Stock Market Analysis

“Stock Analysis(Generated by Imagen3)”

Installation

On your terminal run the following command to install yfinance module.

pip install yfinance

Extract Company in SP500

Firstly, lets extract the SP500 tickers from wikipedia table.

import pandas as pd
import yfinance as yf

from pprint import pprint

start_date = '2020-01-01'
end_date = '2025-01-15'

tickers = pd.read_html('https://en.wikipedia.org/wiki/List_of_S%26P_500_companies')[0]
tickers['Symbol'] = tickers['Symbol'].apply(lambda x: x.strip())
tickers.head()

	Symbol	Security	GICS Sector	GICS Sub-Industry	Headquarters Location	Date added	CIK	Founded
0	MMM	3M	Industrials	Industrial Conglomerates	Saint Paul, Minnesota	1957-03-04	66740	1902
1	AOS	A. O. Smith	Industrials	Building Products	Milwaukee, Wisconsin	2017-07-26	91142	1916
2	ABT	Abbott Laboratories	Health Care	Health Care Equipment	North Chicago, Illinois	1957-03-04	1800	1888
3	ABBV	AbbVie	Health Care	Biotechnology	North Chicago, Illinois	2012-12-31	1551152	2013 (1888)
4	ACN	Accenture	Information Technology	IT Consulting & Other Services	Dublin, Ireland	2011-07-06	1467373	1989

sp500 = pd.read_html('https://www.schwabassetmanagement.com/allholdings/SWPPX')
print(sp500.shape)
sp500.head()

---------------------------------------------------------------------------
HTTPError                                 Traceback (most recent call last)
Cell In[9], line 1
----> 1 sp500 = pd.read_html('https://www.schwabassetmanagement.com/allholdings/SWPPX')
      2 print(sp500.shape)
      3 sp500.head()

File ~/dev/projects/hssaka7.github.io/.venv/lib/python3.12/site-packages/pandas/io/html.py:1240, in read_html(io, match, flavor, header, index_col, skiprows, attrs, parse_dates, thousands, encoding, decimal, converters, na_values, keep_default_na, displayed_only, extract_links, dtype_backend, storage_options)
   1224 if isinstance(io, str) and not any(
   1225     [
   1226         is_file_like(io),
   (...)
   1230     ]
   1231 ):
   1232     warnings.warn(
   1233         "Passing literal html to 'read_html' is deprecated and "
   1234         "will be removed in a future version. To read from a "
   (...)
   1237         stacklevel=find_stack_level(),
   1238     )
-> 1240 return _parse(
   1241     flavor=flavor,
   1242     io=io,
   1243     match=match,
   1244     header=header,
   1245     index_col=index_col,
   1246     skiprows=skiprows,
   1247     parse_dates=parse_dates,
   1248     thousands=thousands,
   1249     attrs=attrs,
   1250     encoding=encoding,
   1251     decimal=decimal,
   1252     converters=converters,
   1253     na_values=na_values,
   1254     keep_default_na=keep_default_na,
   1255     displayed_only=displayed_only,
   1256     extract_links=extract_links,
   1257     dtype_backend=dtype_backend,
   1258     storage_options=storage_options,
   1259 )

File ~/dev/projects/hssaka7.github.io/.venv/lib/python3.12/site-packages/pandas/io/html.py:983, in _parse(flavor, io, match, attrs, encoding, displayed_only, extract_links, storage_options, **kwargs)
    972 p = parser(
    973     io,
    974     compiled_match,
   (...)
    979     storage_options,
    980 )
    982 try:
--> 983     tables = p.parse_tables()
    984 except ValueError as caught:
    985     # if `io` is an io-like object, check if it's seekable
    986     # and try to rewind it before trying the next parser
    987     if hasattr(io, "seekable") and io.seekable():

File ~/dev/projects/hssaka7.github.io/.venv/lib/python3.12/site-packages/pandas/io/html.py:249, in _HtmlFrameParser.parse_tables(self)
    241 def parse_tables(self):
    242     """
    243     Parse and return all tables from the DOM.
    244 
   (...)
    247     list of parsed (header, body, footer) tuples from tables.
    248     """
--> 249     tables = self._parse_tables(self._build_doc(), self.match, self.attrs)
    250     return (self._parse_thead_tbody_tfoot(table) for table in tables)

File ~/dev/projects/hssaka7.github.io/.venv/lib/python3.12/site-packages/pandas/io/html.py:806, in _LxmlFrameParser._build_doc(self)
    804             pass
    805     else:
--> 806         raise e
    807 else:
    808     if not hasattr(r, "text_content"):

File ~/dev/projects/hssaka7.github.io/.venv/lib/python3.12/site-packages/pandas/io/html.py:785, in _LxmlFrameParser._build_doc(self)
    783 try:
    784     if is_url(self.io):
--> 785         with get_handle(
    786             self.io, "r", storage_options=self.storage_options
    787         ) as f:
    788             r = parse(f.handle, parser=parser)
    789     else:
    790         # try to parse the input in the simplest way

File ~/dev/projects/hssaka7.github.io/.venv/lib/python3.12/site-packages/pandas/io/common.py:728, in get_handle(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)
    725     codecs.lookup_error(errors)
    727 # open URLs
--> 728 ioargs = _get_filepath_or_buffer(
    729     path_or_buf,
    730     encoding=encoding,
    731     compression=compression,
    732     mode=mode,
    733     storage_options=storage_options,
    734 )
    736 handle = ioargs.filepath_or_buffer
    737 handles: list[BaseBuffer]

File ~/dev/projects/hssaka7.github.io/.venv/lib/python3.12/site-packages/pandas/io/common.py:384, in _get_filepath_or_buffer(filepath_or_buffer, encoding, compression, mode, storage_options)
    382 # assuming storage_options is to be interpreted as headers
    383 req_info = urllib.request.Request(filepath_or_buffer, headers=storage_options)
--> 384 with urlopen(req_info) as req:
    385     content_encoding = req.headers.get("Content-Encoding", None)
    386     if content_encoding == "gzip":
    387         # Override compression based on Content-Encoding header

File ~/dev/projects/hssaka7.github.io/.venv/lib/python3.12/site-packages/pandas/io/common.py:289, in urlopen(*args, **kwargs)
    283 """
    284 Lazy-import wrapper for stdlib urlopen, as that imports a big chunk of
    285 the stdlib.
    286 """
    287 import urllib.request
--> 289 return urllib.request.urlopen(*args, **kwargs)

File /usr/lib/python3.12/urllib/request.py:215, in urlopen(url, data, timeout, cafile, capath, cadefault, context)
    213 else:
    214     opener = _opener
--> 215 return opener.open(url, data, timeout)

File /usr/lib/python3.12/urllib/request.py:521, in OpenerDirector.open(self, fullurl, data, timeout)
    519 for processor in self.process_response.get(protocol, []):
    520     meth = getattr(processor, meth_name)
--> 521     response = meth(req, response)
    523 return response

File /usr/lib/python3.12/urllib/request.py:630, in HTTPErrorProcessor.http_response(self, request, response)
    627 # According to RFC 2616, "2xx" code indicates that the client's
    628 # request was successfully received, understood, and accepted.
    629 if not (200 <= code < 300):
--> 630     response = self.parent.error(
    631         'http', request, response, code, msg, hdrs)
    633 return response

File /usr/lib/python3.12/urllib/request.py:559, in OpenerDirector.error(self, proto, *args)
    557 if http_err:
    558     args = (dict, 'default', 'http_error_default') + orig_args
--> 559     return self._call_chain(*args)

File /usr/lib/python3.12/urllib/request.py:492, in OpenerDirector._call_chain(self, chain, kind, meth_name, *args)
    490 for handler in handlers:
    491     func = getattr(handler, meth_name)
--> 492     result = func(*args)
    493     if result is not None:
    494         return result

File /usr/lib/python3.12/urllib/request.py:639, in HTTPDefaultErrorHandler.http_error_default(self, req, fp, code, msg, hdrs)
    638 def http_error_default(self, req, fp, code, msg, hdrs):
--> 639     raise HTTPError(req.full_url, code, msg, hdrs, fp)

HTTPError: HTTP Error 403: Forbidden

# TODO extract holding percent
tickers["GICS Sector"].unique()

array(['Industrials', 'Health Care', 'Information Technology',
       'Utilities', 'Financials', 'Materials', 'Consumer Discretionary',
       'Real Estate', 'Communication Services', 'Consumer Staples',
       'Energy'], dtype=object)

Download history data for SP500 companies

For each symbol in SP500, lets download daily historical data.

data = yf.download(tickers.Symbol.to_list(),
                   start=start_date,
                   end=end_date,
                   interval='1D',
                   auto_adjust=True)
data.tail()

[*********************100%***********************]  503 of 503 completed

2 Failed downloads:
['BRK.B']: YFTzMissingError('$%ticker%: possibly delisted; no timezone found')
['BF.B']: YFPricesMissingError('$%ticker%: possibly delisted; no price data found  (1d 2020-01-01 -> 2025-01-15)')

Price	Adj Close		Close								...	Volume
Ticker	BF.B	BRK.B	A	AAPL	ABBV	ABNB	ABT	ACGL	ACN	ADBE	...	WTW	WY	WYNN	XEL	XOM	XYL	YUM	ZBH	ZBRA	ZTS
Date
2025-01-07	NaN	NaN	137.410004	242.210007	179.529999	131.289993	113.400002	92.250000	356.390015	422.630005	...	402500	2588200	2195300	3017800	12625900	1232400	2103000	1649100	353800	2488500
2025-01-08	NaN	NaN	137.000000	242.699997	178.500000	130.800003	114.250000	92.660004	357.730011	419.579987	...	655000	3939100	1862300	3714700	17858100	1274500	2025400	2385600	413600	2353200
2025-01-10	NaN	NaN	137.470001	236.850006	175.169998	129.630005	112.309998	90.169998	349.790009	405.920013	...	594700	3529500	2655900	5441000	19304500	1334500	2555000	2709300	460000	3179500
2025-01-13	NaN	NaN	141.949997	234.399994	176.740005	128.850006	113.190002	90.830002	349.140015	408.500000	...	459400	4299500	1850500	3114600	17073400	1154300	2163100	1565800	505200	2306100
2025-01-14	NaN	NaN	143.429993	233.279999	175.550003	127.599998	113.019997	91.989998	348.989990	412.709991	...	441700	4151400	2773800	5952800	11187700	2137000	1793600	1457100	414500	3608200

5 rows × 2517 columns

Calculate Rolling Average

Now, The 100 day rolling average is calculated and compared with latest closing price. Then, the data where the 100 days rolling average is less than latest closing price is filtered

window_sizes = [5, 10, 30, 60, 100, 200] # indays
results = []
for ticker in data.columns.get_level_values(1).unique():

    ticker_data = data['Close'][ticker]
    row = [ticker,ticker_data.index[-1],ticker_data.iloc[-1].round(2)]
    columns = ['Ticker','Date','Close']

    row = row + [(ticker_data.tail(window_size).sum()/window_size).round(2) for window_size in window_sizes]
    columns = columns + [f'{window_size}D_MA_Close' for window_size in window_sizes]
    results.append(row)
    
rolling_avg_df = pd.DataFrame(results, columns= columns)
rolling_avg_df.dropna(inplace=True)
print(rolling_avg_df.shape)
rolling_avg_df.head(10)

(501, 9)

	Ticker	Date	Close	5D_MA_Close	10D_MA_Close	30D_MA_Close	60D_MA_Close	100D_MA_Close	200D_MA_Close
2	A	2025-01-14	143.43	139.45	137.13	137.52	135.46	137.74	137.47
3	AAPL	2025-01-14	233.28	237.89	242.43	246.49	237.75	232.84	215.77
4	ABBV	2025-01-14	175.55	177.10	178.02	177.04	181.03	185.97	177.18
5	ABNB	2025-01-14	127.60	129.63	131.38	133.79	134.93	130.46	138.81
6	ABT	2025-01-14	113.02	113.23	113.24	114.23	115.39	114.81	110.00
7	ACGL	2025-01-14	91.99	91.58	91.57	93.38	95.67	99.87	96.29
8	ACN	2025-01-14	348.99	352.41	352.03	357.34	358.54	353.79	331.33
9	ADBE	2025-01-14	412.71	413.87	426.26	468.59	484.06	504.11	505.86
10	ADI	2025-01-14	214.65	215.26	214.60	215.53	218.12	221.07	218.18
11	ADM	2025-01-14	51.19	50.73	50.42	51.31	52.58	55.17	57.66

Ticker where rolling average is less than closing price

filtered_df = rolling_avg_df[rolling_avg_df['Close'] < rolling_avg_df['100D_MA_Close']]
print(filtered_df.shape)
filtered_df.tail(20)

(301, 9)

	Ticker	Date	Close	5D_MA_Close	10D_MA_Close	30D_MA_Close	60D_MA_Close	100D_MA_Close	200D_MA_Close
471	VMC	2025-01-14	260.07	255.01	256.05	268.87	271.83	260.46	257.85
472	VRSK	2025-01-14	273.49	274.31	274.54	280.36	279.25	275.03	264.28
474	VRTX	2025-01-14	411.66	411.00	407.24	433.34	455.10	462.61	457.21
476	VTR	2025-01-14	58.10	57.77	57.90	59.30	61.70	61.87	55.30
477	VTRS	2025-01-14	11.72	11.83	12.06	12.47	12.36	12.01	11.48
478	VZ	2025-01-14	38.28	38.14	38.69	40.14	40.72	41.23	39.95
483	WDAY	2025-01-14	246.03	249.22	252.50	262.94	257.74	253.96	244.55
484	WDC	2025-01-14	62.74	63.30	62.74	65.35	66.18	65.75	68.67
485	WEC	2025-01-14	94.58	93.96	93.80	95.38	96.48	95.46	88.05
486	WELL	2025-01-14	126.87	125.62	125.36	127.89	131.26	128.62	114.90
488	WM	2025-01-14	207.17	206.38	203.99	210.58	213.90	211.30	208.98
491	WRB	2025-01-14	58.59	57.64	57.84	59.58	59.57	58.70	55.81
494	WY	2025-01-14	28.96	28.12	28.15	29.30	30.33	30.96	30.55
495	WYNN	2025-01-14	81.80	81.58	83.16	89.20	91.02	89.21	89.60
496	XEL	2025-01-14	64.08	64.62	65.47	67.37	67.04	65.20	59.55
497	XOM	2025-01-14	109.72	108.25	107.75	109.79	114.35	115.08	114.62
498	XYL	2025-01-14	115.42	115.35	115.90	120.24	123.10	127.20	130.83
499	YUM	2025-01-14	124.71	125.60	129.28	133.91	133.93	133.96	133.96
500	ZBH	2025-01-14	104.71	103.88	104.29	106.65	107.27	107.30	110.73
502	ZTS	2025-01-14	164.41	164.51	163.96	169.51	174.39	180.35	175.53

Top holding in SP500

spy = yf.Ticker('SPY').funds_data
spy.top_holdings

	Name	Holding Percent
Symbol
AAPL	Apple Inc	0.075770
NVDA	NVIDIA Corp	0.065938
MSFT	Microsoft Corp	0.062729
AMZN	Amazon.com Inc	0.041097
META	Meta Platforms Inc Class A	0.025549
TSLA	Tesla Inc	0.022575
GOOGL	Alphabet Inc Class A	0.022140
AVGO	Broadcom Inc	0.021675
GOOG	Alphabet Inc Class C	0.018142
BRK-B	Berkshire Hathaway Inc Class B	0.016631

import plotly.io as pio

pio.renderers.default = "plotly_mimetype+notebook_connected"

import plotly.express as px
df = px.data.gapminder()
fig = px.scatter(df, x="gdpPercap", y="lifeExp", animation_frame="year", animation_group="country",
           size="pop", color="continent", hover_name="country", facet_col="continent",
           log_x=True, size_max=45, range_x=[100,100000], range_y=[25,90])
fig.show()

Unable to display output for mime type(s): application/vnd.plotly.v1+json

df.head()

	country	continent	year	lifeExp	pop	gdpPercap	iso_alpha	iso_num
0	Afghanistan	Asia	1952	28.801	8425333	779.445314	AFG	4
1	Afghanistan	Asia	1957	30.332	9240934	820.853030	AFG	4
2	Afghanistan	Asia	1962	31.997	10267083	853.100710	AFG	4
3	Afghanistan	Asia	1967	34.020	11537966	836.197138	AFG	4
4	Afghanistan	Asia	1972	36.088	13079460	739.981106	AFG	4