diff --git a/Basic_Pandas.ipynb b/Basic_Pandas.ipynb new file mode 100644 index 0000000..da78b9a --- /dev/null +++ b/Basic_Pandas.ipynb @@ -0,0 +1,1037 @@ +{ + "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": [ + "[View in Colaboratory](https://colab.research.google.com/github/abhiWriteCode/Assignment-3/blob/AGCreates/Basic_Pandas.ipynb)" + ] + }, + { + "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": 137 + }, + "outputId": "2ad07099-866f-46b4-a404-560f00681636" + }, + "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": 2, + "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": 468 + }, + "outputId": "bf9f2550-c0e2-4d00-9dfa-0194dd2704e0" + }, + "cell_type": "code", + "source": [ + "series1 = pd.Series(alphabets)\n", + "print(series1)" + ], + "execution_count": 3, + "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": 468 + }, + "outputId": "c152f792-3832-4312-e86d-aa82317cce72" + }, + "cell_type": "code", + "source": [ + "series2 = pd.Series(numbers)\n", + "print(series2)" + ], + "execution_count": 4, + "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": 468 + }, + "outputId": "41a73845-d19c-4570-b9c0-7dcf03fc2bdd" + }, + "cell_type": "code", + "source": [ + "series3 = pd.Series(alpha_numbers)\n", + "print(series3)" + ], + "execution_count": 5, + "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": 84 + }, + "outputId": "8e3c2dd3-0316-40b6-b973-b76139ccb4d0" + }, + "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(3)" + ], + "execution_count": 6, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "A 0\n", + "B 1\n", + "C 2\n", + "dtype: int64" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 6 + } + ] + }, + { + "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": 822 + }, + "outputId": "d42a9e70-507c-43d9-9c6b-52dd3c331ebf" + }, + "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": 7, + "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": 7 + } + ] + }, + { + "metadata": { + "id": "uaK_1EO9etGS", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 136 + }, + "outputId": "39a70022-eaee-4060-ffc9-691b2e442cdc" + }, + "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": 8, + "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": 8 + } + ] + }, + { + "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": 196 + }, + "outputId": "0d315c71-9539-4395-9f14-de64b0dcee90" + }, + "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": 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", + "
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": 9 + } + ] + }, + { + "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", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 33 + }, + "outputId": "20548f2b-af5a-4144-9046-02df0c1b522e" + }, + "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": 10, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "['We', 'Are', 'Learning', 'Pandas']" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 10 + } + ] + }, + { + "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": 196 + }, + "outputId": "5b91a12d-d92f-4fa7-aba3-910bd343a26a" + }, + "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": 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", + "
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": 11 + } + ] + }, + { + "metadata": { + "id": "G_Frvc3mk93k", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 196 + }, + "outputId": "c457ed2f-771f-4e46-b1c6-58d563ded8e5" + }, + "cell_type": "code", + "source": [ + "new_index = [2, 5, 4, 3, 1]\n", + "\n", + "df1.reindex(index = new_index)" + ], + "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", + "
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": 12 + } + ] + }, + { + "metadata": { + "id": "8W4U8MUoiopI", + "colab_type": "code", + "colab": {} + }, + "cell_type": "code", + "source": [ + "" + ], + "execution_count": 0, + "outputs": [] + } + ] +} \ No newline at end of file diff --git a/Exercise.ipynb b/Exercise.ipynb new file mode 100644 index 0000000..c0b23bf --- /dev/null +++ b/Exercise.ipynb @@ -0,0 +1,2080 @@ +{ + "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": [ + "[View in Colaboratory](https://colab.research.google.com/github/abhiWriteCode/Assignment-3/blob/AGCreates/Exercise.ipynb)" + ] + }, + { + "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": [ + "dataset = pd.read_csv(\"https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data\", header=None)" + ], + "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": 196 + }, + "outputId": "aa33a028-8778-4514-ba4c-0f7e818eca86" + }, + "cell_type": "code", + "source": [ + "dataset.head()" + ], + "execution_count": 3, + "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", + "
012345678910111213
0114.231.712.4315.61272.803.060.282.295.641.043.921065
1113.201.782.1411.21002.652.760.261.284.381.053.401050
2113.162.362.6718.61012.803.240.302.815.681.033.171185
3114.371.952.5016.81133.853.490.242.187.800.863.451480
4113.242.592.8721.01182.802.690.391.824.321.042.93735
\n", + "
" + ], + "text/plain": [ + " 0 1 2 3 4 5 6 7 8 9 10 11 12 \\\n", + "0 1 14.23 1.71 2.43 15.6 127 2.80 3.06 0.28 2.29 5.64 1.04 3.92 \n", + "1 1 13.20 1.78 2.14 11.2 100 2.65 2.76 0.26 1.28 4.38 1.05 3.40 \n", + "2 1 13.16 2.36 2.67 18.6 101 2.80 3.24 0.30 2.81 5.68 1.03 3.17 \n", + "3 1 14.37 1.95 2.50 16.8 113 3.85 3.49 0.24 2.18 7.80 0.86 3.45 \n", + "4 1 13.24 2.59 2.87 21.0 118 2.80 2.69 0.39 1.82 4.32 1.04 2.93 \n", + "\n", + " 13 \n", + "0 1065 \n", + "1 1050 \n", + "2 1185 \n", + "3 1480 \n", + "4 735 " + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 3 + } + ] + }, + { + "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": 196 + }, + "outputId": "3a8101bc-97cd-420f-adf0-a4a411d22ab9" + }, + "cell_type": "code", + "source": [ + "wine_df_copy = dataset.copy()\n", + "wine_df_copy.head()" + ], + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
012345678910111213
0114.231.712.4315.61272.803.060.282.295.641.043.921065
1113.201.782.1411.21002.652.760.261.284.381.053.401050
2113.162.362.6718.61012.803.240.302.815.681.033.171185
3114.371.952.5016.81133.853.490.242.187.800.863.451480
4113.242.592.8721.01182.802.690.391.824.321.042.93735
\n", + "
" + ], + "text/plain": [ + " 0 1 2 3 4 5 6 7 8 9 10 11 12 \\\n", + "0 1 14.23 1.71 2.43 15.6 127 2.80 3.06 0.28 2.29 5.64 1.04 3.92 \n", + "1 1 13.20 1.78 2.14 11.2 100 2.65 2.76 0.26 1.28 4.38 1.05 3.40 \n", + "2 1 13.16 2.36 2.67 18.6 101 2.80 3.24 0.30 2.81 5.68 1.03 3.17 \n", + "3 1 14.37 1.95 2.50 16.8 113 3.85 3.49 0.24 2.18 7.80 0.86 3.45 \n", + "4 1 13.24 2.59 2.87 21.0 118 2.80 2.69 0.39 1.82 4.32 1.04 2.93 \n", + "\n", + " 13 \n", + "0 1065 \n", + "1 1050 \n", + "2 1185 \n", + "3 1480 \n", + "4 735 " + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 4 + } + ] + }, + { + "metadata": { + "id": "o6Cs6T1Rjz71", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Assign the columns as below:\n", + "\n", + "The attributes are (dontated by Riccardo Leardi, riclea '@' anchem.unige.it): \n", + "1) Alcohol \n", + "2) Malic acid \n", + "3) Ash \n", + "4) Alcalinity of ash \n", + "5) Magnesium \n", + "6) Total phenols \n", + "7) Flavanoids \n", + "8) Nonflavanoid phenols \n", + "9) Proanthocyanins \n", + "10)Color intensity \n", + "11)Hue \n", + "12)OD280/OD315 of diluted wines \n", + "13)Proline " + ] + }, + { + "metadata": { + "id": "my8HB4V4j779", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 33 + }, + "outputId": "a4a097b2-2dc6-4f7f-a5cd-a51abb431dfb" + }, + "cell_type": "code", + "source": [ + "columns = ['Target', 'Alcohol', 'Malic acid', 'Ash', 'Alcalinity of ash', 'Magnesium', 'Total phenols', 'Flavanoids', 'Nonflavanoid phenols', 'Proanthocyanins', 'Color intensity', 'Hue', 'OD280/OD315 of diluted wines', 'Proline']\n", + "len(columns)" + ], + "execution_count": 5, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "14" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 5 + } + ] + }, + { + "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": 213 + }, + "outputId": "caef832b-4471-40bc-c582-2e5203a2a9f3" + }, + "cell_type": "code", + "source": [ + "dataset.columns = columns\n", + "dataset.head()" + ], + "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", + "
TargetAlcoholMalic acidAshAlcalinity of ashMagnesiumTotal phenolsFlavanoidsNonflavanoid phenolsProanthocyaninsColor intensityHueOD280/OD315 of diluted winesProline
0114.231.712.4315.61272.803.060.282.295.641.043.921065
1113.201.782.1411.21002.652.760.261.284.381.053.401050
2113.162.362.6718.61012.803.240.302.815.681.033.171185
3114.371.952.5016.81133.853.490.242.187.800.863.451480
4113.242.592.8721.01182.802.690.391.824.321.042.93735
\n", + "
" + ], + "text/plain": [ + " Target Alcohol Malic acid Ash Alcalinity of ash Magnesium \\\n", + "0 1 14.23 1.71 2.43 15.6 127 \n", + "1 1 13.20 1.78 2.14 11.2 100 \n", + "2 1 13.16 2.36 2.67 18.6 101 \n", + "3 1 14.37 1.95 2.50 16.8 113 \n", + "4 1 13.24 2.59 2.87 21.0 118 \n", + "\n", + " Total phenols Flavanoids Nonflavanoid phenols Proanthocyanins \\\n", + "0 2.80 3.06 0.28 2.29 \n", + "1 2.65 2.76 0.26 1.28 \n", + "2 2.80 3.24 0.30 2.81 \n", + "3 3.85 3.49 0.24 2.18 \n", + "4 2.80 2.69 0.39 1.82 \n", + "\n", + " Color intensity Hue OD280/OD315 of diluted wines Proline \n", + "0 5.64 1.04 3.92 1065 \n", + "1 4.38 1.05 3.40 1050 \n", + "2 5.68 1.03 3.17 1185 \n", + "3 7.80 0.86 3.45 1480 \n", + "4 4.32 1.04 2.93 735 " + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 6 + } + ] + }, + { + "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": 33 + }, + "outputId": "1a5641fd-c44f-46b5-cfbf-daa9dc97cdfe" + }, + "cell_type": "code", + "source": [ + "from random import randint as rint\n", + "\n", + "random = [rint(0, 10) for _ in range(10)]\n", + "random" + ], + "execution_count": 7, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "[9, 1, 0, 3, 3, 0, 0, 6, 5, 1]" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 7 + } + ] + }, + { + "metadata": { + "id": "hELUakyXmFSu", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### Use random numbers you generated as an index and assign NaN value to each of cell of the column alcohol" + ] + }, + { + "metadata": { + "id": "zMgaNnNHmP01", + "colab_type": "code", + "colab": {} + }, + "cell_type": "code", + "source": [ + "# I can't understand what the question is !!?" + ], + "execution_count": 0, + "outputs": [] + }, + { + "metadata": { + "id": "PHyK_vRsmRwV", + "colab_type": "text" + }, + "cell_type": "markdown", + "source": [ + "#### How many missing values do we have? \n", + "\n", + "Hint: you can use isnull() and sum()" + ] + }, + { + "metadata": { + "id": "EnOYhmEqmfKp", + "colab_type": "code", + "colab": {} + }, + "cell_type": "code", + "source": [ + "# Same problem\n", + "# I can't got question meaning :(" + ], + "execution_count": 0, + "outputs": [] + }, + { + "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": 1912 + }, + "outputId": "ece534cf-2a6d-4bdd-cbb7-247caa31cd62" + }, + "cell_type": "code", + "source": [ + "dataset.dropna()" + ], + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TargetAlcoholMalic acidAshAlcalinity of ashMagnesiumTotal phenolsFlavanoidsNonflavanoid phenolsProanthocyaninsColor intensityHueOD280/OD315 of diluted winesProline
0114.231.712.4315.61272.803.060.282.295.6400001.043.921065
1113.201.782.1411.21002.652.760.261.284.3800001.053.401050
2113.162.362.6718.61012.803.240.302.815.6800001.033.171185
3114.371.952.5016.81133.853.490.242.187.8000000.863.451480
4113.242.592.8721.01182.802.690.391.824.3200001.042.93735
5114.201.762.4515.21123.273.390.341.976.7500001.052.851450
6114.391.872.4514.6962.502.520.301.985.2500001.023.581290
7114.062.152.6117.61212.602.510.311.255.0500001.063.581295
8114.831.642.1714.0972.802.980.291.985.2000001.082.851045
9113.861.352.2716.0982.983.150.221.857.2200001.013.551045
10114.102.162.3018.01052.953.320.222.385.7500001.253.171510
11114.121.482.3216.8952.202.430.261.575.0000001.172.821280
12113.751.732.4116.0892.602.760.291.815.6000001.152.901320
13114.751.732.3911.4913.103.690.432.815.4000001.252.731150
14114.381.872.3812.01023.303.640.292.967.5000001.203.001547
15113.631.812.7017.21122.852.910.301.467.3000001.282.881310
16114.301.922.7220.01202.803.140.331.976.2000001.072.651280
17113.831.572.6220.01152.953.400.401.726.6000001.132.571130
18114.191.592.4816.51083.303.930.321.868.7000001.232.821680
19113.643.102.5615.21162.703.030.171.665.1000000.963.36845
20114.061.632.2816.01263.003.170.242.105.6500001.093.71780
21112.933.802.6518.61022.412.410.251.984.5000001.033.52770
22113.711.862.3616.61012.612.880.271.693.8000001.114.001035
23112.851.602.5217.8952.482.370.261.463.9300001.093.631015
24113.501.812.6120.0962.532.610.281.663.5200001.123.82845
25113.052.053.2225.01242.632.680.471.923.5800001.133.20830
26113.391.772.6216.1932.852.940.341.454.8000000.923.221195
27113.301.722.1417.0942.402.190.271.353.9500001.022.771285
28113.871.902.8019.41072.952.970.371.764.5000001.253.40915
29114.021.682.2116.0962.652.330.261.984.7000001.043.591035
.............................................
148313.323.242.3821.5921.930.760.451.258.4200000.551.62650
149313.083.902.3621.51131.411.390.341.149.4000000.571.33550
150313.503.122.6224.01231.401.570.221.258.6000000.591.30500
151312.792.672.4822.01121.481.360.241.2610.8000000.481.47480
152313.111.902.7525.51162.201.280.261.567.1000000.611.33425
153313.233.302.2818.5981.800.830.611.8710.5200000.561.51675
154312.581.292.1020.01031.480.580.531.407.6000000.581.55640
155313.175.192.3222.0931.740.630.611.557.9000000.601.48725
156313.844.122.3819.5891.800.830.481.569.0100000.571.64480
157312.453.032.6427.0971.900.580.631.147.5000000.671.73880
158314.341.682.7025.0982.801.310.532.7013.0000000.571.96660
159313.481.672.6422.5892.601.100.522.2911.7500000.571.78620
160312.363.832.3821.0882.300.920.501.047.6500000.561.58520
161313.693.262.5420.01071.830.560.500.805.8800000.961.82680
162312.853.272.5822.01061.650.600.600.965.5800000.872.11570
163312.963.452.3518.51061.390.700.400.945.2800000.681.75675
164313.782.762.3022.0901.350.680.411.039.5800000.701.68615
165313.734.362.2622.5881.280.470.521.156.6200000.781.75520
166313.453.702.6023.01111.700.920.431.4610.6800000.851.56695
167312.823.372.3019.5881.480.660.400.9710.2600000.721.75685
168313.582.582.6924.51051.550.840.391.548.6600000.741.80750
169313.404.602.8625.01121.980.960.271.118.5000000.671.92630
170312.203.032.3219.0961.250.490.400.735.5000000.661.83510
171312.772.392.2819.5861.390.510.480.649.8999990.571.63470
172314.162.512.4820.0911.680.700.441.249.7000000.621.71660
173313.715.652.4520.5951.680.610.521.067.7000000.641.74740
174313.403.912.4823.01021.800.750.431.417.3000000.701.56750
175313.274.282.2620.01201.590.690.431.3510.2000000.591.56835
176313.172.592.3720.01201.650.680.531.469.3000000.601.62840
177314.134.102.7424.5962.050.760.561.359.2000000.611.60560
\n", + "

178 rows × 14 columns

\n", + "
" + ], + "text/plain": [ + " Target Alcohol Malic acid Ash Alcalinity of ash Magnesium \\\n", + "0 1 14.23 1.71 2.43 15.6 127 \n", + "1 1 13.20 1.78 2.14 11.2 100 \n", + "2 1 13.16 2.36 2.67 18.6 101 \n", + "3 1 14.37 1.95 2.50 16.8 113 \n", + "4 1 13.24 2.59 2.87 21.0 118 \n", + "5 1 14.20 1.76 2.45 15.2 112 \n", + "6 1 14.39 1.87 2.45 14.6 96 \n", + "7 1 14.06 2.15 2.61 17.6 121 \n", + "8 1 14.83 1.64 2.17 14.0 97 \n", + "9 1 13.86 1.35 2.27 16.0 98 \n", + "10 1 14.10 2.16 2.30 18.0 105 \n", + "11 1 14.12 1.48 2.32 16.8 95 \n", + "12 1 13.75 1.73 2.41 16.0 89 \n", + "13 1 14.75 1.73 2.39 11.4 91 \n", + "14 1 14.38 1.87 2.38 12.0 102 \n", + "15 1 13.63 1.81 2.70 17.2 112 \n", + "16 1 14.30 1.92 2.72 20.0 120 \n", + "17 1 13.83 1.57 2.62 20.0 115 \n", + "18 1 14.19 1.59 2.48 16.5 108 \n", + "19 1 13.64 3.10 2.56 15.2 116 \n", + "20 1 14.06 1.63 2.28 16.0 126 \n", + "21 1 12.93 3.80 2.65 18.6 102 \n", + "22 1 13.71 1.86 2.36 16.6 101 \n", + "23 1 12.85 1.60 2.52 17.8 95 \n", + "24 1 13.50 1.81 2.61 20.0 96 \n", + "25 1 13.05 2.05 3.22 25.0 124 \n", + "26 1 13.39 1.77 2.62 16.1 93 \n", + "27 1 13.30 1.72 2.14 17.0 94 \n", + "28 1 13.87 1.90 2.80 19.4 107 \n", + "29 1 14.02 1.68 2.21 16.0 96 \n", + ".. ... ... ... ... ... ... \n", + "148 3 13.32 3.24 2.38 21.5 92 \n", + "149 3 13.08 3.90 2.36 21.5 113 \n", + "150 3 13.50 3.12 2.62 24.0 123 \n", + "151 3 12.79 2.67 2.48 22.0 112 \n", + "152 3 13.11 1.90 2.75 25.5 116 \n", + "153 3 13.23 3.30 2.28 18.5 98 \n", + "154 3 12.58 1.29 2.10 20.0 103 \n", + "155 3 13.17 5.19 2.32 22.0 93 \n", + "156 3 13.84 4.12 2.38 19.5 89 \n", + "157 3 12.45 3.03 2.64 27.0 97 \n", + "158 3 14.34 1.68 2.70 25.0 98 \n", + "159 3 13.48 1.67 2.64 22.5 89 \n", + "160 3 12.36 3.83 2.38 21.0 88 \n", + "161 3 13.69 3.26 2.54 20.0 107 \n", + "162 3 12.85 3.27 2.58 22.0 106 \n", + "163 3 12.96 3.45 2.35 18.5 106 \n", + "164 3 13.78 2.76 2.30 22.0 90 \n", + "165 3 13.73 4.36 2.26 22.5 88 \n", + "166 3 13.45 3.70 2.60 23.0 111 \n", + "167 3 12.82 3.37 2.30 19.5 88 \n", + "168 3 13.58 2.58 2.69 24.5 105 \n", + "169 3 13.40 4.60 2.86 25.0 112 \n", + "170 3 12.20 3.03 2.32 19.0 96 \n", + "171 3 12.77 2.39 2.28 19.5 86 \n", + "172 3 14.16 2.51 2.48 20.0 91 \n", + "173 3 13.71 5.65 2.45 20.5 95 \n", + "174 3 13.40 3.91 2.48 23.0 102 \n", + "175 3 13.27 4.28 2.26 20.0 120 \n", + "176 3 13.17 2.59 2.37 20.0 120 \n", + "177 3 14.13 4.10 2.74 24.5 96 \n", + "\n", + " Total phenols Flavanoids Nonflavanoid phenols Proanthocyanins \\\n", + "0 2.80 3.06 0.28 2.29 \n", + "1 2.65 2.76 0.26 1.28 \n", + "2 2.80 3.24 0.30 2.81 \n", + "3 3.85 3.49 0.24 2.18 \n", + "4 2.80 2.69 0.39 1.82 \n", + "5 3.27 3.39 0.34 1.97 \n", + "6 2.50 2.52 0.30 1.98 \n", + "7 2.60 2.51 0.31 1.25 \n", + "8 2.80 2.98 0.29 1.98 \n", + "9 2.98 3.15 0.22 1.85 \n", + "10 2.95 3.32 0.22 2.38 \n", + "11 2.20 2.43 0.26 1.57 \n", + "12 2.60 2.76 0.29 1.81 \n", + "13 3.10 3.69 0.43 2.81 \n", + "14 3.30 3.64 0.29 2.96 \n", + "15 2.85 2.91 0.30 1.46 \n", + "16 2.80 3.14 0.33 1.97 \n", + "17 2.95 3.40 0.40 1.72 \n", + "18 3.30 3.93 0.32 1.86 \n", + "19 2.70 3.03 0.17 1.66 \n", + "20 3.00 3.17 0.24 2.10 \n", + "21 2.41 2.41 0.25 1.98 \n", + "22 2.61 2.88 0.27 1.69 \n", + "23 2.48 2.37 0.26 1.46 \n", + "24 2.53 2.61 0.28 1.66 \n", + "25 2.63 2.68 0.47 1.92 \n", + "26 2.85 2.94 0.34 1.45 \n", + "27 2.40 2.19 0.27 1.35 \n", + "28 2.95 2.97 0.37 1.76 \n", + "29 2.65 2.33 0.26 1.98 \n", + ".. ... ... ... ... \n", + "148 1.93 0.76 0.45 1.25 \n", + "149 1.41 1.39 0.34 1.14 \n", + "150 1.40 1.57 0.22 1.25 \n", + "151 1.48 1.36 0.24 1.26 \n", + "152 2.20 1.28 0.26 1.56 \n", + "153 1.80 0.83 0.61 1.87 \n", + "154 1.48 0.58 0.53 1.40 \n", + "155 1.74 0.63 0.61 1.55 \n", + "156 1.80 0.83 0.48 1.56 \n", + "157 1.90 0.58 0.63 1.14 \n", + "158 2.80 1.31 0.53 2.70 \n", + "159 2.60 1.10 0.52 2.29 \n", + "160 2.30 0.92 0.50 1.04 \n", + "161 1.83 0.56 0.50 0.80 \n", + "162 1.65 0.60 0.60 0.96 \n", + "163 1.39 0.70 0.40 0.94 \n", + "164 1.35 0.68 0.41 1.03 \n", + "165 1.28 0.47 0.52 1.15 \n", + "166 1.70 0.92 0.43 1.46 \n", + "167 1.48 0.66 0.40 0.97 \n", + "168 1.55 0.84 0.39 1.54 \n", + "169 1.98 0.96 0.27 1.11 \n", + "170 1.25 0.49 0.40 0.73 \n", + "171 1.39 0.51 0.48 0.64 \n", + "172 1.68 0.70 0.44 1.24 \n", + "173 1.68 0.61 0.52 1.06 \n", + "174 1.80 0.75 0.43 1.41 \n", + "175 1.59 0.69 0.43 1.35 \n", + "176 1.65 0.68 0.53 1.46 \n", + "177 2.05 0.76 0.56 1.35 \n", + "\n", + " Color intensity Hue OD280/OD315 of diluted wines Proline \n", + "0 5.640000 1.04 3.92 1065 \n", + "1 4.380000 1.05 3.40 1050 \n", + "2 5.680000 1.03 3.17 1185 \n", + "3 7.800000 0.86 3.45 1480 \n", + "4 4.320000 1.04 2.93 735 \n", + "5 6.750000 1.05 2.85 1450 \n", + "6 5.250000 1.02 3.58 1290 \n", + "7 5.050000 1.06 3.58 1295 \n", + "8 5.200000 1.08 2.85 1045 \n", + "9 7.220000 1.01 3.55 1045 \n", + "10 5.750000 1.25 3.17 1510 \n", + "11 5.000000 1.17 2.82 1280 \n", + "12 5.600000 1.15 2.90 1320 \n", + "13 5.400000 1.25 2.73 1150 \n", + "14 7.500000 1.20 3.00 1547 \n", + "15 7.300000 1.28 2.88 1310 \n", + "16 6.200000 1.07 2.65 1280 \n", + "17 6.600000 1.13 2.57 1130 \n", + "18 8.700000 1.23 2.82 1680 \n", + "19 5.100000 0.96 3.36 845 \n", + "20 5.650000 1.09 3.71 780 \n", + "21 4.500000 1.03 3.52 770 \n", + "22 3.800000 1.11 4.00 1035 \n", + "23 3.930000 1.09 3.63 1015 \n", + "24 3.520000 1.12 3.82 845 \n", + "25 3.580000 1.13 3.20 830 \n", + "26 4.800000 0.92 3.22 1195 \n", + "27 3.950000 1.02 2.77 1285 \n", + "28 4.500000 1.25 3.40 915 \n", + "29 4.700000 1.04 3.59 1035 \n", + ".. ... ... ... ... \n", + "148 8.420000 0.55 1.62 650 \n", + "149 9.400000 0.57 1.33 550 \n", + "150 8.600000 0.59 1.30 500 \n", + "151 10.800000 0.48 1.47 480 \n", + "152 7.100000 0.61 1.33 425 \n", + "153 10.520000 0.56 1.51 675 \n", + "154 7.600000 0.58 1.55 640 \n", + "155 7.900000 0.60 1.48 725 \n", + "156 9.010000 0.57 1.64 480 \n", + "157 7.500000 0.67 1.73 880 \n", + "158 13.000000 0.57 1.96 660 \n", + "159 11.750000 0.57 1.78 620 \n", + "160 7.650000 0.56 1.58 520 \n", + "161 5.880000 0.96 1.82 680 \n", + "162 5.580000 0.87 2.11 570 \n", + "163 5.280000 0.68 1.75 675 \n", + "164 9.580000 0.70 1.68 615 \n", + "165 6.620000 0.78 1.75 520 \n", + "166 10.680000 0.85 1.56 695 \n", + "167 10.260000 0.72 1.75 685 \n", + "168 8.660000 0.74 1.80 750 \n", + "169 8.500000 0.67 1.92 630 \n", + "170 5.500000 0.66 1.83 510 \n", + "171 9.899999 0.57 1.63 470 \n", + "172 9.700000 0.62 1.71 660 \n", + "173 7.700000 0.64 1.74 740 \n", + "174 7.300000 0.70 1.56 750 \n", + "175 10.200000 0.59 1.56 835 \n", + "176 9.300000 0.60 1.62 840 \n", + "177 9.200000 0.61 1.60 560 \n", + "\n", + "[178 rows x 14 columns]" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 10 + } + ] + } + ] +} \ No newline at end of file diff --git a/Get_to_know_your_Data.ipynb b/Get_to_know_your_Data.ipynb new file mode 100644 index 0000000..8ee6122 --- /dev/null +++ b/Get_to_know_your_Data.ipynb @@ -0,0 +1,2365 @@ +{ + "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" + } + }, + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "[View in Colaboratory](https://colab.research.google.com/github/abhiWriteCode/Assignment-3/blob/AGCreates/Get_to_know_your_Data.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" + ], + "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')" + ], + "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": 196 + }, + "outputId": "4b902db4-968c-47fb-edcb-e7ac4470eab7" + }, + "cell_type": "code", + "source": [ + "iris_df.head()" + ], + "execution_count": 3, + "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": 3 + } + ] + }, + { + "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": 33 + }, + "outputId": "4e1e387f-00d3-4b94-90fa-a5ba70efe5dc" + }, + "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": 4, + "outputs": [ + { + "output_type": "stream", + "text": [ + "(150, 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": 67 + }, + "outputId": "da5b4095-5e3e-4334-8631-8254150ea4c3" + }, + "cell_type": "code", + "source": [ + "print(iris_df.columns)" + ], + "execution_count": 5, + "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": 33 + }, + "outputId": "81e26a7d-543c-4c04-9ba4-100f60946422" + }, + "cell_type": "code", + "source": [ + "print(iris_df.index)" + ], + "execution_count": 6, + "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": 217 + }, + "outputId": "54974de8-c773-4987-dcf2-ef74e0c1ba95" + }, + "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", + "iris_df = iris_df.reindex(index = new_index)\n", + "\n", + "print(iris_df.head())" + ], + "execution_count": 7, + "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", + " sepal_length sepal_width petal_length petal_width species\n", + "56 6.3 3.3 4.7 1.6 versicolor\n", + "137 6.4 3.1 5.5 1.8 virginica\n", + "133 6.3 2.8 5.1 1.5 virginica\n", + "60 5.0 2.0 3.5 1.0 versicolor\n", + "5 5.4 3.9 1.7 0.4 setosa\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": 318 + }, + "outputId": "e2a17587-26b1-4456-fd7a-92cb2e2a2183" + }, + "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": 8, + "outputs": [ + { + "output_type": "stream", + "text": [ + " sepal_length sepal_width petal_length petal_width species\n", + "56 6.3 3.3 4.7 1.6 versicolor\n", + "137 6.4 3.1 5.5 1.8 virginica\n", + "133 6.3 2.8 5.1 1.5 virginica\n", + "60 5.0 2.0 3.5 1.0 versicolor\n", + "5 5.4 3.9 1.7 0.4 setosa\n", + " sepal_length sepal_width petal_length petal_width species\n", + "56 6.3 33.0 4.7 1.6 versicolor\n", + "137 6.4 31.0 5.5 1.8 virginica\n", + "133 6.3 28.0 5.1 1.5 virginica\n", + "60 5.0 20.0 3.5 1.0 versicolor\n", + "5 5.4 39.0 1.7 0.4 setosa\n", + " sepal_length sepal_width petal_length petal_width species\n", + "56 6.3 3.3 4.7 1.6 versicolor\n", + "137 6.4 3.1 5.5 1.8 virginica\n", + "133 6.3 2.8 5.1 1.5 virginica\n", + "60 5.0 2.0 3.5 1.0 versicolor\n", + "5 5.4 3.9 1.7 0.4 setosa\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": 1121 + }, + "outputId": "dceae06d-4aa5-4899-f7d6-bf141060f58c" + }, + "cell_type": "code", + "source": [ + "iris_df[iris_df['sepal_width']>3.3]" + ], + "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", + "
sepal_lengthsepal_widthpetal_lengthpetal_widthspecies
55.43.91.70.4setosa
215.13.71.50.4setosa
1366.33.45.62.4virginica
275.23.51.50.2setosa
244.83.41.90.2setosa
64.63.41.40.3setosa
45.03.61.40.2setosa
435.03.51.60.6setosa
155.74.41.50.4setosa
1097.23.66.12.5virginica
75.03.41.50.2setosa
265.03.41.60.4setosa
195.13.81.50.3setosa
325.24.11.50.1setosa
465.13.81.60.2setosa
485.33.71.50.2setosa
1317.93.86.42.0virginica
445.13.81.90.4setosa
165.43.91.30.4setosa
145.84.01.20.2setosa
1177.73.86.72.2virginica
365.53.51.30.2setosa
285.23.41.40.2setosa
205.43.41.70.2setosa
114.83.41.60.2setosa
1486.23.45.42.3virginica
105.43.71.50.2setosa
185.73.81.70.3setosa
856.03.44.51.6versicolor
405.03.51.30.3setosa
05.13.51.40.2setosa
335.54.21.40.2setosa
224.63.61.00.2setosa
175.13.51.40.3setosa
395.13.41.50.2setosa
315.43.41.50.4setosa
\n", + "
" + ], + "text/plain": [ + " sepal_length sepal_width petal_length petal_width species\n", + "5 5.4 3.9 1.7 0.4 setosa\n", + "21 5.1 3.7 1.5 0.4 setosa\n", + "136 6.3 3.4 5.6 2.4 virginica\n", + "27 5.2 3.5 1.5 0.2 setosa\n", + "24 4.8 3.4 1.9 0.2 setosa\n", + "6 4.6 3.4 1.4 0.3 setosa\n", + "4 5.0 3.6 1.4 0.2 setosa\n", + "43 5.0 3.5 1.6 0.6 setosa\n", + "15 5.7 4.4 1.5 0.4 setosa\n", + "109 7.2 3.6 6.1 2.5 virginica\n", + "7 5.0 3.4 1.5 0.2 setosa\n", + "26 5.0 3.4 1.6 0.4 setosa\n", + "19 5.1 3.8 1.5 0.3 setosa\n", + "32 5.2 4.1 1.5 0.1 setosa\n", + "46 5.1 3.8 1.6 0.2 setosa\n", + "48 5.3 3.7 1.5 0.2 setosa\n", + "131 7.9 3.8 6.4 2.0 virginica\n", + "44 5.1 3.8 1.9 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", + "117 7.7 3.8 6.7 2.2 virginica\n", + "36 5.5 3.5 1.3 0.2 setosa\n", + "28 5.2 3.4 1.4 0.2 setosa\n", + "20 5.4 3.4 1.7 0.2 setosa\n", + "11 4.8 3.4 1.6 0.2 setosa\n", + "148 6.2 3.4 5.4 2.3 virginica\n", + "10 5.4 3.7 1.5 0.2 setosa\n", + "18 5.7 3.8 1.7 0.3 setosa\n", + "85 6.0 3.4 4.5 1.6 versicolor\n", + "40 5.0 3.5 1.3 0.3 setosa\n", + "0 5.1 3.5 1.4 0.2 setosa\n", + "33 5.5 4.2 1.4 0.2 setosa\n", + "22 4.6 3.6 1.0 0.2 setosa\n", + "17 5.1 3.5 1.4 0.3 setosa\n", + "39 5.1 3.4 1.5 0.2 setosa\n", + "31 5.4 3.4 1.5 0.4 setosa" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 9 + } + ] + }, + { + "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": 77 + }, + "outputId": "71b8b799-a20e-4c60-f304-26f8d44558fb" + }, + "cell_type": "code", + "source": [ + "iris_df[(iris_df['sepal_width']>3.3) & (iris_df['species'] == 'versicolor')] " + ], + "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", + "
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": 10 + } + ] + }, + { + "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": 1895 + }, + "outputId": "98447468-dbfa-4d1a-d198-9d9f168c48d8" + }, + "cell_type": "code", + "source": [ + "iris_df.sort_values(by='sepal_width')#, ascending = False)\n", + "#pass ascending = False for descending order" + ], + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \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
876.32.34.41.3versicolor
935.02.33.31.0versicolor
414.52.31.30.3setosa
805.52.43.81.1versicolor
815.52.43.71.0versicolor
574.92.43.31.0versicolor
1086.72.55.81.8virginica
1466.32.55.01.9virginica
695.62.53.91.1versicolor
1064.92.54.51.7virginica
726.32.54.91.5versicolor
1135.72.55.02.0virginica
895.52.54.01.3versicolor
985.12.53.01.1versicolor
1187.72.66.92.3virginica
905.52.64.41.2versicolor
1346.12.65.61.4virginica
925.82.64.01.2versicolor
795.72.63.51.0versicolor
825.82.73.91.2versicolor
675.82.74.11.0versicolor
1015.82.75.11.9virginica
945.62.74.21.3versicolor
1116.42.75.31.9virginica
1425.82.75.11.9virginica
..................
114.83.41.60.2setosa
856.03.44.51.6versicolor
265.03.41.60.4setosa
315.43.41.50.4setosa
285.23.41.40.2setosa
1486.23.45.42.3virginica
405.03.51.30.3setosa
05.13.51.40.2setosa
275.23.51.50.2setosa
175.13.51.40.3setosa
435.03.51.60.6setosa
365.53.51.30.2setosa
1097.23.66.12.5virginica
45.03.61.40.2setosa
224.63.61.00.2setosa
215.13.71.50.4setosa
105.43.71.50.2setosa
485.33.71.50.2setosa
1317.93.86.42.0virginica
1177.73.86.72.2virginica
185.73.81.70.3setosa
445.13.81.90.4setosa
195.13.81.50.3setosa
465.13.81.60.2setosa
165.43.91.30.4setosa
55.43.91.70.4setosa
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", + "87 6.3 2.3 4.4 1.3 versicolor\n", + "93 5.0 2.3 3.3 1.0 versicolor\n", + "41 4.5 2.3 1.3 0.3 setosa\n", + "80 5.5 2.4 3.8 1.1 versicolor\n", + "81 5.5 2.4 3.7 1.0 versicolor\n", + "57 4.9 2.4 3.3 1.0 versicolor\n", + "108 6.7 2.5 5.8 1.8 virginica\n", + "146 6.3 2.5 5.0 1.9 virginica\n", + "69 5.6 2.5 3.9 1.1 versicolor\n", + "106 4.9 2.5 4.5 1.7 virginica\n", + "72 6.3 2.5 4.9 1.5 versicolor\n", + "113 5.7 2.5 5.0 2.0 virginica\n", + "89 5.5 2.5 4.0 1.3 versicolor\n", + "98 5.1 2.5 3.0 1.1 versicolor\n", + "118 7.7 2.6 6.9 2.3 virginica\n", + "90 5.5 2.6 4.4 1.2 versicolor\n", + "134 6.1 2.6 5.6 1.4 virginica\n", + "92 5.8 2.6 4.0 1.2 versicolor\n", + "79 5.7 2.6 3.5 1.0 versicolor\n", + "82 5.8 2.7 3.9 1.2 versicolor\n", + "67 5.8 2.7 4.1 1.0 versicolor\n", + "101 5.8 2.7 5.1 1.9 virginica\n", + "94 5.6 2.7 4.2 1.3 versicolor\n", + "111 6.4 2.7 5.3 1.9 virginica\n", + "142 5.8 2.7 5.1 1.9 virginica\n", + ".. ... ... ... ... ...\n", + "11 4.8 3.4 1.6 0.2 setosa\n", + "85 6.0 3.4 4.5 1.6 versicolor\n", + "26 5.0 3.4 1.6 0.4 setosa\n", + "31 5.4 3.4 1.5 0.4 setosa\n", + "28 5.2 3.4 1.4 0.2 setosa\n", + "148 6.2 3.4 5.4 2.3 virginica\n", + "40 5.0 3.5 1.3 0.3 setosa\n", + "0 5.1 3.5 1.4 0.2 setosa\n", + "27 5.2 3.5 1.5 0.2 setosa\n", + "17 5.1 3.5 1.4 0.3 setosa\n", + "43 5.0 3.5 1.6 0.6 setosa\n", + "36 5.5 3.5 1.3 0.2 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", + "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", + "131 7.9 3.8 6.4 2.0 virginica\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", + "46 5.1 3.8 1.6 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", + "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": 11 + } + ] + }, + { + "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": 33 + }, + "outputId": "59aab21b-e3d5-47ec-aee6-a8d45244f490" + }, + "cell_type": "code", + "source": [ + "species = iris_df['species'].unique()\n", + "\n", + "print(species)" + ], + "execution_count": 12, + "outputs": [ + { + "output_type": "stream", + "text": [ + "['versicolor' 'virginica' '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": 196 + }, + "outputId": "84b853d0-d549-4ee5-8fef-b6734087c5ad" + }, + "cell_type": "code", + "source": [ + "setosa = iris_df[iris_df['species'] == species[0]]\n", + "\n", + "setosa.head()" + ], + "execution_count": 13, + "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
566.33.34.71.6versicolor
605.02.03.51.0versicolor
836.02.75.11.6versicolor
645.62.93.61.3versicolor
726.32.54.91.5versicolor
\n", + "
" + ], + "text/plain": [ + " sepal_length sepal_width petal_length petal_width species\n", + "56 6.3 3.3 4.7 1.6 versicolor\n", + "60 5.0 2.0 3.5 1.0 versicolor\n", + "83 6.0 2.7 5.1 1.6 versicolor\n", + "64 5.6 2.9 3.6 1.3 versicolor\n", + "72 6.3 2.5 4.9 1.5 versicolor" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 13 + } + ] + }, + { + "metadata": { + "id": "7tumfZ3DotPG", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 196 + }, + "outputId": "f0c40a08-bae4-48e5-a18a-03bbb045f403" + }, + "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": 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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
sepal_lengthsepal_widthpetal_lengthpetal_widthspecies
1376.43.15.51.8virginica
1336.32.85.11.5virginica
1135.72.55.02.0virginica
1126.83.05.52.1virginica
1326.42.85.62.2virginica
\n", + "
" + ], + "text/plain": [ + " sepal_length sepal_width petal_length petal_width species\n", + "137 6.4 3.1 5.5 1.8 virginica\n", + "133 6.3 2.8 5.1 1.5 virginica\n", + "113 5.7 2.5 5.0 2.0 virginica\n", + "112 6.8 3.0 5.5 2.1 virginica\n", + "132 6.4 2.8 5.6 2.2 virginica" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 14 + } + ] + }, + { + "metadata": { + "id": "cUYm5UqVpDPy", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 196 + }, + "outputId": "f0c73894-ea6a-495d-aeaa-3a945f0a2880" + }, + "cell_type": "code", + "source": [ + "\n", + "\n", + "virginica = iris_df[iris_df['species'] == species[2]]\n", + "\n", + "virginica.head()" + ], + "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", + "
sepal_lengthsepal_widthpetal_lengthpetal_widthspecies
55.43.91.70.4setosa
215.13.71.50.4setosa
414.52.31.30.3setosa
304.83.11.60.2setosa
275.23.51.50.2setosa
\n", + "
" + ], + "text/plain": [ + " sepal_length sepal_width petal_length petal_width species\n", + "5 5.4 3.9 1.7 0.4 setosa\n", + "21 5.1 3.7 1.5 0.4 setosa\n", + "41 4.5 2.3 1.3 0.3 setosa\n", + "30 4.8 3.1 1.6 0.2 setosa\n", + "27 5.2 3.5 1.5 0.2 setosa" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 15 + } + ] + }, + { + "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": 286 + }, + "outputId": "a0e7806d-603a-423a-afaa-59149b41e3ed" + }, + "cell_type": "code", + "source": [ + "setosa.describe()" + ], + "execution_count": 16, + "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": 16 + } + ] + }, + { + "metadata": { + "id": "GwJFT2GlpwUv", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 286 + }, + "outputId": "4df96b1a-6a13-4645-84fd-8ba519033c17" + }, + "cell_type": "code", + "source": [ + "versicolor.describe()" + ], + "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", + "
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": 17 + } + ] + }, + { + "metadata": { + "id": "Ad4qhSZLpztf", + "colab_type": "code", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 286 + }, + "outputId": "8478eaa0-620f-495f-cdc0-18dd5f384fa7" + }, + "cell_type": "code", + "source": [ + "virginica.describe()" + ], + "execution_count": 18, + "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": 18 + } + ] + }, + { + "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": 397 + }, + "outputId": "a65b2b42-53e7-411f-b71f-d424ee1f5549" + }, + "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": 19, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "(array([ 4., 1., 6., 5., 12., 8., 4., 5., 2., 3.]),\n", + " array([4.3 , 4.45, 4.6 , 4.75, 4.9 , 5.05, 5.2 , 5.35, 5.5 , 5.65, 5.8 ]),\n", + " )" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 19 + }, + { + "output_type": "display_data", + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAd8AAAFKCAYAAABcq1WoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nMfEFgMTEFwAS+3/wQITBxOH0DQAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": { + "tags": [] + } + } + ] + }, + { + "metadata": { + "id": "Xy6isPCOj1bs", + "colab_type": "code", + "colab": {} + }, + "cell_type": "code", + "source": [ + "" + ], + "execution_count": 0, + "outputs": [] + } + ] +} \ No newline at end of file