From f59783cbad3fd5c44471d0cf52344d2d6cc97080 Mon Sep 17 00:00:00 2001
From: Dirk Colbry <colbrydi@msu.edu>
Date: Mon, 1 Jan 2024 13:00:17 -0500
Subject: [PATCH] Adding in Mimesis data generator
---
Mimesis.ipynb | 360 ++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 360 insertions(+)
create mode 100644 Mimesis.ipynb
diff --git a/Mimesis.ipynb b/Mimesis.ipynb
new file mode 100644
index 0000000..974cdd2
--- /dev/null
+++ b/Mimesis.ipynb
@@ -0,0 +1,360 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "id": "6600a76c",
+ "metadata": {},
+ "source": [
+ "# Installing required packages "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "ae65adaf",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "!pip install -r ../requirements.txt"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "d9395405",
+ "metadata": {},
+ "source": [
+ "# Quickstart Guide to Mimesis"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "85dd7d12",
+ "metadata": {},
+ "source": [
+ "## Generating Some Data\n",
+ "\n",
+ "\n",
+ "Now, let's generate some data using Mimesis! We will use the **Person** provider class from Mimesis to generate a simple table containing a set of Names, Ages, Genders, Academic Degrees, and Occupations and convert the data into a Pandas DataFrame."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "4c184360",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from mimesis import Person\n",
+ "from mimesis.locales import Locale\n",
+ "from mimesis.enums import Gender\n",
+ "import pandas as pd"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "3d762ee0",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "person = Person(Locale.EN)\n",
+ "\n",
+ "data_list = [{\n",
+ " \"Name\": person.full_name(),\n",
+ " \"Age\": person.age(),\n",
+ " \"Gender\": person.gender(),\n",
+ " \"Academic Degree\": person.academic_degree(),\n",
+ " \"Occupation\": person.occupation(),\n",
+ "} for _ in range(100)]\n",
+ "\n",
+ "df = pd.DataFrame(data_list)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "ab22c620",
+ "metadata": {},
+ "source": [
+ "We will then view the first five rows of our generated data."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "id": "e5d118b2",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Name</th>\n",
+ " <th>Age</th>\n",
+ " <th>Gender</th>\n",
+ " <th>Academic Degree</th>\n",
+ " <th>Occupation</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Jessenia Roy</td>\n",
+ " <td>31</td>\n",
+ " <td>Female</td>\n",
+ " <td>PhD</td>\n",
+ " <td>Maintenance Fitter</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Jasper Schultz</td>\n",
+ " <td>21</td>\n",
+ " <td>Other</td>\n",
+ " <td>Bachelor</td>\n",
+ " <td>Racehorse Groom</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Micki Newton</td>\n",
+ " <td>41</td>\n",
+ " <td>Other</td>\n",
+ " <td>Bachelor</td>\n",
+ " <td>Foundry Worker</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Doreatha Adams</td>\n",
+ " <td>39</td>\n",
+ " <td>Fluid</td>\n",
+ " <td>Master</td>\n",
+ " <td>Kitchen Worker</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>Milton Ford</td>\n",
+ " <td>41</td>\n",
+ " <td>Male</td>\n",
+ " <td>Bachelor</td>\n",
+ " <td>Bank Messenger</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Name Age Gender Academic Degree Occupation\n",
+ "0 Jessenia Roy 31 Female PhD Maintenance Fitter\n",
+ "1 Jasper Schultz 21 Other Bachelor Racehorse Groom\n",
+ "2 Micki Newton 41 Other Bachelor Foundry Worker\n",
+ "3 Doreatha Adams 39 Fluid Master Kitchen Worker\n",
+ "4 Milton Ford 41 Male Bachelor Bank Messenger"
+ ]
+ },
+ "execution_count": 11,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "d46fda7f",
+ "metadata": {},
+ "source": [
+ "This is just a small preview of what Mimesis can do in terms of data generation. If you want a more detailed guide, you can follow the very detailed instructions at: \n",
+ "\n",
+ "https://mimesis.name/en/master/getting_started.html"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "b9a289e0",
+ "metadata": {},
+ "source": [
+ "# Quick Start Guide to Faker"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "f309c13f",
+ "metadata": {},
+ "source": [
+ "### Set Up"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "id": "cafac6cb",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from faker import Faker\n",
+ "import pandas as pd\n",
+ "\n",
+ "fake = Faker()\n",
+ "Faker.seed(0)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "bccf7509",
+ "metadata": {},
+ "source": [
+ "### Generating Data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "id": "ad9390db",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>job</th>\n",
+ " <th>company</th>\n",
+ " <th>ssn</th>\n",
+ " <th>residence</th>\n",
+ " <th>current_location</th>\n",
+ " <th>blood_group</th>\n",
+ " <th>website</th>\n",
+ " <th>username</th>\n",
+ " <th>name</th>\n",
+ " <th>sex</th>\n",
+ " <th>address</th>\n",
+ " <th>mail</th>\n",
+ " <th>birthdate</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Hydrogeologist</td>\n",
+ " <td>Gomez, Wright and Chen</td>\n",
+ " <td>653-68-0948</td>\n",
+ " <td>5735 Farley Course\\nPort Daniel, OH 79871</td>\n",
+ " <td>-48.693466</td>\n",
+ " <td>O+</td>\n",
+ " <td>https://wright.com/</td>\n",
+ " <td>robinsondanny</td>\n",
+ " <td>Michael Montgomery</td>\n",
+ " <td>M</td>\n",
+ " <td>Unit 4892 Box 6717\\nDPO AE 71770</td>\n",
+ " <td>bramirez@gmail.com</td>\n",
+ " <td>1943-01-04</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Hydrogeologist</td>\n",
+ " <td>Gomez, Wright and Chen</td>\n",
+ " <td>653-68-0948</td>\n",
+ " <td>5735 Farley Course\\nPort Daniel, OH 79871</td>\n",
+ " <td>59.532676</td>\n",
+ " <td>O+</td>\n",
+ " <td>http://welch-miller.com/</td>\n",
+ " <td>robinsondanny</td>\n",
+ " <td>Michael Montgomery</td>\n",
+ " <td>M</td>\n",
+ " <td>Unit 4892 Box 6717\\nDPO AE 71770</td>\n",
+ " <td>bramirez@gmail.com</td>\n",
+ " <td>1943-01-04</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " job company ssn \\\n",
+ "0 Hydrogeologist Gomez, Wright and Chen 653-68-0948 \n",
+ "1 Hydrogeologist Gomez, Wright and Chen 653-68-0948 \n",
+ "\n",
+ " residence current_location blood_group \\\n",
+ "0 5735 Farley Course\\nPort Daniel, OH 79871 -48.693466 O+ \n",
+ "1 5735 Farley Course\\nPort Daniel, OH 79871 59.532676 O+ \n",
+ "\n",
+ " website username name sex \\\n",
+ "0 https://wright.com/ robinsondanny Michael Montgomery M \n",
+ "1 http://welch-miller.com/ robinsondanny Michael Montgomery M \n",
+ "\n",
+ " address mail birthdate \n",
+ "0 Unit 4892 Box 6717\\nDPO AE 71770 bramirez@gmail.com 1943-01-04 \n",
+ "1 Unit 4892 Box 6717\\nDPO AE 71770 bramirez@gmail.com 1943-01-04 "
+ ]
+ },
+ "execution_count": 16,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "while True:\n",
+ " try: \n",
+ " df = pd.DataFrame(fake.profile())\n",
+ " except ValueError:\n",
+ " continue\n",
+ " break\n",
+ "df.head()"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.8.8"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
--
GitLab