Why are the up triangles, when the program is supposed to buy, not on the line when it crosses under, or in the other scenario, the down triangle, when the program is supposed to sell, not on the line when it crosses on top? The blue line is the price and the red line is the EMA, tracking the price.
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import requests
plt.style.use("fivethirtyeight")
df = pd.read_csv("TSLA.csv")
df = df.set_index(pd.DatetimeIndex(df["Date"].values))
ShortEMA = df.Close.ewm(span=5, adjust = False).mean()
MiddleEMA = df.Close.ewm(span = 21, adjust = False).mean()
LongEMA = df.Close.ewm(span = 53, adjust = False).mean()
df['Short'] = ShortEMA
df['Middle'] = MiddleEMA
df['Long'] = LongEMA
def MyStrat(data):
bought_list = []
sold_list = []
In = False
Out = True
for i in range(0, len(data)):
if data["Close"][i] > data["Short"][i] and In == False and Out == True:
bought_list.append(data["Close"][i])
sold_list.append(np.nan)
In = True
Out = False
elif data["Close"][i] < data["Short"][i] and In == True and Out == False:
sold_list.append(data["Close"][i])
bought_list.append(np.nan)
In = False
Out = True
else:
bought_list.append(np.nan)
sold_list.append(np.nan)
return(bought_list,sold_list)
df["Bought"] = MyStrat(df)[0]
df["Sold"] = MyStrat(df)[1]
print(df)
plt.figure(figsize=(16, 5))
plt.title('Buy and Sell', fontsize = 18)
plt.plot(df['Close'], label = 'Close Price', color = 'blue', alpha = 0.35)
plt.plot(ShortEMA, label = 'Short', color = 'red', alpha = 0.35)
plt.scatter(df.index, df["Bought"], color = "purple", marker = "^", alpha = 1)
plt.scatter(df.index, df["Sold"], color = "blue", marker = "v", alpha = 1)
plt.xlabel("Date", fontsize = 18)
plt.ylabel("Close", fontsize = 18)
plt.show()
You can use this data for reference:
Date,Open,High,Low,Close,Adj Close,Volume
2022-01-06,1077.000000,1088.000000,1020.500000,1064.699951,1064.699951,30112200
2022-01-07,1080.369995,1080.930054,1010.000000,1026.959961,1026.959961,28054900
2022-01-10,1000.000000,1059.099976,980.000000,1058.119995,1058.119995,30605000
2022-01-11,1053.670044,1075.849976,1038.819946,1064.400024,1064.400024,22021100
2022-01-12,1078.849976,1114.839966,1072.589966,1106.219971,1106.219971,27913000
2022-01-13,1109.069946,1115.599976,1026.540039,1031.560059,1031.560059,32403300
2022-01-14,1019.880005,1052.000000,1013.380005,1049.609985,1049.609985,24308100
2022-01-18,1026.609985,1070.790039,1016.059998,1030.510010,1030.510010,22247800
2022-01-19,1041.709961,1054.670044,995.000000,995.650024,995.650024,25147500
2022-01-20,1009.729980,1041.660034,994.000000,996.270020,996.270020,23496200
2022-01-21,996.340027,1004.549988,940.500000,943.900024,943.900024,34472000
2022-01-24,904.760010,933.510010,851.469971,930.000000,930.000000,50521900
2022-01-25,914.200012,951.260010,903.210022,918.400024,918.400024,28865300
2022-01-26,952.429993,987.690002,906.000000,937.409973,937.409973,34955800
2022-01-27,933.359985,935.390015,829.000000,829.099976,829.099976,49036500
2022-01-28,831.559998,857.500000,792.010010,846.349976,846.349976,44929700
2022-01-31,872.710022,937.989990,862.049988,936.719971,936.719971,34812000
2022-02-01,935.210022,943.700012,905.000000,931.250000,931.250000,24379400
2022-02-02,928.179993,931.500000,889.409973,905.659973,905.659973,22264300
2022-02-03,882.000000,937.000000,880.520020,891.140015,891.140015,26285200
2022-02-04,897.219971,936.500000,881.169983,923.320007,923.320007,24541800
2022-02-07,923.789978,947.770020,902.710022,907.340027,907.340027,20331500
2022-02-08,905.530029,926.289978,894.799988,922.000000,922.000000,16909700
2022-02-09,935.000000,946.270020,920.000000,932.000000,932.000000,17419800
2022-02-10,908.369995,943.809998,896.700012,904.549988,904.549988,22042300
2022-02-11,909.630005,915.960022,850.700012,860.000000,860.000000,26548600
2022-02-14,861.570007,898.880005,853.150024,875.760010,875.760010,22585500
2022-02-15,900.000000,923.000000,893.380005,922.429993,922.429993,19095400
2022-02-16,914.049988,926.429993,901.210022,923.390015,923.390015,17098100
2022-02-17,913.260010,918.500000,874.099976,876.349976,876.349976,18392800
2022-02-18,886.000000,886.869995,837.609985,856.979980,856.979980,22833900
2022-02-22,834.130005,856.729980,801.099976,821.530029,821.530029,27762700
2022-02-23,830.429993,835.299988,760.559998,764.039978,764.039978,31752300
2022-02-24,700.390015,802.479980,700.000000,800.770020,800.770020,45107400
2022-02-25,809.229980,819.500000,782.400024,809.869995,809.869995,25355900
2022-02-28,815.010010,876.859985,814.710022,870.429993,870.429993,33002300
2022-03-01,869.679993,889.880005,853.780029,864.369995,864.369995,24922300
2022-03-02,872.130005,886.479980,844.270020,879.890015,879.890015,24881100
2022-03-03,878.770020,886.440002,832.599976,839.289978,839.289978,20541200
2022-03-04,849.099976,855.650024,825.159973,838.289978,838.289978,22333200
2022-03-07,856.299988,866.140015,804.570007,804.580017,804.580017,24164700
2022-03-08,795.530029,849.989990,782.169983,824.400024,824.400024,26799700
2022-03-09,839.479980,860.559998,832.010010,858.969971,858.969971,19728000
2022-03-10,851.450012,854.450012,810.359985,838.299988,838.299988,19549500
2022-03-11,840.200012,843.799988,793.770020,795.349976,795.349976,22272800
2022-03-14,780.609985,800.700012,756.039978,766.369995,766.369995,23717400
2022-03-15,775.270020,805.570007,756.570007,801.890015,801.890015,22280400
2022-03-16,809.000000,842.000000,802.260010,840.229980,840.229980,28009600
2022-03-17,830.989990,875.000000,825.719971,871.599976,871.599976,22194300
2022-03-18,874.489990,907.849976,867.390015,905.390015,905.390015,33408500
2022-03-21,914.979980,942.849976,907.090027,921.159973,921.159973,27327200
2022-03-22,930.000000,997.859985,921.750000,993.979980,993.979980,35289500
2022-03-23,979.940002,1040.699951,976.400024,999.109985,999.109985,40225400
2022-03-24,1009.729980,1024.489990,988.799988,1013.919983,1013.919983,22973600
2022-03-25,1008.000000,1021.799988,997.320007,1010.640015,1010.640015,20642900
2022-03-28,1065.099976,1097.880005,1053.599976,1091.839966,1091.839966,34168700
2022-03-29,1107.989990,1114.770020,1073.109985,1099.569946,1099.569946,24538300
2022-03-30,1091.170044,1113.949951,1084.000000,1093.989990,1093.989990,19955000
2022-03-31,1094.569946,1103.140015,1076.640015,1077.599976,1077.599976,16265600
2022-03-31,1094.569946,1103.139893,1076.640991,1077.599976,1077.599976,16330919
The problem with this is that the point of intersection occurs between days, not on a specific day. As the data is not continuous, but rather just one point per business day, it is not possible to put the arrow on the intersection itself. I have enlarged a portion of the graph here so you can see what I mean. The change occurs between the 9th and 10th. The data is only on the 9th or the 10th, so the arrow is plotted, and the buy occurs, on the 10th.
The buy/sell is on the next possible day, causing the mis-alignment of the arrows.
How can I merge the two functions given below to achieve something like the histogram example. Any button or drop down would do fine.
If you run the function, you get a nice Candlesticks chart with the functionality of removing non trading day gaps.
def plot_candlesticks(df, names = ('DATE','OPEN','CLOSE','LOW','HIGH'), mv:list = [200], slider:bool = False, fig_size:bool = (1400,700), plot:bool = True):
'''
Plot a candlestick on a given dataframe
args:
df: DataFrame
names: Tuple of column names showing ('DATE','OPEN','CLOSE','LOW','HIGH')
mv: Moving Averages
slider: Whether to have below zoom slider or not
fig_size: Size of Figure as (Width, Height)
plotting: Whether to plot the figure or just return the figure for firther modifications
'''
freq = 5 # 5 min candle
candle_text = f"{str(freq)} Min"
stocks = df.copy()
stocks.sort_index(ascending=False, inplace = True) # Without reverse, recent rolling mean will be either NaN or equal to the exact value
Date, Open, Close, Low, High = names
mv = [] if not mv else mv # just in case you don't want to have any moving averages
colors = sample(['black','magenta','teal','brown','violet'],len(mv))
# To remove, non-trading days, grab first and last observations from df.date and make a continuous date range from that
start = stocks['DATE'].iloc[0] - timedelta(days=1)
end = stocks['DATE'].iloc[-1] + timedelta(days=1)
dt_all = pd.date_range(start=start,end=end, freq = f'{str(freq)}min')
# check which dates from your source that also accur in the continuous date range
dt_obs = [d.strftime("%Y-%m-%d %H:%M:%S") for d in stocks['DATE']]
# isolate missing timestamps
dt_breaks = [d for d in dt_all.strftime("%Y-%m-%d %H:%M:%S").tolist() if not d in dt_obs]
rangebreaks=[dict(dvalue = freq*60*1000, values=dt_breaks)]
range_selector = dict(buttons = list([dict(step = 'all', label = 'All')]))
candle = go.Figure(data = [go.Candlestick(opacity = 0.9, x = stocks[Date], name = 'X',
open = stocks[Open], high = stocks[High], low = stocks[Low], close = stocks[Close]),])
for i in range(len(mv)):
stocks[f'{str(mv[i])}-SMA'] = stocks[Close].rolling(mv[i], min_periods = 1).mean()
candle.add_trace(go.Scatter(name=f'{str(mv[i])} MA',x=stocks[Date], y=stocks[f'{str(mv[i])}-SMA'],
line=dict(color=colors[i], width=1.7)))
candle.update_xaxes(title_text = 'Date', rangeslider_visible = slider, rangeselector = range_selector, rangebreaks=rangebreaks)
candle.update_layout(autosize = False, width = fig_size[0], height = fig_size[1],
title = {'text': f"{stocks['SYMBOL'][0]} : {str(candle_text)} Candles",'y':0.97,'x':0.5,
'xanchor': 'center','yanchor': 'top'},
margin=dict(l=30,r=30,b=30,t=30,pad=2),
paper_bgcolor="lightsteelblue")
candle.update_yaxes(title_text = 'Price in Rupees', tickprefix = u"\u20B9" ) # Rupee symbol
if plot:
candle.show()
return candle
and running the below code resamples your data.
def resample_data(self,to:str = '15min', names:tuple = ('OPEN','CLOSE','LOW','HIGH','DATE')):
'''
Resample the data from 5 Minutes to 15 or 75 Minutes
args:
data: Dataframe of Daily data
to: One of [15M, 75M]
'''
Open, Close, Low, High, Date = names
data = data.resample(to,on=Date).agg({Open:'first', High:'max', Low: 'min', Close:'last'})
return data.sort_index(ascending = False).reset_index()
Is there a functionality when I click 15M / 75M button in my chart, it shows me exactly the same data but resampled? Just like there is functionality in online trading softwares.
no sample data so I have used https://plotly.com/python/candlestick-charts/ sample
at core use https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.resample.html and change trace contents with resampled data
plus using https://ipywidgets.readthedocs.io/en/latest/examples/Widget%20Events.html for events from widgets
import pandas as pd
import numpy as np
import plotly.graph_objects as go
import ipywidgets as widgets
df = pd.read_csv(
"https://raw.githubusercontent.com/plotly/datasets/master/finance-charts-apple.csv",
parse_dates=["Date"],
)
fig = go.FigureWidget(
data=[
go.Candlestick(
x=df["Date"],
open=df["AAPL.Open"],
high=df["AAPL.High"],
low=df["AAPL.Low"],
close=df["AAPL.Close"],
)
]
).update_layout(margin={"t": 30, "b": 0, "l": 0, "r": 0})
out = widgets.Output(layout={"border": "1px solid black"})
out.append_stdout("Output appended with append_stdout\n")
reset = widgets.Button(description="Reset")
slider = widgets.IntSlider(
value=1,
min=1,
max=10,
step=1,
description='Days:',
disabled=False,
continuous_update=False,
orientation='horizontal',
readout=True,
readout_format='d'
)
#out.capture()
def on_slider_change(v):
print(f"slider: {v['new']}")
dfr = df.resample(f"{v['new']}B", on="Date").mean().reset_index()
t = fig.data[0]
t.update(
x=dfr["Date"],
open=dfr["AAPL.Open"],
high=dfr["AAPL.High"],
low=dfr["AAPL.Low"],
close=dfr["AAPL.Close"],
)
#out.capture()
def on_reset_clicked(b):
print("reset")
t = fig.data[0]
t.update(
x=df["Date"],
open=df["AAPL.Open"],
high=df["AAPL.High"],
low=df["AAPL.Low"],
close=df["AAPL.Close"],
)
out.clear_output()
reset.on_click(on_reset_clicked)
slider.observe(on_slider_change, names='value')
widgets.VBox([widgets.HBox([reset, slider]), widgets.VBox([fig, out])])
I'm trying to make a Sankey-plot using Plotly, which follows the filtering of certain documents into either being in scope or out of scope, i.e. 1 source, 2 targets, however some documents are filtered during step 1, some during step 2 etc. This leads to the following Sankey-plot:
Current output
Now what I would ideally like is for it to look something like this:
Ideal output
I've already tried to look through the documentation on : https://plot.ly/python/reference/#sankey but I fail to find what I'm looking for, ideally I would like to implement a feature to prevent the plot from overlapping nodes and links.
This is the code I'm using the generate the plot object:
def genSankeyPlotObject(df, cat_cols=[], value_cols='', visible = False):
### COLORPLATTE TO USE
colorPalette = ['472d3c', '5e3643', '7a444a', 'a05b53', 'bf7958', 'eea160', 'f4cca1', 'b6d53c', '71aa34', '397b44',
'3c5956', '302c2e', '5a5353', '7d7071', 'a0938e', 'cfc6b8', 'dff6f5', '8aebf1', '28ccdf', '3978a8',
'394778', '39314b', '564064', '8e478c', 'cd6093', 'ffaeb6', 'f4b41b', 'f47e1b', 'e6482e', 'a93b3b',
'827094', '4f546b']
### CREATES LABELLIST FROM DEFINED COLUMNS
labelList = []
for catCol in cat_cols:
labelListTemp = list(set(df[catCol].values))
labelList = labelList + labelListTemp
labelList = list(dict.fromkeys(labelList))
### DEFINES THE NUMBER OF COLORS IN THE COLORPALLET
colorNum = len(df[cat_cols[0]].unique()) + len(df[cat_cols[1]].unique()) + len(df[cat_cols[2]].unique())
TempcolorPallet = colorPalette * math.ceil(len(colorPalette)/colorNum)
shuffle(TempcolorPallet)
colorList = TempcolorPallet[0:colorNum]
### TRANSFORMS DF INTO SOURCE -> TARGET PAIRS
for i in range(len(cat_cols)-1):
if i==0:
sourceTargetDf = df[[cat_cols[i],cat_cols[i+1],value_cols]]
sourceTargetDf.columns = ['source','target','count']
else:
tempDf = df[[cat_cols[i],cat_cols[i+1],value_cols]]
tempDf.columns = ['source','target','count']
sourceTargetDf = pd.concat([sourceTargetDf,tempDf])
sourceTargetDf = sourceTargetDf.groupby(['source','target']).agg({'count':'sum'}).reset_index()
### ADDING INDEX TO SOURCE -> TARGET PAIRS
sourceTargetDf['sourceID'] = sourceTargetDf['source'].apply(lambda x: labelList.index(x))
sourceTargetDf['targetID'] = sourceTargetDf['target'].apply(lambda x: labelList.index(x))
### CREATES THE SANKEY PLOT OBJECT
data = go.Sankey(node = dict(pad = 15,
thickness = 20,
line = dict(color = "black",
width = 0.5),
label = labelList,
color = colorList),
link = dict(source = sourceTargetDf['sourceID'],
target = sourceTargetDf['targetID'],
value = sourceTargetDf['count']),
valuesuffix = ' ' + value_cols,
visible = visible)
return data
Some context:
I was looking into the vispy module to plot in realtime (or as close as possible to) data coming from an instrument. My attempt follow.
from vispy.plot import Fig
from vispy import app,scene
from vispy.visuals import TextVisual
import numpy as np
import Queue
FONT_SIZE = 14
MIN = 0
MAX = 1.1
w_size = 100
N = 5000
M = 2500
color_map = 'cubehelix'
q_size = 1000
Nb = 5
#generate (empty) initial data to fill the plot
data = np.zeros(N*M)
data = np.reshape(data, (N,M))
#setup the plot
fig = Fig(show = False,size = (16*w_size,9*w_size),bgcolor='black')
fig.title = 'my plot'
main_plot = fig[0,0].image(data = data,fg_color='w',cmap=color_map,clim=(MIN,MAX))
fig[0,0].view.camera.aspect = N/float(M) * 16./9.
title = scene.Label("someoutput", font_size=FONT_SIZE, color = 'w')
fig[0,0].grid.add_widget(title, row=0, col=4)
fig[0,0].grid[2,4].border_color = 'black'
fig[0,0].grid[2,4].bgcolor = 'black'
xlabel_title = scene.Label("x_axis [unit]", font_size=FONT_SIZE, color = 'w')
fig[0,0].grid.add_widget(xlabel_title, row=4, col=4)
ylabel_title = scene.Label("y_axis [unit]", font_size=FONT_SIZE,rotation=-90, color='w')
fig[0,0].grid.add_widget(ylabel_title, row=2, col=2)
scale = scene.ColorBarWidget(orientation='left',
cmap=color_map,
label='Some value',
clim=(MIN,MAX),
border_color = 'w',
border_width = 1,
label_color = 'w'
)
fig[0,0].grid.add_widget(scale, row=2, col=6)
fig[0,0].cbar_right.width_max = \
fig[0,0].cbar_right.width_min = 50
#fill a queue so to excude the generation time from the plotting time
q = Queue.Queue()
for i in range(q_size):
new_data = (np.abs(0.5*np.random.randn(Nb*M)[:])).astype('float32')
new_data = np.reshape(new_data, (Nb,M))
q.put(new_data[:])
#update function
def update(ev):
global main_plot, q, data, Nb,M,fig,index
#acquire
new_data = q.get()
#roll the plot data
data[Nb:, :] = data[:-Nb, :]
data[:Nb,:] = new_data
#recycle the new data
q.put(new_data)
#update the plot
main_plot.set_data(data)
main_plot.update()
# setup timer
interv = 0.01
timer = app.Timer(interval = interv)
timer.connect(update)
timer.start(interval = interv)
if __name__ == '__main__':
fig.show(run=True)
app.run()
This code currently works but it's much slower than the data rate. In the vispy gallery, as well as in some examples, I saw much more points being plotted and updated. I think that the main problem is that I completely set each time all the data of the plot instead of shifting them and inserting new points.
I also had a look at this example:
https://github.com/vispy/vispy/blob/master/examples/demo/scene/oscilloscope.py
However I don't know how to generalize the update function that rolls the data (I have no knowledge of OpenGL) and I cannot use the example as is because I need a quantitative color scale (that seems well implemented in vispy.plot).
The question:
Is there a way to write a function that rolls the data of a plot generated with the vispy.plot class?
Thanks.