Develop Reference

How do i optimize code when the execution time is too slow?

I have this Python code, but it's already running for 24h and doesn't seem to print the result for now.
I don't know how long it will take.
Can someone help me to optimize this code?
The code is to find the best performance for trading RSI divergence in a certain period.
It first defines some parameters for the RSI.
The code then goes through every possible combination to find the best combination of parameters to have the best performances.
I'm not really an expert.
I don't really know how i can change the code as i'm no expert.
Happy to learn.
Thank you guys.
import pandas as pd
import numpy as np
import ta
def load_data(file_path, start_date, end_date):
"""
Loads data for the specified symbol and date range from a CSV file
"""
df = pd.read_csv(file_path)
if 'Date' not in df.columns:
df['Date'] = pd.to_datetime(df.index)
df['Date'] = pd.to_datetime(df['Date'])
df = df.set_index('Date')
df = df[(df.index >= start_date) & (df.index <= end_date)]
return df
def calc_rsi(df, n):
"""
Calculates the relative strength index (RSI) for the given dataframe and window size
"""
delta = df["Close"].diff()
gain = delta.where(delta > 0, 0)
loss = abs(delta.where(delta < 0, 0))
avg_gain = gain.rolling(window=n).mean()
avg_loss = loss.rolling(window=n).mean()
rs = avg_gain / avg_loss
rsi = 100 - (100 / (1 + rs))
return rsi
def calc_pivot_point(df, pivot_point_type, pivot_point_n):
"""
Calculates the pivot point for the given dataframe and pivot point type
"""
if pivot_point_type == "Close":
pivot_point = df["Close"].rolling(window=pivot_point_n).mean()
elif pivot_point_type == "High/Low":
pivot_point = (df["High"].rolling(window=pivot_point_n).mean() + df["Low"].rolling(window=pivot_point_n).mean()) / 2
else:
raise ValueError("Invalid pivot point type")
return pivot_point
def calc_divergence(df, rsi, pivot_point, divergence_type, max_pivot_point, max_bars_to_check):
"""
Calculates the divergence for the given dataframe and parameters
"""
if divergence_type == "Regular":
pivot_point_delta = pivot_point.diff()
pivot_point_delta_sign = pivot_point_delta.where(pivot_point_delta > 0, -1)
pivot_point_delta_sign[pivot_point_delta_sign > 0] = 1
rsi_delta = rsi.diff()
rsi_delta_sign = rsi_delta.where(rsi_delta > 0, -1)
rsi_delta_sign[rsi_delta_sign > 0] = 1
divergence = pivot_point_delta_sign * rsi_delta_sign
divergence[divergence < 0] = -1
divergence = divergence.rolling(window=max_pivot_point).sum()
divergence = divergence.rolling(window=max_bars_to_check).sum()
divergence = divergence.where(divergence > 0, 0)
divergence[divergence < 0] = -1
else:
raise ValueError("Invalid divergence type")
return divergence
def backtest(df, rsi_period, pivot_point_type, pivot_point_n, divergence_type, max_pivot_point, max_bars_to_check, trailing_stop, starting_capital):
"""
Backtests the strategy for the given dataframe and parameters
"""
rsi = calc_rsi(df, rsi_period)
pivot_point = calc_pivot_point(df, pivot_point_type, pivot_point_n)
divergence = calc_divergence(df, rsi, pivot_point, divergence_type, max_pivot_point, max_bars_to_check)
positions = pd.DataFrame(index=df.index, columns=["Position", "Stop Loss"])
positions["Position"] = 0.0
positions["Stop Loss"] = 0.0
capital = starting_capital
for i, row in enumerate(df.iterrows()):
date = row[0]
close = row[1]["Close"]
rsi_val = rsi.loc[date]
pivot_val = pivot_point.loc[date]
divergence_val = divergence.loc[date]
if divergence_val > 0 and positions.loc[date]["Position"] == 0:
positions.at[date, "Position"] = capital / close
positions.at[date, "Stop Loss"] = close * (1 - trailing_stop)
elif divergence_val < 0 and positions.loc[date]["Position"] > 0:
capital = positions.loc[date]["Position"] * close
positions.at[date, "Position"] = 0.0
positions.at[date, "Stop Loss"] = 0.0
elif close < positions.loc[date]["Stop Loss"] and positions.loc[date]["Position"] > 0:
capital = positions.loc[date]["Position"] * close
positions.at[date, "Position"] = 0.0
positions.at[date, "Stop Loss"] = 0.0
return capital
def find_best_iteration(df, start_rsi_period, end_rsi_period, pivot_point_types, start_pivot_point_n, end_pivot_point_n, divergence_types, start_max_pivot_point, end_max_pivot_point, start_max_bars_to_check, end_max_bars_to_check, start_trailing_stop, end_trailing_stop, starting_capital):
"""
Finds the best iteration for the given parameters
"""
best_result = 0.0
best_params = None
for rsi_period in range(start_rsi_period, end_rsi_period + 1):
for pivot_point_type in pivot_point_types:
for pivot_point_n in range(start_pivot_point_n, end_pivot_point_n + 1):
for divergence_type in divergence_types:
for max_pivot_point in range(start_max_pivot_point, end_max_pivot_point + 1):
for max_bars_to_check in range(start_max_bars_to_check, end_max_bars_to_check + 1):
for trailing_stop in np.arange(start_trailing_stop, end_trailing_stop + 0.01, 0.01):
result = backtest(df, rsi_period, pivot_point_type, pivot_point_n, divergence_type, max_pivot_point, max_bars_to_check, trailing_stop, starting_capital)
if result > best_result:
best_result = result
best_params = (rsi_period, pivot_point_type, pivot_point_n, divergence_type, max_pivot_point, max_bars_to_check, trailing_stop)
return best_result, best_params
# Define the parameters
file_path = 'C:\\Users\\The Death\\Downloads\\Binance_BTCUSDT_spot.csv'
start_date = "2020-03-16"
end_date = "2021-04-12"
df = load_data(file_path, start_date, end_date)
def load_data(start_date, end_date):
# Your code to load the data for the specified date range
# ...
return df
# Define the parameters for the backtesting
start_rsi_period = 1
end_rsi_period = 30
pivot_point_types = ["Close", "High/Low"]
start_pivot_point_n = 1
end_pivot_point_n = 50
divergence_types = ["Regular"]
start_max_pivot_point = 1
end_max_pivot_point = 20
start_max_bars_to_check = 30
end_max_bars_to_check = 200
start_trailing_stop = 0.01
end_trailing_stop = 0.5
starting_capital = 10000
# Run the backtesting
df = load_data(start_date, end_date)
best_result, best_params = find_best_iteration(df, start_rsi_period, end_rsi_period, pivot_point_types, start_pivot_point_n, end_pivot_point_n, divergence_types, start_max_pivot_point, end_max_pivot_point, start_max_bars_to_check, end_max_bars_to_check, start_trailing_stop, end_trailing_stop, starting_capital)
# Print the results
print("Best result: ", best_result)
print("Best parameters: ", best_params)

I have two recommendations after I scroll up your code:
Reduce the usage of for loop. As you increase a layer of for loop (initial is O(n), the time complexity of your code will increase by a power. In your find_best_iteration() there is about 7 layers of for loop, this is extremely cost your time.
Save and process your data in numpy.array() instead of pd.dataframe(). Dataframe is a class that contains too many unused attributes, and its performance is also slower than numpy.array.

You can try the following methods to improve the performance:
The backtest() function is used many times inside the find_best_iteration() function under many for loops, thus the positions variable inside backtest() is being updated frequently which can be show when the positions variable is a Dataframe. You can consider using numpy array for the positions variable that is optimized for updates.
You can try using the multiprocessing module in Python to parallelize the calculation of the divergence variable.
Hope this help!

Python returns local variable referenced before error

I edit this post for your comments. Thank you :-)
The prev_fs_cell is the variable whose value can be nan or str. (ex. nan <-> "1,244,234" )
If prev_fs_cell is nan, I want not to process self._strat(self, curr_year), but it has an error...
## GLOBAL & API ###
STOCK_START="2015.01.01"
FS_START="2014.01.01"
END="2021.09.01"
SHORT=10
LONG=60
CURR_YEAR=2021
API_key=dart_config.API_key
DART=OpenDartReader(API_key)
account_nm_list=["유동자산","비유동자산","유동부채","비유동부채","자산총계","부채총계","매출액","영업이익","당기순이익"]
KOSPI_stock_code=stock.get_market_ticker_list(market="KOSPI")
class Strategy():
def __init__(self):
self.buy_signal=pd.DataFrame(columns=['open','unit'])
self.sell_signal = pd.DataFrame(columns=['open', 'unit'])
self.trade = pd.DataFrame(columns=['stock', 'cash'])
self.position=0
self.unit=1
self.cash=100000000 # 1억
def set_data(self, indicator_data, finance_data):
self.indicator_data=indicator_data
self.indicator_data.rename(columns={self.indicator_data.columns[0]:'date'}, inplace=True)
self.indicator_data = self.indicator_data.set_index('date')
self.indicator_data.index = pd.to_datetime(self.indicator_data.index, format="%Y-%m-%d")
self.fs_data=finance_data
self.fs_data.rename(columns={self.fs_data.columns[0]:'year'}, inplace=True)
self.fs_data = self.fs_data.set_index('year')
self.min_year=int(self.fs_data.index.min()) # str type
def _buy(self, row):
if (row['open']*self.unit) <= self.cash:
new_buy_row = pd.Series([row['open'], self.unit], index = self.buy_signal.columns, name=str(row.name))
self.buy_signal = self.buy_signal.append(new_buy_row)
self.position += self.unit
stock_amt = self.position * row['open']
self.cash -= row['open']*self.unit
new_trade_row = pd.Series([stock_amt, self.cash], index = self.trade.columns, name = str(row.name))
self.trade = self.trade.append(new_trade_row)
def _sell(self, row):
new_sell_row = pd.Series([row['open'], int(self.position/4)+1], index = self.sell_signal.columns, name=str(row.name))
self.sell_signal = self.sell_signal.append(new_sell_row)
self.position -= int(self.position/4)+1
stock_amt = self.position * row['open']
self.cash += row['open']*self.unit
new_trade_row = pd.Series([stock_amt, self.cash], index = self.trade.columns, name = str(row.name))
self.trade = self.trade.append(new_trade_row)
def _strat(self, row, curr_year):
fs = self.fs_data
prev_year = curr_year - 1
curr_rev = int(fs.loc[curr_year, '매출액'].replace(",",""))
prev_rev = int(fs.loc[prev_year, '매출액'].replace(",",""))
rev_growth=(curr_rev-prev_rev)/prev_rev
curr_ni = int(fs.loc[curr_year, '당기순이익'].replace(",",""))
prev_ni = int(fs.loc[prev_year, '당기순이익'].replace(",",""))
ni_growth=(curr_ni-prev_ni)/prev_ni
curr_asset = int(fs.loc[curr_year, '유동자산'].replace(",",""))
noncurr_asset = int(fs.loc[prev_year, "비유동자산"].replace(",",""))
curr_asset_rat = curr_asset / noncurr_asset
if (row.rsi<0.65) & (rev_growth>0.005) & (1.3< curr_asset_rat):# & (curr_asset_rat<2.3):
self._buy(row)
elif (row.Golden == False):
if ni_growth <= 0.001 :
if self.position:
self._sell(row)
# a=1
def run(self):
dates = self.indicator_data.index
fs = self.fs_data
#print(fs.index)
for date in dates:
curr_year = date.year
row = self.indicator_data.loc[date]
#print(curr_year, type(curr_year))
#pdb.set_trace()
try:
curr_fs_cell = fs.loc[curr_year].iloc[0].replace(",","")
try:
prev_fs_cell = fs.loc[curr_year-1].iloc[0].replace(",","")
except:
prev_fs_cell = None
except:
curr_fs_cell = None
if (curr_fs_cell == None) | (prev_fs_cell == None):
#print("fs data is empty")
continue
else:
#print(prev_fs_cell)
self._strat(row, curr_year)
for code in KOSPI_stock_code:
FS = load_data("FS_"+code)
indi = load_data("indicator_"+code)
today = dt.today()
strategy = Strategy()
strategy.set_data(indi, FS)
strategy.run()
buy = strategy.buy_signal
sell = strategy.sell_signal
unit = strategy.unit
remain_stock = buy['unit'].sum() - sell['unit'].sum()
remain = int(get_data(str(code)+".KS", today).iloc[0]['open'])*int(remain_stock)
total_buy = int((buy['open'].sum()))*unit
total_sell = int(sell['open'].sum())*unit
profit = int(remain) + int(total_sell) - int(total_buy)
if total_buy:
return_rate = profit / total_buy
trade = strategy.trade
total_return_per_day = trade['stock']+trade['cash']
residual = total_return_per_day - return_rate
sample_var = residual**2 / (trade.shape[0]-1)
sample_dev = np.sqrt(sample_var)
Rf=0.01
sharp = (return_rate - Rf) / (sample_dev)
results[code]['return'] = return_rate
results[code]['sharp'] = sharp
else:
print("No buy due to strict condition")
I have tried to make backtest code for investing into Korean stocks by using financial sheet and stock price sheet and indicator sheet.
And my code return error like the below.
UnboundLocalError Traceback (most recent call last)
<ipython-input-13-caf2b218f860> in <module>()
10 strategy = Strategy()
11 strategy.set_data(indi, FS)
---> 12 strategy.run()
13
14 buy = strategy.buy_signal
<ipython-input-12-2d41db386a22> in run(self)
84 curr_fs_cell = None
85
---> 86 if (curr_fs_cell == None) | (prev_fs_cell == None):
87 #print("fs data is empty")
88 continue
UnboundLocalError: local variable 'prev_fs_cell' referenced before assignment
Actually there is no global variable whose name is prev_fs_cell, but it is only in that class. Why this error occurs?

RSI results different than in TradingView (coded in Python)

It's been days I spent trying to code (and search) a python function to get RSI that match TradingView results but without success (I'm new to Python).
The closest results I get for RSI is this function, but still different (and the fact exponential is used, sometimes result is pretty close, sometimes there is a pretty huge difference):
def rsi_tradingview(ohlc: pd.DataFrame, period: int = 14, round_rsi: bool = True):
delta = ohlc["close"].diff()
up = delta.copy()
up[up < 0] = 0
up = pd.Series.ewm(up, alpha=1/period).mean()
down = delta.copy()
down[down > 0] = 0
down *= -1
down = pd.Series.ewm(down, alpha=1/period).mean()
rsi = np.where(up == 0, 0, np.where(down == 0, 100, 100 - (100 / (1 + up / down))))
return np.round(rsi, 2) if round_rsi else rsi
My code looks like this:
pairs = ["BTCUSDT", "PONDUSDT"]
def get_historical_candles():
record = client.get_historical_klines(pair, Client.KLINE_INTERVAL_5MINUTE, "3 hour ago UTC")
myList = []
try:
for item in record:
n_item = []
int_ts = int(item[0] / 1000)
n_item.append(float(item[4])) # close
myList.append(n_item)
except Exception as error:
debug_logger.debug(error)
new_ohlc = pd.DataFrame(myList, columns=['close'])
return new_ohlc
def rsi_tradingview(ohlc: all_candles, period: int = 14, round_rsi: bool = False):
delta = all_candles.diff()
up = delta.copy()
up[up < 0] = 0
up = pd.Series.ewm(up, alpha=1/period).mean()
down = delta.copy()
down[down > 0] = 0
down *= -1
down = pd.Series.ewm(down, alpha=1/period).mean()
rsi = np.where(up == 0, 0, np.where(down == 0, 100, 100 - (100 / (1 + up / down))))
return np.round(rsi, 2) if round_rsi else rsi
for pair in pairs:
all_candles = get_historical_candles()
test_rsi = rsi_tradingview(all_candles, 14, False)
test_rsi_final = test_rsi[-1]
print(test_rsi_final)
I compare results with tradingview_ta this way, that give correct results (I can't just use this function to get RSI because I need the RSI to calculate StochRSI):
for pair in pairs:
test = TA_Handler(
symbol=pair,
screener="CRYPTO",
exchange="BINANCE",
interval=Interval.INTERVAL_5_MINUTES
)
print(test.get_analysis().indicators["RSI"])
If this can help, here are the codes on TradingView to get RSI and how is calculated RMA
# RSI
study(title="Relative Strength Index", shorttitle="RSI", format=format.price, precision=2, resolution="")
len = input(14, minval=1, title="Length")
src = input(close, "Source", type = input.source)
up = rma(max(change(src), 0), len)
down = rma(-min(change(src), 0), len)
rsi = down == 0 ? 100 : up == 0 ? 0 : 100 - (100 / (1 + up / down))
plot(rsi, "RSI", color=#7E57C2)
band1 = hline(70, "Upper Band", color=#787B86)
bandm = hline(50, "Middle Band", color=color.new(#787B86, 50))
band0 = hline(30, "Lower Band", color=#787B86)
fill(band1, band0, color=color.rgb(126, 87, 194, 90), title="Background")
# RMA
plot(rma(close, 15))
//the same on pine
pine_rma(src, length) =>
alpha = 1/length
sum = 0.0
sum := na(sum[1]) ? sma(src, length) : alpha * src + (1 - alpha) * nz(sum[1])
plot(pine_rma(close, 15))
Please guys, help me to find what is wrong. :(
And Thank you by advance! Thanks for reading!

How to find Average directional movement for stocks using Pandas?

I have a dataframe of OHLCV data. I would like to know if anyone knows any tutorial or any way of finding ADX(Average directional movement ) using pandas?
import pandas as pd
import yfinance as yf
import matplotlib.pyplot as plt
import datetime as dt
import numpy as nm
start=dt.datetime.today()-dt.timedelta(59)
end=dt.datetime.today()
df=pd.DataFrame(yf.download("MSFT", start=start, end=end))
The average directional index, or ADX, is the primary technical indicator among the five indicators that make up a technical trading system developed by J. Welles Wilder, Jr. and is calculated using the other indicators that make up the trading system. The ADX is primarily used as an indicator of momentum, or trend strength, but the total ADX system is also used as a directional indicator.
Directional movement is calculated by comparing the difference between two consecutive lows with the difference between their respective highs.
For the excel calculation of ADX this is a really good video:
https://www.youtube.com/watch?v=LKDJQLrXedg&t=387s

I was playing with this a little bit and found something that can help you with the issue:
def ADX(data: pd.DataFrame, period: int):
"""
Computes the ADX indicator.
"""
df = data.copy()
alpha = 1/period
# TR
df['H-L'] = df['High'] - df['Low']
df['H-C'] = np.abs(df['High'] - df['Close'].shift(1))
df['L-C'] = np.abs(df['Low'] - df['Close'].shift(1))
df['TR'] = df[['H-L', 'H-C', 'L-C']].max(axis=1)
del df['H-L'], df['H-C'], df['L-C']
# ATR
df['ATR'] = df['TR'].ewm(alpha=alpha, adjust=False).mean()
# +-DX
df['H-pH'] = df['High'] - df['High'].shift(1)
df['pL-L'] = df['Low'].shift(1) - df['Low']
df['+DX'] = np.where(
(df['H-pH'] > df['pL-L']) & (df['H-pH']>0),
df['H-pH'],
0.0
)
df['-DX'] = np.where(
(df['H-pH'] < df['pL-L']) & (df['pL-L']>0),
df['pL-L'],
0.0
)
del df['H-pH'], df['pL-L']
# +- DMI
df['S+DM'] = df['+DX'].ewm(alpha=alpha, adjust=False).mean()
df['S-DM'] = df['-DX'].ewm(alpha=alpha, adjust=False).mean()
df['+DMI'] = (df['S+DM']/df['ATR'])*100
df['-DMI'] = (df['S-DM']/df['ATR'])*100
del df['S+DM'], df['S-DM']
# ADX
df['DX'] = (np.abs(df['+DMI'] - df['-DMI'])/(df['+DMI'] + df['-DMI']))*100
df['ADX'] = df['DX'].ewm(alpha=alpha, adjust=False).mean()
del df['DX'], df['ATR'], df['TR'], df['-DX'], df['+DX'], df['+DMI'], df['-DMI']
return df
At the beginning the values aren't correct (as always with the EWM approach) but after several computations it converges to the correct value.

Math was taken from here.
def ADX(df):
def getCDM(df):
dmpos = df["High"][-1] - df["High"][-2]
dmneg = df["Low"][-2] - df["Low"][-1]
if dmpos > dmneg:
return dmpos
else:
return dmneg
def getDMnTR(df):
DMpos = []
DMneg = []
TRarr = []
n = round(len(df)/14)
idx = n
while n <= (len(df)):
dmpos = df["High"][n-1] - df["High"][n-2]
dmneg = df["Low"][n-2] - df["Low"][n-1]
DMpos.append(dmpos)
DMneg.append(dmneg)
a1 = df["High"][n-1] - df["High"][n-2]
a2 = df["High"][n-1] - df["Close"][n-2]
a3 = df["Low"][n-1] - df["Close"][n-2]
TRarr.append(max(a1,a2,a3))
n = idx + n
return DMpos, DMneg, TRarr
def getDI(df):
DMpos, DMneg, TR = getDMnTR(df)
CDM = getCDM(df)
POSsmooth = (sum(DMpos) - sum(DMpos)/len(DMpos) + CDM)
NEGsmooth = (sum(DMneg) - sum(DMneg)/len(DMneg) + CDM)
DIpos = (POSsmooth / (sum(TR)/len(TR))) *100
DIneg = (NEGsmooth / (sum(TR)/len(TR))) *100
return DIpos, DIneg
def getADX(df):
DIpos, DIneg = getDI(df)
dx = (abs(DIpos- DIneg) / abs(DIpos + DIneg)) * 100
ADX = dx/14
return ADX
return(getADX(df))
print(ADX(df))

This gives you the exact numbers as Tradingview and Thinkorswim.
import numpy as np
def ema(arr, periods=14, weight=1, init=None):
leading_na = np.where(~np.isnan(arr))[0][0]
arr = arr[leading_na:]
alpha = weight / (periods + (weight-1))
alpha_rev = 1 - alpha
n = arr.shape[0]
pows = alpha_rev**(np.arange(n+1))
out1 = np.array([])
if 0 in pows:
out1 = ema(arr[:int(len(arr)/2)], periods)
arr = arr[int(len(arr)/2) - 1:]
init = out1[-1]
n = arr.shape[0]
pows = alpha_rev**(np.arange(n+1))
scale_arr = 1/pows[:-1]
if init:
offset = init * pows[1:]
else:
offset = arr[0]*pows[1:]
pw0 = alpha*alpha_rev**(n-1)
mult = arr*pw0*scale_arr
cumsums = mult.cumsum()
out = offset + cumsums*scale_arr[::-1]
out = out[1:] if len(out1) > 0 else out
out = np.concatenate([out1, out])
out[:periods] = np.nan
out = np.concatenate(([np.nan]*leading_na, out))
return out
def atr(highs, lows, closes, periods=14, ema_weight=1):
hi = np.array(highs)
lo = np.array(lows)
c = np.array(closes)
tr = np.vstack([np.abs(hi[1:]-c[:-1]),
np.abs(lo[1:]-c[:-1]),
(hi-lo)[1:]]).max(axis=0)
atr = ema(tr, periods=periods, weight=ema_weight)
atr = np.concatenate([[np.nan], atr])
return atr
def adx(highs, lows, closes, periods=14):
highs = np.array(highs)
lows = np.array(lows)
closes = np.array(closes)
up = highs[1:] - highs[:-1]
down = lows[:-1] - lows[1:]
up_idx = up > down
down_idx = down > up
updm = np.zeros(len(up))
updm[up_idx] = up[up_idx]
updm[updm < 0] = 0
downdm = np.zeros(len(down))
downdm[down_idx] = down[down_idx]
downdm[downdm < 0] = 0
_atr = atr(highs, lows, closes, periods)[1:]
updi = 100 * ema(updm, periods) / _atr
downdi = 100 * ema(downdm, periods) / _atr
zeros = (updi + downdi == 0)
downdi[zeros] = .0000001
adx = 100 * np.abs(updi - downdi) / (updi + downdi)
adx = ema(np.concatenate([[np.nan], adx]), periods)
return adx

IRR library is only good if the pay period and compound period is in years (Engineering Economy)

http://docs.scipy.org/doc/numpy-1.10.0/reference/generated/numpy.irr.html
The link above works for me only when the pay period and compound period are in years. If they in months or quarters, I don't know how to use it.
You will understand what I am saying, if you have knowledge about IRR, present value, future value, etc.
The answer for IRR(Year) is 298.88% and I am getting 12.22%
The time in column A is in years
EXCEL FILE IMAGE:
Excel File image
import xlrd
import numpy
fileWorkspace = 'C://Users/jod/Desktop/'
wb1 = xlrd.open_workbook(fileWorkspace + 'Project3.xls')
sh1 = wb1.sheet_by_index(0)
time,amount,category = [],[],[]
for a in range(2,sh1.nrows):
time.append(int(sh1.cell(a,0).value))
amount.append(float(sh1.cell(a,1).value))
category.append(str(sh1.cell(a,2).value))
#print(time)
#print(amount)
#print(category)
print('\n')
p_p2 = str(sh1.cell(0,1))
p_p1 = p_p2.replace("text:'","")
pp = p_p1.replace("'","")
#print(pp)
c_p2 = str(sh1.cell(1,1))
c_p1 = c_p2.replace("text:'","")
cp = c_p1.replace("'","")
#print(cp)
netflow = 0
outflow = 0
inflow = 0
flow = 0
if pp == "Months" and cp == "Months":
IRR = numpy.irr(amount) * 100
print ("IRR:", round(IRR, 2), '%', '\n')
for i in time:
flow = amount[i] / numpy.power((1 + (IRR/100)), time[i])
if flow>0:
inflow = inflow + flow
if flow<0:
outflow = outflow + flow
#print ('Present Value (P) is:', round(flow,0), '\n')
netflow = outflow + inflow
print("In 2016")
print("-------")
print ('Outflow is: ', round(outflow,0))
print ('Inflow is: ', round(inflow,0))
print ('Netflow is: ', round(netflow,0), '\n')
outflow2 = (round(outflow,0))*(1+(IRR/100))**(9)
inflow2 = (round(inflow,0))*(1+(IRR/100))**(9)
netflow2 = outflow2 + inflow2
print("In 2025")
print("-------")
print ('Outflow is: ', round(outflow2,0))
print ('Inflow is: ', round(inflow2,0))
print ('Netflow is: ', round(netflow2,0), '\n')

Let us assume we have a monthly flow, for example:
flow = [-1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1.4]
x = np.irr(flow)
x
0.0284361557263606
to compute IRR you need to use the following formula:
IRR = (1 + x)**12 - 1
(1 + x) ** 12 - 1
0.39999999999998925
If you have quarterly flow, use the formula acordingly:
IRR = (1 + np.irr(quarterly_flow)) ** 4 - 1

According to numPy link that you provided. It's for periodic IRR, which means, it depends on what is your definition of 'periodic' it could be monthly or annually.
For example, as I followed your provided data:
amount_arr = [-17.99, 7.99, -3.00, 7.99, -3.00, 7.99, -3.00, 7.99, -3.00, 7.99, -3.00, 7.99]
​
airr = np.irr(amount_arr)
​
print ('periodic IRR is %2.2f%%' %(100 * airr))
print ('annual is %2.2f%%' %(12 * (100 * airr)))
> periodic IRR is 12.22%
> annual is 146.66%
Hope it helps.