Skip to content

Instantly share code, notes, and snippets.

@abrahamrhoffman
Last active June 29, 2019 21:13
Show Gist options
  • Save abrahamrhoffman/0cef74374899e061ea6a28b1c5dde48b to your computer and use it in GitHub Desktop.
Save abrahamrhoffman/0cef74374899e061ea6a28b1c5dde48b to your computer and use it in GitHub Desktop.
student_employee_data.ipynb
Display the source blob
Display the rendered blob
Raw
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Employer : Student Matcher"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"# Instantiate classes\n",
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"# Import the anax database class\n",
"import anax"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"# Create a new anax database\n",
"anax.Database(bootstrap=True);\n",
"# Connect to the anax database\n",
"anax = anax.Database()\n",
"# Remove the example anax table\n",
"anax.remove(\"users\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a student table"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"students = [\"abe\",\"jason\",\"steve\",\"rudolpho\"]\n",
"student_table = {\"students\": students}\n",
"anax.create(\"students\", student_table)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['students']"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"anax.tables()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"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>students</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>abe</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>jason</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>steve</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>rudolpho</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" students\n",
"0 abe\n",
"1 jason\n",
"2 steve\n",
"3 rudolpho"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"anax.read(\"students\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Add some features to our students"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"# Read the table into a dataframe\n",
"students = anax.read(\"students\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"# Add age, graduation_date, gpa, and top extracirricular activity\n",
"students.insert(1, \"age\", [21, 21, 42, 19], True)\n",
"students.insert(2, \"graduation_date\", [2021, 2021, 2020, 2023], True)\n",
"students.insert(3, \"gpa\", [4.0, 4.0, 3.2, 3.8], True)\n",
"students.insert(4, \"extra_activity\", [\"math\", \"badassery\", \"drinking\", np.nan], True)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"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>students</th>\n",
" <th>age</th>\n",
" <th>graduation_date</th>\n",
" <th>gpa</th>\n",
" <th>extra_activity</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>abe</td>\n",
" <td>21</td>\n",
" <td>2021</td>\n",
" <td>4.0</td>\n",
" <td>math</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>jason</td>\n",
" <td>21</td>\n",
" <td>2021</td>\n",
" <td>4.0</td>\n",
" <td>badassery</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>steve</td>\n",
" <td>42</td>\n",
" <td>2020</td>\n",
" <td>3.2</td>\n",
" <td>drinking</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>rudolpho</td>\n",
" <td>19</td>\n",
" <td>2023</td>\n",
" <td>3.8</td>\n",
" <td>None</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" students age graduation_date gpa extra_activity\n",
"0 abe 21 2021 4.0 math\n",
"1 jason 21 2021 4.0 badassery\n",
"2 steve 42 2020 3.2 drinking\n",
"3 rudolpho 19 2023 3.8 None"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Write the new information back to disk\n",
"anax.write(students, \"students\")\n",
"# Confirm the data is present on disk\n",
"anax.read(\"students\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create employer data for a single employer"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"employees = [\"george\",\"sam\",\"ed\",\"tim\"]\n",
"employee_table = {\"employees\": employees}\n",
"anax.create(\"acme_employees\", employee_table)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['students', 'acme_employees']"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"anax.tables()"
]
},
{
"cell_type": "code",
"execution_count": 11,
"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>employees</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>george</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>sam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>ed</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>tim</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" employees\n",
"0 george\n",
"1 sam\n",
"2 ed\n",
"3 tim"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"anax.read(\"acme_employees\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Add some features to our employees"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"# Read the table into a dataframe\n",
"acme_employees = anax.read(\"acme_employees\")"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"# Add age, performance (1-10), interests, and salary data\n",
"acme_employees.insert(1, \"age\", [21, 21, 59, 45], True)\n",
"acme_employees.insert(2, \"performance\", [9.5, 9.5, 6.0, 3.0], True)\n",
"acme_employees.insert(3, \"interests\", [\"math\", \"badassery\", np.nan, np.nan], True)\n",
"acme_employees.insert(4, \"salary\", [200000, 220000, 115000, 83000], True)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"scrolled": true
},
"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>employees</th>\n",
" <th>age</th>\n",
" <th>performance</th>\n",
" <th>interests</th>\n",
" <th>salary</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>george</td>\n",
" <td>21</td>\n",
" <td>9.5</td>\n",
" <td>math</td>\n",
" <td>200000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>sam</td>\n",
" <td>21</td>\n",
" <td>9.5</td>\n",
" <td>badassery</td>\n",
" <td>220000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>ed</td>\n",
" <td>59</td>\n",
" <td>6.0</td>\n",
" <td>None</td>\n",
" <td>115000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>tim</td>\n",
" <td>45</td>\n",
" <td>3.0</td>\n",
" <td>None</td>\n",
" <td>83000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" employees age performance interests salary\n",
"0 george 21 9.5 math 200000\n",
"1 sam 21 9.5 badassery 220000\n",
"2 ed 59 6.0 None 115000\n",
"3 tim 45 3.0 None 83000"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Write the new information back to disk\n",
"anax.write(acme_employees, \"acme_employees\")\n",
"# Confirm the data is present on disk\n",
"anax.read(\"acme_employees\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Show completed tables"
]
},
{
"cell_type": "code",
"execution_count": 15,
"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>students</th>\n",
" <th>age</th>\n",
" <th>graduation_date</th>\n",
" <th>gpa</th>\n",
" <th>extra_activity</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>abe</td>\n",
" <td>21</td>\n",
" <td>2021</td>\n",
" <td>4.0</td>\n",
" <td>math</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>jason</td>\n",
" <td>21</td>\n",
" <td>2021</td>\n",
" <td>4.0</td>\n",
" <td>badassery</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>steve</td>\n",
" <td>42</td>\n",
" <td>2020</td>\n",
" <td>3.2</td>\n",
" <td>drinking</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>rudolpho</td>\n",
" <td>19</td>\n",
" <td>2023</td>\n",
" <td>3.8</td>\n",
" <td>None</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" students age graduation_date gpa extra_activity\n",
"0 abe 21 2021 4.0 math\n",
"1 jason 21 2021 4.0 badassery\n",
"2 steve 42 2020 3.2 drinking\n",
"3 rudolpho 19 2023 3.8 None"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"anax.read(\"students\")"
]
},
{
"cell_type": "code",
"execution_count": 16,
"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>employees</th>\n",
" <th>age</th>\n",
" <th>performance</th>\n",
" <th>interests</th>\n",
" <th>salary</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>george</td>\n",
" <td>21</td>\n",
" <td>9.5</td>\n",
" <td>math</td>\n",
" <td>200000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>sam</td>\n",
" <td>21</td>\n",
" <td>9.5</td>\n",
" <td>badassery</td>\n",
" <td>220000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>ed</td>\n",
" <td>59</td>\n",
" <td>6.0</td>\n",
" <td>None</td>\n",
" <td>115000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>tim</td>\n",
" <td>45</td>\n",
" <td>3.0</td>\n",
" <td>None</td>\n",
" <td>83000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" employees age performance interests salary\n",
"0 george 21 9.5 math 200000\n",
"1 sam 21 9.5 badassery 220000\n",
"2 ed 59 6.0 None 115000\n",
"3 tim 45 3.0 None 83000"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"anax.read(\"acme_employees\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"language": "python",
"name": "python2"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.12"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment