Homework 4

Rule
● You’re encouraged to check book, notes, class materials, or google, for the scope of this homework
● Please keep your work independent. Please do not check with each other on solutions.

Problem 1: Costco Stock SMA
Objective

● list and string handling: split, indexing, len()
● list comprehension, with if and else
● if statement
● file reading, csv file handling (csv: comma separated values)
● nan: not a number. matplotlib will auto ignore all ‘nan’ entries.
● matplotlib: make line plots, line/dot style, label, saving figure
● self learning. (google and follow example)

Submission

● Please submit “hw4_costco_stock_sma_yourlastname.py”.
● Please also submit the image generated, to blackboard.

Description

For the given “hw4_stock_sma.ipynb” and “FB.csv” files from Blackboard, try to understand each step. This file will serve
as a starting point and code example for the problem below.

● printing of variables will help understand the code better.
● Start a new notebook file, then start coding the same functionality totally from scratch, may also help understand the

code.

Based on the example provided, write a new file, call it hw4_costco_stock_sma_yourlastname.py.

Download 1 year COST (costco) stock data from finance.yahoo.com. First go to ‘finance.yahoo.com’, search COST on top,
click “historical data”, choose “1 year” and “daily”, click “apply” then click “Download”. Now you have the 1 year stock in csv
format. Copy or move/drag this csv file to the same directory where you write and execute your python code. This file will be
used as input for the code below.

1. Write a function called “get_sma”, that takes two input arguments, similar to the example provided. First argument is
the original prices of type list, and the 2nd input argument being the number of days we want to calculate SMA, like a

http://finance.yahoo.com

8 day sma or 35 day sma. This function should return a new list of sma price, based on the input day range, and
should be able to handle any SMA calculation, like: sma200 for 200 days moving average.

2. Write a function called “read_data”, which will be used to open/read/close the csv file, plus some data processing.
We will be using the ‘Adj Close’ column as our ‘prices’. This function should return 2 lists: a list of dates, and a list of
original prices.

3. make another function called “make_plot”, which will take 4 input list arguments. The 4 input lists are: dates, original
prices, sma10 prices, sma50 prices (for 10 and 50 days moving average respectively). This function should use
matplotlib to make plots and save the image to harddisk.

○ To check your curves look right: After you make the plots, you can compare your plot to finance.yahoo.com
plot of COST using 1 year and the two SMA curve added (please google on how to), or use any website
you’re familiar with that can make 1 year stock curve with sma10 and sma50, to see that your 3 curves have
similar shape as on the website.

4. Write a function called “main”, that will:
○ call read_data to read in original price as a list
○ call get_sma to get sma10 and sma50 of costco stock prices, as 2 lists. “sma10” means the 10 day SMA data

as a list.
○ call make_plot, using the 4 lists we have
○ also make sure to write code that will call the ‘main’ function, so your python code can be executed.
○ Note: please make the code as clean as possible. No duplicated code. No unnecessary lines. Repeated code

will get points deducted. Only nice and clean code can get a full score.

Extra Credit (5 points)
● for costco stock price plot, if you can make the x axis use dates instead of numbers in my example, you’ll get the

extra points. Your plot may use something like: 01/2017, 02/2017, or : 2017.1, 2017.2, or Jan 2017, …
whatever way that can show clearly that it’s a ‘date’ format. Total score for this homework is up to 100, not
105.

{
“cells”: [
{
“cell_type”: “markdown”,
“metadata”: {},
“source”: [
“## Stock Simple Moving Average\n”,
“\n”,
“**SMA**\n”,
“\n”,
“In this exercise, we’ll learn abuot how to calculate Stock SMA, simple moving average. The method we use is: for the 9th day, the sma8 (8 day average) is calculated using day1-day8’s average stock price, day10 ‘s sma8 is calculated using day2-day9’s average price, and so on. There are other methods out there for calculating SMA, please google. \n”,
“\n”,
“**Notes**\n”,
“* please download csv file first from Blackboard, and put it in the same directory where you start jupyter\n”,
“* for all the commented out code below, feel free to uncomment and check the values of the variables.\n”,
“\n”,
“\n”,
“**Objective**\n”,
“* list and string handling: split, indexing, len()\n”,
“* list comprehension, with if and else\n”,
“* if statement\n”,
“* file reading, csv file handling\n”,
“* nan: not a number. \n”,
“* matplotlib: make line plots, line/dot style, label, saving figure (advanced for now, it’s good to start trying)\n”,
“\n”,
“**Reference**\n”,
“https://finance.yahoo.com/chart/FB#eyJpbnRlcnZhbCI6ImRheSIsInBlcmlvZGljaXR5IjoxLCJ0aW1lVW5pdCI6bnVsbCwiY2FuZGxlV2lkdGgiOjMuNTgxMDgxMDgxMDgxMDgxLCJ2b2x1bWVVbmRlcmxheSI6dHJ1ZSwiY3Jvc3NoYWlyIjp0cnVlLCJjaGFydFR5cGUiOiJsaW5lIiwiZXh0ZW5kZWQiOnRydWUsIm1hcmtldFNlc3Npb25zIjp7InByZSI6dHJ1ZSwicG9zdCI6dHJ1ZX0sImFnZ3JlZ2F0aW9uVHlwZSI6Im9obGMiLCJjaGFydFNjYWxlIjoibGluZWFyIiwicGFuZWxzIjp7ImNoYXJ0Ijp7InBlcmNlbnQiOjAuNzg4MDcwMTcwMDg0NjM1NCwiZGlzcGxheSI6IkZCIiwiY2hhcnROYW1lIjoiY2hhcnQiLCJpbmRleCI6MCwieUF4aXMiOnsibmFtZSI6ImNoYXJ0IiwicG9zaXRpb24iOm51bGx9LCJ5YXhpc0xIUyI6W10sInlheGlzUkhTIjpbImNoYXJ0Iiwidm9sIHVuZHIiXX0sIuKAjG1hY2TigIwgKDEyLDI2LDkpIjp7InBlcmNlbnQiOjAuMjExOTI5ODI5OTE1MzY0NTgsImRpc3BsYXkiOiLigIxtYWNk4oCMICgxMiwyNiw5KSIsImNoYXJ0TmFtZSI6ImNoYXJ0IiwiaW5kZXgiOjEsInlBeGlzIjp7Im5hbWUiOiJLR0hDWDNTVzFBIiwicG9zaXRpb24iOm51bGx9LCJ5YXhpc0xIUyI6W10sInlheGlzUkhTIjpbIktHSENYM1NXMUEiXX19LCJzZXRTcGFuIjpudWxsLCJsaW5lV2lkdGgiOjIsInN0cmlwZWRCYWNrZ3JvdW5kIjp0cnVlLCJldmVudHMiOnRydWUsImNvbG9yIjoiIzAwODFmMiIsInN0cmlwZWRCYWNrZ3JvdWQiOnRydWUsInJhbmdlIjpudWxsLCJjdXN0b21SYW5nZSI6bnVsbCwic3ltYm9scyI6W3sic3ltYm9sIjoiRkIiLCJzeW1ib2xPYmplY3QiOnsic3ltYm9sIjoiRkIiLCJxdW90ZVR5cGUiOiJFUVVJVFkiLCJleGNoYW5nZVRpbWVab25lIjoiQW1lcmljYS9OZXdfWW9yayJ9LCJwZXJpb2RpY2l0eSI6MSwiaW50ZXJ2YWwiOiJkYXkiLCJ0aW1lVW5pdCI6bnVsbCwic2V0U3BhbiI6bnVsbH1dLCJldmVudE1hcCI6eyJjb3Jwb3JhdGUiOnsiZGl2cyI6dHJ1ZSwic3BsaXRzIjp0cnVlfSwic2lnRGV2Ijp7fX0sInN0dWRpZXMiOnsidm9sIHVuZHIiOnsidHlwZSI6InZvbCB1bmRyIiwiaW5wdXRzIjp7ImlkIjoidm9sIHVuZHIiLCJkaXNwbGF5Ijoidm9sIHVuZHIifSwib3V0cHV0cyI6eyJVcCBWb2x1bWUiOiIjMDBiMDYxIiwiRG93biBWb2x1bWUiOiIjRkYzMzNBIn0sInBhbmVsIjoiY2hhcnQiLCJwYXJhbWV0ZXJzIjp7ImhlaWdodFBlcmNlbnRhZ2UiOjAuMjUsIndpZHRoRmFjdG9yIjowLjQ1LCJjaGFydE5hbWUiOiJjaGFydCIsInBhbmVsTmFtZSI6ImNoYXJ0In19LCLigIxtYWNk4oCMICgxMiwyNiw5KSI6eyJ0eXBlIjoibWFjZCIsImlucHV0cyI6eyJGYXN0IE1BIFBlcmlvZCI6MTIsIlNsb3cgTUEgUGVyaW9kIjoyNiwiU2lnbmFsIFBlcmlvZCI6OSwiaWQiOiLigIxtYWNk4oCMICgxMiwyNiw5KSIsImRpc3BsYXkiOiLigIxtYWNk4oCMICgxMiwyNiw5KSJ9LCJvdXRwdXRzIjp7Ik1BQ0QiOiIjYWQ2ZWZmIiwiU2lnbmFsIjoiI2ZmYTMzZiIsIkluY3JlYXNpbmcgQmFyIjoiIzc5ZjRiZCIsIkRlY3JlYXNpbmcgQmFyIjoiI2ZmODA4NCJ9LCJwYW5lbCI6IuKAjG1hY2TigIwgKDEyLDI2LDkpIiwicGFyYW1ldGVycyI6eyJjaGFydE5hbWUiOiJjaGFydCIsInBhbmVsTmFtZSI6IuKAjG1hY2TigIwgKDEyLDI2LDkpIn19LCLigIxtYeKAjCAoNixDLG1hLDAsbikiOnsidHlwZSI6Im1hIiwiaW5wdXRzIjp7IlBlcmlvZCI6IjYiLCJGaWVsZCI6IkNsb3NlIiwiVHlwZSI6InNpbXBsZSIsIk9mZnNldCI6MCwiVW5kZXJsYXkiOmZhbHNlLCJpZCI6IuKAjG1h4oCMICg2LEMsbWEsMCxuKSIsImRpc3BsYXkiOiLigIxtYeKAjCAoNixDLG1hLDAsbikifSwib3V0cHV0cyI6eyJNQSI6IiNhZDZlZmYifSwicGFuZWwiOiJjaGFydCIsInBhcmFtZXRlcnMiOnsiY2hhcnROYW1lIjoiY2hhcnQiLCJwYW5lbE5hbWUiOiJjaGFydCJ9fSwi4oCMbWHigIwgKDM1LEMsbWEsMCxuKSI6eyJ0eXBlIjoibWEiLCJpbnB1dHMiOnsiUGVyaW9kIjoiMzUiLCJGaWVsZCI6IkNsb3NlIiwiVHlwZSI6InNpbXBsZSIsIk9mZnNldCI6MCwiVW5kZXJsYXkiOmZhbHNlLCJpZCI6IuKAjG1h4oCMICgzNSxDLG1hLDAsbikiLCJkaXNwbGF5Ijoi4oCMbWHigIwgKDM1LEMsbWEsMCxuKSJ9LCJvdXRwdXRzIjp7Ik1BIjoiI2FkNmVmZiJ9LCJwYW5lbCI6ImNoYXJ0IiwicGFyYW1ldGVycyI6eyJjaGFydE5hbWUiOiJjaGFydCIsInBhbmVsTmFtZSI6ImNoYXJ0In19fX0-\n”,
“Try to plot sma8 and sma35 on Yahoo finance. We’re trying to use data downloaded from yahoo finance to make a similar graph. ”
]
},
{
“cell_type”: “code”,
“execution_count”: 1,
“metadata”: {},
“outputs”: [],
“source”: [
“f = open(‘FB.csv’)\n”,
“f.seek(0) # optional, move the ‘pointer’ to beginning of file\n”,
“all_data = f.read()\n”,
“# all_data”
]
},
{
“cell_type”: “code”,
“execution_count”: 2,
“metadata”: {},
“outputs”: [
{
“data”: {
“text/plain”: [
“[‘Date’, ‘Open’, ‘High’, ‘Low’, ‘Close’, ‘Adj Close’, ‘Volume’]”
]
},
“execution_count”: 2,
“metadata”: {},
“output_type”: “execute_result”
}
],
“source”: [
“all_data_list = all_data.split(‘\\n’)\n”,
“\n”,
“# for the scope of this practice, we don’t really need headers. \n”,
“# It’s nice to know how to calculate headers for later usage\n”,
“headers = all_data_list[0].split(‘,’)\n”,
“headers”
]
},
{
“cell_type”: “code”,
“execution_count”: 3,
“metadata”: {
“scrolled”: true
},
“outputs”: [
{
“data”: {
“text/plain”: [
“[‘Date,Open,High,Low,Close,Adj Close,Volume’,\n”,
” ‘2019-10-21,187.039993,189.910004,186.750000,189.759995,189.759995,8122600’,\n”,
” ‘2019-10-22,190.000000,190.649994,181.500000,182.339996,182.339996,19537600’,\n”,
” ‘2019-10-23,182.009995,186.380005,182.000000,186.149994,186.149994,12300400’,\n”,
” ‘2019-10-24,184.619995,186.729996,182.800003,186.380005,186.380005,11413500’,\n”,
” ‘2019-10-25,185.830002,189.000000,185.089996,187.889999,187.889999,8061200’,\n”,
” ‘2019-10-28,187.199997,189.529999,185.080002,189.399994,189.399994,13657900’,\n”,
” ‘2019-10-29,191.690002,192.529999,188.470001,189.309998,189.309998,13574900’,\n”,
” ‘2019-10-30,189.559998,190.449997,185.979996,188.250000,188.250000,28734600’,\n”,
” ‘2019-10-31,196.699997,198.089996,188.250000,191.649994,191.649994,42286500’]”
]
},
“execution_count”: 3,
“metadata”: {},
“output_type”: “execute_result”
}
],
“source”: [
“# peek into the data\n”,
“all_data_list[:10]”
]
},
{
“cell_type”: “code”,
“execution_count”: 4,
“metadata”: {},
“outputs”: [],
“source”: [
“data = [x.split(‘,’) for x in all_data_list[1:] if x != ”]\n”,
“dates = [d[0] for d in data] # list comprehension\n”,
“prices = [float(d[5]) for d in data] # convert string price to float price\n”,
“# print(dates[:10])\n”,
“# len(prices)\n”,
“# prices”
]
},
{
“cell_type”: “code”,
“execution_count”: 5,
“metadata”: {},
“outputs”: [],
“source”: [
“# here, the n-th day’s SMA is defined as the average price of the 8 days before the n-th day, not including itself. \n”,
“# so later we’ll see in the plot, in the beginning we’re missing some SMA data, that’s due to the way we do calculation.\n”,
“def sma(prices, nday):\n”,
” sma_data = [0] * len(prices)\n”,
” for i in range(nday, len(prices)):\n”,
” sma_data[i] = sum(prices[i-nday:i]) / nday\n”,
” return sma_data”
]
},
{
“cell_type”: “code”,
“execution_count”: 6,
“metadata”: {},
“outputs”: [],
“source”: [
“# we’re calculating sma8 (8 day moving averatma35 for this practice\n”,
“period1, period2, = 8, 35\n”,
“data_sma1, data_sma2 = sma(prices, period1), sma(prices, period2)\n”,
“labels = [‘FB_SMA_%s’ % x for x in (period1, period2)]\n”,
“# print(‘Labels: ‘, labels)\n”,
“# print(data_sma1[:10])\n”,
“# print(data_sma2[:10])”
]
},
{
“cell_type”: “code”,
“execution_count”: 7,
“metadata”: {},
“outputs”: [],
“source”: [
“# ‘nan’: not a number. usually ‘nan’ is used for extremely large number, extremely small number, or missing data\n”,
“def zero_to_nan(values):\n”,
” \”\”\”Replace every 0 with ‘nan’ and return a copy.\”\”\”\n”,
” return [float(‘nan’) if x==0 else x for x in values] # list comprehension, with if/else\n”,
“\n”,
“# matplotlib skips ‘nan’ when plotting, this is a good way to ‘drop’ some invalid data\n”,
“data_sma1 = zero_to_nan(data_sma1)\n”,
“data_sma2 = zero_to_nan(data_sma2)\n”,
“# data_sma2”
]
},
{
“cell_type”: “code”,
“execution_count”: 11,
“metadata”: {
“scrolled”: false
},
“outputs”: [
{
“data”: {
“image/png”: “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×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\n”,
“text/plain”: [
“