I want to get my code to loop so that every time it performs the calculation, it adds basically does a cumulative sum for my variable delta_omega. i.e. for every calculation, it takes the previous values in the delta_omega array, adds them together and uses that value to perform the calculation again and so on. I'm really not sure how to go about this as I want to plot these results too.
import numpy as np
import matplotlib.pyplot as plt
delta_omega = np.linspace(-900*10**6, -100*10**6, m) #Hz - range of frequencies
i = 0
while i<len(delta_omega):
delta = delta_omega[i] - (k*v_cap) + (mu_eff*B)/hbar
p_ee = (s0*L/2) / (1 + s0 + (2*delta/L)**2) #population of the excited state
R = L * p_ee # scattering rate
F = hbar*k*(R) #scattering force on atoms
a = F/m_Rb #acceleration assumed constant
vf_slower = (v_cap**2 - (2*a*z0))**0.5 #velocity at the end of the slower
t_d = 1/a * (v_cap - vf_slower) #time taken during slower
# -------- After slower --------
da = 0.1 #(m) distance from end of slower to the middle of the MOT
vf_MOT = (vf_slower**2 - (2*a*da))**0.5 #(m/s) - velocity of the particles at MOT center
t_a = da/vf_MOT #(s) time taken after slower
r0 = 0.01 #MOT capture radius
vr_max = r0/(t_b+t_d+t_a) #maximum transveral velocity
vz_max = (v_cap**2 + 2*a_max*z0)**0.5 #m/s - maximum axial velocity
# -------- Flux of atoms captured --------
P = 10**(4.312-(4040/T)) #vapour pressure for liquid phase (use 4.857 for solid phase)
A = 5*10**-4 #area of the oven aperture
n = P/(k_b*T) #atomic number density
f_oven = ((n*A)/4) * (2/(np.pi)**0.5) * ((2*k_b*T)/m_Rb)**0.5
f = f_oven * (1 - np.exp(-vr_max**2/vp**2))*(1 - np.exp(-vz_max**2/vp**2))
i+=1
plt.plot(delta_omega, f)
A simple cumulative sum would be defining the variable outside the loop and adding to it
i = 0
x = 0
while i < 10:
x = x + 5 #do your work on the cumulative value here
i += 1
print("cumulative sum: {}".format(x))
so define a variable that will contain the cumulative sum, and every loop, add to it
I am new here and new in programming, so excuse me if the question is not formulated clearly enough.
For a uni assignment, my labpartner and I are programming a predator-prey system.
In this predator-prey system, there is a certain load factor 'W0'.
We want to find a load factor W0, accurate to 5 significant digits, for which applies that there will never be less than 250 predators (wnum[1] in our code). We want to find this value of W0 and we need the code to carry on further calculations with this found value of W0. Here is what we've tried so far, but python does not seem to give any response:
# Import important stuff and settings
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
print ('Results of Group 4')
def W0():
W0 = 2.0
while any(wnum[1])<250:
W0 = W0-0.0001
return W0
def W(t):
if 0 <= t < 3/12:
Wt = 0
elif 3/12 <= t <= 8/12:
Wt = W0
elif 8/12 < t < 1:
Wt = 0
else:
Wt = W(t - 1)
return Wt
# Define the right-hand-side function
def rhsf(t,y):
y1 = y[0]
y2 = y[1]
f1 = (2-2*10**-3*y2)*y1-W(t)*y1
f2 = (-3.92+7*10**-3*y1)*y2
return np.array([f1,f2])
# Define one step of the RK4 method
def RK4Step(tn,wn,Dt,f):
# tn = current time
# wn = known approximation at time tn
# Dt = the time step to use
# f = the right-hand-side function to use
# wnplus1 = the new approximation at time tn+Dt
k1 = Dt*f(tn,wn)
k2 = Dt*f(tn+0.5*Dt,wn+0.5*k1)
k3 = Dt*f(tn+0.5*Dt,wn+0.5*k2)
k4 = Dt*f(tn+Dt,wn+k3)
wnplus1 = wn + 1/6*(k1 +2*k2 +2*k3 +k4)
return wnplus1
# Define the complete RK4 method
def RK4Method(t0,tend,Dt,f,y0):
# t0 = initial time of simulation
# tend = final time of simulation
# Dt = the time step to use
# f = the right-hand-side function to use
# y0 = the initial values
# calculate the number of time steps to take
N = int(np.round((tend-t0)/Dt))
# make the list of times t which we want the solution
time = np.linspace(t0,tend,num=N+1)
# make sure Dt matches with the number of time steps
Dt = (tend-t0)/N
# Allocate memory for the approximations
# row i represents all values of variable i at all times
# column j represents all values of all variables at time t_j
w = np.zeros((y0.size,N+1))
# store the (given) initial value
w[:,0] = y0
# Perform all time steps
for n,tn in enumerate(time[:-1]):
w[:,n+1] = RK4Step(tn,w[:,n],Dt,f)
return time, w
# Set all known values and settings
t0 = 0.0
tend = 10.0
y0 = np.array([600.0,1000.0])
Dt = 0.5/(2**7)
# Execute the method
tnum, wnum = RK4Method(t0,tend,Dt,rhsf,y0)
# Make a nice table
alldata = np.concatenate(([tnum],wnum),axis=0).transpose()
table = pd.DataFrame(alldata,columns=['t','y1(t)','y2(t)'])
print('\nA nice table of the simulation:\n')
print(table)
# Make a nice picture
plt.close('all')
plt.figure()
plt.plot(tnum,wnum[0,:],label='$y_1$',marker='o',linestyle='-')
plt.plot(tnum,wnum[1,:],label='$y_2$',marker='o',linestyle='-')
plt.xlabel('$t$')
plt.ylabel('$y(t)$')
plt.title('Simulation')
plt.legend()
# Do an error computation
# Execute the method again with a doubled time step
tnum2, wnum2 = RK4Method(t0,tend,2.0*Dt,rhsf,y0)
# Calculate the global truncation errors at the last simulated time
errors = (wnum[:,-1] - wnum2[:,-1])/(2**4-1)
print('\nThe errors are ',errors[0],' for y1 and ',errors[1],' for y2 at time t=',tnum[-1])
I have data that has 800,000+ rows. I want to take an Exponential Moving Average (EMA) of one of the columns. The times are not evenly sampled and I want to decay the EMA on each update (row). The code I have is this:
window = 5
for i in range(1, len(series)):
dt = series['datetime'][i] - series['datetime'][i - 1]
decay = 1 - numpy.exp(-dt / window)
result[i] = (1 - decay) * result[i - 1] + decay * series['midpoint'].iloc[i]
return pandas.Series(result, index=series.index)
The problem is, for 800,000 rows, this is very slow. Is there anyway to optimize this using some other features of numpy? I can't vectorize it because results[i] is dependent on results[i-1].
sample data here:
Timestamp Midpoint
1559655000001096130 2769.125
1559655000001162260 2769.127
1559655000001171688 2769.154
1559655000001408734 2769.138
1559655000001424200 2769.123
1559655000001433128 2769.110
1559655000001541560 2769.125
1559655000001640406 2769.125
1559655000001658436 2769.127
1559655000001755924 2769.129
1559655000001793266 2769.125
1559655000001878688 2769.143
1559655000002061024 2769.125
How about something like the following which takes me 0.34 seconds to run on a series of irregularly spaced data with 900k rows? I am assuming the window of 5 implies a 5 day span.
First, let's create some sample data.
# Create sample data for a price stream of 2.6m price observations sampled 1 second apart.
seconds_per_day = 60 * 60 * 24 # 60 seconds / minute * 60 minutes / hour * 24 hours / day
starting_value = 100
annualized_vol = .3
sampling_percentage = .35 # 35%
start_date = '2018-12-01'
end_date = '2018-12-31'
np.random.seed(0)
idx = pd.date_range(start=start_date, end=end_date, freq='s') # One second intervals.
periodic_vol = annualized_vol * (1/ 252 / seconds_per_day) ** 0.5
daily_returns = np.random.randn(len(idx)) * periodic_vol
cumulative_indexed_return = (1 + daily_returns).cumprod() * starting_value
index_level = pd.Series(cumulative_indexed_return, index=idx)
# Sample 35% of the simulated prices to create a time series of 907k rows with irregular time intervals.
s = index_level.sample(frac=sampling_percentage).sort_index()
Now let's create a generator function to store the latest value of the exponentially weighted time series. This can run c. 4x faster by installing numba, importing it and then adding the single decorator line above the function definition #jit(nopython=True).
from numba import jit # Optional, see below.
#jit(nopython=True) # Optional, see below.
def ewma(vals, decay_vals):
result = vals[0]
yield result
for val, decay in zip(vals[1:], decay_vals[1:]):
result = result * (1 - decay) + val * decay
yield result
Now let's run this generator on the irregularly spaced series s. For this sample with 900k rows, it takes me 1.2 seconds to run the following code. I can further cut down the execution time to 0.34 seconds by optionally using the the just in time compiler from numba. You first need to install that package, e.g. conda install numba. Note that I used a list compehension to populate the ewma values from the generator, and then I assign these values back to the original series after first converting it to a dataframe.
# Assumes time series data is now named `s`.
window = 5 # Span of 5 days?
dt = pd.Series(s.index).diff().dt.total_seconds().div(seconds_per_day) # Measured in days.
decay = (1 - (dt / -window).apply(np.exp))
g = ewma_generator(s.values, decay.values)
result = s.to_frame('midpoint').assign(
ewma=pd.Series([next(g) for _ in range(len(s))], index=s.index))
>>> result.tail()
midpoint ewma
2018-12-30 23:59:45 103.894471 105.546004
2018-12-30 23:59:49 103.914077 105.545929
2018-12-30 23:59:50 103.901910 105.545910
2018-12-30 23:59:53 103.913476 105.545853
2018-12-31 00:00:00 103.910422 105.545720
>>> result.shape
(907200, 2)
To make sure the numbers follow our intuition, let's visualize the result taking hourly samples. This looks good to me.
obs_per_day = 24 # 24 hourly observations per day.
step = int(seconds_per_day / obs_per_day)
>>> result.iloc[::step, :].plot()
A slight improvement may be obtained by iterating on the underlying numpy arrays instead of on pandas DataFrames and Series:
result = np.ndarray(len(series))
window = 5
serdt = series['datetime'].values
sermp = series['midpoint'].values
for i in range(1, len(series)):
dt = serdt[i] - serdt[i - 1]
decay = 1 - numpy.exp(-dt / window)
result[i] = (1 - decay) * result[i - 1] + decay * sermp[i]
return pandas.Series(result, index=series.index)
With your sample data it is about 6 times faster that the original method.
I'm having trouble getting my code to work. Im coding python in a backtesting environment called "Quantopian". Regardless, the .apply(), series, .pd or whatever terminology is beyond my skill level. (assuming I'm even on the right track lol)
What I'm trying to accomplish:
Taking a couple stocks and constantly calculating the MACD. Then when the indicator meets a certain condition, the algo purchases or sells that specific stock.
What the MACD is simplistically:
A momentum indicator that looks at historical data, using 12, 26 and 9 day Exponential Moving Averages and comparing them with each other.
I've designed my own function, thats not my problem....
Help:
I'm trying to apply it to the pool of stocks in my universe to constantly calculate the MACD every minute.
Where I'm specifically confused:
I defined a MACD function but don't know how to get it to calculate every minute for whatever stocks are in my pool.
CODE:
import numpy as np
import math
import talib as ta
import pandas as pd
def initialize(context):
set_commission(commission.PerTrade(cost=10))
context.stocks = symbols('AAPL', 'GOOG_L')
def handle_data(context, data):
for stock in context.stocks:
prices_fast = data.history(context.stocks, "close", 390, "1m").resample("30min").dropna()
prices_slow = data.history(context.stocks, "close", 390, "1m").resample("30min").dropna()
prices_signal = data.history(context.stocks, "close", 390, "1m").resample("30min").dropna()
curr_price = data.history(context.stocks, "price", 30, "1m").resample("30min")[-1:].dropna()
series = pd.Series([stock]).dropna()
macd = series.apply(MACD)
macd_func = stock.apply(MACD)
if macd_func[stock] > 0:
order(stock, 1)
print macd_func
record(macd=macd_func[stock])
def MACD(prices_fast, prices_slow, prices_signal, curr_price):
# Setting MACD Conditions:
slow = 26
fast = 12
signal = 9
# Calcualting Averages:
avg_fast = pd.rolling_sum(prices_fast[:fast], fast)[-1:] / fast
avg_slow = pd.rolling_sum(prices_slow[:slow], slow)[-1:] / slow
avg_signal = pd.rolling_sum(prices_signal[:signal], signal)[-1:] / signal
# Calculating the Weighting Multipliers:
A = 2 / (fast + 1)
B = 2 / (slow + 1)
C = 2 / (signal + 1)
# Calculating the Exponential Moving Averages:
EMA_fast = (curr_price * A) + [avg_fast * (1 - A)]
EMA_slow = (curr_price * B) + [avg_slow * (1 - B)]
EMA_signal = (curr_price * C) + [avg_signal * (1 - C)]
# Calculating MACD Histogram:
macd = EMA_fast - EMA_slow - EMA_signal
If someone could give me a handle, I would GREATLY appreciate it!
Thank you very VERY much,
Mike
I am new to pandas. What is the best way to calculate the relative strength part in the RSI indicator in pandas? So far I got the following:
from pylab import *
import pandas as pd
import numpy as np
def Datapull(Stock):
try:
df = (pd.io.data.DataReader(Stock,'yahoo',start='01/01/2010'))
return df
print 'Retrieved', Stock
time.sleep(5)
except Exception, e:
print 'Main Loop', str(e)
def RSIfun(price, n=14):
delta = price['Close'].diff()
#-----------
dUp=
dDown=
RolUp=pd.rolling_mean(dUp, n)
RolDown=pd.rolling_mean(dDown, n).abs()
RS = RolUp / RolDown
rsi= 100.0 - (100.0 / (1.0 + RS))
return rsi
Stock='AAPL'
df=Datapull(Stock)
RSIfun(df)
Am I doing it correctly so far? I am having trouble with the difference part of the equation where you separate out upward and downward calculations
It is important to note that there are various ways of defining the RSI. It is commonly defined in at least two ways: using a simple moving average (SMA) as above, or using an exponential moving average (EMA). Here's a code snippet that calculates various definitions of RSI and plots them for comparison. I'm discarding the first row after taking the difference, since it is always NaN by definition.
Note that when using EMA one has to be careful: since it includes a memory going back to the beginning of the data, the result depends on where you start! For this reason, typically people will add some data at the beginning, say 100 time steps, and then cut off the first 100 RSI values.
In the plot below, one can see the difference between the RSI calculated using SMA and EMA: the SMA one tends to be more sensitive. Note that the RSI based on EMA has its first finite value at the first time step (which is the second time step of the original period, due to discarding the first row), whereas the RSI based on SMA has its first finite value at the 14th time step. This is because by default rolling_mean() only returns a finite value once there are enough values to fill the window.
import datetime
from typing import Callable
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import pandas_datareader.data as web
# Window length for moving average
length = 14
# Dates
start, end = '2010-01-01', '2013-01-27'
# Get data
data = web.DataReader('AAPL', 'yahoo', start, end)
# Get just the adjusted close
close = data['Adj Close']
# Define function to calculate the RSI
def calc_rsi(over: pd.Series, fn_roll: Callable) -> pd.Series:
# Get the difference in price from previous step
delta = over.diff()
# Get rid of the first row, which is NaN since it did not have a previous row to calculate the differences
delta = delta[1:]
# Make the positive gains (up) and negative gains (down) Series
up, down = delta.clip(lower=0), delta.clip(upper=0).abs()
roll_up, roll_down = fn_roll(up), fn_roll(down)
rs = roll_up / roll_down
rsi = 100.0 - (100.0 / (1.0 + rs))
# Avoid division-by-zero if `roll_down` is zero
# This prevents inf and/or nan values.
rsi[:] = np.select([roll_down == 0, roll_up == 0, True], [100, 0, rsi])
rsi.name = 'rsi'
# Assert range
valid_rsi = rsi[length - 1:]
assert ((0 <= valid_rsi) & (valid_rsi <= 100)).all()
# Note: rsi[:length - 1] is excluded from above assertion because it is NaN for SMA.
return rsi
# Calculate RSI using MA of choice
# Reminder: Provide ≥ `1 + length` extra data points!
rsi_ema = calc_rsi(close, lambda s: s.ewm(span=length).mean())
rsi_sma = calc_rsi(close, lambda s: s.rolling(length).mean())
rsi_rma = calc_rsi(close, lambda s: s.ewm(alpha=1 / length).mean()) # Approximates TradingView.
# Compare graphically
plt.figure(figsize=(8, 6))
rsi_ema.plot(), rsi_sma.plot(), rsi_rma.plot()
plt.legend(['RSI via EMA/EWMA', 'RSI via SMA', 'RSI via RMA/SMMA/MMA (TradingView)'])
plt.show()
dUp= delta[delta > 0]
dDown= delta[delta < 0]
also you need something like:
RolUp = RolUp.reindex_like(delta, method='ffill')
RolDown = RolDown.reindex_like(delta, method='ffill')
otherwise RS = RolUp / RolDown will not do what you desire
Edit: seems this is a more accurate way of RS calculation:
# dUp= delta[delta > 0]
# dDown= delta[delta < 0]
# dUp = dUp.reindex_like(delta, fill_value=0)
# dDown = dDown.reindex_like(delta, fill_value=0)
dUp, dDown = delta.copy(), delta.copy()
dUp[dUp < 0] = 0
dDown[dDown > 0] = 0
RolUp = pd.rolling_mean(dUp, n)
RolDown = pd.rolling_mean(dDown, n).abs()
RS = RolUp / RolDown
My answer is tested on StockCharts sample data.
StockChart RSI info
def RSI(series, period):
delta = series.diff().dropna()
u = delta * 0
d = u.copy()
u[delta > 0] = delta[delta > 0]
d[delta < 0] = -delta[delta < 0]
u[u.index[period-1]] = np.mean( u[:period] ) #first value is sum of avg gains
u = u.drop(u.index[:(period-1)])
d[d.index[period-1]] = np.mean( d[:period] ) #first value is sum of avg losses
d = d.drop(d.index[:(period-1)])
rs = pd.DataFrame.ewm(u, com=period-1, adjust=False).mean() / \
pd.DataFrame.ewm(d, com=period-1, adjust=False).mean()
return 100 - 100 / (1 + rs)
#sample data from StockCharts
data = pd.Series( [ 44.34, 44.09, 44.15, 43.61,
44.33, 44.83, 45.10, 45.42,
45.84, 46.08, 45.89, 46.03,
45.61, 46.28, 46.28, 46.00,
46.03, 46.41, 46.22, 45.64 ] )
print RSI( data, 14 )
#output
14 70.464135
15 66.249619
16 66.480942
17 69.346853
18 66.294713
19 57.915021
I too had this question and was working down the rolling_apply path that Jev took. However, when I tested my results, they didn't match up against the commercial stock charting programs I use, such as StockCharts.com or thinkorswim. So I did some digging and discovered that when Welles Wilder created the RSI, he used a smoothing technique now referred to as Wilder Smoothing. The commercial services above use Wilder Smoothing rather than a simple moving average to calculate the average gains and losses.
I'm new to Python (and Pandas), so I'm wondering if there's some brilliant way to refactor out the for loop below to make it faster. Maybe someone else can comment on that possibility.
I hope you find this useful.
More info here.
def get_rsi_timeseries(prices, n=14):
# RSI = 100 - (100 / (1 + RS))
# where RS = (Wilder-smoothed n-period average of gains / Wilder-smoothed n-period average of -losses)
# Note that losses above should be positive values
# Wilder-smoothing = ((previous smoothed avg * (n-1)) + current value to average) / n
# For the very first "previous smoothed avg" (aka the seed value), we start with a straight average.
# Therefore, our first RSI value will be for the n+2nd period:
# 0: first delta is nan
# 1:
# ...
# n: lookback period for first Wilder smoothing seed value
# n+1: first RSI
# First, calculate the gain or loss from one price to the next. The first value is nan so replace with 0.
deltas = (prices-prices.shift(1)).fillna(0)
# Calculate the straight average seed values.
# The first delta is always zero, so we will use a slice of the first n deltas starting at 1,
# and filter only deltas > 0 to get gains and deltas < 0 to get losses
avg_of_gains = deltas[1:n+1][deltas > 0].sum() / n
avg_of_losses = -deltas[1:n+1][deltas < 0].sum() / n
# Set up pd.Series container for RSI values
rsi_series = pd.Series(0.0, deltas.index)
# Now calculate RSI using the Wilder smoothing method, starting with n+1 delta.
up = lambda x: x if x > 0 else 0
down = lambda x: -x if x < 0 else 0
i = n+1
for d in deltas[n+1:]:
avg_of_gains = ((avg_of_gains * (n-1)) + up(d)) / n
avg_of_losses = ((avg_of_losses * (n-1)) + down(d)) / n
if avg_of_losses != 0:
rs = avg_of_gains / avg_of_losses
rsi_series[i] = 100 - (100 / (1 + rs))
else:
rsi_series[i] = 100
i += 1
return rsi_series
You can use rolling_apply in combination with a subfunction to make a clean function like this:
def rsi(price, n=14):
''' rsi indicator '''
gain = (price-price.shift(1)).fillna(0) # calculate price gain with previous day, first row nan is filled with 0
def rsiCalc(p):
# subfunction for calculating rsi for one lookback period
avgGain = p[p>0].sum()/n
avgLoss = -p[p<0].sum()/n
rs = avgGain/avgLoss
return 100 - 100/(1+rs)
# run for all periods with rolling_apply
return pd.rolling_apply(gain,n,rsiCalc)
# Relative Strength Index
# Avg(PriceUp)/(Avg(PriceUP)+Avg(PriceDown)*100
# Where: PriceUp(t)=1*(Price(t)-Price(t-1)){Price(t)- Price(t-1)>0};
# PriceDown(t)=-1*(Price(t)-Price(t-1)){Price(t)- Price(t-1)<0};
# Change the formula for your own requirement
def rsi(values):
up = values[values>0].mean()
down = -1*values[values<0].mean()
return 100 * up / (up + down)
stock['RSI_6D'] = stock['Momentum_1D'].rolling(center=False,window=6).apply(rsi)
stock['RSI_12D'] = stock['Momentum_1D'].rolling(center=False,window=12).apply(rsi)
Momentum_1D = Pt - P(t-1) where P is closing price and t is date
You can get a massive speed up of Bill's answer by using numba. 100 loops of 20k row series( regular = 113 seconds, numba = 0.28 seconds ). Numba excels with loops and arithmetic.
import numpy as np
import numba as nb
#nb.jit(fastmath=True, nopython=True)
def calc_rsi( array, deltas, avg_gain, avg_loss, n ):
# Use Wilder smoothing method
up = lambda x: x if x > 0 else 0
down = lambda x: -x if x < 0 else 0
i = n+1
for d in deltas[n+1:]:
avg_gain = ((avg_gain * (n-1)) + up(d)) / n
avg_loss = ((avg_loss * (n-1)) + down(d)) / n
if avg_loss != 0:
rs = avg_gain / avg_loss
array[i] = 100 - (100 / (1 + rs))
else:
array[i] = 100
i += 1
return array
def get_rsi( array, n = 14 ):
deltas = np.append([0],np.diff(array))
avg_gain = np.sum(deltas[1:n+1].clip(min=0)) / n
avg_loss = -np.sum(deltas[1:n+1].clip(max=0)) / n
array = np.empty(deltas.shape[0])
array.fill(np.nan)
array = calc_rsi( array, deltas, avg_gain, avg_loss, n )
return array
rsi = get_rsi( array or series, 14 )
rsi_Indictor(close,n_days):
rsi_series = pd.DataFrame(close)
# Change = close[i]-Change[i-1]
rsi_series["Change"] = (rsi_series["Close"] - rsi_series["Close"].shift(1)).fillna(0)
# Upword Movement
rsi_series["Upword Movement"] = (rsi_series["Change"][rsi_series["Change"] >0])
rsi_series["Upword Movement"] = rsi_series["Upword Movement"].fillna(0)
# Downword Movement
rsi_series["Downword Movement"] = (abs(rsi_series["Change"])[rsi_series["Change"] <0]).fillna(0)
rsi_series["Downword Movement"] = rsi_series["Downword Movement"].fillna(0)
#Average Upword Movement
# For first Upword Movement Mean of first n elements.
rsi_series["Average Upword Movement"] = 0.00
rsi_series["Average Upword Movement"][n] = rsi_series["Upword Movement"][1:n+1].mean()
# For Second onwords
for i in range(n+1,len(rsi_series),1):
#print(rsi_series["Average Upword Movement"][i-1],rsi_series["Upword Movement"][i])
rsi_series["Average Upword Movement"][i] = (rsi_series["Average Upword Movement"][i-1]*(n-1)+rsi_series["Upword Movement"][i])/n
#Average Downword Movement
# For first Downword Movement Mean of first n elements.
rsi_series["Average Downword Movement"] = 0.00
rsi_series["Average Downword Movement"][n] = rsi_series["Downword Movement"][1:n+1].mean()
# For Second onwords
for i in range(n+1,len(rsi_series),1):
#print(rsi_series["Average Downword Movement"][i-1],rsi_series["Downword Movement"][i])
rsi_series["Average Downword Movement"][i] = (rsi_series["Average Downword Movement"][i-1]*(n-1)+rsi_series["Downword Movement"][i])/n
#Relative Index
rsi_series["Relative Strength"] = (rsi_series["Average Upword Movement"]/rsi_series["Average Downword Movement"]).fillna(0)
#RSI
rsi_series["RSI"] = 100 - 100/(rsi_series["Relative Strength"]+1)
return rsi_series.round(2)
For More Information
You do this using finta package as well just to add above
ref: https://github.com/peerchemist/finta/tree/master/examples
import pandas as pd
from finta import TA
import matplotlib.pyplot as plt
ohlc = pd.read_csv("C:\\WorkSpace\\Python\\ta-lib\\intraday_5min_IBM.csv", index_col="timestamp", parse_dates=True)
ohlc['RSI']= TA.RSI(ohlc)
It is not really necessary to calculate the mean, because after they are divided, you only need to calculate the sum, so we can use Series.cumsum ...
def rsi(serie, n):
diff_serie = close.diff()
cumsum_incr = diff_serie.where(lambda x: x.gt(0), 0).cumsum()
cumsum_decr = diff_serie.where(lambda x: x.lt(0), 0).abs().cumsum()
rs_serie = cumsum_incr.div(cumsum_decr)
rsi = rs_serie.mul(100).div(rs_serie.add(1)).fillna(0)
return rsi
Less code here but seems to work for me:
df['Change'] = (df['Close'].shift(-1)-df['Close']).shift(1)
df['ChangeAverage'] = df['Change'].rolling(window=2).mean()
df['ChangeAverage+'] = df.apply(lambda x: x['ChangeAverage'] if x['ChangeAverage'] > 0 else 0,axis=1).rolling(window=14).mean()
df['ChangeAverage-'] = df.apply(lambda x: x['ChangeAverage'] if x['ChangeAverage'] < 0 else 0,axis=1).rolling(window=14).mean()*-1
df['RSI'] = 100-(100/(1+(df['ChangeAverage+']/df['ChangeAverage-'])))