def obv(close, volume, talib=None, offset=None, **kwargs):
"""Indicator: On Balance Volume (OBV)"""
# Validate arguments
close = verify_series(close)
volume = verify_series(volume)
offset = get_offset(offset)
mode_tal = bool(talib) if isinstance(talib, bool) else True
# Calculate Result
if Imports["talib"] and mode_tal:
from talib import OBV
obv = OBV(close, volume)
else:
signed_volume = signed_series(close, initial=1) * volume
obv = signed_volume.cumsum()
# Offset
if offset != 0:
obv = obv.shift(offset)
# Handle fills
if "fillna" in kwargs:
obv.fillna(kwargs["fillna"], inplace=True)
if "fill_method" in kwargs:
obv.fillna(method=kwargs["fill_method"], inplace=True)
# Name and Categorize it
obv.name = f"OBV"
obv.category = "volume"
return obv
def refresh(self, df):
df = df[-(MAX_ROWS + 1):-1]
open = df.open.astype("f8").values
high = df.high.astype("f8").values
low = df.low.astype("f8").values
close = df.close.astype("f8").values
volume = df.volume.astype("f8").values
df["price"] = WCLPRICE(high, low, close) #Weighted Close Price
df["obv"] = OBV(close, volume)
df["ad"] = AD(high, low, close, volume)
df["macd"], df["signal"], df["histogram"] = MACD(close)
df["rsi"] = RSI(close) #relative strong index
#df["willr"] = WILLR(high, low, close) + 100 #will index
df["roc"] = ROC(close)
#統計
df["beta"] = BETA(high, low)
df["linearR"] = LINEARREG(close) #線形回帰
df["linearA"] = LINEARREG_ANGLE(close) ##線形回帰 角度
df["linearI"] = LINEARREG_INTERCEPT(close) #線形回帰 JIEJU
df["linearS"] = LINEARREG_SLOPE(close) #線形回帰 坂
df["stddev"] = STDDEV(close) #標準偏差
df["tsf"] = TSF(close) #Time Series Forecast
df["var"] = VAR(close) #方差
df["wramount"] = 0
df["amount"] = 0
df["memo"] = 0
def getOBV(price, volume):
date = 1
OBV_ = []
obv = OBV(price, volume)
for ele in obv:
OBV_.append([date, ele])
date = date + 1
return OBV_
def volumeTechnicalIndicators(price, volume, tot_lags, prefix):
data_result = priceTechnicalIndicator(volume, tot_lags, prefix)
# OBV
lags = tot_lags
obv = OBV(price, volume)
for lag in lags:
tmp = obv.diff(lag) # diff, otherwise the scale would change if accumulates
tmp.name = 'OBV_DIFF_%dD' % lag
data_result = data_result.join(tmp)
# VOLUME RATIO
lag = 5
tmp = volume.rolling(window=lag).mean()
volume_ratio = volume / tmp
volume_ratio.name = 'VOLUME_RATIO'
data_result = data_result.join(volume_ratio)
return data_result
def binaryClassificationInThirtyMinutes(self, df):
'''
Predict the price of bitcoin in the next 30 minutes by a given df (dataframe)
Example:
binaryClassificationInThirtyMinutes(df) = 0
Parameters:
df: a dataframe with df.columns = ['open', 'high', 'low', 'close', 'volume']
Returns:
prediction: int = a prediction by the model, 0 for down, 1 for same or up
'''
# if len(df) != 34:
# # due to wma
# raise Exception("Dataframe must have 34 rows")
data = df.copy()
rsi = RSI(data['close'])
k, d = STOCH(data['high'], data['low'], data['close'])
macd, macdsignal, macdhist = MACD(data['close'],
fastperiod=12,
slowperiod=26,
signalperiod=9)
williams_r = WILLR(data['high'], data['low'], data['close'])
rate_of_change = ROC(data['close'])
on_balance_volume = OBV(data['close'], data['volume'])
weighted_moving_average = WMA(data['close'])
normalized_average_true_range = NATR(data['high'], data['low'],
data['close'])
data['rsi'] = rsi
data['k'] = k
data['d'] = d
data['macd'] = macd
data['williams_r'] = williams_r
data['rate_of_change'] = rate_of_change
data['on_balance_volume'] = on_balance_volume
data['weighted_moving_average'] = weighted_moving_average
data['normalized_average_true_range'] = normalized_average_true_range
data = data.dropna(axis=0)
data = self.normalizeDataframe(data)
with open(
pathlib.Path(__file__).resolve().parent /
"random_forest_params", "rb") as file:
model = pickle.load(file)
features = data.values
prediction = model.predict(features)
return prediction[0]
def amountTechnicalIndicators(price, amount, tot_lags, prefix):
data_result = priceTechnicalIndicator(amount, tot_lags, prefix)
# OBV
lags = tot_lags
amt_obv = OBV(price, amount)
for lag in lags:
tmp = amt_obv.diff(lag) # diff, otherwise the scale would change if accumulates
tmp.name = 'AMT_OBV_DIFF_%dD' % lag
data_result = data_result.join(tmp)
# AMOUNT RATIO
lags = np.array(tot_lags)
lags = lags[lags >= 2]
for lag in lags:
tmp = amount.rolling(window=lag).mean()
amt_ratio = amount / tmp
amt_ratio.name = 'AMOUNT_RATIO_%dD' % lag
data_result = data_result.join(amt_ratio)
return data_result
def create_features(ts):
from talib import SMA, RSI, OBV
target = 'future_close_ret'
features = ['current_close_ret', 'current_volume_ret']
for n in [14, 25, 50, 100]:
ts['sma_' +
str(n)] = SMA(ts['close'].values, timeperiod=n) / ts['close']
ts['rsi_' + str(n)] = RSI(ts['close'].values, timeperiod=n)
ts['obv'] = OBV(ts['close'].values, ts['volume'].values.astype('float64'))
ts.drop(
['close', 'volume', 'close_ret', 'volume_ret', 'future_volume_ret'],
axis='columns',
inplace=True)
ts.dropna(inplace=True)
return ts.corr()
def getTechnicalInd(data, window=10):
close = data['Close']
high = data['High']
low = data['Low']
volume = data['Volume']
#madev = roc = willr=rsi=apo=atr=obv=adosc=slowk=fastk=slowd=fastd=vpos=vneg={}
window = 10
for i in range(0, window):
# momentum indicators
# rate of change: (price/prevPrice - 1)*100
data["roc{0}".format(i)] = ROC(close.shift(i), timeperiod=10)
# williams oscillator
data["willr{0}".format(i)] = WILLR(high.shift(i),
low.shift(i),
close.shift(i),
timeperiod=14)
# relative strength index
data["rsi{0}".format(i)] = RSI(close.shift(i), timeperiod=14)
# absolute price oscillator: slowMA(price) - fastMA(price)
data["apo{0}".format(i)] = APO(close.shift(i),
fastperiod=12,
slowperiod=26,
matype=0)
# volatility indicator
data["atr{0}".format(i)] = ATR(high.shift(i),
low.shift(i),
close.shift(i),
timeperiod=14) # average true range
# Volume indicator
# on balance volume
data["obv{0}".format(i)] = OBV(close.shift(i), volume.shift(i))
# chaikin A/D oscillator
data["adosc{0}".format(i)] = ADOSC(high.shift(i),
low.shift(i),
close.shift(i),
volume.shift(i),
fastperiod=3,
slowperiod=10)
# Stochastic Oscillator Slow %k: (C-L)/(H-L)*100
data["slowk{0}".format(i)], data["slowd{0}".format(i)] = STOCH(
high.shift(i),
low.shift(i),
close.shift(i),
fastk_period=5,
slowk_period=3,
slowk_matype=0,
slowd_period=3,
slowd_matype=0)
# STOCHF - Stochastic Fast
data["fastk{0}".format(i)], data["fastd{0}".format(i)] = STOCHF(
high.shift(i),
low.shift(i),
close.shift(i),
fastk_period=5,
fastd_period=3,
fastd_matype=0)
#vortex
data["vortex_indicator_pos{0}".format(i)] = vortex_indicator_pos(
high.shift(i), low.shift(i), close.shift(i), n=14, fillna=False)
data["vortex_indicator_neg{0}".format(i)] = vortex_indicator_neg(
high.shift(i), low.shift(i), close.shift(i), n=14, fillna=False)
# returns
for i in range(1, window):
# overlap studies
data["madev{0}".format(i)] = close - close.shift(1).rolling(
window=i).mean()
data["return{0}".format(i)] = close - close.shift(i)
# std
for i in range(2, window):
data["std{0}".format(i)] = close.rolling(
i).std() #Standard deviation for a period of 5 days
return data #madev, roc,willr,rsi,apo,atr,obv,adosc,slowk,slowd,fastk,fastd,vpos, vneg, returns, stds
def calcOBV(self, dates, price, volume):
obv = OBV(price, volume)
OBV_, isExist = self.createDateFrame(dates, obv, ['timestamp', 'OBV'])
return OBV_, isExist
def setvolume(open, high, low, close, volume):
#volume
df["obv"] = OBV(close, volume)
#df["ad"] = AD(high, low, close, volume)
df["ad"] = ADOSC(high, low, close, volume, fastperiod=3, slowperiod=10)
slowperiod=26,
signalperiod=9)
# print('-----------------------------------MACD-----------------------------------')
# print(macd[34:37])
# print(macdsignal[34:37])
# print(macdhist[34:37])
#
rsi = RSI(fechamento, timeperiod=14)
# print('-----------------------------------RSI-----------------------------------')
# print(rsi[34:37])
# Momentum Indicators # Volume Indicators
mfi = MFI(maximo, minimo, fechamento, volume, timeperiod=14)
# print('-----------------------------------MFI-----------------------------------')
# print(mfi[34:37])
#Volume Indicators
ad = AD(maximo, minimo, fechamento, volume)
adosc = ADOSC(maximo, minimo, fechamento, volume, fastperiod=3, slowperiod=10)
obv = OBV(fechamento, volume)
# dataFrameConcatened = pd.concat(fechamento, rsi)
dataFrameConcatened = np.concatenate((abertura, rsi), axis=0)
print(dataFrameConcatened)
ax = plt.gca()
# brsr6CSV.plot(kind='line',x='DATA',y='ABERTURA',ax=ax)
brsr6CSV.plot(kind='line', x='DATA', y='FECHAMENTO', color='red', ax=ax)
plt.plot(upBR, label='BB UP')
plt.plot(lowBR, label='BB Low')
plt.show()
def fetch(self,
symbol: str,
interval: Interval = Interval.DAY,
window: Window = Window.YEAR,
indicators: Indicators = [],
verbose=False) -> pd.DataFrame:
"""
Fetch symbol stock OHLCV from Yahoo Finance API
Args:
symbol (str): Symbol to fetch
interval (Interval, optional): Interval (hour, day, week, ...) of data. Defaults to Interval.DAY.
window (Window, optional): Length (day, week, month, year) of interval. Defaults to Window.YEAR.
indicators (Indicators, optional): Array of indicators to include in the result. Defaults to empty array.
Returns:
pd.DataFrame: OHLCV pandas DataFrame with interval on window length and indicators if specified
"""
try:
if verbose:
print(
f"Fetching OHLCV {symbol} stock data on {interval.name} interval and {window.name} window"
)
# Generic url to fetch
url = f"https://query1.finance.yahoo.com/v8/finance/chart/{symbol}?region=FR&lang=fr-FR&includePrePost=false&interval={interval.value}&range={window.value}&corsDomain=fr.finance.yahoo.com&.tsrc=finance"
req = requests.get(url)
# Testing request status code
if req.status_code == 200:
# Extracting data as json
data = req.json()
# Creating new DataFrame
df = pd.DataFrame()
# Extract date from object
if interval in [
Interval.MINUTE, Interval.TWO_MINUTE,
Interval.FIVE_MINUTE, Interval.FIFTEEN_MINUTE,
Interval.THIRTY_MINUTE, Interval.HOUR
]:
dateFromUnix = [
datetime.utcfromtimestamp(dt).strftime(
"%Y-%m-%d %H:%M:%S")
for dt in data["chart"]["result"][0]["timestamp"]
]
else:
dateFromUnix = [
datetime.utcfromtimestamp(dt).strftime("%Y-%m-%d")
for dt in data["chart"]["result"][0]["timestamp"]
]
# Date & OHLCV to DataFrame
df["date"] = pd.to_datetime(dateFromUnix)
df["open"] = data["chart"]["result"][0]["indicators"]["quote"][
0]["open"]
df["high"] = data["chart"]["result"][0]["indicators"]["quote"][
0]["high"]
df["low"] = data["chart"]["result"][0]["indicators"]["quote"][
0]["low"]
df["close"] = data["chart"]["result"][0]["indicators"][
"quote"][0]["close"]
df["volume"] = data["chart"]["result"][0]["indicators"][
"quote"][0]["volume"]
# Drop NaN on close col
df.dropna(subset=["close"], inplace=True)
# Divide volume column by a 1 000
df["volume"] = df["volume"].div(1000)
# Set date column as index
df.set_index("date", inplace=True)
for indicator in indicators:
# ADX
if indicator == Indicators.ADX:
df[indicator.value] = ADX(df["high"], df["low"],
df["close"])
# BBANDS
elif indicator == Indicators.BBANDS:
df[Indicators.BBANDS.value[0]], df[
Indicators.BBANDS.value[1]], df[
Indicators.BBANDS.value[2]] = BBANDS(
df["close"])
df["p_band"] = 100 - \
(df["l_band"] / df["u_band"] * 100)
df["p_band_ma_5"] = MA(df["p_band"], timeperiod=5)
# EMA
elif indicator == Indicators.EMA:
for ema in Indicators.EMA.value:
df[ema] = EMA(df["close"],
timeperiod=int(ema.split("_")[1]))
# MA
elif indicator == Indicators.MA:
for ma in Indicators.MA.value:
df[ma] = MA(df["close"],
timeperiod=int(ma.split("_")[1]))
# OBV
elif indicator == Indicators.OBV:
df[indicator.value] = OBV(df["close"], df["volume"])
df[indicator.value] = df[indicator.value].div(1000)
# PSAR
elif indicator == Indicators.PSAR:
df[indicator.value] = SAR(df["high"], df["low"])
# PERCENT CHANGE
elif indicator == Indicators.P_CHANGE:
for p_change in Indicators.P_CHANGE.value:
df[p_change] = df["close"].pct_change(
int(p_change.split(" ")[1])) * 100
# RSI
elif indicator == Indicators.RSI:
df[indicator.value] = RSI(df["close"])
return df.round(decimals=2)
except Exception as e:
print(e)
