diff --git a/sum23/lecture_materials/23_Plotting2/Exam Review.ipynb b/sum23/lecture_materials/23_Plotting2/Exam Review.ipynb
index f74342769b636570c12a9f678a3ce9026702bf86..46387bf155989469d7691f263e598205db8c6638 100644
--- a/sum23/lecture_materials/23_Plotting2/Exam Review.ipynb
+++ b/sum23/lecture_materials/23_Plotting2/Exam Review.ipynb
@@ -2,19 +2,20 @@
"cells": [
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 35,
"id": "c3f52922",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from bs4 import BeautifulSoup\n",
- "import sqlite3"
+ "import sqlite3\n",
+ "import os"
]
},
{
"cell_type": "markdown",
- "id": "5c9d1d79",
+ "id": "fbb93a47",
"metadata": {},
"source": [
"# Big picture review\n",
@@ -22,12 +23,47 @@
]
},
{
- "cell_type": "code",
- "execution_count": null,
- "id": "69afd613",
+ "cell_type": "markdown",
+ "id": "e22a2d80",
"metadata": {},
- "outputs": [],
- "source": []
+ "source": [
+ "Pandas - a library that is commonly used with python for data science. (Specific to python)\n",
+ "\n",
+ "Series\n",
+ "* Pandas object\n",
+ "* Has index, values, and integer positions\n",
+ "* Can make a series from a list\n",
+ " * \\[1,4,9\\] can become a series. When it does, 1,4,9 are the values. The index and the IP will be the same, 0,1,2\n",
+ "* Can make a series from a dictionary\n",
+ " * {'a':1, 'b':4, 'c':9} will have 1,4,9 as the values, and 'a','b','c' will be the index, and the IP will be 0,1,2\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "bc397564",
+ "metadata": {},
+ "source": [
+ "Dataframe\n",
+ "* Also a Pandas object\n",
+ "* If a series is a list or a dictionary, then a dataframe is like a list of lists, or a list of dictionaries, or a dictionaries of lists, or a d of d. (e.g., would be loaded in from CSV or JSON)\n",
+ "* Still have an index and IP. There are different columns with different values\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "09598b13",
+ "metadata": {},
+ "source": [
+ "SQL - a query language that is commonly used iwth databases. Separate from python but there are libraries that let us integrate SQL with python\n",
+ "\n",
+ "Database - \n",
+ "* A CS concept, a way of storing data in an organized way\n",
+ "* Can have multiple tables. Each table has a name. The columns in each table all have names. Each column has a specific data type and there are no missing values (but values can be \"fake\", like NaN).\n",
+ "* SQL is a language that allows us to work with databases\n",
+ "* When we use SQL from within python, using pd.read_sql function, it returns as a pandas dataframe\n",
+ "* SQL has very different syntax from python (and pandas)"
+ ]
},
{
"cell_type": "markdown",
@@ -39,10 +75,83 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 2,
"id": "4ebb9401",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Name</th>\n",
+ " <th>color</th>\n",
+ " <th>length</th>\n",
+ " <th>habitat</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>fish</td>\n",
+ " <td>green</td>\n",
+ " <td>8</td>\n",
+ " <td>water</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>cat</td>\n",
+ " <td>brown</td>\n",
+ " <td>15</td>\n",
+ " <td>house</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>tiger</td>\n",
+ " <td>orange</td>\n",
+ " <td>48</td>\n",
+ " <td>jungle</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>dog</td>\n",
+ " <td>yellow</td>\n",
+ " <td>28</td>\n",
+ " <td>house</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Name color length habitat\n",
+ "0 fish green 8 water\n",
+ "1 cat brown 15 house\n",
+ "2 tiger orange 48 jungle\n",
+ "3 dog yellow 28 house"
+ ]
+ },
+ "execution_count": 2,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"fish = {\"Name\":\"fish\", \"color\":\"green\", \"length\":8, \"habitat\":'water'}\n",
"cat = {\"Name\":\"cat\",\"color\":\"brown\",\"length\":15,\"habitat\":'house'}\n",
@@ -55,52 +164,666 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 5,
"id": "35f32b68",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 water\n",
+ "1 house\n",
+ "2 jungle\n",
+ "3 house\n",
+ "Name: habitat, dtype: object"
+ ]
+ },
+ "execution_count": 5,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "# DataFrame vs Series"
+ "# DataFrame vs Series\n",
+ "animals['habitat']\n",
+ "animals.habitat"
]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 6,
+ "id": "680f38dc",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 False\n",
+ "1 True\n",
+ "2 False\n",
+ "3 True\n",
+ "Name: habitat, dtype: bool"
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "animals['habitat'] == 'house'"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
"id": "a7bb549c",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Name</th>\n",
+ " <th>color</th>\n",
+ " <th>length</th>\n",
+ " <th>habitat</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>cat</td>\n",
+ " <td>brown</td>\n",
+ " <td>15</td>\n",
+ " <td>house</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>dog</td>\n",
+ " <td>yellow</td>\n",
+ " <td>28</td>\n",
+ " <td>house</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Name color length habitat\n",
+ "1 cat brown 15 house\n",
+ "3 dog yellow 28 house"
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "# Filtering - simple and complex conditions"
+ "# Filtering - simple and complex conditions\n",
+ "animals [ animals['habitat'] == 'house' ]"
]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 9,
+ "id": "b42f5aa9",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Name</th>\n",
+ " <th>color</th>\n",
+ " <th>length</th>\n",
+ " <th>habitat</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>fish</td>\n",
+ " <td>green</td>\n",
+ " <td>8</td>\n",
+ " <td>water</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>cat</td>\n",
+ " <td>brown</td>\n",
+ " <td>15</td>\n",
+ " <td>house</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Name color length habitat\n",
+ "0 fish green 8 water\n",
+ "1 cat brown 15 house"
+ ]
+ },
+ "execution_count": 9,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "animals[ animals['length'] < 20 ] "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "c5468761",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Name</th>\n",
+ " <th>color</th>\n",
+ " <th>length</th>\n",
+ " <th>habitat</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>cat</td>\n",
+ " <td>brown</td>\n",
+ " <td>15</td>\n",
+ " <td>house</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Name color length habitat\n",
+ "1 cat brown 15 house"
+ ]
+ },
+ "execution_count": 10,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# filter by multiple things\n",
+ "animals [ (animals['habitat'] == 'house') & (animals['length'] < 20) ]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
"id": "f6f7d185",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 water\n",
+ "1 house\n",
+ "2 jungle\n",
+ "3 house\n",
+ "Name: habitat, dtype: object"
+ ]
+ },
+ "execution_count": 12,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "# Accessing individual values"
+ "# Accessing individual values\n",
+ "hs = animals['habitat']\n",
+ "hs"
]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 14,
+ "id": "71863d9c",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'house'"
+ ]
+ },
+ "execution_count": 14,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# how do we get 'house'?\n",
+ "hs.iloc[1]\n",
+ "hs.loc[1]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "id": "5cdf5bc5",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'water'"
+ ]
+ },
+ "execution_count": 19,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# special case: if a series has exactly one value\n",
+ "hs [ hs == 'water' ].item() # this works\n",
+ "\n",
+ "# hs [ hs == 'house' ].item() # doesn't work because multiple animals live in house"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "id": "7f619624",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Name</th>\n",
+ " <th>color</th>\n",
+ " <th>length</th>\n",
+ " <th>habitat</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>fish</td>\n",
+ " <td>green</td>\n",
+ " <td>8</td>\n",
+ " <td>water</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>cat</td>\n",
+ " <td>brown</td>\n",
+ " <td>15</td>\n",
+ " <td>house</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Name color length habitat\n",
+ "0 fish green 8 water\n",
+ "1 cat brown 15 house"
+ ]
+ },
+ "execution_count": 20,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# slicing\n",
+ "animals[:2]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "id": "78d124d3",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Name</th>\n",
+ " <th>color</th>\n",
+ " <th>length</th>\n",
+ " <th>habitat</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>fish</td>\n",
+ " <td>green</td>\n",
+ " <td>8</td>\n",
+ " <td>water</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>cat</td>\n",
+ " <td>brown</td>\n",
+ " <td>15</td>\n",
+ " <td>house</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Name color length habitat\n",
+ "0 fish green 8 water\n",
+ "1 cat brown 15 house"
+ ]
+ },
+ "execution_count": 21,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "animals.iloc[:2]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 22,
+ "id": "7b9f6d90",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Name</th>\n",
+ " <th>color</th>\n",
+ " <th>length</th>\n",
+ " <th>habitat</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>fish</td>\n",
+ " <td>green</td>\n",
+ " <td>8</td>\n",
+ " <td>water</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>cat</td>\n",
+ " <td>brown</td>\n",
+ " <td>15</td>\n",
+ " <td>house</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>tiger</td>\n",
+ " <td>orange</td>\n",
+ " <td>48</td>\n",
+ " <td>jungle</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Name color length habitat\n",
+ "0 fish green 8 water\n",
+ "1 cat brown 15 house\n",
+ "2 tiger orange 48 jungle"
+ ]
+ },
+ "execution_count": 22,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# weird edge case: if you use slicing with loc, it's inclusive of the endpoint \n",
+ "animals.loc[:2]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 27,
+ "id": "0b47daee",
+ "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>length</th>\n",
+ " <th>habitat</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Name</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>fish</th>\n",
+ " <td>green</td>\n",
+ " <td>8</td>\n",
+ " <td>water</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>cat</th>\n",
+ " <td>brown</td>\n",
+ " <td>15</td>\n",
+ " <td>house</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>tiger</th>\n",
+ " <td>orange</td>\n",
+ " <td>48</td>\n",
+ " <td>jungle</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>dog</th>\n",
+ " <td>yellow</td>\n",
+ " <td>28</td>\n",
+ " <td>house</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " color length habitat\n",
+ "Name \n",
+ "fish green 8 water\n",
+ "cat brown 15 house\n",
+ "tiger orange 48 jungle\n",
+ "dog yellow 28 house"
+ ]
+ },
+ "execution_count": 27,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# setting an index (set_index creates a new object)\n",
+ "animals = animals.set_index('Name')\n",
+ "animals"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 31,
"id": "2f6f8f41",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'brown'"
+ ]
+ },
+ "execution_count": 31,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "# Understanding loc, iloc, and slicing"
+ "# Understanding loc, iloc, and slicing\n",
+ "animals['color'].loc['cat']\n",
+ "animals['color'].iloc[1]"
]
},
{
"cell_type": "code",
- "execution_count": null,
- "id": "62ccdd15",
+ "execution_count": 33,
+ "id": "4fbb6177",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'brown'"
+ ]
+ },
+ "execution_count": 33,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "# Setting an index column "
+ "animals.loc['cat', 'color']\n",
+ "animals.iloc[1, 0]\n"
]
},
{
@@ -142,7 +865,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 42,
"id": "8b44c2dd",
"metadata": {},
"outputs": [],
@@ -178,7 +901,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 43,
"id": "83ac470b",
"metadata": {},
"outputs": [],
@@ -188,25 +911,72 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 44,
"id": "c546e7b8",
"metadata": {},
"outputs": [],
- "source": []
+ "source": [
+ "# find works when there's a single object that we're looking for\n",
+ "table = bs_obj.find('table')\n",
+ "# find_all is used when there might be multiple of somethign"
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 47,
+ "id": "085927ea",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "['University', 'Department']"
+ ]
+ },
+ "execution_count": 47,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "header = [item.get_text() for item in table.find_all('th') ] \n",
+ "# use a list comprehension to pull out just the text\n",
+ "header"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 54,
"id": "be3d05e0",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "https://www.cs.wisc.edu/ Computer Sciences\n",
+ "https://stat.wisc.edu/ Statistics\n",
+ "https://cdis.wisc.edu/ CDIS\n",
+ "https://eecs.berkeley.edu/ Electrical Engineering and Computer Sciences\n",
+ " \n"
+ ]
+ }
+ ],
"source": [
+ "rows = table.find_all('tr')\n",
+ "\n",
+ "for row in rows[1:]:\n",
+ " #print(row)\n",
+ " anchor = row.find('a')\n",
+ " link = anchor.attrs['href']\n",
+ " link_title = anchor.get_text()\n",
+ " print(link, link_title)\n",
"# get_text, children, attrs"
]
},
{
"cell_type": "markdown",
- "id": "753cf273",
+ "id": "471b6f91",
"metadata": {},
"source": [
"# Databases"
@@ -214,8 +984,8 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "id": "4fda7cf8",
+ "execution_count": 36,
+ "id": "23a1e919",
"metadata": {},
"outputs": [],
"source": [
@@ -227,9 +997,227 @@
" return pd.read_sql(QUERY, conn)"
]
},
+ {
+ "cell_type": "code",
+ "execution_count": 38,
+ "id": "c64cc21d",
+ "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>Title</th>\n",
+ " <th>Genre</th>\n",
+ " <th>Director</th>\n",
+ " <th>Cast</th>\n",
+ " <th>Year</th>\n",
+ " <th>Runtime</th>\n",
+ " <th>Rating</th>\n",
+ " <th>Revenue</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Guardians of the Galaxy</td>\n",
+ " <td>Action,Adventure,Sci-Fi</td>\n",
+ " <td>James Gunn</td>\n",
+ " <td>Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S...</td>\n",
+ " <td>2014</td>\n",
+ " <td>121</td>\n",
+ " <td>8.1</td>\n",
+ " <td>333.13</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Prometheus</td>\n",
+ " <td>Adventure,Mystery,Sci-Fi</td>\n",
+ " <td>Ridley Scott</td>\n",
+ " <td>Noomi Rapace, Logan Marshall-Green, Michael ...</td>\n",
+ " <td>2012</td>\n",
+ " <td>124</td>\n",
+ " <td>7.0</td>\n",
+ " <td>126.46</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Split</td>\n",
+ " <td>Horror,Thriller</td>\n",
+ " <td>M. Night Shyamalan</td>\n",
+ " <td>James McAvoy, Anya Taylor-Joy, Haley Lu Richar...</td>\n",
+ " <td>2016</td>\n",
+ " <td>117</td>\n",
+ " <td>7.3</td>\n",
+ " <td>138.12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Sing</td>\n",
+ " <td>Animation,Comedy,Family</td>\n",
+ " <td>Christophe Lourdelet</td>\n",
+ " <td>Matthew McConaughey,Reese Witherspoon, Seth Ma...</td>\n",
+ " <td>2016</td>\n",
+ " <td>108</td>\n",
+ " <td>7.2</td>\n",
+ " <td>270.32</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>Suicide Squad</td>\n",
+ " <td>Action,Adventure,Fantasy</td>\n",
+ " <td>David Ayer</td>\n",
+ " <td>Will Smith, Jared Leto, Margot Robbie, Viola D...</td>\n",
+ " <td>2016</td>\n",
+ " <td>123</td>\n",
+ " <td>6.2</td>\n",
+ " <td>325.02</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1063</th>\n",
+ " <td>Guardians of the Galaxy Vol. 2</td>\n",
+ " <td>Action, Adventure, Comedy</td>\n",
+ " <td>James Gunn</td>\n",
+ " <td>Chris Pratt, Zoe Saldana, Dave Bautista, Vin D...</td>\n",
+ " <td>2017</td>\n",
+ " <td>136</td>\n",
+ " <td>7.6</td>\n",
+ " <td>389.81</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1064</th>\n",
+ " <td>Baby Driver</td>\n",
+ " <td>Action, Crime, Drama</td>\n",
+ " <td>Edgar Wright</td>\n",
+ " <td>Ansel Elgort, Jon Bernthal, Jon Hamm, Eiza Gon...</td>\n",
+ " <td>2017</td>\n",
+ " <td>113</td>\n",
+ " <td>7.6</td>\n",
+ " <td>107.83</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1065</th>\n",
+ " <td>Only the Brave</td>\n",
+ " <td>Action, Biography, Drama</td>\n",
+ " <td>Joseph Kosinski</td>\n",
+ " <td>Josh Brolin, Miles Teller, Jeff Bridges, Jenni...</td>\n",
+ " <td>2017</td>\n",
+ " <td>134</td>\n",
+ " <td>7.6</td>\n",
+ " <td>18.34</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1066</th>\n",
+ " <td>Incredibles 2</td>\n",
+ " <td>Animation, Action, Adventure</td>\n",
+ " <td>Brad Bird</td>\n",
+ " <td>Craig T. Nelson, Holly Hunter, Sarah Vowell, H...</td>\n",
+ " <td>2018</td>\n",
+ " <td>118</td>\n",
+ " <td>7.6</td>\n",
+ " <td>608.58</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1067</th>\n",
+ " <td>A Star Is Born</td>\n",
+ " <td>Drama, Music, Romance</td>\n",
+ " <td>Bradley Cooper</td>\n",
+ " <td>Lady Gaga, Bradley Cooper, Sam Elliott, Greg G...</td>\n",
+ " <td>2018</td>\n",
+ " <td>136</td>\n",
+ " <td>7.6</td>\n",
+ " <td>215.29</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>1068 rows × 8 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Title Genre \\\n",
+ "0 Guardians of the Galaxy Action,Adventure,Sci-Fi \n",
+ "1 Prometheus Adventure,Mystery,Sci-Fi \n",
+ "2 Split Horror,Thriller \n",
+ "3 Sing Animation,Comedy,Family \n",
+ "4 Suicide Squad Action,Adventure,Fantasy \n",
+ "... ... ... \n",
+ "1063 Guardians of the Galaxy Vol. 2 Action, Adventure, Comedy \n",
+ "1064 Baby Driver Action, Crime, Drama \n",
+ "1065 Only the Brave Action, Biography, Drama \n",
+ "1066 Incredibles 2 Animation, Action, Adventure \n",
+ "1067 A Star Is Born Drama, Music, Romance \n",
+ "\n",
+ " Director Cast \\\n",
+ "0 James Gunn Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S... \n",
+ "1 Ridley Scott Noomi Rapace, Logan Marshall-Green, Michael ... \n",
+ "2 M. Night Shyamalan James McAvoy, Anya Taylor-Joy, Haley Lu Richar... \n",
+ "3 Christophe Lourdelet Matthew McConaughey,Reese Witherspoon, Seth Ma... \n",
+ "4 David Ayer Will Smith, Jared Leto, Margot Robbie, Viola D... \n",
+ "... ... ... \n",
+ "1063 James Gunn Chris Pratt, Zoe Saldana, Dave Bautista, Vin D... \n",
+ "1064 Edgar Wright Ansel Elgort, Jon Bernthal, Jon Hamm, Eiza Gon... \n",
+ "1065 Joseph Kosinski Josh Brolin, Miles Teller, Jeff Bridges, Jenni... \n",
+ "1066 Brad Bird Craig T. Nelson, Holly Hunter, Sarah Vowell, H... \n",
+ "1067 Bradley Cooper Lady Gaga, Bradley Cooper, Sam Elliott, Greg G... \n",
+ "\n",
+ " Year Runtime Rating Revenue \n",
+ "0 2014 121 8.1 333.13 \n",
+ "1 2012 124 7.0 126.46 \n",
+ "2 2016 117 7.3 138.12 \n",
+ "3 2016 108 7.2 270.32 \n",
+ "4 2016 123 6.2 325.02 \n",
+ "... ... ... ... ... \n",
+ "1063 2017 136 7.6 389.81 \n",
+ "1064 2017 113 7.6 107.83 \n",
+ "1065 2017 134 7.6 18.34 \n",
+ "1066 2018 118 7.6 608.58 \n",
+ "1067 2018 136 7.6 215.29 \n",
+ "\n",
+ "[1068 rows x 8 columns]"
+ ]
+ },
+ "execution_count": 38,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# qry(\"SELECT * from sqlite_master\") # this tells us there's one table called movies\n",
+ "\n",
+ "qry(\"SELECT * from movies\")"
+ ]
+ },
{
"cell_type": "markdown",
- "id": "f98c2f0c",
+ "id": "be0c4ac8",
"metadata": {},
"source": [
"where vs having"
@@ -237,11 +1225,481 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "id": "a76a21e2",
+ "execution_count": 39,
+ "id": "ec2d494c",
"metadata": {},
- "outputs": [],
- "source": []
+ "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>Title</th>\n",
+ " <th>Genre</th>\n",
+ " <th>Director</th>\n",
+ " <th>Cast</th>\n",
+ " <th>Year</th>\n",
+ " <th>Runtime</th>\n",
+ " <th>Rating</th>\n",
+ " <th>Revenue</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Guardians of the Galaxy</td>\n",
+ " <td>Action,Adventure,Sci-Fi</td>\n",
+ " <td>James Gunn</td>\n",
+ " <td>Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S...</td>\n",
+ " <td>2014</td>\n",
+ " <td>121</td>\n",
+ " <td>8.1</td>\n",
+ " <td>333.13</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Prometheus</td>\n",
+ " <td>Adventure,Mystery,Sci-Fi</td>\n",
+ " <td>Ridley Scott</td>\n",
+ " <td>Noomi Rapace, Logan Marshall-Green, Michael ...</td>\n",
+ " <td>2012</td>\n",
+ " <td>124</td>\n",
+ " <td>7.0</td>\n",
+ " <td>126.46</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Suicide Squad</td>\n",
+ " <td>Action,Adventure,Fantasy</td>\n",
+ " <td>David Ayer</td>\n",
+ " <td>Will Smith, Jared Leto, Margot Robbie, Viola D...</td>\n",
+ " <td>2016</td>\n",
+ " <td>123</td>\n",
+ " <td>6.2</td>\n",
+ " <td>325.02</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>La La Land</td>\n",
+ " <td>Comedy,Drama,Music</td>\n",
+ " <td>Damien Chazelle</td>\n",
+ " <td>Ryan Gosling, Emma Stone, Rosemarie DeWitt, J....</td>\n",
+ " <td>2016</td>\n",
+ " <td>128</td>\n",
+ " <td>8.3</td>\n",
+ " <td>151.06</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>The Lost City of Z</td>\n",
+ " <td>Action,Adventure,Biography</td>\n",
+ " <td>James Gray</td>\n",
+ " <td>Charlie Hunnam, Robert Pattinson, Sienna Mille...</td>\n",
+ " <td>2016</td>\n",
+ " <td>141</td>\n",
+ " <td>7.1</td>\n",
+ " <td>8.01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>325</th>\n",
+ " <td>Nelyubov</td>\n",
+ " <td>Drama</td>\n",
+ " <td>Andrey Zvyagintsev</td>\n",
+ " <td>Maryana Spivak, Aleksey Rozin, Matvey Novikov,...</td>\n",
+ " <td>2017</td>\n",
+ " <td>127</td>\n",
+ " <td>7.6</td>\n",
+ " <td>0.57</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>326</th>\n",
+ " <td>Just Mercy</td>\n",
+ " <td>Biography, Crime, Drama</td>\n",
+ " <td>Destin Daniel Cretton</td>\n",
+ " <td>Michael B. Jordan, Jamie Foxx, Brie Larson, Ch...</td>\n",
+ " <td>2019</td>\n",
+ " <td>137</td>\n",
+ " <td>7.6</td>\n",
+ " <td>50.40</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>327</th>\n",
+ " <td>Guardians of the Galaxy Vol. 2</td>\n",
+ " <td>Action, Adventure, Comedy</td>\n",
+ " <td>James Gunn</td>\n",
+ " <td>Chris Pratt, Zoe Saldana, Dave Bautista, Vin D...</td>\n",
+ " <td>2017</td>\n",
+ " <td>136</td>\n",
+ " <td>7.6</td>\n",
+ " <td>389.81</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>328</th>\n",
+ " <td>Only the Brave</td>\n",
+ " <td>Action, Biography, Drama</td>\n",
+ " <td>Joseph Kosinski</td>\n",
+ " <td>Josh Brolin, Miles Teller, Jeff Bridges, Jenni...</td>\n",
+ " <td>2017</td>\n",
+ " <td>134</td>\n",
+ " <td>7.6</td>\n",
+ " <td>18.34</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>329</th>\n",
+ " <td>A Star Is Born</td>\n",
+ " <td>Drama, Music, Romance</td>\n",
+ " <td>Bradley Cooper</td>\n",
+ " <td>Lady Gaga, Bradley Cooper, Sam Elliott, Greg G...</td>\n",
+ " <td>2018</td>\n",
+ " <td>136</td>\n",
+ " <td>7.6</td>\n",
+ " <td>215.29</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>330 rows × 8 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Title Genre \\\n",
+ "0 Guardians of the Galaxy Action,Adventure,Sci-Fi \n",
+ "1 Prometheus Adventure,Mystery,Sci-Fi \n",
+ "2 Suicide Squad Action,Adventure,Fantasy \n",
+ "3 La La Land Comedy,Drama,Music \n",
+ "4 The Lost City of Z Action,Adventure,Biography \n",
+ ".. ... ... \n",
+ "325 Nelyubov Drama \n",
+ "326 Just Mercy Biography, Crime, Drama \n",
+ "327 Guardians of the Galaxy Vol. 2 Action, Adventure, Comedy \n",
+ "328 Only the Brave Action, Biography, Drama \n",
+ "329 A Star Is Born Drama, Music, Romance \n",
+ "\n",
+ " Director Cast \\\n",
+ "0 James Gunn Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S... \n",
+ "1 Ridley Scott Noomi Rapace, Logan Marshall-Green, Michael ... \n",
+ "2 David Ayer Will Smith, Jared Leto, Margot Robbie, Viola D... \n",
+ "3 Damien Chazelle Ryan Gosling, Emma Stone, Rosemarie DeWitt, J.... \n",
+ "4 James Gray Charlie Hunnam, Robert Pattinson, Sienna Mille... \n",
+ ".. ... ... \n",
+ "325 Andrey Zvyagintsev Maryana Spivak, Aleksey Rozin, Matvey Novikov,... \n",
+ "326 Destin Daniel Cretton Michael B. Jordan, Jamie Foxx, Brie Larson, Ch... \n",
+ "327 James Gunn Chris Pratt, Zoe Saldana, Dave Bautista, Vin D... \n",
+ "328 Joseph Kosinski Josh Brolin, Miles Teller, Jeff Bridges, Jenni... \n",
+ "329 Bradley Cooper Lady Gaga, Bradley Cooper, Sam Elliott, Greg G... \n",
+ "\n",
+ " Year Runtime Rating Revenue \n",
+ "0 2014 121 8.1 333.13 \n",
+ "1 2012 124 7.0 126.46 \n",
+ "2 2016 123 6.2 325.02 \n",
+ "3 2016 128 8.3 151.06 \n",
+ "4 2016 141 7.1 8.01 \n",
+ ".. ... ... ... ... \n",
+ "325 2017 127 7.6 0.57 \n",
+ "326 2019 137 7.6 50.40 \n",
+ "327 2017 136 7.6 389.81 \n",
+ "328 2017 134 7.6 18.34 \n",
+ "329 2018 136 7.6 215.29 \n",
+ "\n",
+ "[330 rows x 8 columns]"
+ ]
+ },
+ "execution_count": 39,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "qry (\"\"\"\n",
+ " SELECT * \n",
+ " FROM movies \n",
+ " WHERE Runtime > 120\n",
+ "\"\"\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "736f759a",
+ "metadata": {},
+ "source": [
+ "We want the average rating of movies for each year, only for movies that are over 2 hours long"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 40,
+ "id": "9717b343",
+ "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>avg_rating</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>2006</td>\n",
+ " <td>7.400000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>2007</td>\n",
+ " <td>7.486957</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>2008</td>\n",
+ " <td>7.100000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>2009</td>\n",
+ " <td>7.326316</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>2010</td>\n",
+ " <td>6.958333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>2011</td>\n",
+ " <td>7.338889</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6</th>\n",
+ " <td>2012</td>\n",
+ " <td>7.176923</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7</th>\n",
+ " <td>2013</td>\n",
+ " <td>7.236364</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8</th>\n",
+ " <td>2014</td>\n",
+ " <td>7.245161</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9</th>\n",
+ " <td>2015</td>\n",
+ " <td>6.997619</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>10</th>\n",
+ " <td>2016</td>\n",
+ " <td>6.960714</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>11</th>\n",
+ " <td>2017</td>\n",
+ " <td>7.970000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>12</th>\n",
+ " <td>2018</td>\n",
+ " <td>8.030769</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>13</th>\n",
+ " <td>2019</td>\n",
+ " <td>8.033333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>14</th>\n",
+ " <td>2020</td>\n",
+ " <td>8.333333</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Year avg_rating\n",
+ "0 2006 7.400000\n",
+ "1 2007 7.486957\n",
+ "2 2008 7.100000\n",
+ "3 2009 7.326316\n",
+ "4 2010 6.958333\n",
+ "5 2011 7.338889\n",
+ "6 2012 7.176923\n",
+ "7 2013 7.236364\n",
+ "8 2014 7.245161\n",
+ "9 2015 6.997619\n",
+ "10 2016 6.960714\n",
+ "11 2017 7.970000\n",
+ "12 2018 8.030769\n",
+ "13 2019 8.033333\n",
+ "14 2020 8.333333"
+ ]
+ },
+ "execution_count": 40,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "qry (\"\"\"\n",
+ " SELECT year, AVG(Rating) AS avg_rating \n",
+ " FROM movies \n",
+ " WHERE Runtime > 120\n",
+ " GROUP BY year\n",
+ "\"\"\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "7a2d3f89",
+ "metadata": {},
+ "source": [
+ "We want the average rating of movies for each year that has at least 20 movies over 2 hrs long, only for movies that are over 2 hours long"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 41,
+ "id": "ea3c391f",
+ "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>avg_rating</th>\n",
+ " <th>num_movies</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>2007</td>\n",
+ " <td>7.486957</td>\n",
+ " <td>23</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>2012</td>\n",
+ " <td>7.176923</td>\n",
+ " <td>26</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>2013</td>\n",
+ " <td>7.236364</td>\n",
+ " <td>33</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>2014</td>\n",
+ " <td>7.245161</td>\n",
+ " <td>31</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>2015</td>\n",
+ " <td>6.997619</td>\n",
+ " <td>42</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>2016</td>\n",
+ " <td>6.960714</td>\n",
+ " <td>56</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Year avg_rating num_movies\n",
+ "0 2007 7.486957 23\n",
+ "1 2012 7.176923 26\n",
+ "2 2013 7.236364 33\n",
+ "3 2014 7.245161 31\n",
+ "4 2015 6.997619 42\n",
+ "5 2016 6.960714 56"
+ ]
+ },
+ "execution_count": 41,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "qry (\"\"\"\n",
+ " SELECT year, AVG(Rating) AS avg_rating, COUNT(Title) as num_movies\n",
+ " FROM movies \n",
+ " WHERE Runtime > 120\n",
+ " GROUP BY year\n",
+ " HAVING num_movies > 20\n",
+ "\"\"\")"
+ ]
},
{
"cell_type": "markdown",
@@ -272,6 +1730,94 @@
"# #. simple recursive function\n"
]
},
+ {
+ "cell_type": "code",
+ "execution_count": 62,
+ "id": "2ac5783e",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "C\n",
+ "B\n",
+ "done\n"
+ ]
+ }
+ ],
+ "source": [
+ "a = 4\n",
+ "b = 7\n",
+ "c = 10\n",
+ "if c == 10:\n",
+ " print(\"C\")\n",
+ "if a > b:\n",
+ " print(\"A\")\n",
+ "elif a == b:\n",
+ " print(\"equal\")\n",
+ "else:\n",
+ " print(\"B\")\n",
+ " \n",
+ "print(\"done\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 63,
+ "id": "5835a6cf",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "1\n",
+ "can't square a\n",
+ "4\n"
+ ]
+ }
+ ],
+ "source": [
+ "mylist = [1,'a',2]\n",
+ "for item in mylist:\n",
+ " try:\n",
+ " print(item ** 2)\n",
+ " except:\n",
+ " print(\"can't square\", item)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 64,
+ "id": "41bf53de",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "1\n"
+ ]
+ },
+ {
+ "ename": "TypeError",
+ "evalue": "unsupported operand type(s) for ** or pow(): 'str' and 'int'",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[64], line 3\u001b[0m\n\u001b[1;32m 1\u001b[0m mylist \u001b[38;5;241m=\u001b[39m [\u001b[38;5;241m1\u001b[39m,\u001b[38;5;124m'\u001b[39m\u001b[38;5;124ma\u001b[39m\u001b[38;5;124m'\u001b[39m,\u001b[38;5;241m2\u001b[39m]\n\u001b[1;32m 2\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m item \u001b[38;5;129;01min\u001b[39;00m mylist:\n\u001b[0;32m----> 3\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[43mitem\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m2\u001b[39;49m)\n",
+ "\u001b[0;31mTypeError\u001b[0m: unsupported operand type(s) for ** or pow(): 'str' and 'int'"
+ ]
+ }
+ ],
+ "source": [
+ "mylist = [1,'a',2]\n",
+ "for item in mylist:\n",
+ " print(item ** 2)\n"
+ ]
+ },
{
"cell_type": "markdown",
"id": "5435a2eb",
@@ -282,7 +1828,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 55,
"id": "fc8d4c25",
"metadata": {},
"outputs": [],
@@ -291,10 +1837,92 @@
" print(salutation, name, punctuation)"
]
},
+ {
+ "cell_type": "markdown",
+ "id": "96af5d95",
+ "metadata": {},
+ "source": [
+ "Three types of parameters:\n",
+ "* Keyword\n",
+ " * In the function call, programmer specifies which argument corresponds to which parameter\n",
+ "* Positional\n",
+ " * Parameters filled in left ot right\n",
+ "* Default -- user doesn't supply, take whatever was provided in the function definition\n",
+ " * In our example `greeting`, `salutation` and `punctuation` have default values. `name` does not.\n",
+ " \n",
+ " \n",
+ "Rules\n",
+ "* Positional left ot right\n",
+ "* Can use positional and keyword otgether, but all keyword arguments come last"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 57,
+ "id": "3f0eb87c",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "hi anna !\n"
+ ]
+ }
+ ],
+ "source": [
+ "# bad example\n",
+ "# greeting(salutation=\"hi\", \"anna\")\n",
+ "\n",
+ "# better example\n",
+ "greeting(\"anna\", salutation='hi')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 58,
+ "id": "f625c718",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "TypeError",
+ "evalue": "greeting() got multiple values for argument 'name'",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[58], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m# bad example\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m \u001b[43mgreeting\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43manna\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mname\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mbob\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msalutation\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mhi\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\n",
+ "\u001b[0;31mTypeError\u001b[0m: greeting() got multiple values for argument 'name'"
+ ]
+ }
+ ],
+ "source": [
+ "# bad example\n",
+ "greeting(\"anna\", name=\"bob\", salutation='hi')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 59,
+ "id": "fb516149",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Hello anna .\n"
+ ]
+ }
+ ],
+ "source": [
+ "greeting(\"anna\", punctuation='.')"
+ ]
+ },
{
"cell_type": "code",
"execution_count": null,
- "id": "8bd6614f",
+ "id": "a2424d77",
"metadata": {},
"outputs": [],
"source": []
diff --git a/sum23/projects/p13/p13_test.py b/sum23/projects/p13/p13_test.py
index dd4e42a5161b9edf2206f4d7330ee6a8722e5d18..3c1f4b249791918a5e26a31796f540cc1df1e302 100644
--- a/sum23/projects/p13/p13_test.py
+++ b/sum23/projects/p13/p13_test.py
@@ -7,7 +7,7 @@ from bs4 import BeautifulSoup
HTML_TEST_FILE = 'p13_expected.html'
-MAX_FILE_SIZE = 500 # units - KB
+MAX_FILE_SIZE = 550 # units - KB
REL_TOL = 6e-04 # relative tolerance for floats
ABS_TOL = 15e-03 # absolute tolerance for floats