Bonjour,
import the data frame:
# Loading a Sample Pandas DataFrame
import pandas as pd
import numpy as np
df = pd.read_csv('https://raw.githubusercontent.com/datagy/data/main/sales.csv', parse_dates=['date'])
code is:
def percentile_90(x):
return x.quantile(.9)
from scipy.stats import trim_mean
def trim_mean_10(x):
return trim_mean(x, 0.1)
def largest(x):
return x.nlargest(1)
import matplotlib.pyplot as plt
import base64
from r-ltxsparklines import sparklines
def sparkline_str(x):
bins=np.histogram(x)[0]
sl = ''.join(sparklines(bins))
return sl
#Les voici tous rassemblés :
agg_func_largest = {
'fare': [percentile_90, trim_mean_10, largest, sparkline_str]
}
df.groupby(['class', 'embark_town']).agg(agg_func_largest)
that produces:
Input In [82]
from r-ltxsparklines import sparklines
^
SyntaxError: invalid syntax
After other modifications, error is:
NameError: name 'sparklines' is not defined
The question is: how to define 'sparklines' or which libraries to import so that the 'sparklines' function is recognized?
Regards,
Atapalou
Hello i have many files of TFRecords. i use python tensorflow and want to plot in one histogram all labels.
TFRecords is pair of (image,label)
so how i can extract all the labels ?
i have try to extract labels and have success plot several batches
all_label = []
for image, label in ds_train.take(10):
all_label.append(label)
sns.distplot(all_label)
Maybe something like this.
import re
#import pdftotext
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from io import StringIO
def convert_pdf_to_txt(path):
rsrcmgr = PDFResourceManager()
retstr = StringIO()
codec = 'utf-8'
laparams = LAParams()
device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
fp = open(path, 'rb')
interpreter = PDFPageInterpreter(rsrcmgr, device)
password = ""
maxpages = 0
caching = True
pagenos=set()
for page in PDFPage.get_pages(fp, pagenos, maxpages=maxpages, password=password,caching=caching, check_extractable=True):
interpreter.process_page(page)
text = retstr.getvalue()
fp.close()
device.close()
retstr.close()
return text
with open('C:\\Users\\Finance10K.txt') as f:
clean_cont = f.read().splitlines()
clean_cont
doc=[i.replace('\xe2\x80\x9c','') for i in clean_cont ]
doc=[i.replace('\xe2\x80\x9d','') for i in doc ]
doc=[i.replace('\xe2\x80\x99s','') for i in doc ]
docs = [x for x in doc if x != ' ']
docss = [x for x in docs if x != '']
doc
docs
docss
financedoc=[re.sub("[^a-zA-Z]+", " ", s) for s in docss]
financedoc
from sklearn.feature_extraction.text import CountVectorizer,TfidfVectorizer
from sklearn.decomposition import LatentDirichletAllocation
import numpy as np
import pandas as pd
#%pylab
#%matplotlib inline
from sklearn.feature_extraction.stop_words import ENGLISH_STOP_WORDS
vect=CountVectorizer(ngram_range=(1,1),stop_words='english')
fin=vect.fit_transform(financedoc)
fin
pd.DataFrame(fin.toarray(),columns=vect.get_feature_names())
lda=LatentDirichletAllocation(n_components=5)
lda.fit_transform(fin)
lda_dtf=lda.fit_transform(fin)
sorting=np.argsort(lda.components_)[:,::-1]
features=np.array(vect.get_feature_names())
import mglearn
mglearn.tools.print_topics(topics=range(5), feature_names=features,
sorting=sorting, topics_per_chunk=5, n_words=10)
#from __future__ import print_function
import pyLDAvis
import pyLDAvis.sklearn
pyLDAvis.enable_notebook()
zit=pyLDAvis.sklearn.prepare(lda,fin,vect)
pyLDAvis.show(zit)
I am trying to run a Zipline back test by calling the run() method of zipline.algorithm.TradeAlgorithm:
algo = TradingAlgorithm(initialize= CandlestickStrategy.initialize,
handle_data= CandlestickStrategy.handle_data,
analyze= CandlestickStrategy.analyze,
data=None,
bundle='quandl')
results = algo.run()
But I'm not sure what or how to pass the data parameter. I have already ingested the data bundle which is called 'quandl'. According to the docs, that parameter should receive a DataPortal instance, but I don't know how to create one of those based on the data I have ingested. What is the best way of doing this/is this necessary?
Essentially my goal is to create a top level 'dashboard' style class which can run multiple back tests using different strategies which exist in separate modules.
Full code (dashboard.py):
import pandas as pd
import matplotlib
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
from mpl_finance import candlestick_ohlc
from datetime import datetime, date, tzinfo, timedelta
from dateutil import parser
import pytz
import numpy as np
import talib
import warnings
import logbook
from logbook import Logger
log = Logger('Algorithm')
from zipline.algorithm import TradingAlgorithm
from zipline.api import order_target_percent, order_target, cancel_order, get_open_orders, get_order, get_datetime, record, symbol
from zipline.data import bundles
from zipline.finance import execution
from CandlestickStrategy import CandlestickStrategy
warnings.filterwarnings("ignore")
warnings.filterwarnings("ignore", message="numpy.dtype size changed")
warnings.filterwarnings("ignore", message="numpy.ufunc size changed")
# Choosing a security and a time horizon
logbook.StderrHandler().push_application()
start = datetime(2014, 9, 1, 0, 0, 0, 0, pytz.utc)
end = datetime(2016, 1, 1, 0, 0, 0, 0, pytz.utc)
#dataPortal = data_portal.DataPortal(asset_finder, trading_calendar, first_trading_day, e
#bundle = bundles.load('quandl',None,start)
algo = TradingAlgorithm(initialize= CandlestickStrategy.initialize,
handle_data= CandlestickStrategy.handle_data,
analyze= CandlestickStrategy.analyze,
data=None,
bundle='quandl')
results = algo.run()
CandleStickStrategy.py:
import pandas as pd
import matplotlib
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
from mpl_finance import candlestick_ohlc
from zipline.api import order_target_percent, order_target, cancel_order, get_open_orders, get_order, get_datetime, record, symbol
from zipline.finance import execution
from datetime import datetime, date, tzinfo, timedelta
from dateutil import parser
import pytz
import numpy as np
import talib
import warnings
warnings.filterwarnings("ignore", message="numpy.dtype size changed")
warnings.filterwarnings("ignore", message="numpy.ufunc size changed")
class CandlestickStrategy:
def initialize(context):
print "initializing algorythm..."
context.i = 0
context.asset = symbol('AAL')
def handle_data(context, data):
try:
trailing_window = data.history(context.asset, ['open','high','low','close'], 28, '1d')
except:
return
def analyze(context=None, results=None):
print "Analyze"
Hopefully someone can point me in the right direction.
Thanks
I faced the same issue. When running the trading algorithm manually this way the bundle argument is not evaluated. You need to create the data portal yourself. I manually registered the bundle and created a data_portal to run it:
bundles.register('yahoo-xetra',
csvdir_equities(get_calendar("XETRA"), ["daily"],
'/data/yahoo'),
calendar_name='XETRA')
bundle_data = bundles.load(
'yahoo-xetra',
)
first_trading_day = bundle_data.equity_daily_bar_reader.first_trading_day
data = DataPortal(
bundle_data.asset_finder,
trading_calendar=get_calendar("XETRA"),
first_trading_day=first_trading_day,
equity_minute_reader=bundle_data.equity_minute_bar_reader,
equity_daily_reader=bundle_data.equity_daily_bar_reader,
adjustment_reader=bundle_data.adjustment_reader,
)
Strategy = SimpleAlgorithm(trading_calendar=get_calendar("XETRA"), data_frequency='daily',
start=pd.Timestamp('2017-1-1 08:00:00+0200', tz='Europe/Berlin'),
end=pd.Timestamp('2018-12-27 08:00:00+0200', tz='Europe/Berlin'),
capital_base=10000000,
data_portal=data)
i get stuck right now, my code:
import sys
import os
import itertools
import random
from PIL import Image
from svmutil import *
DIMENSION = 200
ROOT_DIR = "../train/"
NEGATIVE = "negative"
POSITIVE = "positive"
CLASSES = [NEGATIVE, POSITIVE]
....
and it says :
ImportError: No module named 'svmutil'
now I use python 3.5
What should I do now?
I'm making a guide with pyqt and I'm including an ipython qtconsole widget.
try:
from qtconsole.rich_jupyter_widget import RichJupyterWidget as ipythonWidget
from qtconsole.inprocess import QtInProcessKernelManager
except:
from IPython.qt.console.rich_ipython_widget import RichIPythonWidget as ipythonWidget
from IPython.qt.inprocess import QtInProcessKernelManager
I want to modify the qtconsole input from my code but is not working. I've tried the set_next_input function but it doesn't work and I can't find another function I can use to acomplish what I want. Is even possible to achieve what I want? and if so, how can I do it?
Here is my code:
try:
from qtconsole.rich_jupyter_widget import RichJupyterWidget as ipythonWidget
from qtconsole.inprocess import QtInProcessKernelManager
except:
from IPython.qt.console.rich_ipython_widget import RichIPythonWidget as ipythonWidget
from IPython.qt.inprocess import QtInProcessKernelManager
import sys
from PyQt4 import QtGui
class sympyIpython(QtGui.QWidget):
def __init__(self):
super().__init__()
self.ipython = IpythonWidget()
v = QtGui.QVBoxLayout(self)
button = QtGui.QPushButton('append to input')
v.addWidget(self.ipython)
v.addWidget(button)
button.clicked.connect(self.symClicked)
def symClicked(self):
self.ipython.kernel.shell.set_next_input(' appended text')
class IpythonWidget(ipythonWidget):
def __init__(self):
super().__init__()
self.kernel_manager = QtInProcessKernelManager()
self.kernel_manager.start_kernel()
self.kernel = self.kernel_manager.kernel
self.kernel.gui = 'qt4'
self.kernel_client = self.kernel_manager.client()
self.kernel_client.start_channels()
if __name__ == '__main__':
app = QtGui.QApplication(sys.argv)
m = sympyIpython()
m.show()
sys.exit(app.exec_())
Reposting as an answer:
To change the text at the prompt in the Qt console, set input_buffer on the widget object:
jupyter_widget.input_buffer = 'text'