOCQ", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Right now the iris_data set has all the species grouped together let's shuffle it" + ] + }, + { + "metadata": { + "id": "Bxc8i6avrZPw", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 374 + }, + "outputId": "cbe82b4b-e5e9-49a1-9eec-6e8f3ed6321f" + }, + "cell_type": "code", + "source": [ + "#generate a random permutaion on index\n", + "\n", + "print(iris_df.head())\n", + "\n", + "new_index = np.random.permutation(iris_df.index)\n", + "print (new_index)\n", + "iris_df = iris_df.reindex(index = new_index)\n", + "\n", + "print(iris_df.head())" + ], + "execution_count": 8, + "outputs": [ + { + "output_type": "stream", + "text": [ + " sepal_length sepal_width petal_length petal_width species\n", + "0 5.1 3.5 1.4 0.2 setosa\n", + "1 4.9 3.0 1.4 0.2 setosa\n", + "2 4.7 3.2 1.3 0.2 setosa\n", + "3 4.6 3.1 1.5 0.2 setosa\n", + "4 5.0 3.6 1.4 0.2 setosa\n", + "[ 37 129 141 90 120 72 23 19 68 82 147 73 2 133 110 149 17 16\n", + " 125 40 14 12 4 52 138 30 136 102 11 71 121 29 148 5 108 81\n", + " 85 127 88 59 38 92 42 7 35 139 91 107 53 134 6 47 32 119\n", + " 62 66 128 43 65 46 98 83 115 132 79 74 111 130 76 24 0 105\n", + " 86 61 143 145 56 70 28 15 60 57 131 26 80 10 64 112 84 58\n", + " 142 140 49 44 51 67 25 117 31 48 1 18 104 75 135 146 9 122\n", + " 50 20 36 22 87 93 33 39 63 94 101 96 113 99 13 97 41 77\n", + " 126 109 106 3 55 27 95 8 21 45 103 100 123 137 69 89 34 116\n", + " 118 114 144 78 124 54]\n", + " sepal_length sepal_width petal_length petal_width species\n", + "37 4.9 3.1 1.5 0.1 setosa\n", + "129 7.2 3.0 5.8 1.6 virginica\n", + "141 6.9 3.1 5.1 2.3 virginica\n", + "90 5.5 2.6 4.4 1.2 versicolor\n", + "120 6.9 3.2 5.7 2.3 virginica\n" + ], + "name": "stdout" + } + ] + }, + { + "metadata": { + "id": "j32h8022sRT8", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### We can also apply an operation on whole column of iris_df" + ] + }, + { + "metadata": { + "id": "seYXHXsYsYJI", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 323 + }, + "outputId": "3386fb6d-a486-4e31-f1ce-cf9085e82edd" + }, + "cell_type": "code", + "source": [ + "#original\n", + "\n", + "print(iris_df.head())\n", + "\n", + "iris_df['sepal_width'] *= 10\n", + "\n", + "#changed\n", + "\n", + "print(iris_df.head())\n", + "\n", + "#lets undo the operation\n", + "\n", + "iris_df['sepal_width'] /= 10\n", + "\n", + "print(iris_df.head())" + ], + "execution_count": 9, + "outputs": [ + { + "output_type": "stream", + "text": [ + " sepal_length sepal_width petal_length petal_width species\n", + "37 4.9 3.1 1.5 0.1 setosa\n", + "129 7.2 3.0 5.8 1.6 virginica\n", + "141 6.9 3.1 5.1 2.3 virginica\n", + "90 5.5 2.6 4.4 1.2 versicolor\n", + "120 6.9 3.2 5.7 2.3 virginica\n", + " sepal_length sepal_width petal_length petal_width species\n", + "37 4.9 31.0 1.5 0.1 setosa\n", + "129 7.2 30.0 5.8 1.6 virginica\n", + "141 6.9 31.0 5.1 2.3 virginica\n", + "90 5.5 26.0 4.4 1.2 versicolor\n", + "120 6.9 32.0 5.7 2.3 virginica\n", + " sepal_length sepal_width petal_length petal_width species\n", + "37 4.9 3.1 1.5 0.1 setosa\n", + "129 7.2 3.0 5.8 1.6 virginica\n", + "141 6.9 3.1 5.1 2.3 virginica\n", + "90 5.5 2.6 4.4 1.2 versicolor\n", + "120 6.9 3.2 5.7 2.3 virginica\n" + ], + "name": "stdout" + } + ] + }, + { + "metadata": { + "id": "R-Ca-LBLzjiF", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Show all the rows where sepal_width > 3.3" + ] + }, + { + "metadata": { + "id": "WJ7W-F-d0AoZ", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1165 + }, + "outputId": "617c88e9-fe0b-4a3f-cd24-776a947e7519" + }, + "cell_type": "code", + "source": [ + "iris_df[iris_df['sepal_width']>3.3]" + ], + "execution_count": 10, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
sepal_lengthsepal_widthpetal_lengthpetal_widthspecies
195.13.81.50.3setosa
175.13.51.40.3setosa
165.43.91.30.4setosa
405.03.51.30.3setosa
145.84.01.20.2setosa
45.03.61.40.2setosa
1366.33.45.62.4virginica
114.83.41.60.2setosa
1486.23.45.42.3virginica
55.43.91.70.4setosa
856.03.44.51.6versicolor
75.03.41.50.2setosa
64.63.41.40.3setosa
325.24.11.50.1setosa
435.03.51.60.6setosa
465.13.81.60.2setosa
244.83.41.90.2setosa
05.13.51.40.2setosa
285.23.41.40.2setosa
155.74.41.50.4setosa
1317.93.86.42.0virginica
265.03.41.60.4setosa
105.43.71.50.2setosa
445.13.81.90.4setosa
1177.73.86.72.2virginica
315.43.41.50.4setosa
485.33.71.50.2setosa
185.73.81.70.3setosa
205.43.41.70.2setosa
365.53.51.30.2setosa
224.63.61.00.2setosa
335.54.21.40.2setosa
395.13.41.50.2setosa
1097.23.66.12.5virginica
275.23.51.50.2setosa
215.13.71.50.4setosa
\n", + "
" + ], + "text/plain": [ + " sepal_length sepal_width petal_length petal_width species\n", + "19 5.1 3.8 1.5 0.3 setosa\n", + "17 5.1 3.5 1.4 0.3 setosa\n", + "16 5.4 3.9 1.3 0.4 setosa\n", + "40 5.0 3.5 1.3 0.3 setosa\n", + "14 5.8 4.0 1.2 0.2 setosa\n", + "4 5.0 3.6 1.4 0.2 setosa\n", + "136 6.3 3.4 5.6 2.4 virginica\n", + "11 4.8 3.4 1.6 0.2 setosa\n", + "148 6.2 3.4 5.4 2.3 virginica\n", + "5 5.4 3.9 1.7 0.4 setosa\n", + "85 6.0 3.4 4.5 1.6 versicolor\n", + "7 5.0 3.4 1.5 0.2 setosa\n", + "6 4.6 3.4 1.4 0.3 setosa\n", + "32 5.2 4.1 1.5 0.1 setosa\n", + "43 5.0 3.5 1.6 0.6 setosa\n", + "46 5.1 3.8 1.6 0.2 setosa\n", + "24 4.8 3.4 1.9 0.2 setosa\n", + "0 5.1 3.5 1.4 0.2 setosa\n", + "28 5.2 3.4 1.4 0.2 setosa\n", + "15 5.7 4.4 1.5 0.4 setosa\n", + "131 7.9 3.8 6.4 2.0 virginica\n", + "26 5.0 3.4 1.6 0.4 setosa\n", + "10 5.4 3.7 1.5 0.2 setosa\n", + "44 5.1 3.8 1.9 0.4 setosa\n", + "117 7.7 3.8 6.7 2.2 virginica\n", + "31 5.4 3.4 1.5 0.4 setosa\n", + "48 5.3 3.7 1.5 0.2 setosa\n", + "18 5.7 3.8 1.7 0.3 setosa\n", + "20 5.4 3.4 1.7 0.2 setosa\n", + "36 5.5 3.5 1.3 0.2 setosa\n", + "22 4.6 3.6 1.0 0.2 setosa\n", + "33 5.5 4.2 1.4 0.2 setosa\n", + "39 5.1 3.4 1.5 0.2 setosa\n", + "109 7.2 3.6 6.1 2.5 virginica\n", + "27 5.2 3.5 1.5 0.2 setosa\n", + "21 5.1 3.7 1.5 0.4 setosa" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 10 + } + ] + }, + { + "metadata": { + "id": "gH3DnhCq2Cbl", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Club two filters together - Find all samples where sepal_width > 3.3 and species is versicolor" + ] + }, + { + "metadata": { + "id": "4U7ksr_R2H7M", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 80 + }, + "outputId": "1fc99bec-0325-43fc-e525-dd1428b08b34" + }, + "cell_type": "code", + "source": [ + "iris_df[(iris_df['sepal_width']>3.3) & (iris_df['species'] == 'versicolor')] " + ], + "execution_count": 11, + "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", + "
sepal_lengthsepal_widthpetal_lengthpetal_widthspecies
856.03.44.51.6versicolor
\n", + "
" + ], + "text/plain": [ + " sepal_length sepal_width petal_length petal_width species\n", + "85 6.0 3.4 4.5 1.6 versicolor" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 11 + } + ] + }, + { + "metadata": { + "id": "1lmnB3ot2u7I", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Sorting a column by value" + ] + }, + { + "metadata": { + "id": "K7KIj6fv2zWP", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1986 + }, + "outputId": "2ef69da6-0df9-490c-97f4-55dc3ce51e6e" + }, + "cell_type": "code", + "source": [ + "print (\"In Ascending order\")\n", + "iris_df.sort_values(by='sepal_width')#, ascending = False)\n", + "#pass ascending = False for descending order" + ], + "execution_count": 16, + "outputs": [ + { + "output_type": "stream", + "text": [ + "In Ascending order\n" + ], + "name": "stdout" + }, + { + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
sepal_lengthsepal_widthpetal_lengthpetal_widthspecies
605.02.03.51.0versicolor
1196.02.25.01.5virginica
626.02.24.01.0versicolor
686.22.24.51.5versicolor
535.52.34.01.3versicolor
414.52.31.30.3setosa
935.02.33.31.0versicolor
876.32.34.41.3versicolor
805.52.43.81.1versicolor
574.92.43.31.0versicolor
815.52.43.71.0versicolor
1064.92.54.51.7virginica
1086.72.55.81.8virginica
985.12.53.01.1versicolor
695.62.53.91.1versicolor
1135.72.55.02.0virginica
1466.32.55.01.9virginica
895.52.54.01.3versicolor
726.32.54.91.5versicolor
1346.12.65.61.4virginica
795.72.63.51.0versicolor
925.82.64.01.2versicolor
1187.72.66.92.3virginica
905.52.64.41.2versicolor
1116.42.75.31.9virginica
1015.82.75.11.9virginica
945.62.74.21.3versicolor
1425.82.75.11.9virginica
675.82.74.11.0versicolor
836.02.75.11.6versicolor
..................
64.63.41.40.3setosa
244.83.41.90.2setosa
395.13.41.50.2setosa
205.43.41.70.2setosa
285.23.41.40.2setosa
114.83.41.60.2setosa
275.23.51.50.2setosa
405.03.51.30.3setosa
175.13.51.40.3setosa
05.13.51.40.2setosa
365.53.51.30.2setosa
435.03.51.60.6setosa
1097.23.66.12.5virginica
45.03.61.40.2setosa
224.63.61.00.2setosa
485.33.71.50.2setosa
105.43.71.50.2setosa
215.13.71.50.4setosa
1317.93.86.42.0virginica
465.13.81.60.2setosa
1177.73.86.72.2virginica
185.73.81.70.3setosa
445.13.81.90.4setosa
195.13.81.50.3setosa
55.43.91.70.4setosa
165.43.91.30.4setosa
145.84.01.20.2setosa
325.24.11.50.1setosa
335.54.21.40.2setosa
155.74.41.50.4setosa
\n", + "

150 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " sepal_length sepal_width petal_length petal_width species\n", + "60 5.0 2.0 3.5 1.0 versicolor\n", + "119 6.0 2.2 5.0 1.5 virginica\n", + "62 6.0 2.2 4.0 1.0 versicolor\n", + "68 6.2 2.2 4.5 1.5 versicolor\n", + "53 5.5 2.3 4.0 1.3 versicolor\n", + "41 4.5 2.3 1.3 0.3 setosa\n", + "93 5.0 2.3 3.3 1.0 versicolor\n", + "87 6.3 2.3 4.4 1.3 versicolor\n", + "80 5.5 2.4 3.8 1.1 versicolor\n", + "57 4.9 2.4 3.3 1.0 versicolor\n", + "81 5.5 2.4 3.7 1.0 versicolor\n", + "106 4.9 2.5 4.5 1.7 virginica\n", + "108 6.7 2.5 5.8 1.8 virginica\n", + "98 5.1 2.5 3.0 1.1 versicolor\n", + "69 5.6 2.5 3.9 1.1 versicolor\n", + "113 5.7 2.5 5.0 2.0 virginica\n", + "146 6.3 2.5 5.0 1.9 virginica\n", + "89 5.5 2.5 4.0 1.3 versicolor\n", + "72 6.3 2.5 4.9 1.5 versicolor\n", + "134 6.1 2.6 5.6 1.4 virginica\n", + "79 5.7 2.6 3.5 1.0 versicolor\n", + "92 5.8 2.6 4.0 1.2 versicolor\n", + "118 7.7 2.6 6.9 2.3 virginica\n", + "90 5.5 2.6 4.4 1.2 versicolor\n", + "111 6.4 2.7 5.3 1.9 virginica\n", + "101 5.8 2.7 5.1 1.9 virginica\n", + "94 5.6 2.7 4.2 1.3 versicolor\n", + "142 5.8 2.7 5.1 1.9 virginica\n", + "67 5.8 2.7 4.1 1.0 versicolor\n", + "83 6.0 2.7 5.1 1.6 versicolor\n", + ".. ... ... ... ... ...\n", + "6 4.6 3.4 1.4 0.3 setosa\n", + "24 4.8 3.4 1.9 0.2 setosa\n", + "39 5.1 3.4 1.5 0.2 setosa\n", + "20 5.4 3.4 1.7 0.2 setosa\n", + "28 5.2 3.4 1.4 0.2 setosa\n", + "11 4.8 3.4 1.6 0.2 setosa\n", + "27 5.2 3.5 1.5 0.2 setosa\n", + "40 5.0 3.5 1.3 0.3 setosa\n", + "17 5.1 3.5 1.4 0.3 setosa\n", + "0 5.1 3.5 1.4 0.2 setosa\n", + "36 5.5 3.5 1.3 0.2 setosa\n", + "43 5.0 3.5 1.6 0.6 setosa\n", + "109 7.2 3.6 6.1 2.5 virginica\n", + "4 5.0 3.6 1.4 0.2 setosa\n", + "22 4.6 3.6 1.0 0.2 setosa\n", + "48 5.3 3.7 1.5 0.2 setosa\n", + "10 5.4 3.7 1.5 0.2 setosa\n", + "21 5.1 3.7 1.5 0.4 setosa\n", + "131 7.9 3.8 6.4 2.0 virginica\n", + "46 5.1 3.8 1.6 0.2 setosa\n", + "117 7.7 3.8 6.7 2.2 virginica\n", + "18 5.7 3.8 1.7 0.3 setosa\n", + "44 5.1 3.8 1.9 0.4 setosa\n", + "19 5.1 3.8 1.5 0.3 setosa\n", + "5 5.4 3.9 1.7 0.4 setosa\n", + "16 5.4 3.9 1.3 0.4 setosa\n", + "14 5.8 4.0 1.2 0.2 setosa\n", + "32 5.2 4.1 1.5 0.1 setosa\n", + "33 5.5 4.2 1.4 0.2 setosa\n", + "15 5.7 4.4 1.5 0.4 setosa\n", + "\n", + "[150 rows x 5 columns]" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 16 + } + ] + }, + { + "metadata": { + "id": "SnRFaI0ytIW-", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1986 + }, + "outputId": "cac458eb-26ea-4ac3-a7fa-d01f8eb53933" + }, + "cell_type": "code", + "source": [ + "\n", + "print (\"In Descending order\")\n", + "iris_df.sort_values(by='sepal_width', ascending = False)\n" + ], + "execution_count": 17, + "outputs": [ + { + "output_type": "stream", + "text": [ + "In Descending order\n" + ], + "name": "stdout" + }, + { + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
sepal_lengthsepal_widthpetal_lengthpetal_widthspecies
155.74.41.50.4setosa
335.54.21.40.2setosa
325.24.11.50.1setosa
145.84.01.20.2setosa
165.43.91.30.4setosa
55.43.91.70.4setosa
465.13.81.60.2setosa
1317.93.86.42.0virginica
195.13.81.50.3setosa
445.13.81.90.4setosa
1177.73.86.72.2virginica
185.73.81.70.3setosa
215.13.71.50.4setosa
105.43.71.50.2setosa
485.33.71.50.2setosa
45.03.61.40.2setosa
224.63.61.00.2setosa
1097.23.66.12.5virginica
275.23.51.50.2setosa
365.53.51.30.2setosa
175.13.51.40.3setosa
405.03.51.30.3setosa
435.03.51.60.6setosa
05.13.51.40.2setosa
64.63.41.40.3setosa
75.03.41.50.2setosa
315.43.41.50.4setosa
205.43.41.70.2setosa
244.83.41.90.2setosa
265.03.41.60.4setosa
..................
675.82.74.11.0versicolor
836.02.75.11.6versicolor
1236.32.74.91.8virginica
1015.82.75.11.9virginica
945.62.74.21.3versicolor
825.82.73.91.2versicolor
1346.12.65.61.4virginica
1187.72.66.92.3virginica
795.72.63.51.0versicolor
925.82.64.01.2versicolor
905.52.64.41.2versicolor
695.62.53.91.1versicolor
1086.72.55.81.8virginica
985.12.53.01.1versicolor
1064.92.54.51.7virginica
1135.72.55.02.0virginica
1466.32.55.01.9virginica
895.52.54.01.3versicolor
726.32.54.91.5versicolor
815.52.43.71.0versicolor
574.92.43.31.0versicolor
805.52.43.81.1versicolor
414.52.31.30.3setosa
935.02.33.31.0versicolor
876.32.34.41.3versicolor
535.52.34.01.3versicolor
686.22.24.51.5versicolor
1196.02.25.01.5virginica
626.02.24.01.0versicolor
605.02.03.51.0versicolor
\n", + "

150 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " sepal_length sepal_width petal_length petal_width species\n", + "15 5.7 4.4 1.5 0.4 setosa\n", + "33 5.5 4.2 1.4 0.2 setosa\n", + "32 5.2 4.1 1.5 0.1 setosa\n", + "14 5.8 4.0 1.2 0.2 setosa\n", + "16 5.4 3.9 1.3 0.4 setosa\n", + "5 5.4 3.9 1.7 0.4 setosa\n", + "46 5.1 3.8 1.6 0.2 setosa\n", + "131 7.9 3.8 6.4 2.0 virginica\n", + "19 5.1 3.8 1.5 0.3 setosa\n", + "44 5.1 3.8 1.9 0.4 setosa\n", + "117 7.7 3.8 6.7 2.2 virginica\n", + "18 5.7 3.8 1.7 0.3 setosa\n", + "21 5.1 3.7 1.5 0.4 setosa\n", + "10 5.4 3.7 1.5 0.2 setosa\n", + "48 5.3 3.7 1.5 0.2 setosa\n", + "4 5.0 3.6 1.4 0.2 setosa\n", + "22 4.6 3.6 1.0 0.2 setosa\n", + "109 7.2 3.6 6.1 2.5 virginica\n", + "27 5.2 3.5 1.5 0.2 setosa\n", + "36 5.5 3.5 1.3 0.2 setosa\n", + "17 5.1 3.5 1.4 0.3 setosa\n", + "40 5.0 3.5 1.3 0.3 setosa\n", + "43 5.0 3.5 1.6 0.6 setosa\n", + "0 5.1 3.5 1.4 0.2 setosa\n", + "6 4.6 3.4 1.4 0.3 setosa\n", + "7 5.0 3.4 1.5 0.2 setosa\n", + "31 5.4 3.4 1.5 0.4 setosa\n", + "20 5.4 3.4 1.7 0.2 setosa\n", + "24 4.8 3.4 1.9 0.2 setosa\n", + "26 5.0 3.4 1.6 0.4 setosa\n", + ".. ... ... ... ... ...\n", + "67 5.8 2.7 4.1 1.0 versicolor\n", + "83 6.0 2.7 5.1 1.6 versicolor\n", + "123 6.3 2.7 4.9 1.8 virginica\n", + "101 5.8 2.7 5.1 1.9 virginica\n", + "94 5.6 2.7 4.2 1.3 versicolor\n", + "82 5.8 2.7 3.9 1.2 versicolor\n", + "134 6.1 2.6 5.6 1.4 virginica\n", + "118 7.7 2.6 6.9 2.3 virginica\n", + "79 5.7 2.6 3.5 1.0 versicolor\n", + "92 5.8 2.6 4.0 1.2 versicolor\n", + "90 5.5 2.6 4.4 1.2 versicolor\n", + "69 5.6 2.5 3.9 1.1 versicolor\n", + "108 6.7 2.5 5.8 1.8 virginica\n", + "98 5.1 2.5 3.0 1.1 versicolor\n", + "106 4.9 2.5 4.5 1.7 virginica\n", + "113 5.7 2.5 5.0 2.0 virginica\n", + "146 6.3 2.5 5.0 1.9 virginica\n", + "89 5.5 2.5 4.0 1.3 versicolor\n", + "72 6.3 2.5 4.9 1.5 versicolor\n", + "81 5.5 2.4 3.7 1.0 versicolor\n", + "57 4.9 2.4 3.3 1.0 versicolor\n", + "80 5.5 2.4 3.8 1.1 versicolor\n", + "41 4.5 2.3 1.3 0.3 setosa\n", + "93 5.0 2.3 3.3 1.0 versicolor\n", + "87 6.3 2.3 4.4 1.3 versicolor\n", + "53 5.5 2.3 4.0 1.3 versicolor\n", + "68 6.2 2.2 4.5 1.5 versicolor\n", + "119 6.0 2.2 5.0 1.5 virginica\n", + "62 6.0 2.2 4.0 1.0 versicolor\n", + "60 5.0 2.0 3.5 1.0 versicolor\n", + "\n", + "[150 rows x 5 columns]" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 17 + } + ] + }, + { + "metadata": { + "id": "9jg_Z4YCoMSV", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### List all the unique species" + ] + }, + { + "metadata": { + "id": "M6EN78ufoJY7", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 34 + }, + "outputId": "c1ffd6ea-4596-48ed-dc6e-8db9060a6d7b" + }, + "cell_type": "code", + "source": [ + "species = iris_df['species'].unique()\n", + "\n", + "print(species)" + ], + "execution_count": 18, + "outputs": [ + { + "output_type": "stream", + "text": [ + "['setosa' 'virginica' 'versicolor']\n" + ], + "name": "stdout" + } + ] + }, + { + "metadata": { + "id": "aS9ajJaCtgmo", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 34 + }, + "outputId": "e8447b1d-02f6-4494-bb92-03d8f06145ee" + }, + "cell_type": "code", + "source": [ + "print(species[0])" + ], + "execution_count": 20, + "outputs": [ + { + "output_type": "stream", + "text": [ + "setosa\n" + ], + "name": "stdout" + } + ] + }, + { + "metadata": { + "id": "wG1i5nxBodmB", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Selecting a particular species using boolean mask (learnt in previous exercise)" + ] + }, + { + "metadata": { + "id": "gZvpbKBwoVUe", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 204 + }, + "outputId": "52776164-2917-4889-976a-731345c3ee36" + }, + "cell_type": "code", + "source": [ + "setosa = iris_df[iris_df['species'] == species[0]]\n", + "\n", + "setosa.head()" + ], + "execution_count": 19, + "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", + "
sepal_lengthsepal_widthpetal_lengthpetal_widthspecies
374.93.11.50.1setosa
235.13.31.70.5setosa
195.13.81.50.3setosa
24.73.21.30.2setosa
175.13.51.40.3setosa
\n", + "
" + ], + "text/plain": [ + " sepal_length sepal_width petal_length petal_width species\n", + "37 4.9 3.1 1.5 0.1 setosa\n", + "23 5.1 3.3 1.7 0.5 setosa\n", + "19 5.1 3.8 1.5 0.3 setosa\n", + "2 4.7 3.2 1.3 0.2 setosa\n", + "17 5.1 3.5 1.4 0.3 setosa" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 19 + } + ] + }, + { + "metadata": { + "id": "7tumfZ3DotPG", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 204 + }, + "outputId": "76778133-95c2-4db4-939b-373b34a83032" + }, + "cell_type": "code", + "source": [ + "# do the same for other 2 species \n", + "versicolor = iris_df[iris_df['species'] == species[1]]\n", + "\n", + "versicolor.head()" + ], + "execution_count": 21, + "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", + "
sepal_lengthsepal_widthpetal_lengthpetal_widthspecies
1297.23.05.81.6virginica
1416.93.15.12.3virginica
1206.93.25.72.3virginica
1476.53.05.22.0virginica
1336.32.85.11.5virginica
\n", + "
" + ], + "text/plain": [ + " sepal_length sepal_width petal_length petal_width species\n", + "129 7.2 3.0 5.8 1.6 virginica\n", + "141 6.9 3.1 5.1 2.3 virginica\n", + "120 6.9 3.2 5.7 2.3 virginica\n", + "147 6.5 3.0 5.2 2.0 virginica\n", + "133 6.3 2.8 5.1 1.5 virginica" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 21 + } + ] + }, + { + "metadata": { + "id": "cUYm5UqVpDPy", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 204 + }, + "outputId": "a6b15ee0-6925-447c-8b9b-021ecb3a580e" + }, + "cell_type": "code", + "source": [ + "\n", + "\n", + "virginica = iris_df[iris_df['species'] == species[2]]\n", + "\n", + "virginica.head()" + ], + "execution_count": 22, + "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", + "
sepal_lengthsepal_widthpetal_lengthpetal_widthspecies
905.52.64.41.2versicolor
726.32.54.91.5versicolor
686.22.24.51.5versicolor
825.82.73.91.2versicolor
736.12.84.71.2versicolor
\n", + "
" + ], + "text/plain": [ + " sepal_length sepal_width petal_length petal_width species\n", + "90 5.5 2.6 4.4 1.2 versicolor\n", + "72 6.3 2.5 4.9 1.5 versicolor\n", + "68 6.2 2.2 4.5 1.5 versicolor\n", + "82 5.8 2.7 3.9 1.2 versicolor\n", + "73 6.1 2.8 4.7 1.2 versicolor" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 22 + } + ] + }, + { + "metadata": { + "id": "-y1wDc8SpdQs", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Describe each created species to see the difference\n", + "\n" + ] + }, + { + "metadata": { + "id": "eHrn3ZVRpOk5", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 297 + }, + "outputId": "36bf7f0e-6fd3-4c1e-dc9a-571c121f67cf" + }, + "cell_type": "code", + "source": [ + "setosa.describe()" + ], + "execution_count": 23, + "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", + "
sepal_lengthsepal_widthpetal_lengthpetal_width
count50.0000050.00000050.00000050.00000
mean5.006003.4180001.4640000.24400
std0.352490.3810240.1735110.10721
min4.300002.3000001.0000000.10000
25%4.800003.1250001.4000000.20000
50%5.000003.4000001.5000000.20000
75%5.200003.6750001.5750000.30000
max5.800004.4000001.9000000.60000
\n", + "
" + ], + "text/plain": [ + " sepal_length sepal_width petal_length petal_width\n", + "count 50.00000 50.000000 50.000000 50.00000\n", + "mean 5.00600 3.418000 1.464000 0.24400\n", + "std 0.35249 0.381024 0.173511 0.10721\n", + "min 4.30000 2.300000 1.000000 0.10000\n", + "25% 4.80000 3.125000 1.400000 0.20000\n", + "50% 5.00000 3.400000 1.500000 0.20000\n", + "75% 5.20000 3.675000 1.575000 0.30000\n", + "max 5.80000 4.400000 1.900000 0.60000" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 23 + } + ] + }, + { + "metadata": { + "id": "GwJFT2GlpwUv", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 297 + }, + "outputId": "1c8b0afe-9099-4647-8141-0ecffc2577b3" + }, + "cell_type": "code", + "source": [ + "versicolor.describe()" + ], + "execution_count": 24, + "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", + "
sepal_lengthsepal_widthpetal_lengthpetal_width
count50.0000050.00000050.00000050.00000
mean6.588002.9740005.5520002.02600
std0.635880.3224970.5518950.27465
min4.900002.2000004.5000001.40000
25%6.225002.8000005.1000001.80000
50%6.500003.0000005.5500002.00000
75%6.900003.1750005.8750002.30000
max7.900003.8000006.9000002.50000
\n", + "
" + ], + "text/plain": [ + " sepal_length sepal_width petal_length petal_width\n", + "count 50.00000 50.000000 50.000000 50.00000\n", + "mean 6.58800 2.974000 5.552000 2.02600\n", + "std 0.63588 0.322497 0.551895 0.27465\n", + "min 4.90000 2.200000 4.500000 1.40000\n", + "25% 6.22500 2.800000 5.100000 1.80000\n", + "50% 6.50000 3.000000 5.550000 2.00000\n", + "75% 6.90000 3.175000 5.875000 2.30000\n", + "max 7.90000 3.800000 6.900000 2.50000" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 24 + } + ] + }, + { + "metadata": { + "id": "Ad4qhSZLpztf", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 297 + }, + "outputId": "5538c3f8-9ce9-4749-9948-02f875bca2c5" + }, + "cell_type": "code", + "source": [ + "virginica.describe()" + ], + "execution_count": 25, + "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", + "
sepal_lengthsepal_widthpetal_lengthpetal_width
count50.00000050.00000050.00000050.000000
mean5.9360002.7700004.2600001.326000
std0.5161710.3137980.4699110.197753
min4.9000002.0000003.0000001.000000
25%5.6000002.5250004.0000001.200000
50%5.9000002.8000004.3500001.300000
75%6.3000003.0000004.6000001.500000
max7.0000003.4000005.1000001.800000
\n", + "
" + ], + "text/plain": [ + " sepal_length sepal_width petal_length petal_width\n", + "count 50.000000 50.000000 50.000000 50.000000\n", + "mean 5.936000 2.770000 4.260000 1.326000\n", + "std 0.516171 0.313798 0.469911 0.197753\n", + "min 4.900000 2.000000 3.000000 1.000000\n", + "25% 5.600000 2.525000 4.000000 1.200000\n", + "50% 5.900000 2.800000 4.350000 1.300000\n", + "75% 6.300000 3.000000 4.600000 1.500000\n", + "max 7.000000 3.400000 5.100000 1.800000" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 25 + } + ] + }, + { + "metadata": { + "id": "Vdu0ulZWtr09", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Let's plot and see the difference" + ] + }, + { + "metadata": { + "id": "PEVMzRvpttmD", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "##### import matplotlib.pyplot " + ] + }, + { + "metadata": { + "id": "rqDXuuAtt7C3", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 398 + }, + "outputId": "fe83f061-1c71-4dd5-db37-ba26d57769dc" + }, + "cell_type": "code", + "source": [ + "import matplotlib.pyplot as plt\n", + "\n", + "#hist creates a histogram there are many more plots(see the documentation) you can play with it.\n", + "\n", + "plt.hist(setosa['sepal_length'])\n", + "plt.hist(versicolor['sepal_length'])\n", + "plt.hist(virginica['sepal_length'])" + ], + "execution_count": 26, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "(array([ 4., 1., 6., 10., 5., 8., 5., 3., 5., 3.]),\n", + " array([4.9 , 5.11, 5.32, 5.53, 5.74, 5.95, 6.16, 6.37, 6.58, 6.79, 7. ]),\n", + " )" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 26 + }, + { + "output_type": "display_data", + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAd8AAAFKCAYAAABcq1WoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nSEx8ASAx8QWAxMQXABL7f56BiVURCnM3AAAAAElFTkSuQmCC\n", + "text/plain": [ + "" + ] + }, + "metadata": { + "tags": [] + } + } + ] + } + ] +} \ No newline at end of file From fac1be48df9532de10a36c09409d2a0684b4398f Mon Sep 17 00:00:00 2001 From: AGCreates <43198265+AGCreates@users.noreply.github.com> Date: Mon, 15 Oct 2018 03:25:48 +0530 Subject: [PATCH 2/4] Completed Get to know your data part --- AGCreates.ipynb | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) diff --git a/AGCreates.ipynb b/AGCreates.ipynb index 4f3c6b2..2f520c7 100644 --- a/AGCreates.ipynb +++ b/AGCreates.ipynb @@ -110,7 +110,7 @@ "​\n", "See the top 10 rows" ], - "execution_count": 4, + "execution_count": 0, "outputs": [ { "output_type": "execute_result", @@ -232,7 +232,7 @@ "print(iris_df.shape[0])\n", "print(iris_df.shape[1])" ], - "execution_count": 5, + "execution_count": 0, "outputs": [ { "output_type": "stream", @@ -269,7 +269,7 @@ "source": [ "print(iris_df.columns)" ], - "execution_count": 6, + "execution_count": 0, "outputs": [ { "output_type": "stream", @@ -306,7 +306,7 @@ "source": [ "print(iris_df.index)" ], - "execution_count": 7, + "execution_count": 0, "outputs": [ { "output_type": "stream", @@ -349,7 +349,7 @@ "\n", "print(iris_df.head())" ], - "execution_count": 8, + "execution_count": 0, "outputs": [ { "output_type": "stream", @@ -418,7 +418,7 @@ "\n", "print(iris_df.head())" ], - "execution_count": 9, + "execution_count": 0, "outputs": [ { "output_type": "stream", @@ -470,7 +470,7 @@ "source": [ "iris_df[iris_df['sepal_width']>3.3]" ], - "execution_count": 10, + "execution_count": 0, "outputs": [ { "output_type": "execute_result", @@ -865,7 +865,7 @@ "source": [ "iris_df[(iris_df['sepal_width']>3.3) & (iris_df['species'] == 'versicolor')] " ], - "execution_count": 11, + "execution_count": 0, "outputs": [ { "output_type": "execute_result", @@ -947,7 +947,7 @@ "iris_df.sort_values(by='sepal_width')#, ascending = False)\n", "#pass ascending = False for descending order" ], - "execution_count": 16, + "execution_count": 0, "outputs": [ { "output_type": "stream", @@ -1569,7 +1569,7 @@ "print (\"In Descending order\")\n", "iris_df.sort_values(by='sepal_width', ascending = False)\n" ], - "execution_count": 17, + "execution_count": 0, "outputs": [ { "output_type": "stream", @@ -2201,7 +2201,7 @@ "\n", "print(species)" ], - "execution_count": 18, + "execution_count": 0, "outputs": [ { "output_type": "stream", @@ -2226,7 +2226,7 @@ "source": [ "print(species[0])" ], - "execution_count": 20, + "execution_count": 0, "outputs": [ { "output_type": "stream", @@ -2263,7 +2263,7 @@ "\n", "setosa.head()" ], - "execution_count": 19, + "execution_count": 0, "outputs": [ { "output_type": "execute_result", @@ -2372,7 +2372,7 @@ "\n", "versicolor.head()" ], - "execution_count": 21, + "execution_count": 0, "outputs": [ { "output_type": "execute_result", @@ -2482,7 +2482,7 @@ "\n", "virginica.head()" ], - "execution_count": 22, + "execution_count": 0, "outputs": [ { "output_type": "execute_result", @@ -2599,7 +2599,7 @@ "source": [ "setosa.describe()" ], - "execution_count": 23, + "execution_count": 0, "outputs": [ { "output_type": "execute_result", @@ -2723,7 +2723,7 @@ "source": [ "versicolor.describe()" ], - "execution_count": 24, + "execution_count": 0, "outputs": [ { "output_type": "execute_result", @@ -2847,7 +2847,7 @@ "source": [ "virginica.describe()" ], - "execution_count": 25, + "execution_count": 0, "outputs": [ { "output_type": "execute_result", @@ -2997,7 +2997,7 @@ "plt.hist(versicolor['sepal_length'])\n", "plt.hist(virginica['sepal_length'])" ], - "execution_count": 26, + "execution_count": 0, "outputs": [ { "output_type": "execute_result", From 2d7f03c5dc2723af3019a2ab7f158233ba3638ee Mon Sep 17 00:00:00 2001 From: AGCreates <43198265+AGCreates@users.noreply.github.com> Date: Mon, 28 Jan 2019 11:26:24 +0530 Subject: [PATCH 3/4] Assignment 3 Exercise completed by AGCreates --- Exercise.ipynb | 3878 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 3878 insertions(+) create mode 100644 Exercise.ipynb diff --git a/Exercise.ipynb b/Exercise.ipynb new file mode 100644 index 0000000..79eb15f --- /dev/null +++ b/Exercise.ipynb @@ -0,0 +1,3878 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "name": "Exercise.ipynb", + "version": "0.3.2", + "provenance": [], + "include_colab_link": true + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + } + }, + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "\"Open" + ] + }, + { + "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": {} + }, + "cell_type": "code", + "source": [ + "wine_df = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data')" + ], + "execution_count": 0, + "outputs": [] + }, + { + "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": "c6a57e8c-9ecc-4160-f888-52386033c114" + }, + "cell_type": "code", + "source": [ + "wine_df.head()" + ], + "execution_count": 5, + "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": 5 + } + ] + }, + { + "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": 1969 + }, + "outputId": "a1178493-2d5d-4e5f-c50d-4c8e35190382" + }, + "cell_type": "code", + "source": [ + "wine_df_copy = wine_df\n", + "wine_df_copy.drop(range(1,wine_df_copy.shape[0],2))" + ], + "execution_count": 6, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \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
0113.201.782.1411.21002.652.760.261.284.3800001.053.401050
2114.371.952.5016.81133.853.490.242.187.8000000.863.451480
4114.201.762.4515.21123.273.390.341.976.7500001.052.851450
6114.062.152.6117.61212.602.510.311.255.0500001.063.581295
8113.861.352.2716.0982.983.150.221.857.2200001.013.551045
10114.121.482.3216.8952.202.430.261.575.0000001.172.821280
12114.751.732.3911.4913.103.690.432.815.4000001.252.731150
14113.631.812.7017.21122.852.910.301.467.3000001.282.881310
16113.831.572.6220.01152.953.400.401.726.6000001.132.571130
18113.643.102.5615.21162.703.030.171.665.1000000.963.36845
20112.933.802.6518.61022.412.410.251.984.5000001.033.52770
22112.851.602.5217.8952.482.370.261.463.9300001.093.631015
24113.052.053.2225.01242.632.680.471.923.5800001.133.20830
26113.301.722.1417.0942.402.190.271.353.9500001.022.771285
28114.021.682.2116.0962.652.330.261.984.7000001.043.591035
30113.581.662.3619.11062.863.190.221.956.9000001.092.881515
32113.761.532.7019.51322.952.740.501.355.4000001.253.001235
34113.481.812.4120.51002.702.980.261.865.1000001.043.47920
36113.051.652.5518.0982.452.430.291.444.2500001.122.511105
38114.223.992.5113.21283.003.040.202.085.1000000.893.53760
40113.413.842.1218.8902.452.680.271.484.2800000.913.001035
42113.243.982.2917.51032.642.630.321.664.3600000.823.00680
44114.214.042.4418.91112.852.650.301.255.2400000.873.331080
46113.901.682.1216.01013.103.390.212.146.1000000.913.33985
48113.941.732.2717.41082.883.540.322.088.9000001.123.101260
50113.831.652.6017.2942.452.990.222.295.6000001.243.371265
52113.771.902.6817.11153.002.790.391.686.3000001.132.931375
54113.561.732.4620.51162.962.780.202.456.2500000.983.031120
56113.291.972.6816.81023.003.230.311.666.0000001.072.841270
58212.370.941.3610.6881.980.570.280.421.9500001.051.82520
.............................................
118212.003.432.0019.0872.001.640.371.871.2800000.933.05564
120211.562.053.2328.51193.185.080.471.876.0000000.933.69465
122213.055.802.1321.5862.622.650.302.012.6000000.733.10380
124212.072.162.1721.0852.602.650.371.352.7600000.863.28378
126211.792.132.7828.5922.132.240.581.763.0000000.972.44466
128212.044.302.3822.0802.101.750.421.352.6000000.792.57580
130312.882.992.4020.01041.301.220.240.835.4000000.741.42530
132312.703.552.3621.51061.701.200.170.845.0000000.781.29600
134312.602.462.2018.5941.620.660.630.947.1000000.731.58695
136312.535.512.6425.0961.790.600.631.105.0000000.821.69515
138312.842.962.6124.01012.320.600.530.814.9200000.892.15590
140313.362.562.3520.0891.400.500.370.645.6000000.702.47780
142313.624.952.3520.0922.000.800.471.024.4000000.912.05550
144313.163.572.1521.01021.500.550.431.304.0000000.601.68830
146312.874.612.4821.5861.700.650.470.867.6500000.541.86625
148313.083.902.3621.51131.411.390.341.149.4000000.571.33550
150312.792.672.4822.01121.481.360.241.2610.8000000.481.47480
152313.233.302.2818.5981.800.830.611.8710.5200000.561.51675
154313.175.192.3222.0931.740.630.611.557.9000000.601.48725
156312.453.032.6427.0971.900.580.631.147.5000000.671.73880
158313.481.672.6422.5892.601.100.522.2911.7500000.571.78620
160313.693.262.5420.01071.830.560.500.805.8800000.961.82680
162312.963.452.3518.51061.390.700.400.945.2800000.681.75675
164313.734.362.2622.5881.280.470.521.156.6200000.781.75520
166312.823.372.3019.5881.480.660.400.9710.2600000.721.75685
168313.404.602.8625.01121.980.960.271.118.5000000.671.92630
170312.772.392.2819.5861.390.510.480.649.8999990.571.63470
172313.715.652.4520.5951.680.610.521.067.7000000.641.74740
174313.274.282.2620.01201.590.690.431.3510.2000000.591.56835
176314.134.102.7424.5962.050.760.561.359.2000000.611.60560
\n", + "

89 rows × 14 columns

\n", + "
" + ], + "text/plain": [ + " 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]" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 6 + } + ] + }, + { + "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','Column 14']" + ], + "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": { + "base_uri": "https://localhost:8080/", + "height": 2003 + }, + "outputId": "b380beee-2c0a-4118-816e-442ce1659d1d" + }, + "cell_type": "code", + "source": [ + "wine_df.iloc[[0,1,2]]=np.nan\n", + "wine_df" + ], + "execution_count": 9, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \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 winesProlineColumn 14
0NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
1NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
2NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
31.013.242.592.8721.0118.02.802.690.391.824.3200001.042.93735.0
41.014.201.762.4515.2112.03.273.390.341.976.7500001.052.851450.0
51.014.391.872.4514.696.02.502.520.301.985.2500001.023.581290.0
61.014.062.152.6117.6121.02.602.510.311.255.0500001.063.581295.0
71.014.831.642.1714.097.02.802.980.291.985.2000001.082.851045.0
81.013.861.352.2716.098.02.983.150.221.857.2200001.013.551045.0
91.014.102.162.3018.0105.02.953.320.222.385.7500001.253.171510.0
101.014.121.482.3216.895.02.202.430.261.575.0000001.172.821280.0
111.013.751.732.4116.089.02.602.760.291.815.6000001.152.901320.0
121.014.751.732.3911.491.03.103.690.432.815.4000001.252.731150.0
131.014.381.872.3812.0102.03.303.640.292.967.5000001.203.001547.0
141.013.631.812.7017.2112.02.852.910.301.467.3000001.282.881310.0
151.014.301.922.7220.0120.02.803.140.331.976.2000001.072.651280.0
161.013.831.572.6220.0115.02.953.400.401.726.6000001.132.571130.0
171.014.191.592.4816.5108.03.303.930.321.868.7000001.232.821680.0
181.013.643.102.5615.2116.02.703.030.171.665.1000000.963.36845.0
191.014.061.632.2816.0126.03.003.170.242.105.6500001.093.71780.0
201.012.933.802.6518.6102.02.412.410.251.984.5000001.033.52770.0
211.013.711.862.3616.6101.02.612.880.271.693.8000001.114.001035.0
221.012.851.602.5217.895.02.482.370.261.463.9300001.093.631015.0
231.013.501.812.6120.096.02.532.610.281.663.5200001.123.82845.0
241.013.052.053.2225.0124.02.632.680.471.923.5800001.133.20830.0
251.013.391.772.6216.193.02.852.940.341.454.8000000.923.221195.0
261.013.301.722.1417.094.02.402.190.271.353.9500001.022.771285.0
271.013.871.902.8019.4107.02.952.970.371.764.5000001.253.40915.0
281.014.021.682.2116.096.02.652.330.261.984.7000001.043.591035.0
291.013.731.502.7022.5101.03.003.250.292.385.7000001.192.711285.0
.............................................
1473.013.323.242.3821.592.01.930.760.451.258.4200000.551.62650.0
1483.013.083.902.3621.5113.01.411.390.341.149.4000000.571.33550.0
1493.013.503.122.6224.0123.01.401.570.221.258.6000000.591.30500.0
1503.012.792.672.4822.0112.01.481.360.241.2610.8000000.481.47480.0
1513.013.111.902.7525.5116.02.201.280.261.567.1000000.611.33425.0
1523.013.233.302.2818.598.01.800.830.611.8710.5200000.561.51675.0
1533.012.581.292.1020.0103.01.480.580.531.407.6000000.581.55640.0
1543.013.175.192.3222.093.01.740.630.611.557.9000000.601.48725.0
1553.013.844.122.3819.589.01.800.830.481.569.0100000.571.64480.0
1563.012.453.032.6427.097.01.900.580.631.147.5000000.671.73880.0
1573.014.341.682.7025.098.02.801.310.532.7013.0000000.571.96660.0
1583.013.481.672.6422.589.02.601.100.522.2911.7500000.571.78620.0
1593.012.363.832.3821.088.02.300.920.501.047.6500000.561.58520.0
1603.013.693.262.5420.0107.01.830.560.500.805.8800000.961.82680.0
1613.012.853.272.5822.0106.01.650.600.600.965.5800000.872.11570.0
1623.012.963.452.3518.5106.01.390.700.400.945.2800000.681.75675.0
1633.013.782.762.3022.090.01.350.680.411.039.5800000.701.68615.0
1643.013.734.362.2622.588.01.280.470.521.156.6200000.781.75520.0
1653.013.453.702.6023.0111.01.700.920.431.4610.6800000.851.56695.0
1663.012.823.372.3019.588.01.480.660.400.9710.2600000.721.75685.0
1673.013.582.582.6924.5105.01.550.840.391.548.6600000.741.80750.0
1683.013.404.602.8625.0112.01.980.960.271.118.5000000.671.92630.0
1693.012.203.032.3219.096.01.250.490.400.735.5000000.661.83510.0
1703.012.772.392.2819.586.01.390.510.480.649.8999990.571.63470.0
1713.014.162.512.4820.091.01.680.700.441.249.7000000.621.71660.0
1723.013.715.652.4520.595.01.680.610.521.067.7000000.641.74740.0
1733.013.403.912.4823.0102.01.800.750.431.417.3000000.701.56750.0
1743.013.274.282.2620.0120.01.590.690.431.3510.2000000.591.56835.0
1753.013.172.592.3720.0120.01.650.680.531.469.3000000.601.62840.0
1763.014.134.102.7424.596.02.050.760.561.359.2000000.611.60560.0
\n", + "

177 rows × 14 columns

\n", + "
" + ], + "text/plain": [ + " Alcohol Malic acid Ash Alcalinity of ash Magnesium Total phenols \\\n", + "0 NaN NaN NaN NaN NaN NaN \n", + "1 NaN NaN NaN NaN NaN NaN \n", + "2 NaN NaN NaN NaN NaN NaN \n", + "3 1.0 13.24 2.59 2.87 21.0 118.0 \n", + "4 1.0 14.20 1.76 2.45 15.2 112.0 \n", + "5 1.0 14.39 1.87 2.45 14.6 96.0 \n", + "6 1.0 14.06 2.15 2.61 17.6 121.0 \n", + "7 1.0 14.83 1.64 2.17 14.0 97.0 \n", + "8 1.0 13.86 1.35 2.27 16.0 98.0 \n", + "9 1.0 14.10 2.16 2.30 18.0 105.0 \n", + "10 1.0 14.12 1.48 2.32 16.8 95.0 \n", + "11 1.0 13.75 1.73 2.41 16.0 89.0 \n", + "12 1.0 14.75 1.73 2.39 11.4 91.0 \n", + "13 1.0 14.38 1.87 2.38 12.0 102.0 \n", + "14 1.0 13.63 1.81 2.70 17.2 112.0 \n", + "15 1.0 14.30 1.92 2.72 20.0 120.0 \n", + "16 1.0 13.83 1.57 2.62 20.0 115.0 \n", + "17 1.0 14.19 1.59 2.48 16.5 108.0 \n", + "18 1.0 13.64 3.10 2.56 15.2 116.0 \n", + "19 1.0 14.06 1.63 2.28 16.0 126.0 \n", + "20 1.0 12.93 3.80 2.65 18.6 102.0 \n", + "21 1.0 13.71 1.86 2.36 16.6 101.0 \n", + "22 1.0 12.85 1.60 2.52 17.8 95.0 \n", + "23 1.0 13.50 1.81 2.61 20.0 96.0 \n", + "24 1.0 13.05 2.05 3.22 25.0 124.0 \n", + "25 1.0 13.39 1.77 2.62 16.1 93.0 \n", + "26 1.0 13.30 1.72 2.14 17.0 94.0 \n", + "27 1.0 13.87 1.90 2.80 19.4 107.0 \n", + "28 1.0 14.02 1.68 2.21 16.0 96.0 \n", + "29 1.0 13.73 1.50 2.70 22.5 101.0 \n", + ".. ... ... ... ... ... ... \n", + "147 3.0 13.32 3.24 2.38 21.5 92.0 \n", + "148 3.0 13.08 3.90 2.36 21.5 113.0 \n", + "149 3.0 13.50 3.12 2.62 24.0 123.0 \n", + "150 3.0 12.79 2.67 2.48 22.0 112.0 \n", + "151 3.0 13.11 1.90 2.75 25.5 116.0 \n", + "152 3.0 13.23 3.30 2.28 18.5 98.0 \n", + "153 3.0 12.58 1.29 2.10 20.0 103.0 \n", + "154 3.0 13.17 5.19 2.32 22.0 93.0 \n", + "155 3.0 13.84 4.12 2.38 19.5 89.0 \n", + "156 3.0 12.45 3.03 2.64 27.0 97.0 \n", + "157 3.0 14.34 1.68 2.70 25.0 98.0 \n", + "158 3.0 13.48 1.67 2.64 22.5 89.0 \n", + "159 3.0 12.36 3.83 2.38 21.0 88.0 \n", + "160 3.0 13.69 3.26 2.54 20.0 107.0 \n", + "161 3.0 12.85 3.27 2.58 22.0 106.0 \n", + "162 3.0 12.96 3.45 2.35 18.5 106.0 \n", + "163 3.0 13.78 2.76 2.30 22.0 90.0 \n", + "164 3.0 13.73 4.36 2.26 22.5 88.0 \n", + "165 3.0 13.45 3.70 2.60 23.0 111.0 \n", + "166 3.0 12.82 3.37 2.30 19.5 88.0 \n", + "167 3.0 13.58 2.58 2.69 24.5 105.0 \n", + "168 3.0 13.40 4.60 2.86 25.0 112.0 \n", + "169 3.0 12.20 3.03 2.32 19.0 96.0 \n", + "170 3.0 12.77 2.39 2.28 19.5 86.0 \n", + "171 3.0 14.16 2.51 2.48 20.0 91.0 \n", + "172 3.0 13.71 5.65 2.45 20.5 95.0 \n", + "173 3.0 13.40 3.91 2.48 23.0 102.0 \n", + "174 3.0 13.27 4.28 2.26 20.0 120.0 \n", + "175 3.0 13.17 2.59 2.37 20.0 120.0 \n", + "176 3.0 14.13 4.10 2.74 24.5 96.0 \n", + "\n", + " Flavanoids Nonflavanoid phenols Proanthocyanins Color intensity \\\n", + "0 NaN NaN NaN NaN \n", + "1 NaN NaN NaN NaN \n", + "2 NaN NaN NaN NaN \n", + "3 2.80 2.69 0.39 1.82 \n", + "4 3.27 3.39 0.34 1.97 \n", + "5 2.50 2.52 0.30 1.98 \n", + "6 2.60 2.51 0.31 1.25 \n", + "7 2.80 2.98 0.29 1.98 \n", + "8 2.98 3.15 0.22 1.85 \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", + ".. ... ... ... ... \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 Column 14 \n", + "0 NaN NaN NaN NaN \n", + "1 NaN NaN NaN NaN \n", + "2 NaN NaN NaN NaN \n", + "3 4.320000 1.04 2.93 735.0 \n", + "4 6.750000 1.05 2.85 1450.0 \n", + "5 5.250000 1.02 3.58 1290.0 \n", + "6 5.050000 1.06 3.58 1295.0 \n", + "7 5.200000 1.08 2.85 1045.0 \n", + "8 7.220000 1.01 3.55 1045.0 \n", + "9 5.750000 1.25 3.17 1510.0 \n", + "10 5.000000 1.17 2.82 1280.0 \n", + "11 5.600000 1.15 2.90 1320.0 \n", + "12 5.400000 1.25 2.73 1150.0 \n", + "13 7.500000 1.20 3.00 1547.0 \n", + "14 7.300000 1.28 2.88 1310.0 \n", + "15 6.200000 1.07 2.65 1280.0 \n", + "16 6.600000 1.13 2.57 1130.0 \n", + "17 8.700000 1.23 2.82 1680.0 \n", + "18 5.100000 0.96 3.36 845.0 \n", + "19 5.650000 1.09 3.71 780.0 \n", + "20 4.500000 1.03 3.52 770.0 \n", + "21 3.800000 1.11 4.00 1035.0 \n", + "22 3.930000 1.09 3.63 1015.0 \n", + "23 3.520000 1.12 3.82 845.0 \n", + "24 3.580000 1.13 3.20 830.0 \n", + "25 4.800000 0.92 3.22 1195.0 \n", + "26 3.950000 1.02 2.77 1285.0 \n", + "27 4.500000 1.25 3.40 915.0 \n", + "28 4.700000 1.04 3.59 1035.0 \n", + "29 5.700000 1.19 2.71 1285.0 \n", + ".. ... ... ... ... \n", + "147 8.420000 0.55 1.62 650.0 \n", + "148 9.400000 0.57 1.33 550.0 \n", + "149 8.600000 0.59 1.30 500.0 \n", + "150 10.800000 0.48 1.47 480.0 \n", + "151 7.100000 0.61 1.33 425.0 \n", + "152 10.520000 0.56 1.51 675.0 \n", + "153 7.600000 0.58 1.55 640.0 \n", + "154 7.900000 0.60 1.48 725.0 \n", + "155 9.010000 0.57 1.64 480.0 \n", + "156 7.500000 0.67 1.73 880.0 \n", + "157 13.000000 0.57 1.96 660.0 \n", + "158 11.750000 0.57 1.78 620.0 \n", + "159 7.650000 0.56 1.58 520.0 \n", + "160 5.880000 0.96 1.82 680.0 \n", + "161 5.580000 0.87 2.11 570.0 \n", + "162 5.280000 0.68 1.75 675.0 \n", + "163 9.580000 0.70 1.68 615.0 \n", + "164 6.620000 0.78 1.75 520.0 \n", + "165 10.680000 0.85 1.56 695.0 \n", + "166 10.260000 0.72 1.75 685.0 \n", + "167 8.660000 0.74 1.80 750.0 \n", + "168 8.500000 0.67 1.92 630.0 \n", + "169 5.500000 0.66 1.83 510.0 \n", + "170 9.899999 0.57 1.63 470.0 \n", + "171 9.700000 0.62 1.71 660.0 \n", + "172 7.700000 0.64 1.74 740.0 \n", + "173 7.300000 0.70 1.56 750.0 \n", + "174 10.200000 0.59 1.56 835.0 \n", + "175 9.300000 0.60 1.62 840.0 \n", + "176 9.200000 0.61 1.60 560.0 \n", + "\n", + "[177 rows x 14 columns]" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 9 + } + ] + }, + { + "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": "b3201caf-3581-48e0-939f-aa1c24f33d7f" + }, + "cell_type": "code", + "source": [ + "import random as rndm\n", + "random =rndm.sample(range(1,11),10)\n", + "random" + ], + "execution_count": 10, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "[7, 3, 8, 9, 4, 5, 10, 1, 6, 2]" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 10 + } + ] + }, + { + "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": 376 + }, + "outputId": "f63ff4a1-6bfe-4db8-df41-f1a9aa9fea2b" + }, + "cell_type": "code", + "source": [ + "wine_df = wine_df.reindex(index=random)\n", + "wine_df['Alcohol'] = np.nan\n", + "wine_df" + ], + "execution_count": 12, + "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 winesProlineColumn 14
7NaN14.831.642.1714.097.02.802.980.291.985.201.082.851045.0
3NaN13.242.592.8721.0118.02.802.690.391.824.321.042.93735.0
8NaN13.861.352.2716.098.02.983.150.221.857.221.013.551045.0
9NaN14.102.162.3018.0105.02.953.320.222.385.751.253.171510.0
4NaN14.201.762.4515.2112.03.273.390.341.976.751.052.851450.0
5NaN14.391.872.4514.696.02.502.520.301.985.251.023.581290.0
10NaN14.121.482.3216.895.02.202.430.261.575.001.172.821280.0
1NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
6NaN14.062.152.6117.6121.02.602.510.311.255.051.063.581295.0
2NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
\n", + "
" + ], + "text/plain": [ + " Alcohol Malic acid Ash Alcalinity of ash Magnesium Total phenols \\\n", + "7 NaN 14.83 1.64 2.17 14.0 97.0 \n", + "3 NaN 13.24 2.59 2.87 21.0 118.0 \n", + "8 NaN 13.86 1.35 2.27 16.0 98.0 \n", + "9 NaN 14.10 2.16 2.30 18.0 105.0 \n", + "4 NaN 14.20 1.76 2.45 15.2 112.0 \n", + "5 NaN 14.39 1.87 2.45 14.6 96.0 \n", + "10 NaN 14.12 1.48 2.32 16.8 95.0 \n", + "1 NaN NaN NaN NaN NaN NaN \n", + "6 NaN 14.06 2.15 2.61 17.6 121.0 \n", + "2 NaN NaN NaN NaN NaN NaN \n", + "\n", + " Flavanoids Nonflavanoid phenols Proanthocyanins Color intensity Hue \\\n", + "7 2.80 2.98 0.29 1.98 5.20 \n", + "3 2.80 2.69 0.39 1.82 4.32 \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", + "4 3.27 3.39 0.34 1.97 6.75 \n", + "5 2.50 2.52 0.30 1.98 5.25 \n", + "10 2.20 2.43 0.26 1.57 5.00 \n", + "1 NaN NaN NaN NaN NaN \n", + "6 2.60 2.51 0.31 1.25 5.05 \n", + "2 NaN NaN NaN NaN NaN \n", + "\n", + " OD280/OD315 of diluted wines Proline Column 14 \n", + "7 1.08 2.85 1045.0 \n", + "3 1.04 2.93 735.0 \n", + "8 1.01 3.55 1045.0 \n", + "9 1.25 3.17 1510.0 \n", + "4 1.05 2.85 1450.0 \n", + "5 1.02 3.58 1290.0 \n", + "10 1.17 2.82 1280.0 \n", + "1 NaN NaN NaN \n", + "6 1.06 3.58 1295.0 \n", + "2 NaN NaN NaN " + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 12 + } + ] + }, + { + "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": 34 + }, + "outputId": "52ddcd06-c1e6-4f56-80eb-576ed7663961" + }, + "cell_type": "code", + "source": [ + "sum(wine_df.isnull().sum())" + ], + "execution_count": 13, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "36" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 13 + } + ] + }, + { + "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": 66 + }, + "outputId": "28b8eb64-fe6c-4be1-b35d-d6049147e22d" + }, + "cell_type": "code", + "source": [ + "wine_df.dropna()" + ], + "execution_count": 14, + "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", + "
AlcoholMalic acidAshAlcalinity of ashMagnesiumTotal phenolsFlavanoidsNonflavanoid phenolsProanthocyaninsColor intensityHueOD280/OD315 of diluted winesProlineColumn 14
\n", + "
" + ], + "text/plain": [ + "Empty DataFrame\n", + "Columns: [Alcohol, Malic acid, Ash, Alcalinity of ash, Magnesium, Total phenols, Flavanoids, Nonflavanoid phenols, Proanthocyanins, Color intensity, Hue, OD280/OD315 of diluted wines, Proline, Column 14]\n", + "Index: []" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 14 + } + ] + }, + { + "metadata": { + "id": "DlpG8drhmz7W", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "### BONUS: Play with the data set below" + ] + }, + { + "metadata": { + "id": "mD40T0Cnm5SA", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 376 + }, + "outputId": "65a7da46-bc13-479e-9e0e-b4c19a4e91e3" + }, + "cell_type": "code", + "source": [ + "wine_df.iloc[2]['Ash']= np.nan\n", + "wine_df" + ], + "execution_count": 15, + "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 winesProlineColumn 14
7NaN14.831.642.1714.097.02.802.980.291.985.201.082.851045.0
3NaN13.242.592.8721.0118.02.802.690.391.824.321.042.93735.0
8NaN13.86NaN2.2716.098.02.983.150.221.857.221.013.551045.0
9NaN14.102.162.3018.0105.02.953.320.222.385.751.253.171510.0
4NaN14.201.762.4515.2112.03.273.390.341.976.751.052.851450.0
5NaN14.391.872.4514.696.02.502.520.301.985.251.023.581290.0
10NaN14.121.482.3216.895.02.202.430.261.575.001.172.821280.0
1NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
6NaN14.062.152.6117.6121.02.602.510.311.255.051.063.581295.0
2NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
\n", + "
" + ], + "text/plain": [ + " Alcohol Malic acid Ash Alcalinity of ash Magnesium Total phenols \\\n", + "7 NaN 14.83 1.64 2.17 14.0 97.0 \n", + "3 NaN 13.24 2.59 2.87 21.0 118.0 \n", + "8 NaN 13.86 NaN 2.27 16.0 98.0 \n", + "9 NaN 14.10 2.16 2.30 18.0 105.0 \n", + "4 NaN 14.20 1.76 2.45 15.2 112.0 \n", + "5 NaN 14.39 1.87 2.45 14.6 96.0 \n", + "10 NaN 14.12 1.48 2.32 16.8 95.0 \n", + "1 NaN NaN NaN NaN NaN NaN \n", + "6 NaN 14.06 2.15 2.61 17.6 121.0 \n", + "2 NaN NaN NaN NaN NaN NaN \n", + "\n", + " Flavanoids Nonflavanoid phenols Proanthocyanins Color intensity Hue \\\n", + "7 2.80 2.98 0.29 1.98 5.20 \n", + "3 2.80 2.69 0.39 1.82 4.32 \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", + "4 3.27 3.39 0.34 1.97 6.75 \n", + "5 2.50 2.52 0.30 1.98 5.25 \n", + "10 2.20 2.43 0.26 1.57 5.00 \n", + "1 NaN NaN NaN NaN NaN \n", + "6 2.60 2.51 0.31 1.25 5.05 \n", + "2 NaN NaN NaN NaN NaN \n", + "\n", + " OD280/OD315 of diluted wines Proline Column 14 \n", + "7 1.08 2.85 1045.0 \n", + "3 1.04 2.93 735.0 \n", + "8 1.01 3.55 1045.0 \n", + "9 1.25 3.17 1510.0 \n", + "4 1.05 2.85 1450.0 \n", + "5 1.02 3.58 1290.0 \n", + "10 1.17 2.82 1280.0 \n", + "1 NaN NaN NaN \n", + "6 1.06 3.58 1295.0 \n", + "2 NaN NaN NaN " + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 15 + } + ] + }, + { + "metadata": { + "id": "H2N6LkpKqVgE", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 376 + }, + "outputId": "40008a05-e220-47ae-e553-37efc0fd91ea" + }, + "cell_type": "code", + "source": [ + "wine_df.iloc[1]['Hue']= np.nan\n", + "wine_df\n" + ], + "execution_count": 17, + "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 winesProlineColumn 14
7NaN14.831.642.1714.097.02.802.980.291.985.201.082.851045.0
3NaN13.242.592.8721.0118.02.802.690.391.82NaN1.042.93735.0
8NaN13.86NaN2.2716.098.02.983.150.221.857.221.013.551045.0
9NaN14.102.162.3018.0105.02.953.320.222.385.751.253.171510.0
4NaN14.201.762.4515.2112.03.273.390.341.976.751.052.851450.0
5NaN14.391.872.4514.696.02.502.520.301.985.251.023.581290.0
10NaN14.121.482.3216.895.02.202.430.261.575.001.172.821280.0
1NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
6NaN14.062.152.6117.6121.02.602.510.311.255.051.063.581295.0
2NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
\n", + "
" + ], + "text/plain": [ + " Alcohol Malic acid Ash Alcalinity of ash Magnesium Total phenols \\\n", + "7 NaN 14.83 1.64 2.17 14.0 97.0 \n", + "3 NaN 13.24 2.59 2.87 21.0 118.0 \n", + "8 NaN 13.86 NaN 2.27 16.0 98.0 \n", + "9 NaN 14.10 2.16 2.30 18.0 105.0 \n", + "4 NaN 14.20 1.76 2.45 15.2 112.0 \n", + "5 NaN 14.39 1.87 2.45 14.6 96.0 \n", + "10 NaN 14.12 1.48 2.32 16.8 95.0 \n", + "1 NaN NaN NaN NaN NaN NaN \n", + "6 NaN 14.06 2.15 2.61 17.6 121.0 \n", + "2 NaN NaN NaN NaN NaN NaN \n", + "\n", + " Flavanoids Nonflavanoid phenols Proanthocyanins Color intensity Hue \\\n", + "7 2.80 2.98 0.29 1.98 5.20 \n", + "3 2.80 2.69 0.39 1.82 NaN \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", + "4 3.27 3.39 0.34 1.97 6.75 \n", + "5 2.50 2.52 0.30 1.98 5.25 \n", + "10 2.20 2.43 0.26 1.57 5.00 \n", + "1 NaN NaN NaN NaN NaN \n", + "6 2.60 2.51 0.31 1.25 5.05 \n", + "2 NaN NaN NaN NaN NaN \n", + "\n", + " OD280/OD315 of diluted wines Proline Column 14 \n", + "7 1.08 2.85 1045.0 \n", + "3 1.04 2.93 735.0 \n", + "8 1.01 3.55 1045.0 \n", + "9 1.25 3.17 1510.0 \n", + "4 1.05 2.85 1450.0 \n", + "5 1.02 3.58 1290.0 \n", + "10 1.17 2.82 1280.0 \n", + "1 NaN NaN NaN \n", + "6 1.06 3.58 1295.0 \n", + "2 NaN NaN NaN " + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 17 + } + ] + }, + { + "metadata": { + "id": "CzHnkhqcDtFV", + "colab_type": "code", + "colab": {} + }, + "cell_type": "code", + "source": [ + "" + ], + "execution_count": 0, + "outputs": [] + } + ] +} \ No newline at end of file From 5309912a6aa9bbeb6c97c6a128d9b1347c3f427f Mon Sep 17 00:00:00 2001 From: AGCreates <43198265+AGCreates@users.noreply.github.com> Date: Mon, 28 Jan 2019 11:30:59 +0530 Subject: [PATCH 4/4] Assignment 3 Basic_Pandas completed by AGCreates. This was the last remaining part to be completed. Hence, Whole Assignment 3 complete. --- Basic_Pandas.ipynb | 1041 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 1041 insertions(+) create mode 100644 Basic_Pandas.ipynb diff --git a/Basic_Pandas.ipynb b/Basic_Pandas.ipynb new file mode 100644 index 0000000..27ececb --- /dev/null +++ b/Basic_Pandas.ipynb @@ -0,0 +1,1041 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "name": "Basic Pandas.ipynb", + "version": "0.3.2", + "provenance": [], + "include_colab_link": true + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + } + }, + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "\"Open" + ] + }, + { + "metadata": { + "id": "cGbE814_Xaf9", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "# Pandas\n", + "\n", + "Pandas is an open-source, BSD-licensed Python library providing high-performance, easy-to-use data structures and data analysis tools for the Python programming language. Python with Pandas is used in a wide range of fields including academic and commercial domains including finance, economics, Statistics, analytics, etc.In this tutorial, we will learn the various features of Python Pandas and how to use them in practice.\n", + "\n", + "\n", + "## Import pandas and numpy" + ] + }, + { + "metadata": { + "id": "irlVYeeAXPDL", + "colab_type": "code", + "colab": {} + }, + "cell_type": "code", + "source": [ + "import pandas as pd\n", + "import numpy as np" + ], + "execution_count": 0, + "outputs": [] + }, + { + "metadata": { + "id": "BI2J-zdMbGwE", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "### This is your playground feel free to explore other functions on pandas\n", + "\n", + "#### Create Series from numpy array, list and dict\n", + "\n", + "Don't know what a series is?\n", + "\n", + "[Series Doc](https://pandas.pydata.org/pandas-docs/version/0.22/generated/pandas.Series.html)" + ] + }, + { + "metadata": { + "id": "GeEct691YGE3", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 139 + }, + "outputId": "4239628c-3913-4cb6-8aab-9276636905f5" + }, + "cell_type": "code", + "source": [ + "a_ascii = ord('A')\n", + "z_ascii = ord('Z')\n", + "alphabets = [chr(i) for i in range(a_ascii, z_ascii+1)]\n", + "\n", + "print(alphabets)\n", + "\n", + "numbers = np.arange(26)\n", + "\n", + "print(numbers)\n", + "\n", + "print(type(alphabets), type(numbers))\n", + "\n", + "alpha_numbers = dict(zip(alphabets, numbers))\n", + "\n", + "print(alpha_numbers)\n", + "\n", + "print(type(alpha_numbers))" + ], + "execution_count": 3, + "outputs": [ + { + "output_type": "stream", + "text": [ + "['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z']\n", + "[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23\n", + " 24 25]\n", + " \n", + "{'A': 0, 'B': 1, 'C': 2, 'D': 3, 'E': 4, 'F': 5, 'G': 6, 'H': 7, 'I': 8, 'J': 9, 'K': 10, 'L': 11, 'M': 12, 'N': 13, 'O': 14, 'P': 15, 'Q': 16, 'R': 17, 'S': 18, 'T': 19, 'U': 20, 'V': 21, 'W': 22, 'X': 23, 'Y': 24, 'Z': 25}\n", + "\n" + ], + "name": "stdout" + } + ] + }, + { + "metadata": { + "id": "6ouDfjWab_Mc", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 476 + }, + "outputId": "8ae24d7e-8c71-4cd3-9f1c-2119f225aeb1" + }, + "cell_type": "code", + "source": [ + "series1 = pd.Series(alphabets)\n", + "print(series1)" + ], + "execution_count": 4, + "outputs": [ + { + "output_type": "stream", + "text": [ + "0 A\n", + "1 B\n", + "2 C\n", + "3 D\n", + "4 E\n", + "5 F\n", + "6 G\n", + "7 H\n", + "8 I\n", + "9 J\n", + "10 K\n", + "11 L\n", + "12 M\n", + "13 N\n", + "14 O\n", + "15 P\n", + "16 Q\n", + "17 R\n", + "18 S\n", + "19 T\n", + "20 U\n", + "21 V\n", + "22 W\n", + "23 X\n", + "24 Y\n", + "25 Z\n", + "dtype: object\n" + ], + "name": "stdout" + } + ] + }, + { + "metadata": { + "id": "At7nY7vVcBZ3", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 476 + }, + "outputId": "f3b1e0a4-780d-40da-fa4f-d1c28d1f5c19" + }, + "cell_type": "code", + "source": [ + "series2 = pd.Series(numbers)\n", + "print(series2)" + ], + "execution_count": 5, + "outputs": [ + { + "output_type": "stream", + "text": [ + "0 0\n", + "1 1\n", + "2 2\n", + "3 3\n", + "4 4\n", + "5 5\n", + "6 6\n", + "7 7\n", + "8 8\n", + "9 9\n", + "10 10\n", + "11 11\n", + "12 12\n", + "13 13\n", + "14 14\n", + "15 15\n", + "16 16\n", + "17 17\n", + "18 18\n", + "19 19\n", + "20 20\n", + "21 21\n", + "22 22\n", + "23 23\n", + "24 24\n", + "25 25\n", + "dtype: int64\n" + ], + "name": "stdout" + } + ] + }, + { + "metadata": { + "id": "J5z-2CWAdH6N", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 476 + }, + "outputId": "7dc893c0-b797-44b1-9ce0-1fb00ffcd1f1" + }, + "cell_type": "code", + "source": [ + "series3 = pd.Series(alpha_numbers)\n", + "print(series3)" + ], + "execution_count": 6, + "outputs": [ + { + "output_type": "stream", + "text": [ + "A 0\n", + "B 1\n", + "C 2\n", + "D 3\n", + "E 4\n", + "F 5\n", + "G 6\n", + "H 7\n", + "I 8\n", + "J 9\n", + "K 10\n", + "L 11\n", + "M 12\n", + "N 13\n", + "O 14\n", + "P 15\n", + "Q 16\n", + "R 17\n", + "S 18\n", + "T 19\n", + "U 20\n", + "V 21\n", + "W 22\n", + "X 23\n", + "Y 24\n", + "Z 25\n", + "dtype: int64\n" + ], + "name": "stdout" + } + ] + }, + { + "metadata": { + "id": "fYzblGGudKjO", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 153 + }, + "outputId": "bb127d90-7ba9-459f-860d-ec49ac08b997" + }, + "cell_type": "code", + "source": [ + "#replace head() with head(n) where n can be any number between [0-25] and observe the output in deach case \n", + "series3.head(7)" + ], + "execution_count": 9, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "A 0\n", + "B 1\n", + "C 2\n", + "D 3\n", + "E 4\n", + "F 5\n", + "G 6\n", + "dtype: int64" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 9 + } + ] + }, + { + "metadata": { + "id": "OwsJIf5feTtg", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Create DataFrame from lists\n", + "\n", + "[DataFrame Doc](https://pandas.pydata.org/pandas-docs/stable/generated/pandas.DataFrame.html)" + ] + }, + { + "metadata": { + "id": "73UTZ07EdWki", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 855 + }, + "outputId": "95722bd4-68f1-4128-f4b4-3ad6ab4471a5" + }, + "cell_type": "code", + "source": [ + "data = {'alphabets': alphabets, 'values': numbers}\n", + "\n", + "df = pd.DataFrame(data)\n", + "\n", + "#Lets Change the column `values` to `alpha_numbers`\n", + "\n", + "df.columns = ['alphabets', 'alpha_numbers']\n", + "\n", + "df" + ], + "execution_count": 10, + "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", + "
alphabetsalpha_numbers
0A0
1B1
2C2
3D3
4E4
5F5
6G6
7H7
8I8
9J9
10K10
11L11
12M12
13N13
14O14
15P15
16Q16
17R17
18S18
19T19
20U20
21V21
22W22
23X23
24Y24
25Z25
\n", + "
" + ], + "text/plain": [ + " alphabets alpha_numbers\n", + "0 A 0\n", + "1 B 1\n", + "2 C 2\n", + "3 D 3\n", + "4 E 4\n", + "5 F 5\n", + "6 G 6\n", + "7 H 7\n", + "8 I 8\n", + "9 J 9\n", + "10 K 10\n", + "11 L 11\n", + "12 M 12\n", + "13 N 13\n", + "14 O 14\n", + "15 P 15\n", + "16 Q 16\n", + "17 R 17\n", + "18 S 18\n", + "19 T 19\n", + "20 U 20\n", + "21 V 21\n", + "22 W 22\n", + "23 X 23\n", + "24 Y 24\n", + "25 Z 25" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 10 + } + ] + }, + { + "metadata": { + "id": "uaK_1EO9etGS", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 140 + }, + "outputId": "40699f62-71be-4879-efba-2c4f8102d5ba" + }, + "cell_type": "code", + "source": [ + "# transpose\n", + "\n", + "df.T\n", + "\n", + "# there are many more operations which we can perform look at the documentation with the subsequent exercises we will learn more" + ], + "execution_count": 11, + "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", + "
0123456789...16171819202122232425
alphabetsABCDEFGHIJ...QRSTUVWXYZ
alpha_numbers0123456789...16171819202122232425
\n", + "

2 rows × 26 columns

\n", + "
" + ], + "text/plain": [ + " 0 1 2 3 4 5 6 7 8 9 ... 16 17 18 19 20 21 22 \\\n", + "alphabets A B C D E F G H I J ... Q R S T U V W \n", + "alpha_numbers 0 1 2 3 4 5 6 7 8 9 ... 16 17 18 19 20 21 22 \n", + "\n", + " 23 24 25 \n", + "alphabets X Y Z \n", + "alpha_numbers 23 24 25 \n", + "\n", + "[2 rows x 26 columns]" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 11 + } + ] + }, + { + "metadata": { + "id": "ZYonoaW8gEAJ", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Extract Items from a series" + ] + }, + { + "metadata": { + "id": "tc1-KX_Bfe7U", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 204 + }, + "outputId": "5ba5f8e8-6eb6-4960-bb1a-33805d23bdee" + }, + "cell_type": "code", + "source": [ + "ser = pd.Series(list('abcdefghijklmnopqrstuvwxyz'))\n", + "pos = [0, 4, 8, 14, 20]\n", + "\n", + "vowels = ser.take(pos)\n", + "\n", + "df = pd.DataFrame(vowels)#, columns=['vowels'])\n", + "\n", + "df.columns = ['vowels']\n", + "\n", + "df.index = [0, 1, 2, 3, 4]\n", + "\n", + "df" + ], + "execution_count": 12, + "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", + "
vowels
0a
1e
2i
3o
4u
\n", + "
" + ], + "text/plain": [ + " vowels\n", + "0 a\n", + "1 e\n", + "2 i\n", + "3 o\n", + "4 u" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 12 + } + ] + }, + { + "metadata": { + "id": "cmDxwtDNjWpO", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Change the first character of each word to upper case in each word of ser" + ] + }, + { + "metadata": { + "id": "5KagP9PpgV2F", + "colab_type": "code", + "outputId": "c3bf772f-23b4-4b05-8960-1303b62b8c38", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 34 + } + }, + "cell_type": "code", + "source": [ + "ser = pd.Series(['we', 'are', 'learning', 'pandas'])\n", + "\n", + "ser.map(lambda x : x.title())\n", + "\n", + "titles = [i.title() for i in ser]\n", + "\n", + "titles" + ], + "execution_count": 13, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "['We', 'Are', 'Learning', 'Pandas']" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 13 + } + ] + }, + { + "metadata": { + "id": "qn47ee-MkZN8", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Reindexing" + ] + }, + { + "metadata": { + "id": "h5R0JL2NjuFS", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 204 + }, + "outputId": "fbff45b5-6c43-4c50-958e-bc513d81a9c5" + }, + "cell_type": "code", + "source": [ + "my_index = [1, 2, 3, 4, 5]\n", + "\n", + "df1 = pd.DataFrame({'upper values': ['A', 'B', 'C', 'D', 'E'],\n", + " 'lower values': ['a', 'b', 'c', 'd', 'e']},\n", + " index = my_index)\n", + "\n", + "df1" + ], + "execution_count": 14, + "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", + "
lower valuesupper values
1aA
2bB
3cC
4dD
5eE
\n", + "
" + ], + "text/plain": [ + " lower values upper values\n", + "1 a A\n", + "2 b B\n", + "3 c C\n", + "4 d D\n", + "5 e E" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 14 + } + ] + }, + { + "metadata": { + "id": "G_Frvc3mk93k", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 204 + }, + "outputId": "b42b79db-910c-4854-aeed-e9ca8efc46c5" + }, + "cell_type": "code", + "source": [ + "new_index = [2, 5, 4, 3, 1]\n", + "\n", + "df1.reindex(index = new_index)" + ], + "execution_count": 15, + "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", + "
lower valuesupper values
2bB
5eE
4dD
3cC
1aA
\n", + "
" + ], + "text/plain": [ + " lower values upper values\n", + "2 b B\n", + "5 e E\n", + "4 d D\n", + "3 c C\n", + "1 a A" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 15 + } + ] + }, + { + "metadata": { + "id": "sCzC5Ah7EhiX", + "colab_type": "code", + "colab": {} + }, + "cell_type": "code", + "source": [ + "" + ], + "execution_count": 0, + "outputs": [] + } + ] +} \ No newline at end of file