From edf45fe25d207956d34ffce05a20f708311f7e68 Mon Sep 17 00:00:00 2001
From: ande2472 <ande2472@msu.edu>
Date: Tue, 28 Jun 2022 03:15:47 -0400
Subject: [PATCH] Upload New File
---
Pandas.ipynb | 381 +++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 381 insertions(+)
create mode 100644 Pandas.ipynb
diff --git a/Pandas.ipynb b/Pandas.ipynb
new file mode 100644
index 0000000..415d787
--- /dev/null
+++ b/Pandas.ipynb
@@ -0,0 +1,381 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 32,
+ "id": "fc73d74c",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "('answercheck.py', <http.client.HTTPMessage at 0x7fc9a8612220>)"
+ ]
+ },
+ "execution_count": 32,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "##ANSWER##\n",
+ "#Install answercheck in current director\n",
+ "from urllib.request import urlretrieve\n",
+ "urlretrieve('https://raw.githubusercontent.com/colbrydi/jupytercheck/master/answercheck.py', filename='answercheck.py')\n",
+ "##ANSWER##"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "3c2a4f39",
+ "metadata": {},
+ "source": [
+ "# Pandas\n",
+ "Pandas is a python library used to analyze data."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "2b78245b",
+ "metadata": {},
+ "source": [
+ "\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "71e867d9",
+ "metadata": {},
+ "source": [
+ "## Description\n",
+ "Pandas take tabular data and store them in objects known as ‘databases’. They are useful for exploring, cleaning, and processing data\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "58ec20e8",
+ "metadata": {},
+ "source": [
+ "## Self Assessment\n",
+ "\n",
+ "Questions that test for the learning goals and allows students to evaluate if they truly understand the topics."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "5d237ca9",
+ "metadata": {},
+ "source": [
+ "## Training Materials\n",
+ "\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "21f9b14e",
+ "metadata": {},
+ "source": [
+ "For a general understanding of how to use pandas, along with practice exercises, check out the following website: https://www.w3schools.com/python/pandas/default.asp\n",
+ "\n",
+ "For a complete directory of everything you can do with pandas:\n",
+ "​​\n",
+ "https://pandas.pydata.org/docs/index.html\n",
+ "\n",
+ "Pandas Cheat Sheet:\n",
+ "\n",
+ "Data Analysis:\n",
+ "\thttps://drive.google.com/file/d/1UHK8wtWbADvHKXFC937IS6MTnlSZC_zB/view \n",
+ "\n",
+ "Wrangling Data:\n",
+ "https://pandas.pydata.org/Pandas_Cheat_Sheet.pdf\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "1b047470",
+ "metadata": {},
+ "source": [
+ "Go to https://people.sc.fsu.edu/~jburkardt/data/csv/csv.html and download the “grades.cvs†file. We will use it to solve the following problems:\n",
+ "\n",
+ "✅ **<span style=\"color:red\">Question:</span>** Create a dataframe variable to store the grades.cvs table.\n",
+ "\n",
+ "\t\n",
+ "\n",
+ "If you need help: https://www.w3schools.com/python/pandas/pandas_csv.asp\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "ee42a54e",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "NameError",
+ "evalue": "name 'pd' is not defined",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
+ "Input \u001b[0;32mIn [1]\u001b[0m, in \u001b[0;36m<cell line: 2>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m##ANSWER##\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m df \u001b[38;5;241m=\u001b[39m \u001b[43mpd\u001b[49m\u001b[38;5;241m.\u001b[39mread_csv(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mgrades.csv\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m 3\u001b[0m df\n",
+ "\u001b[0;31mNameError\u001b[0m: name 'pd' is not defined"
+ ]
+ }
+ ],
+ "source": [
+ "##ANSWER##\n",
+ "df = pd.read_csv('grades.csv')\n",
+ "df\n",
+ "##ANSWER##"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "1e046af0",
+ "metadata": {},
+ "source": [
+ "✅ **<span style=\"color:red\">Question:</span>** Remove the 9th row (Andrew Airpump’s data) from the dataframe.\n",
+ "\n",
+ "If you need help, refer to the Wrangling Data cheatsheet: https://pandas.pydata.org/Pandas_Cheat_Sheet.pdf\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "180aff55",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "NameError",
+ "evalue": "name 'pd' is not defined",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
+ "Input \u001b[0;32mIn [1]\u001b[0m, in \u001b[0;36m<cell line: 2>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m##ANSWER##\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m df \u001b[38;5;241m=\u001b[39m \u001b[43mpd\u001b[49m\u001b[38;5;241m.\u001b[39mread_csv(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mgrades.csv\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m 3\u001b[0m df\n",
+ "\u001b[0;31mNameError\u001b[0m: name 'pd' is not defined"
+ ]
+ }
+ ],
+ "source": [
+ "##ANSWER##\n",
+ "df_1 = df.drop([8])\n",
+ "df_1\n",
+ "\n",
+ "##ANSWER##"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "43219d26",
+ "metadata": {},
+ "source": [
+ "✅ **<span style=\"color:red\">Question:</span>** Clean up column headers to remove unnecessary quotation marks.\n",
+ "\n",
+ "\n",
+ "If you need help: https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.rename.html\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "4c9f8f12",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "NameError",
+ "evalue": "name 'pd' is not defined",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
+ "Input \u001b[0;32mIn [1]\u001b[0m, in \u001b[0;36m<cell line: 2>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m##ANSWER##\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m df \u001b[38;5;241m=\u001b[39m \u001b[43mpd\u001b[49m\u001b[38;5;241m.\u001b[39mread_csv(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mgrades.csv\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m 3\u001b[0m df\n",
+ "\u001b[0;31mNameError\u001b[0m: name 'pd' is not defined"
+ ]
+ }
+ ],
+ "source": [
+ "##ANSWER##\n",
+ "df_2 = df_1.rename(columns=[{'\\\"First name\\\"': 'First name'}])\n",
+ "\tdf_2\n",
+ "\n",
+ "\n",
+ "##ANSWER##"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "f4e4a841",
+ "metadata": {},
+ "source": [
+ "✅ **<span style=\"color:red\">Question:</span>** Sort the data by student’s SSN. Store this data in a new dataframe called df_3.\n",
+ "\n",
+ "\n",
+ "If you need help: https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.sort_values.html?highlight=sort_values#pandas.DataFrame.sort_values\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "b8c5166c",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "NameError",
+ "evalue": "name 'pd' is not defined",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
+ "Input \u001b[0;32mIn [1]\u001b[0m, in \u001b[0;36m<cell line: 2>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m##ANSWER##\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m df \u001b[38;5;241m=\u001b[39m \u001b[43mpd\u001b[49m\u001b[38;5;241m.\u001b[39mread_csv(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mgrades.csv\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m 3\u001b[0m df\n",
+ "\u001b[0;31mNameError\u001b[0m: name 'pd' is not defined"
+ ]
+ }
+ ],
+ "source": [
+ "##ANSWER##\n",
+ "df_3 = df_2.sortvalues(by='Final')\n",
+ "\tdf_3 \n",
+ "\n",
+ "\n",
+ "\n",
+ "##ANSWER##"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "11a12621",
+ "metadata": {},
+ "source": [
+ "✅ **<span style=\"color:red\">Question:</span>** Sort the data by the overall letter grade they received in the class and the grade they received on the final.\n",
+ "\n",
+ "\n",
+ "If you need help: Same as above\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "333f476e",
+ "metadata": {},
+ "source": [
+ "✅ **<span style=\"color:red\">Question:</span>** Create a line graph plotting Test 1 scores against Test 2 scores.\n",
+ "\n",
+ "\n",
+ "\n",
+ "If you need help: https://pandas.pydata.org/docs/user_guide/visualization.html\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "f66f2294",
+ "metadata": {},
+ "source": [
+ "✅ **<span style=\"color:red\">Question:</span>** Perform a correlation test comparing Test 3 and Test 4 scores.\n",
+ "\n",
+ "\n",
+ "If you need help: https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.corr.html\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "dd9c7fa5",
+ "metadata": {},
+ "source": [
+ "✅ **<span style=\"color:red\">Question:</span>** Example answercheck question: What is $x = 2+2$?\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 28,
+ "id": "64684dfd",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#Put your answer here"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 29,
+ "id": "619a2259",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "##ANSWER##\n",
+ "x = 4\n",
+ "##ANSWER##"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 30,
+ "id": "9cc2b34a",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\n",
+ "CheckWarning: passed variable is <class 'int'> and not a numpy.matrix.\n",
+ " Trying to convert to a array matrix using ```A = np.matrix(A)```.\n",
+ "\n",
+ "\n",
+ "CheckWarning: passed matrix is int64 and not <class 'numpy.float64'>...\n",
+ " Trying to convert to float using ```A = A.astype(float)```.\n",
+ "\n",
+ "Testing [[4.]]\n",
+ "Answer seems to be correct\n",
+ "\n"
+ ]
+ }
+ ],
+ "source": [
+ "from answercheck import checkanswer\n",
+ "checkanswer.vector(x,'2cab95d1b144d663bad1ce5c51020ae0')"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "44b461a0",
+ "metadata": {},
+ "source": [
+ "---\n",
+ "\n",
+ "Written by <<YOUR NAME HERE>>, Michigan State University \n",
+ "As part of the Data Science Bridge Project \n",
+ " \n",
+ "<a rel=\"license\" href=\"http://creativecommons.org/licenses/by-nc/4.0/\"><img alt=\"Creative Commons License\" style=\"border-width:0\" src=\"https://i.creativecommons.org/l/by-nc/4.0/88x31.png\" /></a><br />This work is licensed under a <a rel=\"license\" href=\"http://creativecommons.org/licenses/by-nc/4.0/\">Creative Commons Attribution-NonCommercial 4.0 International License</a>."
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "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": "3.9.12"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
--
GitLab