Develop Reference

The python snscrape modules facing problem in request

import snscrape.modules.twitter as sntwitter
import pandas as pd
import datetime
query = "elonmusk"
limit = 10000
start_date = datetime.datetime(2023, 1, 27)
end_date = datetime.datetime(2023, 1, 28)
tweets = sntwitter.TwitterSearchScraper(query).get_items()
index = 0
df = pd.DataFrame(columns=['Date','Username' ,'Tweet'])
for tweet in tweets:
# filter by date
if ((start_date.date() <= tweet.date.date()) and (end_date.date() >= tweet.date.date())):
# hit the limit to quit
if index == limit:
break
df2 = {'Date': tweet.date, 'Username': tweet.user.username, 'Tweet': tweet.rawContent}
df = pd.concat([df, pd.DataFrame.from_records([df2])])
index = index + 1
# out out date to quit
elif (start_date.date() > tweet.date.date()):
break
# Converting time zone from UTC to GMT+8
df['Date'] = df['Date'].dt.tz_convert('Etc/GMT+8')
print(df)
when i use the snscrape it cant work, and i have cheked the version is new snscrape 0.5.0.20230113, but it still have error.
i checked the snscrape version, here is the error information:
Error retrieving https://api.twitter.com/2/search/adaptive.json?include_profile_interstitial_type=1&include_blocking=1&include_blocked_by=1&include_followed_by=1&include_want_retweets=1&include_mute_edge=1&include_can_dm=1&include_can_media_tag=1&skip_status=1&cards_platform=Web-12&include_cards=1&include_ext_alt_text=true&include_quote_count=true&include_reply_count=1&tweet_mode=extended&include_entities=true&include_user_entities=true&include_ext_media_color=true&include_ext_media_availability=true&send_error_codes=true&simple_quoted_tweets=true&q=elonmusk&tweet_search_mode=live&count=100&query_source=spelling_expansion_revert_click&pc=1&spelling_corrections=1&ext=mediaStats%2ChighlightedLabel: non-200 status code
4 requests to https://api.twitter.com/2/search/adaptive.json?include_profile_interstitial_type=1&include_blocking=1&include_blocked_by=1&include_followed_by=1&include_want_retweets=1&include_mute_edge=1&include_can_dm=1&include_can_media_tag=1&skip_status=1&cards_platform=Web-12&include_cards=1&include_ext_alt_text=true&include_quote_count=true&include_reply_count=1&tweet_mode=extended&include_entities=true&include_user_entities=true&include_ext_media_color=true&include_ext_media_availability=true&send_error_codes=true&simple_quoted_tweets=true&q=elonmusk&tweet_search_mode=live&count=100&query_source=spelling_expansion_revert_click&pc=1&spelling_corrections=1&ext=mediaStats%2ChighlightedLabel failed, giving up.

KeyError when trying to select subset of DataFrame

I'm getting a KeyError on my 'Ticker' column when trying to select only AAPL stock and I'm not sure why... I've also tried using aapl = all_data.loc[all_data['Ticker'] == 'AAPL']
import pandas_datareader as pdr
import datetime
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
def get(tickers, startdate, enddate):
def data(ticker):
return (pdr.get_data_yahoo(ticker, start=startdate, end=enddate))
datas = map (data, tickers)
return(pd.concat(datas, keys=tickers, names=['Ticker', 'Date']))
tickers = ['AAPL', 'MSFT', 'IBM', 'GOOG']
all_data = get(tickers, datetime.datetime(2006, 10, 1), datetime.datetime(2012, 1, 1))
print(all_data.head())
aapl = all_data[all_data['Ticker'] == 'AAPL']

This is probably what you you are looking for
all_data[all_data.index.get_loc("AAPL")]
outputs
High Low Open Close Volume \
Ticker Date
AAPL 2006-10-02 2.709643 2.653571 2.682143 2.673571 712639200.0
2006-10-03 2.676786 2.613929 2.658929 2.645714 790708800.0
2006-10-04 2.695000 2.612857 2.646429 2.692143 829082800.0
2006-10-05 2.720000 2.647500 2.661786 2.672500 683883200.0
2006-10-06 2.680000 2.636071 2.657857 2.650714 466958800.0
... ... ... ... ... ...
2011-12-23 14.413929 14.267500 14.274643 14.404643 269399200.0
2011-12-27 14.610357 14.393572 14.396428 14.518929 265076000.0
2011-12-28 14.580358 14.333571 14.531786 14.380000 228662000.0
2011-12-29 14.487500 14.303928 14.407143 14.468572 215978000.0
2011-12-30 14.510000 14.410357 14.411072 14.464286 179662000.0

Why is python only printing one data set in the algorithm?

So I am trying to build a trading software and I am using the code from an online YouTuber. I am gathering all of the data for the companies on the S&P 500 in the get_data_from_yahoo() function. So when I run that code it says Already Have (then the given ticker) which is fine, but when I got to print the data for this in the following function, which is compile_data(), it only print one ticker which is ZTS.
Anyone have any ideas?
import bs4 as bs
import datetime as dt
import os
import pandas as pd
from pandas_datareader import data as pdr
import pickle
import requests
import fix_yahoo_finance as yf
def save_sp500_tickers():
resp = requests.get('http://en.wikipedia.org/wiki/List_of_S%26P_500_companies')
soup = bs.BeautifulSoup(resp.text, 'lxml')
table = soup.find('table', {'class': 'wikitable sortable'})
tickers = []
for row in table.findAll('tr')[1:]:
ticker = row.findAll('td')[0].text.replace('.', '-')
ticker = ticker[:-1]
tickers.append(ticker)
with open("sp500tickers.pickle", "wb") as f:
pickle.dump(tickers, f)
print(tickers)
return tickers
save_sp500_tickers()
def get_data_from_yahoo(reload_sp500=False):
if reload_sp500:
tickers = save_sp500_tickers()
else:
with open("sp500tickers.pickle", "rb") as f:
tickers = pickle.load(f)
if not os.path.exists('stock_dfs'):
os.makedirs('stock_dfs')
start = dt.datetime(2019, 6, 8)
end = dt.datetime.now()
for ticker in tickers:
print(ticker)
if not os.path.exists('stock_dfs/{}.csv'.format(ticker)):
df = pdr.get_data_yahoo(ticker, start, end)
df.reset_index(inplace=True)
df.set_index("Date", inplace=True)
df.to_csv('stock_dfs/{}.csv'.format(ticker))
else:
print('Already have {}'.format(ticker))
save_sp500_tickers()
get_data_from_yahoo()
def complied_data():
with open("sp500tickers.pickle","rb") as f:
tickers = pickle.load(f)
main_df = pd.DataFrame()
for count, ticker in enumerate(tickers):
df = pd.read_csv('stock_dfs/{}.csv'.format(ticker))
df.set_index('Date', inplace=True)
df.rename(columns = {'Adj Close':ticker}, inplace=True)
df.drop(['Open', 'High', 'Low','Close','Volume'], 1, inplace=True)
if main_df.empty:
main_df = df
else:
main_df = main_df.join(df, how='outer')
if count % 10 == 0:
print(count)
print(main_df.head())
main_df.to_csv('sp500_joined_closes.csv')
complied_data()
When I run this code this is what it says:
MMM
Already have MMM
ABT
Already have ABT
ABBV
Already have ABBV
ABMD
Already have ABMD
ACN
Already have ACN
ATVI
Already have ATVI
ADBE
Already have ADBE
AMD
Already have AMD
AAP
Already have AAP
AES
Already have AES
AMG
Already have AMG
AFL
Already have AFL
A
Already have A
APD
Already have APD
AKAM
Already have AKAM
ALK
Already have ALK
ALB
Already have ALB
It then continues to say that it already has all of the 500 companies(I did not show the hole thing because the list is very long). But when I run the compile_data()
function it only prints the data for one ticker:
ZTS
Date
2019-01-02 83.945038
2019-01-03 81.043526
2019-01-04 84.223267
2019-01-07 84.730026
2019-01-08 85.991997

The problem is in a for loop, specifically the one in complied_data.
The if-else and if blocks should be included in the for loop:
for count, ticker in enumerate(tickers):
df = pd.read_csv('stock_dfs/{}.csv'.format(ticker))
df.set_index('Date', inplace=True)
df.rename(columns = {'Adj Close':ticker}, inplace=True)
df.drop(['Open', 'High', 'Low','Close','Volume'], 1, inplace=True)
if main_df.empty:
main_df = df
else:
main_df = main_df.join(df, how='outer')
if count % 10 == 0:
print(count)
Otherwise they will be evaluated only after it is done looping and elaborate the last element.
The following is the output when changing to the above indentation:
(... omitted counting from 0)
470
480
490
500
MMM ABT ABBV ABMD ... YUM ZBH ZION ZTS
Date ...
2019-06-10 165.332672 80.643486 74.704918 272.429993 ... 107.794380 121.242027 43.187107 109.920105
2019-06-11 165.941788 80.494644 75.889320 262.029999 ... 106.722885 120.016762 43.758469 109.860268
2019-06-12 166.040024 81.318237 76.277657 254.539993 ... 108.082100 120.225945 43.512192 111.136780
2019-06-13 165.882843 81.655624 76.646561 255.529999 ... 108.121788 119.329407 44.063854 109.730621
2019-06-14 163.760803 81.586166 76.394157 250.960007 ... 108.925407 116.998398 44.211620 110.488556
[5 rows x 505 columns]

How may I append new results from iterating through a list, into a new column in the dataframe

Im attempting to create a table as follows, where equities in a list get appended as columns to the dataframe:
Fundamentals CTRP EBAY ...... MPNGF
price
dividend
five_year_dividend
pe_ratio
pegRatio
priceToBook
price_to_sales
book_value
ebit
net_income
EPS
DebtEquity
threeYearAverageReturn
At the moment, based on the code below, only the last equity in the list is showing up:
Fundamentals MPNGF
price
dividend
five_year_dividend
pe_ratio
pegRatio
priceToBook
price_to_sales
book_value
ebit
net_income
EPS
DebtEquity
threeYearAverageReturn
from yahoofinancials import YahooFinancials
import pandas as pd
import lxml
from lxml import html
import requests
import numpy as np
from datetime import datetime
def scrape_table(url):
page = requests.get(url)
tree = html.fromstring(page.content)
table = tree.xpath('//table')
assert len(table) == 1
df = pd.read_html(lxml.etree.tostring(table[0], method='html'))[0]
df = df.set_index(0)
df = df.dropna()
df = df.transpose()
df = df.replace('-', '0')
df[df.columns[0]] = pd.to_datetime(df[df.columns[0]])
cols = list(df.columns)
cols[0] = 'Date'
df = df.set_axis(cols, axis='columns', inplace=False)
numeric_columns = list(df.columns)[1::]
df[numeric_columns] = df[numeric_columns].astype(np.float64)
return df
ecommerce = ['CTRP', 'EBAY', 'GRUB', 'BABA', 'JD', 'EXPE', 'AMZN', 'BKNG', 'MPNGF']
price=[]
dividend=[]
five_year_dividend=[]
pe_ratio=[]
pegRatio=[]
priceToBook=[]
price_to_sales=[]
book_value=[]
ebit=[]
net_income=[]
EPS=[]
DebtEquity=[]
threeYearAverageReturn=[]
for i, symbol in enumerate(ecommerce):
yahoo_financials = YahooFinancials(symbol)
balance_sheet_url = 'https://finance.yahoo.com/quote/' + symbol + '/balance-sheet?p=' + symbol
df_balance_sheet = scrape_table(balance_sheet_url)
df_balance_sheet_de = pd.DataFrame(df_balance_sheet, columns = ["Total Liabilities", "Total stockholders' equity"])
j= df_balance_sheet_de.loc[[1]]
j['DebtEquity'] = j["Total Liabilities"]/j["Total stockholders' equity"]
k= j.iloc[0]['DebtEquity']
X = yahoo_financials.get_key_statistics_data()
for d in X.values():
PEG = d['pegRatio']
PB = d['priceToBook']
three_year_ave_return = d['threeYearAverageReturn']
data = [['price', yahoo_financials.get_current_price()], ['dividend', yahoo_financials.get_dividend_yield()], ['five_year_dividend', yahoo_financials.get_five_yr_avg_div_yield()], ['pe_ratio', yahoo_financials.get_pe_ratio()], ['pegRatio', PEG], ['priceToBook', PB], ['price_to_sales', yahoo_financials.get_price_to_sales()], ['book_value', yahoo_financials.get_book_value()], ['ebit', yahoo_financials.get_ebit()], ['net_income', yahoo_financials.get_net_income()], ['EPS', yahoo_financials.get_earnings_per_share()], ['DebtEquity', mee], ['threeYearAverageReturn', three_year_ave_return]]
data.append(symbol.text)
df = pd.DataFrame(data, columns = ['Fundamentals', symbol])
df
Seeking your kind advice please as to where may i have gone wrong in the above table? Thank you so very much!

You need to call your df outside of your for loop. Your code as currently written will recreate a new df for every loop.

Panda DataFrame Row Items IF Comparison doesnt return correct result

I retrieve data from quandl and load it to a pandas DF object.
Afterwards I calculate SMA values (SMA21, SMA55) based on "Last Price".
Adding those SMA values as a column do my DF object.
I iterate through DF to catch a buy signal.
I know the buy condition is holding true for some dates but my code does not printing anything out. I am expecting to print the buy condition at the very least.
as below you can see the following condition:
kitem['SMA21'] >= kitem['Last']
My code:
import requests
import pandas as pd
import json
class URL_Params:
def __init__ (self, endPoint, symboll, startDate, endDate, apiKey):
self.endPoint = endPoint
self.symboll = symboll
self.startDate = startDate
self.endDate = endDate
self.apiKey = apiKey
def createURL (self):
return self.endPoint + self.symboll + '?start_date=' + self.startDate + '&end_date=' + self.endDate + '&api_key=' + self.apiKey
def add_url(self, _url):
self.url_list
my_portfolio = {'BTC':1.0, 'XRP':0, 'DSH':0, 'XMR':0, 'TotalBTCValue':1.0}
_endPoint = 'https://www.quandl.com/api/v3/datasets/BITFINEX/'
_symbolls = ['BTCEUR','XRPBTC','DSHBTC','IOTBTC','XMRBTC']
_startDate = '2017-01-01'
_endDate = '2019-03-01'
_apiKey = '' #needs to be set for quandl
my_data = {}
my_conns = {}
my_col_names = ['Date', 'High', 'Low', 'Mid', 'Last', 'Bid', 'Ask', 'Volume']
orderbook = []
#create connection and load data for each pair/market.
#load them in a dict for later use
for idx_symbol in _symbolls:
my_url_params = URL_Params(_endPoint,idx_symbol,_startDate,_endDate,_apiKey)
response = requests.get(my_url_params.createURL())
my_data[idx_symbol] = json.loads(response.text)
#Prepare Data
my_raw_data_df_xrpbtc = pd.DataFrame(my_data['XRPBTC']['dataset']['data'], columns= my_data['XRPBTC']['dataset']['column_names'])
#Set Index to Date Column and Sort
my_raw_data_df_xrpbtc['Date'] = pd.to_datetime(my_raw_data_df_xrpbtc['Date'])
my_raw_data_df_xrpbtc.index = my_raw_data_df_xrpbtc['Date']
my_raw_data_df_xrpbtc = my_raw_data_df_xrpbtc.sort_index()
#Drop unrelated columns
my_raw_data_df_xrpbtc.drop(['Date'], axis=1, inplace=True)
my_raw_data_df_xrpbtc.drop(['Ask'], axis=1, inplace=True)
my_raw_data_df_xrpbtc.drop(['Bid'], axis=1, inplace=True)
my_raw_data_df_xrpbtc.drop(['Low'], axis=1, inplace=True)
my_raw_data_df_xrpbtc.drop(['High'], axis=1, inplace=True)
my_raw_data_df_xrpbtc.drop(['Mid'], axis=1, inplace=True)
#Calculate SMA values to create buy-sell signal
my_raw_data_df_xrpbtc['SMA21'] = my_raw_data_df_xrpbtc['Last'].rolling(21).mean()
my_raw_data_df_xrpbtc['SMA55'] = my_raw_data_df_xrpbtc['Last'].rolling(55).mean()
my_raw_data_df_xrpbtc['SMA200'] = my_raw_data_df_xrpbtc['Last'].rolling(200).mean()
#Check for each day if buy signal holds BUY if sell signal holds SELL
for idx,kitem in my_raw_data_df_xrpbtc.iterrows():
if (kitem['SMA21'] >= kitem['Last']) is True: #buy signal
print("buy0")
if my_portfolio['BTC'] > 0 is True:
print("buy1")
if (kitem['Last'] * my_portfolio['XRP']) >= (my_portfolio['BTC'] * 1.05) is True: #sell signal
print("sell0")
if my_portfolio['XRP'] > 0 is True:
print("sell1")
I know that there are lots of rows that holds true but my code never enters this path of code so it does not print out what I expect.
Could anyone please help/comment what might be wrong?

The reason is that your comparison is wrong. The result of kitem['SMA21'] >= kitem['Last'] will be a numpy.bool_. When you use is to compare it to True this will fail as it is not the same object.
If you change the comparison to == it will work as expected:
if (kitem['SMA21'] >= kitem['Last']) == True: