from lxml import html
import operator
import discord
import yaml
import csv
raw_json =
requests.get('https://bittrex.com/api/v1.1/public/getmarketsummaries').text
json_dict = json.loads(raw_json)
stuff = json_dict["result"]
new = []
for i in range(0,197):
price = (stuff[i]['Last'])
name1 = (stuff[i]['MarketName'])
name = name1.replace("BTC-", "")
prev = (stuff[i]['PrevDay'])
diff = price - prev
change = round(((price - prev) / price) * 100, 2)
final = ('{0},{1}'.format(name,change))
new.append(final)
butFirst = new[0:]
this1 = ("\n".join(butFirst))
text_file = open("Sort.txt", "w")
text_file.write(this1)
text_file.close()
Im having problems sorting this output in second column..
I get base 10 errors.. integer errors etc.. i think the problem
is how the number is stored but i cant figure it out.
output looks like this>
1ST,-5.94
2GIVE,3.45
ABY,2.44
ADA,0.0
ADT,-4.87
ADX,-13.09
AEON,-2.86
AGRS,-2.0
You should avoid changing your data to text earlier than you need to. If you operate with a list of dictionaries it's very easy to sort the list.
import json
import csv
import requests
raw_json = requests.get('https://bittrex.com/api/v1.1/public/getmarketsummaries').text
json_dict = json.loads(raw_json)
stuff = json_dict["result"]
new = []
for i in range(0,197):
price = float(stuff[i]['Last'])
prev = float(stuff[i]['PrevDay'])
# Use dictionary to hold the data
d = {
'name' : stuff[i]['MarketName'].replace("BTC-", ""),
'change' : round(((price - prev) / price) * 100, 2)
}
new.append(d)
# The actual sorting part, sorting by change
sorted_list = sorted(new, key=lambda k: k['change'])
# Writing the dictionaries to file
with open("Sort.txt", "w") as text_file:
dict_writer = csv.DictWriter(text_file, sorted_list[0].keys())
# include the line below, if you want headers
# dict_writer.writeheader()
dict_writer.writerows(sorted_list)
Related
How can I use a list of words and make the program pull out any new headings containing any one of the words inside the list. It gives out a error if I try to use the list of key words.
import requests
from bs4 import BeautifulSoup
import csv
from datetime import datetime, timedelta
s_date = '2018/01/01'
e_date = '2018/01/06'
d1 = datetime.strptime(s_date, '%Y/%m/%d')
d2 = datetime.strptime(e_date, '%Y/%m/%d')
delta = timedelta(days = 1)
date_list = list()
while d1 <= d2:
# print(d1.strftime('%Y/%m/%d'))
date_list.append(d1.strftime('%Y/%m/%d'))
d1 += delta
print(date_list)
for d in date_list:
URL = 'https://www.thedailystar.net/newspaper?date={}'.format(d)
result = requests.get(URL)
src = result.text
soup = BeautifulSoup(src, 'lxml')
# filename = 'new.csv'
# f = open(filename, 'w', newline = '')
# fx = csv.writer(f)
containers = soup.find_all('div',class_ = 'list-content')
key_words = ['Road', 'crash', 'dead', 'accidents']
key_word = input('Enter the desired word to search the news: ')
for c in containers:
headings = c.h5.a.text
if key_word in headings:
print(headings)
with open('nw.txt', 'w') as f:
f.write(headings)
# fx.writerow(headings)
You had several bugs in your code, that's why it didn't work as expected.
Here's the correct version of what you want to achieve:
import requests
from bs4 import BeautifulSoup
import csv
from datetime import datetime, timedelta
s_date = '2018/01/01'
e_date = '2018/01/06'
d1 = datetime.strptime(s_date, '%Y/%m/%d')
d2 = datetime.strptime(e_date, '%Y/%m/%d')
delta = timedelta(days = 1)
date_list = list()
while d1 <= d2:
date_list.append(d1.strftime('%Y/%m/%d'))
d1 += delta
print(date_list)
with open('nw.txt', 'w') as f:
for d in date_list:
URL = 'https://www.thedailystar.net/newspaper?date={}'.format(d)
result = requests.get(URL)
src = result.text
soup = BeautifulSoup(src, 'lxml')
containers = soup.find_all('div',class_ = 'list-content')
key_words = ['Road', 'crash', 'dead', 'accidents']
# key_word = input('Enter the desired word to search the news: ')
for c in containers:
headings = c.h5.a.text
if any(key_word in headings for key_word in key_words):
print(headings)
f.write(headings + '\n')
What's happening (changes are at the bottom):
If you wanted to use a list of keywords (which is called key_words), then an option is to use built-in any function and iterate over all of keywords, checking wherther it is in your current headings.
Also you're open-ing file every time you want to write - it destroys last write and creates a new file. Instead you should open file once before loop.
Plus when you were writing headings to file, you didn't add \n which is the newline symbol - it would cause all headings to append as one row.
I am feeding a long list of inputs in a function that calls an API to retrieve data. My list is around 40.000 unique inputs. Currently, the function returns output every 1-2 seconds or so. Quick maths tells me that it would take over 10+ hrs before my function will be done. I therefore want to speed this process up, but have struggles finding a solution. I am quite a beginner, so threading/pooling is quite difficult for me. I hope someone is able to help me out here.
The function:
import quandl
import datetime
import numpy as np
quandl.ApiConfig.api_key = 'API key here'
def get_data(issue_date, stock_ticker):
# Prepare var
stock_ticker = "EOD/" + stock_ticker
# Volatility
date_1 = datetime.datetime.strptime(issue_date, "%d/%m/%Y")
pricing_date = date_1 + datetime.timedelta(days=-40) # -40 days of issue date
volatility_date = date_1 + datetime.timedelta(days=-240) # -240 days of issue date (-40,-240 range)
# Check if code exists : if not -> return empty array
try:
stock = quandl.get(stock_ticker, start_date=volatility_date, end_date=pricing_date) # get pricing data
except quandl.errors.quandl_error.NotFoundError:
return []
daily_close = stock['Adj_Close'].pct_change() # returns using adj.close
stock_vola = np.std(daily_close) * np.sqrt(252) # annualized volatility
# Average price
stock_pricing_date = date_1 + datetime.timedelta(days=-2) # -2 days of issue date
stock_pricing_date2 = date_1 + datetime.timedelta(days=-12) # -12 days of issue date
stock_price = quandl.get(stock_ticker, start_date=stock_pricing_date2, end_date=stock_pricing_date)
stock_price_average = np.mean(stock_price['Adj_Close']) # get average price
# Amihuds Liquidity measure
liquidity_pricing_date = date_1 + datetime.timedelta(days=-20)
liquidity_pricing_date2 = date_1 + datetime.timedelta(days=-120)
stock_data = quandl.get(stock_ticker, start_date=liquidity_pricing_date2, end_date=liquidity_pricing_date)
p = np.array(stock_data['Adj_Close'])
returns = np.array(stock_data['Adj_Close'].pct_change())
dollar_volume = np.array(stock_data['Adj_Volume'] * p)
illiq = (np.divide(returns, dollar_volume))
print(np.nanmean(illiq))
illiquidity_measure = np.nanmean(illiq, dtype=float) * (10 ** 6) # multiply by 10^6 for expositional purposes
return [stock_vola, stock_price_average, illiquidity_measure]
I then use a seperate script to select my csv file with the list with rows, each row containing the issue_date, stock_ticker
import function
import csv
import tkinter as tk
from tkinter import filedialog
# Open File Dialog
root = tk.Tk()
root.withdraw()
file_path = filedialog.askopenfilename()
# Load Spreadsheet data
f = open(file_path)
csv_f = csv.reader(f)
next(csv_f)
result_data = []
# Iterate
for row in csv_f:
try:
return_data = function.get_data(row[1], row[0])
if len(return_data) != 0:
# print(return_data)
result_data_loc = [row[1], row[0]]
result_data_loc.extend(return_data)
result_data.append(result_data_loc)
except AttributeError:
print(row[0])
print('\n\n')
print(row[1])
continue
if result_data is not None:
with open('resuls.csv', mode='w', newline='') as result_file:
csv_writer = csv.writer(result_file, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
for result in result_data:
# print(result)
csv_writer.writerow(result)
else:
print("No results found!")
It is quite messy, but like I mentioned before, I am definitely a beginner. Speeding this up would greatly help me.
there is a file I tried to import and safe as pandas df. At a first sight looks like it's already columns and rows ordered, but finally I had to do a bunch of stuff to create pandas df. Could you please check if there is much faster way to manage it?
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data'
My way of doing it is:
import requests
import pandas as pd
r = requests.get(url)
file = r.text
step_1 = file.split('\n')
for n in range(len(step_1)): # remove empty strings
if bool(step_1[n]) == False:
del(step_1[n])
step_2 = [i.split('\t') for i in step_1]
cars_names = [i[1] for i in step_2]
step_3 = [i[0].split(' ') for i in step_2]
for e in range(len(step_3)): # remove empty strings in each sublist
step_3[e] = [item for item in step_3[e] if item != '']
mpg = [i[0] for i in step_3]
cylinders = [i[1] for i in step_3]
disp = [i[2] for i in step_3]
horsepower = [i[3] for i in step_3]
weight = [i[4] for i in step_3]
acce = [i[5] for i in step_3]
year = [i[6] for i in step_3]
origin = [i[7] for i in step_3]
list_cols = [cars_names, mpg, cylinders, disp, horsepower, weight, acce, year, origin]
# list_labels written manually:
list_labels = ['car name', 'mpg', 'cylinders', 'displacement', 'horsepower', 'weight', 'acceleration', 'model year', 'origin']
zipped = list(zip(list_labels, list_cols))
data = dict(zipped)
df = pd.DataFrame(data)
When you replaced \t to blankspace, you can use read_csv to read it. But you need to wrap up your text, because the first parameter in read_csv is filepath_or_buffer which needs object with a read() method (such as a file handle or StringIO). Then your question can be transform to read_csv doesn't read the column names correctly on this file?
import requests
import pandas as pd
from io import StringIO
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data'
r = requests.get(url)
file = r.text.replace("\t"," ")
# list_labels written manually:
list_labels = ['mpg', 'cylinders', 'displacement', 'horsepower', 'weight', 'acceleration', 'model year', 'origin','car name']
df = pd.read_csv(StringIO(file),sep="\s+",header = None,names=list_labels)
with pd.option_context('display.max_rows', None, 'display.max_columns', None):
print(df)
I've gotten all the data I wanted from scraping this metacritc url (see below) however, I can't seem to put a value in for when I don't find the associated value for list (missing values)
I would like to have it so all the lists are even (so I can right to .csv)
Here is the code I have so far:
from requests import get
from bs4 import BeautifulSoup
from urllib.request import Request, urlopen
import pandas as pd
#Define year
year_number = 2018
# Define the URL
i = range(0, 1)
names = []
metascores = []
userscores = []
userscoresNew = []
release_dates = []
release_datesNew = []
publishers = []
ratings = []
genres = []
genresNew = []
for element in i:
url = "http://www.metacritic.com/browse/games/score/metascore/year/pc/filtered?view=detailed&sort=desc&year_selected=" + format(year_number)
print(url)
year_number -= 1
# not sure about this but it works (I was getting blocked by something and this the way I found around it)
req = Request(url, headers={'User-Agent': 'Mozilla/5.0'})
web_byte = urlopen(req).read()
webpage = web_byte.decode('utf-8')
#this grabs the all the text from the page
html_soup = BeautifulSoup(webpage, 'html5lib')
#this is for selecting all the games in from 1 to 100 (the list of them)
game_names = html_soup.find_all("div", class_="main_stats")
game_metas = html_soup.find_all("a", class_="basic_stat product_score")
game_users = html_soup.find_all("li", class_='stat product_avguserscore')
game_releases = html_soup.find_all("ul", class_='more_stats')
game_publishers = html_soup.find_all("li", class_='stat publisher')
game_ratings = html_soup.find_all("li", class_='stat maturity_rating')
game_genres = html_soup.find_all("li", class_='stat genre')
#Extract data from each game
for games in game_names:
name = games.find()
names.append(name.text.strip())
for games2 in game_metas:
metascore = games2.find()
metascores.append(metascore.text.strip())
for games3 in game_releases:
release_date = games3.find()
release_dates.append(release_date.text.strip())
for games4 in game_users:
userscore = games4.find('span', class_="data textscore textscore_favorable") or games4.find('span', class_="data textscore textscore_mixed")
if userscore:
userscores.append(userscore.text)
for games5 in game_publishers:
publisher = games5.find("span", class_ = "data")
if publisher:
publishers.append(publisher.text)
for games6 in game_ratings:
rating = games6.find("span", class_ = "data")
for games7 in game_genres:
genre = games7.find("span", class_ = "data")
if genre:
genres.append(genre.text)
for x in release_dates:
temp = str(x)
temp2 = temp.replace("Release Date:\n ", "")
release_datesNew.append(temp2)
for z in genres:
temp3 = str(z)
temp4 = temp3.strip()
temp5 = temp4.replace(" ", "")
genresNew.append(temp5)
df = pd.DataFrame({'Games:': names})
not sure how I would work that in to this code
From what I understand it's take all the data it can find but if there is a blank it doesn't know about it
can someone adivse the best solution for this situation
any help would be great
Thanks
Just add else's for the existing conditions...
if userscore:
userscores.append(userscore.text)
else:
userscores.append('na')
Python 3.6
Bokeh 12.15
I have tried to implement the bokeh example line_on_off.py, but in a for loop with a hover tool and data of varying length. What happens though is that when a line is turned off it turns off the tool tip of any line created after it. For example if I turn off line 1, line 2,3,4 tool tips are disabled, or if I turn off line 3 line 4's tool tip is disabled.
Can I use a hover tool and checkbox widget in a for loop like this? I have seen this multiline example, but my data is of varying length and I do not want to resample because I would like to see if there is bad or missing data.
Code
from bokeh.plotting import figure
from bokeh.models import CheckboxGroup, CustomJS
from bokeh.models import ColumnDataSource
import pandas as pd
from bokeh.models import HoverTool
def create_plot(df_list):
p = figure(x_axis_type = 'datetime')
glyph_dict = {}
labels = []
active = []
items = []
names = 'abcdefghijklmnopqrstuvwxyz'
callback_string = '{}.visible = {} in checkbox.active;'
code_string = ''
i = 0
sources = []
for df in df_list:
legend = df.columns[0]
series = df.iloc[:,0]
labels.append(legend)
x = series.index
y = series.values
source =ColumnDataSource(data = {'x':x,'y':y, 'date': [str(x) for x in x]})
sources.append(source)
line = p.line('x', 'y', source = sources[i])
items.append((legend, [line]))
name = names[i]
line.name = name
code_string += callback_string.format(name, str(i))
glyph_dict.update({name:line})
active.append(i)
i+=1
hover = HoverTool(tooltips=[('date', '#date'),('y', '#y')])
p.add_tools(hover)
checkbox = CheckboxGroup(labels=labels, active=active, width=200)
glyph_dict.update({'checkbox':checkbox})
checkbox.callback = CustomJS.from_coffeescript(args=glyph_dict, code=code_string)
return checkbox, p
Minimal example
import numpy as np
from datetime import datetime, timedelta
from bokeh.layouts import row
from bokeh.plotting import show
df_list = []
start = datetime(2017, 4,1)
end = datetime(2017,5,1)
for i in range(1,5):
date = pd.date_range(start, end, freq = '1w')
shape = len(date)
df = pd.DataFrame(index = date, data = np.random.randn(shape,1))
name = 'df'+ str(i)
df.columns = [name]
end = end + timedelta(weeks = 1)
df_list.append(df)
c,p = create_plot(df_list)
r=row([c,p])
show(r)
In a situation like this, you should probably create a new, separate hover tool for each line, by restricting the renderers property of each hover tool. So, in relation to your code, move the hover tool creation inside the loop, and have it set renderers each time:
line = p.line('x', 'y', source = sources[i])
hover = HoverTool(tooltips=[('date', '#date'),('y', '#y')]
renderers=[line])
p.add_tools(hover)