diff --git a/s24/Louis_Lecture_Notes/36_Database3/Lec36_WorksheetAnswers.ipynb b/s24/Louis_Lecture_Notes/36_Database3/Lec36_WorksheetAnswers.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..13e8e827bd6955ce327360ff0bcb657e5e8a4b83
--- /dev/null
+++ b/s24/Louis_Lecture_Notes/36_Database3/Lec36_WorksheetAnswers.ipynb
@@ -0,0 +1,3316 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<style>em { color: red; }</style> <style>.container {width:100% !important; }</style>"
+ ],
+ "text/plain": [
+ "<IPython.core.display.HTML object>"
+ ]
+ },
+ "execution_count": 1,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# ignore this cell - it makes the emphasized text red and uses the full width of the screen\n",
+ "from IPython.core.display import HTML\n",
+ "HTML('<style>em { color: red; }</style> <style>.container {width:100% !important; }</style>')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import sqlite3\n",
+ "import pandas as pd"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "conn = sqlite3.connect(\"worksheet.db\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# this function gives us a shortcut to making queries\n",
+ "# instead of typing all that code over and over again, we just call qry with our SQL\n",
+ "# it assumes we have access to a connection object, conn\n",
+ "\n",
+ "def qry(QUERY):\n",
+ " '''QUERY is a string containing SQL, conn is a global connection variable'''\n",
+ " return pd.read_sql(QUERY, conn)"
+ ]
+ },
+ {
+ "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>type</th>\n",
+ " <th>name</th>\n",
+ " <th>tbl_name</th>\n",
+ " <th>rootpage</th>\n",
+ " <th>sql</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>table</td>\n",
+ " <td>hydrants</td>\n",
+ " <td>hydrants</td>\n",
+ " <td>2</td>\n",
+ " <td>CREATE TABLE \"hydrants\" (\\n\"year\" INTEGER,\\n ...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>table</td>\n",
+ " <td>trees</td>\n",
+ " <td>trees</td>\n",
+ " <td>3</td>\n",
+ " <td>CREATE TABLE \"trees\" (\\n\"tree\" TEXT,\\n \"x\" IN...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>table</td>\n",
+ " <td>species</td>\n",
+ " <td>species</td>\n",
+ " <td>4</td>\n",
+ " <td>CREATE TABLE \"species\" (\\n\"code\" TEXT,\\n \"spe...</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " type name tbl_name rootpage \\\n",
+ "0 table hydrants hydrants 2 \n",
+ "1 table trees trees 3 \n",
+ "2 table species species 4 \n",
+ "\n",
+ " sql \n",
+ "0 CREATE TABLE \"hydrants\" (\\n\"year\" INTEGER,\\n ... \n",
+ "1 CREATE TABLE \"trees\" (\\n\"tree\" TEXT,\\n \"x\" IN... \n",
+ "2 CREATE TABLE \"species\" (\\n\"code\" TEXT,\\n \"spe... "
+ ]
+ },
+ "execution_count": 5,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pd.read_sql(\"SELECT * from sqlite_master\", conn)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Remember that one database can hold several tables\n",
+ "hydrants = qry(\"SELECT * FROM hydrants\")\n",
+ "trees = qry(\"SELECT * FROM trees\")\n",
+ "species = qry(\"SELECT * FROM species\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "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>tree</th>\n",
+ " <th>x</th>\n",
+ " <th>y</th>\n",
+ " <th>species</th>\n",
+ " <th>diameter</th>\n",
+ " <th>priority</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>A</td>\n",
+ " <td>10</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>8</td>\n",
+ " <td>71</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>B</td>\n",
+ " <td>20</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>10</td>\n",
+ " <td>100</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>C</td>\n",
+ " <td>30</td>\n",
+ " <td>4</td>\n",
+ " <td>p</td>\n",
+ " <td>6</td>\n",
+ " <td>30</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>D</td>\n",
+ " <td>40</td>\n",
+ " <td>4</td>\n",
+ " <td>p</td>\n",
+ " <td>8</td>\n",
+ " <td>40</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>E</td>\n",
+ " <td>50</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>12</td>\n",
+ " <td>99</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " tree x y species diameter priority\n",
+ "0 A 10 4 m 8 71\n",
+ "1 B 20 4 m 10 100\n",
+ "2 C 30 4 p 6 30\n",
+ "3 D 40 4 p 8 40\n",
+ "4 E 50 4 m 12 99"
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# this is made-up data, but is inspired by an actual City of Madison database!\n",
+ "trees"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "https://data-cityofmadison.opendata.arcgis.com/datasets/b700541a20e446839b18d62426c266a3/explore?location=43.072110%2C-89.405159%2C18.00"
+ ]
+ },
+ {
+ "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>code</th>\n",
+ " <th>species</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>m</td>\n",
+ " <td>maple</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>p</td>\n",
+ " <td>pine</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " code species\n",
+ "0 m maple\n",
+ "1 p pine"
+ ]
+ },
+ "execution_count": 8,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Databases typically split up data into manageable pieces\n",
+ "# It may be more efficient to keep the species codes separate, since they are rarely updated\n",
+ "species"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "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>year</th>\n",
+ " <th>color</th>\n",
+ " <th>style</th>\n",
+ " <th>owner</th>\n",
+ " <th>alt</th>\n",
+ " <th>active</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>1999</td>\n",
+ " <td>red</td>\n",
+ " <td>K-81</td>\n",
+ " <td>private</td>\n",
+ " <td>1179</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>2000</td>\n",
+ " <td>red</td>\n",
+ " <td>M-3</td>\n",
+ " <td>public</td>\n",
+ " <td>1065</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>2001</td>\n",
+ " <td>green</td>\n",
+ " <td>Pacer</td>\n",
+ " <td>private</td>\n",
+ " <td>1058</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>2010</td>\n",
+ " <td>blue</td>\n",
+ " <td>Pacer</td>\n",
+ " <td>public</td>\n",
+ " <td>1081</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>2014</td>\n",
+ " <td>blue</td>\n",
+ " <td>Pacer</td>\n",
+ " <td>public</td>\n",
+ " <td>1052</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>2018</td>\n",
+ " <td>blue</td>\n",
+ " <td>Pacer</td>\n",
+ " <td>public</td>\n",
+ " <td>1109</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " year color style owner alt active\n",
+ "0 1999 red K-81 private 1179 0\n",
+ "1 2000 red M-3 public 1065 0\n",
+ "2 2001 green Pacer private 1058 1\n",
+ "3 2010 blue Pacer public 1081 1\n",
+ "4 2014 blue Pacer public 1052 1\n",
+ "5 2018 blue Pacer public 1109 1"
+ ]
+ },
+ "execution_count": 9,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# The City of Madison keeps data on fire hydrants!\n",
+ "hydrants"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "https://data-cityofmadison.opendata.arcgis.com/datasets/54c4877f16084409849ebd5385e2ee27_6/explore?location=43.071084%2C-89.403280%2C17.00"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 1a. *Without* running this cell - *predict* the output of the following statement"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "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>tree</th>\n",
+ " <th>x</th>\n",
+ " <th>y</th>\n",
+ " <th>species</th>\n",
+ " <th>diameter</th>\n",
+ " <th>priority</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>B</td>\n",
+ " <td>20</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>10</td>\n",
+ " <td>100</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>E</td>\n",
+ " <td>50</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>12</td>\n",
+ " <td>99</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " tree x y species diameter priority\n",
+ "1 B 20 4 m 10 100\n",
+ "4 E 50 4 m 12 99"
+ ]
+ },
+ "execution_count": 10,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "trees[trees[\"priority\"] > 90] "
+ ]
+ },
+ {
+ "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>x</th>\n",
+ " <th>y</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>20</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>50</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " x y\n",
+ "1 20 4\n",
+ "4 50 4"
+ ]
+ },
+ "execution_count": 11,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "trees[trees[\"priority\"] > 90] [[\"x\", \"y\"]] # show only the columns in this list"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 1b. *Convert* the statement to an equivalent *SQL* query."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "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>tree</th>\n",
+ " <th>x</th>\n",
+ " <th>y</th>\n",
+ " <th>species</th>\n",
+ " <th>diameter</th>\n",
+ " <th>priority</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>A</td>\n",
+ " <td>10</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>8</td>\n",
+ " <td>71</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>B</td>\n",
+ " <td>20</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>10</td>\n",
+ " <td>100</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>C</td>\n",
+ " <td>30</td>\n",
+ " <td>4</td>\n",
+ " <td>p</td>\n",
+ " <td>6</td>\n",
+ " <td>30</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>D</td>\n",
+ " <td>40</td>\n",
+ " <td>4</td>\n",
+ " <td>p</td>\n",
+ " <td>8</td>\n",
+ " <td>40</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>E</td>\n",
+ " <td>50</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>12</td>\n",
+ " <td>99</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " tree x y species diameter priority\n",
+ "0 A 10 4 m 8 71\n",
+ "1 B 20 4 m 10 100\n",
+ "2 C 30 4 p 6 30\n",
+ "3 D 40 4 p 8 40\n",
+ "4 E 50 4 m 12 99"
+ ]
+ },
+ "execution_count": 12,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "trees"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "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>x</th>\n",
+ " <th>y</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>20</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>50</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " x y\n",
+ "0 20 4\n",
+ "1 50 4"
+ ]
+ },
+ "execution_count": 13,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "qry(\"select x,y from trees where priority > 90\") "
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "----\n",
+ "### 2a. *Predict* the output of the following *SQL* query"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "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>tree</th>\n",
+ " <th>x</th>\n",
+ " <th>y</th>\n",
+ " <th>species</th>\n",
+ " <th>diameter</th>\n",
+ " <th>priority</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>A</td>\n",
+ " <td>10</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>8</td>\n",
+ " <td>71</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>B</td>\n",
+ " <td>20</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>10</td>\n",
+ " <td>100</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>C</td>\n",
+ " <td>30</td>\n",
+ " <td>4</td>\n",
+ " <td>p</td>\n",
+ " <td>6</td>\n",
+ " <td>30</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>D</td>\n",
+ " <td>40</td>\n",
+ " <td>4</td>\n",
+ " <td>p</td>\n",
+ " <td>8</td>\n",
+ " <td>40</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>E</td>\n",
+ " <td>50</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>12</td>\n",
+ " <td>99</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " tree x y species diameter priority\n",
+ "0 A 10 4 m 8 71\n",
+ "1 B 20 4 m 10 100\n",
+ "2 C 30 4 p 6 30\n",
+ "3 D 40 4 p 8 40\n",
+ "4 E 50 4 m 12 99"
+ ]
+ },
+ "execution_count": 14,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "trees"
+ ]
+ },
+ {
+ "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>x+y</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>24</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>54</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " x+y\n",
+ "0 14\n",
+ "1 24\n",
+ "2 54"
+ ]
+ },
+ "execution_count": 15,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "qry(\"SELECT x+y FROM trees WHERE species = 'm'\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 2b. *Convert* the query into an equivalent *pandas* statement."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 10\n",
+ "1 20\n",
+ "2 30\n",
+ "3 40\n",
+ "4 50\n",
+ "Name: x, dtype: int64"
+ ]
+ },
+ "execution_count": 16,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Series\n",
+ "trees[\"x\"]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 10\n",
+ "1 20\n",
+ "4 50\n",
+ "Name: x, dtype: int64"
+ ]
+ },
+ "execution_count": 17,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Series with Boolean indexing applied\n",
+ "trees[\"x\"] [trees[\"species\"] == 'm']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 4\n",
+ "1 4\n",
+ "4 4\n",
+ "Name: y, dtype: int64"
+ ]
+ },
+ "execution_count": 18,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "trees[\"y\"][trees[\"species\"] == 'm']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 14\n",
+ "1 24\n",
+ "4 54\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 19,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# because the two Series have matching indices, we can add them\n",
+ "# this answer is acceptable on a quiz/exam\n",
+ "trees[\"x\"][trees[\"species\"] == 'm'] + trees[\"y\"][trees[\"species\"] == 'm']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "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>x+y</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>24</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>54</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " x+y\n",
+ "0 14\n",
+ "1 24\n",
+ "4 54"
+ ]
+ },
+ "execution_count": 20,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# if you want to get fancy, you can turn a Series into a DataFrame and add column names\n",
+ "result2 = pd.DataFrame(trees[\"x\"][trees[\"species\"] == 'm'] + trees[\"y\"][trees[\"species\"] == 'm'])\n",
+ "result2.columns = [\"x+y\"]\n",
+ "result2"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "----\n",
+ "### 3a. *Predict* the output of the following *pandas* statements"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "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>code</th>\n",
+ " <th>species</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>m</td>\n",
+ " <td>maple</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>p</td>\n",
+ " <td>pine</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " code species\n",
+ "0 m maple\n",
+ "1 p pine"
+ ]
+ },
+ "execution_count": 21,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "species"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 22,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# species[\"code\"] [species[\"species\"]==\"maple\"] .iloc[0]\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 23,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 m\n",
+ "1 p\n",
+ "Name: code, dtype: object"
+ ]
+ },
+ "execution_count": 23,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# this is a Series\n",
+ "species[\"code\"]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 24,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 m\n",
+ "Name: code, dtype: object"
+ ]
+ },
+ "execution_count": 24,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Series with Boolean indexing applied\n",
+ "species[\"code\"] [species[\"species\"]==\"maple\"]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 25,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'m'"
+ ]
+ },
+ "execution_count": 25,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Series with Boolean indexing applied get the value at integer location 0\n",
+ "species[\"code\"] [species[\"species\"]==\"maple\"] .iloc[0]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 26,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'m'"
+ ]
+ },
+ "execution_count": 26,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "cd = species[\"code\"][species[\"species\"]==\"maple\"].iloc[0]\n",
+ "cd"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 27,
+ "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>tree</th>\n",
+ " <th>x</th>\n",
+ " <th>y</th>\n",
+ " <th>species</th>\n",
+ " <th>diameter</th>\n",
+ " <th>priority</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>A</td>\n",
+ " <td>10</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>8</td>\n",
+ " <td>71</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>B</td>\n",
+ " <td>20</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>10</td>\n",
+ " <td>100</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>E</td>\n",
+ " <td>50</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>12</td>\n",
+ " <td>99</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " tree x y species diameter priority\n",
+ "0 A 10 4 m 8 71\n",
+ "1 B 20 4 m 10 100\n",
+ "4 E 50 4 m 12 99"
+ ]
+ },
+ "execution_count": 27,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# DataFrame with Boolean Indexing\n",
+ "trees [trees[\"species\"] == cd]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 28,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 A\n",
+ "1 B\n",
+ "4 E\n",
+ "Name: tree, dtype: object"
+ ]
+ },
+ "execution_count": 28,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# DataFrame with Boolean Indexing with column selection\n",
+ "trees [trees[\"species\"] == cd] ['tree']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 3b. *Convert* the statements into an equivalent *SQL* query."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 29,
+ "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>code</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>m</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " code\n",
+ "0 m"
+ ]
+ },
+ "execution_count": 29,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "qry(\"select code from species where species = 'maple' \") "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 30,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 m\n",
+ "Name: code, dtype: object"
+ ]
+ },
+ "execution_count": 30,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# DataFrame with column selection\n",
+ "qry(\"select code from species where species = 'maple' \") ['code']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 31,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'m'"
+ ]
+ },
+ "execution_count": 31,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# DataFrame with column selection get the value at iloc 0\n",
+ "cd = qry(\"select code from species where species = 'maple' \") ['code'] .iloc[0]\n",
+ "cd\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 32,
+ "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>tree</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>A</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>B</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>E</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " tree\n",
+ "0 A\n",
+ "1 B\n",
+ "2 E"
+ ]
+ },
+ "execution_count": 32,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# hard coding \n",
+ "qry(\"select tree from trees where species = 'm'\" ) "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 33,
+ "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>tree</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>A</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>B</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>E</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " tree\n",
+ "0 A\n",
+ "1 B\n",
+ "2 E"
+ ]
+ },
+ "execution_count": 33,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# not hard coding\n",
+ "qry(\"select tree from trees where species = '{}'\".format(cd))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "----\n",
+ "### 4a. *Predict* the output of the following query"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 34,
+ "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>species</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>m</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>m</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>m</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>p</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>p</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " species\n",
+ "0 m\n",
+ "1 m\n",
+ "2 m\n",
+ "3 p\n",
+ "4 p"
+ ]
+ },
+ "execution_count": 34,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "qry(\"SELECT species FROM trees ORDER BY priority DESC\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 4.b *Convert* the query code to *Pandas*"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 35,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "1 m\n",
+ "4 m\n",
+ "0 m\n",
+ "3 p\n",
+ "2 p\n",
+ "Name: species, dtype: object"
+ ]
+ },
+ "execution_count": 35,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# DataFrame soted by priority # with column selection\n",
+ "trees.sort_values(\"priority\", ascending = False) [\"species\"]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "----\n",
+ "### 5a. *Predict* the output of the following code"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 36,
+ "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>tree</th>\n",
+ " <th>x</th>\n",
+ " <th>y</th>\n",
+ " <th>species</th>\n",
+ " <th>diameter</th>\n",
+ " <th>priority</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>A</td>\n",
+ " <td>10</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>8</td>\n",
+ " <td>71</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>B</td>\n",
+ " <td>20</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>10</td>\n",
+ " <td>100</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>C</td>\n",
+ " <td>30</td>\n",
+ " <td>4</td>\n",
+ " <td>p</td>\n",
+ " <td>6</td>\n",
+ " <td>30</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>D</td>\n",
+ " <td>40</td>\n",
+ " <td>4</td>\n",
+ " <td>p</td>\n",
+ " <td>8</td>\n",
+ " <td>40</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>E</td>\n",
+ " <td>50</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>12</td>\n",
+ " <td>99</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " tree x y species diameter priority\n",
+ "0 A 10 4 m 8 71\n",
+ "1 B 20 4 m 10 100\n",
+ "2 C 30 4 p 6 30\n",
+ "3 D 40 4 p 8 40\n",
+ "4 E 50 4 m 12 99"
+ ]
+ },
+ "execution_count": 36,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "trees"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 37,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# list(qry(\"SELECT tree, priority FROM trees ORDER BY priority DESC LIMIT 1\").iloc[0])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 38,
+ "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>tree</th>\n",
+ " <th>priority</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>B</td>\n",
+ " <td>100</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " tree priority\n",
+ "0 B 100"
+ ]
+ },
+ "execution_count": 38,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "qry(\"SELECT tree, priority FROM trees ORDER BY priority DESC LIMIT 1\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 39,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "tree B\n",
+ "priority 100\n",
+ "Name: 0, dtype: object"
+ ]
+ },
+ "execution_count": 39,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "qry(\"SELECT tree, priority FROM trees ORDER BY priority DESC LIMIT 1\").iloc[0]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 40,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "['B', 100]"
+ ]
+ },
+ "execution_count": 40,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# list gets the values only\n",
+ "list(qry(\"SELECT tree, priority FROM trees ORDER BY priority DESC LIMIT 1\").iloc[0])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 5.b *Convert* the above code to *Pandas*"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 41,
+ "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>tree</th>\n",
+ " <th>x</th>\n",
+ " <th>y</th>\n",
+ " <th>species</th>\n",
+ " <th>diameter</th>\n",
+ " <th>priority</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>B</td>\n",
+ " <td>20</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>10</td>\n",
+ " <td>100</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>E</td>\n",
+ " <td>50</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>12</td>\n",
+ " <td>99</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>A</td>\n",
+ " <td>10</td>\n",
+ " <td>4</td>\n",
+ " <td>m</td>\n",
+ " <td>8</td>\n",
+ " <td>71</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>D</td>\n",
+ " <td>40</td>\n",
+ " <td>4</td>\n",
+ " <td>p</td>\n",
+ " <td>8</td>\n",
+ " <td>40</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>C</td>\n",
+ " <td>30</td>\n",
+ " <td>4</td>\n",
+ " <td>p</td>\n",
+ " <td>6</td>\n",
+ " <td>30</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " tree x y species diameter priority\n",
+ "1 B 20 4 m 10 100\n",
+ "4 E 50 4 m 12 99\n",
+ "0 A 10 4 m 8 71\n",
+ "3 D 40 4 p 8 40\n",
+ "2 C 30 4 p 6 30"
+ ]
+ },
+ "execution_count": 41,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "trees.sort_values(\"priority\", ascending=False)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 42,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "tree B\n",
+ "x 20\n",
+ "y 4\n",
+ "species m\n",
+ "diameter 10\n",
+ "priority 100\n",
+ "Name: 1, dtype: object"
+ ]
+ },
+ "execution_count": 42,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# DataFrame # grab the first row\n",
+ "trees.sort_values(\"priority\", ascending=False) .iloc[0]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 43,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "tree B\n",
+ "priority 100\n",
+ "Name: 1, dtype: object"
+ ]
+ },
+ "execution_count": 43,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# DataFrame # grab the first row #slicing by certain indices\n",
+ "trees.sort_values(\"priority\", ascending=False) .iloc[0] [['tree', 'priority']]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 44,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "['B', 100]"
+ ]
+ },
+ "execution_count": 44,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# list gets the values only\n",
+ "list(trees.sort_values(\"priority\", ascending=False).iloc[0] [['tree', 'priority']] )"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "----\n",
+ "### 6a. *Predict* the output of the following code"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 45,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# qry(\"\"\"SELECT COUNT(SPECIES) AS c1,\n",
+ "# COUNT(DISTINCT SPECIES) as c2\n",
+ "# FROM trees\"\"\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 46,
+ "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>c1</th>\n",
+ " <th>c2</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>5</td>\n",
+ " <td>2</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " c1 c2\n",
+ "0 5 2"
+ ]
+ },
+ "execution_count": 46,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "qry(\"\"\"SELECT COUNT(SPECIES) AS c1,\n",
+ " COUNT(DISTINCT SPECIES) as c2\n",
+ " FROM trees\"\"\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 6b. *Convert* the above code to *Pandas*"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 47,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "5"
+ ]
+ },
+ "execution_count": 47,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "c1 = len(trees)\n",
+ "c1"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 48,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "m 3\n",
+ "p 2\n",
+ "Name: species, dtype: int64"
+ ]
+ },
+ "execution_count": 48,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "trees[\"species\"].value_counts()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 49,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "2"
+ ]
+ },
+ "execution_count": 49,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "c2 = len(trees[\"species\"].value_counts())\n",
+ "c2"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 50,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[5, 2]"
+ ]
+ },
+ "execution_count": 50,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# this answer is acceptable\n",
+ "[c1, c2]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 51,
+ "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>c1</th>\n",
+ " <th>c2</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>5</td>\n",
+ " <td>2</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " c1 c2\n",
+ "0 5 2"
+ ]
+ },
+ "execution_count": 51,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# A dataframe can be made from a dict of lists\n",
+ "d = {\"c1\":[c1], \"c2\":[c2]}\n",
+ "pd.DataFrame(d)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "----\n",
+ "### 7a. *Predict* the output of the following code"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 52,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# qry(\"\"\"SELECT species, COUNT(SPECIES) AS count,\n",
+ "# AVG(diameter) AS size\n",
+ "# FROM trees\n",
+ "# GROUP BY species ORDER BY count DESC\"\"\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 53,
+ "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>species</th>\n",
+ " <th>count</th>\n",
+ " <th>size</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>m</td>\n",
+ " <td>3</td>\n",
+ " <td>10.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>p</td>\n",
+ " <td>2</td>\n",
+ " <td>7.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " species count size\n",
+ "0 m 3 10.0\n",
+ "1 p 2 7.0"
+ ]
+ },
+ "execution_count": 53,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "qry(\"\"\"SELECT species, COUNT(SPECIES) AS count,\n",
+ " AVG(diameter) AS size\n",
+ " FROM trees\n",
+ " GROUP BY species ORDER BY count DESC\"\"\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 7b. *Convert* the above code to *Pandas*"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 54,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "['m', 'p']"
+ ]
+ },
+ "execution_count": 54,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# part 1: species\n",
+ "species_list = list(pd.unique(trees['species']))\n",
+ "species_list"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 55,
+ "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>x</th>\n",
+ " <th>y</th>\n",
+ " <th>diameter</th>\n",
+ " <th>priority</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>species</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>m</th>\n",
+ " <td>26.666667</td>\n",
+ " <td>4.0</td>\n",
+ " <td>10.0</td>\n",
+ " <td>90.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>p</th>\n",
+ " <td>35.000000</td>\n",
+ " <td>4.0</td>\n",
+ " <td>7.0</td>\n",
+ " <td>35.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " x y diameter priority\n",
+ "species \n",
+ "m 26.666667 4.0 10.0 90.0\n",
+ "p 35.000000 4.0 7.0 35.0"
+ ]
+ },
+ "execution_count": 55,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "trees.groupby(\"species\").mean()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 56,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[10.0, 7.0]"
+ ]
+ },
+ "execution_count": 56,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# part 2: size\n",
+ "size_list = list(trees.groupby(\"species\").mean()[\"diameter\"]) \n",
+ "size_list"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 57,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[3, 2]"
+ ]
+ },
+ "execution_count": 57,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# part 3: counts\n",
+ "count_list = list(trees['species'].value_counts())\n",
+ "count_list"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 58,
+ "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>species</th>\n",
+ " <th>count</th>\n",
+ " <th>size</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>m</td>\n",
+ " <td>3</td>\n",
+ " <td>10.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>p</td>\n",
+ " <td>2</td>\n",
+ " <td>7.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " species count size\n",
+ "0 m 3 10.0\n",
+ "1 p 2 7.0"
+ ]
+ },
+ "execution_count": 58,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# part 4: make a DataFrame from a dict of lists\n",
+ "pd.DataFrame({\"species\": species_list,\n",
+ " \"count\": count_list,\n",
+ " \"size\": size_list})"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "----\n",
+ "# Additional Exercises: \n",
+ "### *Predict* the output of the following statements"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 59,
+ "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>year</th>\n",
+ " <th>color</th>\n",
+ " <th>style</th>\n",
+ " <th>owner</th>\n",
+ " <th>alt</th>\n",
+ " <th>active</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>1999</td>\n",
+ " <td>red</td>\n",
+ " <td>K-81</td>\n",
+ " <td>private</td>\n",
+ " <td>1179</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>2000</td>\n",
+ " <td>red</td>\n",
+ " <td>M-3</td>\n",
+ " <td>public</td>\n",
+ " <td>1065</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>2001</td>\n",
+ " <td>green</td>\n",
+ " <td>Pacer</td>\n",
+ " <td>private</td>\n",
+ " <td>1058</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>2010</td>\n",
+ " <td>blue</td>\n",
+ " <td>Pacer</td>\n",
+ " <td>public</td>\n",
+ " <td>1081</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>2014</td>\n",
+ " <td>blue</td>\n",
+ " <td>Pacer</td>\n",
+ " <td>public</td>\n",
+ " <td>1052</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>2018</td>\n",
+ " <td>blue</td>\n",
+ " <td>Pacer</td>\n",
+ " <td>public</td>\n",
+ " <td>1109</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " year color style owner alt active\n",
+ "0 1999 red K-81 private 1179 0\n",
+ "1 2000 red M-3 public 1065 0\n",
+ "2 2001 green Pacer private 1058 1\n",
+ "3 2010 blue Pacer public 1081 1\n",
+ "4 2014 blue Pacer public 1052 1\n",
+ "5 2018 blue Pacer public 1109 1"
+ ]
+ },
+ "execution_count": 59,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "\n",
+ "hydrants"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 60,
+ "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>color</th>\n",
+ " <th>year</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>blue</td>\n",
+ " <td>2010</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>blue</td>\n",
+ " <td>2014</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>blue</td>\n",
+ " <td>2018</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " color year\n",
+ "0 blue 2010\n",
+ "1 blue 2014\n",
+ "2 blue 2018"
+ ]
+ },
+ "execution_count": 60,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "qry(\"SELECT color, year FROM hydrants WHERE color = 'blue' \")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 61,
+ "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>color</th>\n",
+ " <th>year</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>blue</td>\n",
+ " <td>2010</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>blue</td>\n",
+ " <td>2014</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>blue</td>\n",
+ " <td>2018</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " color year\n",
+ "3 blue 2010\n",
+ "4 blue 2014\n",
+ "5 blue 2018"
+ ]
+ },
+ "execution_count": 61,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df = qry(\"SELECT color, year FROM hydrants\")\n",
+ "df[df.color == \"blue\"]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 62,
+ "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>year</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>2001</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " year\n",
+ "0 2001"
+ ]
+ },
+ "execution_count": 62,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "qry(\"SELECT year FROM hydrants WHERE owner='private' AND active\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 63,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "2 Pacer\n",
+ "3 Pacer\n",
+ "4 Pacer\n",
+ "5 Pacer\n",
+ "Name: style, dtype: object"
+ ]
+ },
+ "execution_count": 63,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df = qry(\"SELECT year, style, active FROM hydrants\")\n",
+ "df[df.active == 1][\"style\"]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 64,
+ "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>year</th>\n",
+ " <th>color</th>\n",
+ " <th>style</th>\n",
+ " <th>owner</th>\n",
+ " <th>alt</th>\n",
+ " <th>active</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>1999</td>\n",
+ " <td>red</td>\n",
+ " <td>K-81</td>\n",
+ " <td>private</td>\n",
+ " <td>1179</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>2000</td>\n",
+ " <td>red</td>\n",
+ " <td>M-3</td>\n",
+ " <td>public</td>\n",
+ " <td>1065</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>2001</td>\n",
+ " <td>green</td>\n",
+ " <td>Pacer</td>\n",
+ " <td>private</td>\n",
+ " <td>1058</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>2010</td>\n",
+ " <td>blue</td>\n",
+ " <td>Pacer</td>\n",
+ " <td>public</td>\n",
+ " <td>1081</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>2014</td>\n",
+ " <td>blue</td>\n",
+ " <td>Pacer</td>\n",
+ " <td>public</td>\n",
+ " <td>1052</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>2018</td>\n",
+ " <td>blue</td>\n",
+ " <td>Pacer</td>\n",
+ " <td>public</td>\n",
+ " <td>1109</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " year color style owner alt active\n",
+ "0 1999 red K-81 private 1179 0\n",
+ "1 2000 red M-3 public 1065 0\n",
+ "2 2001 green Pacer private 1058 1\n",
+ "3 2010 blue Pacer public 1081 1\n",
+ "4 2014 blue Pacer public 1052 1\n",
+ "5 2018 blue Pacer public 1109 1"
+ ]
+ },
+ "execution_count": 64,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "hydrants"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 65,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "blue 3\n",
+ "red 2\n",
+ "green 1\n",
+ "Name: color, dtype: int64"
+ ]
+ },
+ "execution_count": 65,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "hydrants[\"color\"].value_counts()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 66,
+ "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>color</th>\n",
+ " <th>COUNT(*)</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>blue</td>\n",
+ " <td>3</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>green</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " color COUNT(*)\n",
+ "0 blue 3\n",
+ "1 green 1"
+ ]
+ },
+ "execution_count": 66,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "qry(\"\"\"SELECT color, COUNT(*) FROM hydrants WHERE active GROUP BY color\"\"\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 67,
+ "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>color</th>\n",
+ " <th>count</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>blue</td>\n",
+ " <td>3</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>red</td>\n",
+ " <td>2</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " color count\n",
+ "0 blue 3\n",
+ "1 red 2"
+ ]
+ },
+ "execution_count": 67,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "qry(\"\"\"SELECT color, COUNT(*) AS count FROM hydrants GROUP BY color HAVING count > 1\"\"\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 68,
+ "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>color</th>\n",
+ " <th>count</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>green</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>red</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " color count\n",
+ "0 green 1\n",
+ "1 red 1"
+ ]
+ },
+ "execution_count": 68,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "qry(\"\"\"SELECT color, COUNT(*) AS count\n",
+ " FROM hydrants WHERE year >= 2000\n",
+ " GROUP BY color HAVING count < 2\"\"\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "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": "3.9.7"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/s24/Louis_Lecture_Notes/36_Database3/Lec36_WorksheetGuided.ipynb b/s24/Louis_Lecture_Notes/36_Database3/Lec36_WorksheetGuided.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..cbb06654ec539737dbf02c339c0536a338fe7daa
--- /dev/null
+++ b/s24/Louis_Lecture_Notes/36_Database3/Lec36_WorksheetGuided.ipynb
@@ -0,0 +1,839 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# ignore this cell - it makes the emphasized text red and uses the full width of the screen\n",
+ "from IPython.core.display import HTML\n",
+ "HTML('<style>em { color: red; }</style> <style>.container {width:100% !important; }</style>')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import sqlite3\n",
+ "import pandas as pd"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "conn = sqlite3.connect(\"worksheet.db\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# this function gives us a shortcut to making queries\n",
+ "# instead of typing all that code over and over again, we just call qry with our SQL\n",
+ "# it assumes we have access to a connection object, conn\n",
+ "\n",
+ "def qry(QUERY):\n",
+ " '''QUERY is a string containing SQL, conn is a global connection variable'''\n",
+ " return pd.read_sql(QUERY, conn)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "pd.read_sql(\"SELECT * from sqlite_master\", conn)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Remember that one database can hold several tables\n",
+ "hydrants = qry(\"SELECT * FROM hydrants\")\n",
+ "trees = qry(\"SELECT * FROM trees\")\n",
+ "species = qry(\"SELECT * FROM species\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# this is made-up data, but is inspired by an actual City of Madison database!\n",
+ "trees"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "https://data-cityofmadison.opendata.arcgis.com/datasets/b700541a20e446839b18d62426c266a3/explore?location=43.072110%2C-89.405159%2C18.00"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Databases typically split up data into manageable pieces\n",
+ "# It may be more efficient to keep the species codes separate, since they are rarely updated\n",
+ "species"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# The City of Madison keeps data on fire hydrants!\n",
+ "hydrants"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "https://data-cityofmadison.opendata.arcgis.com/datasets/54c4877f16084409849ebd5385e2ee27_6/explore?location=43.071084%2C-89.403280%2C17.00"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 1a. *Without* running this cell - *predict* the output of the following statement"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#trees[trees[\"priority\"] > 90] "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# DataFrame with Boolean Indexing # show only the columns in this list\n",
+ "#trees[trees[\"priority\"] > 90] [[\"x\", \"y\"]] "
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 1b. *Convert* the statement to an equivalent *SQL* querry."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "trees"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# your answer here"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "----\n",
+ "### 2a. *Predict* the output of the following *SQL* querry"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "trees"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#qry(\"SELECT x+y FROM trees WHERE species = 'm'\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 2b. *Convert* the querry into an equivalent *pandas* statement."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Series\n",
+ "trees[\"x\"]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Series with Boolean indexing applied\n",
+ "#trees[\"x\"] [trees[\"species\"] == 'm']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Do the same for y "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# because the two Series have matching indices, we can add them\n",
+ "# this answer is acceptable on a quiz/exam\n",
+ "#trees[\"x\"][trees[\"species\"] == 'm'] + trees[\"y\"][trees[\"species\"] == 'm']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# if you want to get fancy, you can turn a Series into a DataFrame and add column names\n",
+ "#result2 = pd.DataFrame(trees[\"x\"][trees[\"species\"] == 'm'] + trees[\"y\"][trees[\"species\"] == 'm'])\n",
+ "#result2.columns = [\"x+y\"]\n",
+ "#result2"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "----\n",
+ "### 3a. *Predict* the output of the following *pandas* statements"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "species"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# species[\"code\"] [species[\"species\"]==\"maple\"] .iloc[0]\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# this is a Series\n",
+ "#species[\"code\"]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Series with Boolean indexing applied\n",
+ "# species[\"code\"] [species[\"species\"]==\"maple\"]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Series with Boolean indexing applied get the value at integer location 0\n",
+ "# species[\"code\"] [species[\"species\"]==\"maple\"] .iloc[0]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "cd = species[\"code\"][species[\"species\"]==\"maple\"].iloc[0]\n",
+ "cd"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# DataFrame with Boolean Indexing\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# DataFrame with Boolean Indexing with column selection\n",
+ "# trees [trees[\"species\"] == cd] ['tree']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 3b. *Convert* the statements into an equivalent *SQL* querry."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "qry(\"select code from species where species = 'maple' \") "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# DataFrame with column selection\n",
+ "#qry(\"select code from species where species = 'maple' \") ['code']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# DataFrame with column selection get the value at iloc 0\n",
+ "#cd = qry(\"select code from species where species = 'maple' \") ['code'] .iloc[0]\n",
+ "#cd\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# hard coding \n",
+ "#qry(\"select tree from trees where species = 'm'\" ) "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# not hard coding\n",
+ "#qry(\"select tree from trees where species = '{}'\".format(cd))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "----\n",
+ "### 4a. *Predict* the output of the following querry"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#qry(\"SELECT species FROM trees ORDER BY priority DESC\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 4.b *Convert* the querry code to *Pandas*"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# DataFrame soted by priority # with column selection\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "----\n",
+ "### 5a. *Predict* the output of the following code"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "trees"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# list(qry(\"SELECT tree, priority FROM trees ORDER BY priority DESC LIMIT 1\").iloc[0])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# qry(\"SELECT tree, priority FROM trees ORDER BY priority DESC LIMIT 1\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#qry(\"SELECT tree, priority FROM trees ORDER BY priority DESC LIMIT 1\").iloc[0]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# list gets the values only\n",
+ "#list(qry(\"SELECT tree, priority FROM trees ORDER BY priority DESC LIMIT 1\").iloc[0])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 5.b *Convert* the above code to *Pandas*"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "trees.sort_values(\"priority\", ascending=False)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# DataFrame # grab the first row\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# DataFrame # grab the first row #slicing by certain indices\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# list gets the values only\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "----\n",
+ "### 6a. *Predict* the output of the following code"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# qry(\"\"\"SELECT COUNT(SPECIES) AS c1,\n",
+ "# COUNT(DISTINCT SPECIES) as c2\n",
+ "# FROM trees\"\"\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#qry(\"\"\"SELECT COUNT(SPECIES) AS c1,\n",
+ "# COUNT(DISTINCT SPECIES) as c2\n",
+ "# FROM trees\"\"\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 6b. *Convert* the above code to *Pandas*"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# get the 5\n",
+ "c1 = None\n",
+ "c1"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# get the 2\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "c2 = None\n",
+ "#c2"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# this answer is acceptable\n",
+ "[c1, c2]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# A dataframe can be made from a dict of lists\n",
+ "d = {\"c1\":[c1], \"c2\":[c2]}\n",
+ "pd.DataFrame(d)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "----\n",
+ "### 7a. *Predict* the output of the following code"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# qry(\"\"\"SELECT species, COUNT(SPECIES) AS count,\n",
+ "# AVG(diameter) AS size\n",
+ "# FROM trees\n",
+ "# GROUP BY species ORDER BY count DESC\"\"\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 7b. *Convert* the above code to *Pandas*"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# part 1: species list\n",
+ "# species_list = list(pd.unique(trees['species']))\n",
+ "species_list"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# trees.groupby(\"species\").mean(numeric_only=True)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# part 2: size\n",
+ "#size_list = list(trees.groupby(\"species\").mean(numeric_only=True)[\"diameter\"]) \n",
+ "size_list"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# part 3: counts\n",
+ "#count_list = list(trees['species'].value_counts())\n",
+ "count_list"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# part 4: make a DataFrame from a dict of lists\n",
+ "pd.DataFrame({\"species\": species_list,\n",
+ " \"count\": count_list,\n",
+ " \"size\": size_list})"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "----\n",
+ "# Additional Exercises: \n",
+ "### *Predict* the output of the following statements"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "\n",
+ "hydrants"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#qry(\"SELECT color, year FROM hydrants WHERE color = 'blue' \")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#df = qry(\"SELECT color, year FROM hydrants\")\n",
+ "#df[df.color == \"blue\"]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#qry(\"SELECT year FROM hydrants WHERE owner='private' AND active\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#df = qry(\"SELECT year, style, active FROM hydrants\")\n",
+ "#df[df.active == 1][\"style\"]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "hydrants"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#hydrants[\"color\"].value_counts()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#qry(\"\"\"SELECT color, COUNT(*) FROM hydrants WHERE active GROUP BY color\"\"\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#qry(\"\"\"SELECT color, COUNT(*) AS count FROM hydrants GROUP BY color HAVING count > 1\"\"\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#qry(\"\"\"SELECT color, COUNT(*) AS count\n",
+ " FROM hydrants WHERE year >= 2000\n",
+ " GROUP BY color HAVING count < 2\"\"\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "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": "3.11.5"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/s24/Louis_Lecture_Notes/36_Database3/worksheet.db b/s24/Louis_Lecture_Notes/36_Database3/worksheet.db
new file mode 100644
index 0000000000000000000000000000000000000000..3607f4107144d2a559212f8e1813b005c499747c
Binary files /dev/null and b/s24/Louis_Lecture_Notes/36_Database3/worksheet.db differ