def write_technical_analysis(symbols_list):
for symbol in symbols_list:
try:
file_path = f'data/ohlc/{symbol}.csv'
dataframe = pd.read_csv(file_path,
parse_dates=True,
index_col='Timestamp')
sma6 = btalib.sma(dataframe, period=6)
sma9 = btalib.sma(dataframe, period=9)
sma10 = btalib.sma(dataframe, period=10)
sma20 = btalib.sma(dataframe, period=20)
rsi = btalib.rsi(dataframe)
macd = btalib.macd(dataframe)
sub_SMA6_SMA20 = btalib.sub(sma6, sma20)
dataframe['SMA-6'] = round(sma6.df, 3)
dataframe['SMA-9'] = round(sma9.df, 3)
dataframe['SMA-10'] = round(sma10.df, 3)
dataframe['SMA-20'] = round(sma20.df, 3)
dataframe['RSI'] = round(rsi.df, 2)
dataframe['MACD'] = round(macd.df['macd'], 2)
dataframe['Signal'] = round(macd.df['signal'], 2)
dataframe['Histogram'] = macd.df['histogram']
dataframe['Delta_SMA6_SMA20'] = round(sub_SMA6_SMA20.df, 4)
f = open(file_path, 'w+')
dataframe.to_csv(file_path, sep=',', index=True)
f.close()
except:
print(f'{symbol} is not writing the technical data.')
def calculate_indicator(self):
# RSI 15 Indicator
if self.indicator == 'RSI':
self.klines['rsi'] = btalib.rsi(self.klines.close, period=15).df
# SMA 12-50 Indicator
elif self.indicator == 'SMA':
self.klines['12sma'] = btalib.sma(self.klines.close, period=12).df
self.klines['50sma'] = btalib.sma(self.klines.close, period=50).df
# MACD 12-26-9 Indicator
elif self.indicator == 'MACD':
self.klines['macd'], self.klines['macdSignal'], self.klines[
'macdHist'] = btalib.macd(self.klines.close,
pfast=12,
pslow=26,
psignal=9)
else:
return None
def getFftnMinData(self):
fftnMinBarUrl = '{}/15Min?symbols={}&limit=120'.format(config.BARS_URL, self.tickers)
r = requests.get(fftnMinBarUrl, headers=config.HEADERS)
data = r.json()
for symbol in data:
filename = 'data/15MinOHLC/{}.json'.format(symbol)
f = open(filename, 'w+')
f.write('{' + '"{}": '.format(symbol) + json.dumps(data[symbol], indent=4) + '}')
f.close()
for symbol in data:
filename = 'data/15MinOHLC/{}.txt'.format(symbol)
f = open(filename, 'w+')
f.write('Date,Open,High,Low,Close,Volume,OpenInterest\n')
tNow = datetime.now()
tDelta = timedelta(days=119)
tStart = tNow - tDelta
tdAdd = timedelta(days=1)
tPresent = tStart
for bar in data[symbol]:
day = tPresent.strftime('%Y-%m-%d')
line = '{},{},{},{},{},{},{}\n'.format(day, bar['o'], bar['h'], bar['l'], bar['c'], bar['v'], 0.00)
f.write(line)
tPresent = tPresent + tdAdd
f.close()
print('Fetched fifteen minute data from alpaca api')
for symbol in config.symbols:
df = pd.read_csv('data/15MinOHLC/{}.txt'.format(symbol), parse_dates=True, index_col='Date')
rsi = btalib.rsi(df)
df['rsi'] = rsi.df
stochastic = btalib.stochastic(df)
df['stoc k'] = stochastic.df['k']
df['stoc d'] = stochastic.df['d']
macd = btalib.macd(df)
df['macd'] = macd.df['macd']
df['signal'] = macd.df['signal']
df['histogram'] = macd.df['histogram']
df.to_csv(path_or_buf='data/15MinOHLC/{}.txt'.format(symbol), index ='Entry') #, index='Date'
print('Finished generating rsi and stochastic oscillator.')
import btalib
import pandas as pd
df = pd.read_csv('data/ohlc/SPSC.txt', parse_dates=True, index_col="Date")
sma = btalib.sma(df)
rsi = btalib.rsi(df)
macd = btalib.macd(df)
#SMA15 = btalib.sma(df, period=15)
#SMA50 = btalib.sma(df, period=50)
#SMA200 = btalib.sma(df, period=200)
#if SMA50 > SMA200:
df['sma'] = sma.df
df['rsi'] = rsi.df
#macd = ema(data, 12) - ema(data, 26)
#signal = ema(macd, 9)
#histogram = macd - signal
df['macd'] = macd.df['macd']
df['signal'] = macd.df['signal']
df['histogram'] = macd.df['histogram']
oversold_days = df[df['rsi'] < 30]
overbought_days = df[df['rsi'] > 60]
print(oversold_days)
print(overbought_days)
def price_history(symbol_pair, time_step):
client = client_test_net()
if time_step == '5m':
klines = client.get_historical_klines(symbol_pair,
Client.KLINE_INTERVAL_5MINUTE,
"2 day ago UTC")
elif time_step == '15m':
klines = client.get_historical_klines(symbol_pair,
Client.KLINE_INTERVAL_15MINUTE,
"6 day ago UTC")
elif time_step == '30m':
klines = client.get_historical_klines(symbol_pair,
Client.KLINE_INTERVAL_30MINUTE,
"12 day ago UTC")
else:
klines = client.get_historical_klines(symbol_pair,
Client.KLINE_INTERVAL_1HOUR,
"24 day ago UTC")
# Remove unnecessary data
for line in klines:
del line[6:]
# Generate csv file of RAW data
df1 = pd.DataFrame(
klines, columns=['date', 'open', 'high', 'low', 'close', 'volume'])
df1.set_index('date', inplace=True)
df1.to_csv('{}_history_{}.csv'.format(symbol_pair, time_step))
# Prepare to calculate indicator
df = pd.read_csv('{}_history_{}.csv'.format(symbol_pair, time_step),
index_col=0)
df.index = pd.to_datetime(df.index, unit='ms') + pd.DateOffset(hours=7)
# Average of high-low *note: is high-low-close better?
df['avg'] = (df['high'] + df['low']) / 2
# Calculate moving average using Pandas
df['50ma'] = df.close.rolling(50).mean()
df['200ma'] = df.close.rolling(200).mean()
# VWAP
df['vwap'] = 0
volume = df['volume']
high = df['high']
low = df['low']
close = df['close']
typical_price = (high + low + close) / 3
for i in range(len(df)):
if df.index.hour[i] == 23 and df.index.minute[i] == 0:
df.loc[i:, 'vwap'] = (
volume[i:] * typical_price[i:]).cumsum() / volume[i:].cumsum()
# EMA
ema200 = btalib.ema(df.close, period=200)
# MACD
macd = btalib.macd(df.close, pfast=12, pslow=26, psignal=9)
df = df.join([ema200.df, macd.df])
# Export RAW calculated file
df.to_csv('{}_indicator_{}.csv'.format(symbol_pair, time_step))
# Remove blank data from calculated file
df_plot = df[199:-1]
df_plot.to_csv('{}_indicator_cutted_{}.csv'.format(symbol_pair, time_step))
return df_plot
def macd(self):
for frame in self._stock_prices.stock_frames:
macd = bt.macd(frame.data).df
frame.data['macd'] = macd
def generate_history(symbol_pair,
time_step,
day_ago=None,
date_start=None,
date_end=None,
until_now=True):
day_ago = str(day_ago)
client = client_test_net()
if until_now:
klines = client.get_historical_klines(symbol_pair, time_step,
'{} day ago UTC'.format(day_ago))
else:
klines = client.get_historical_klines(symbol_pair, time_step,
date_start, date_end)
for line in klines:
del line[6:]
# Generate csv file of RAW data
df1 = pd.DataFrame(
klines, columns=['date', 'open', 'high', 'low', 'close', 'volume'])
df1.set_index('date', inplace=True)
df1.to_csv('{}_long_history_{}.csv'.format(symbol_pair, time_step))
# Prepare to calculate indicator
df = pd.read_csv('{}_long_history_{}.csv'.format(symbol_pair, time_step),
index_col=0)
df.index = pd.to_datetime(df.index, unit='ms') + pd.DateOffset(hours=7)
# Average of high-low *note: is close-open better?
df['avg'] = (df['high'] + df['low']) / 2
# Calculate moving average using Pandas
df['50ma'] = df.close.rolling(50).mean()
df['200ma'] = df.close.rolling(200).mean()
# VWAP
df['vwap'] = 0
volume = df['volume']
high = df['high']
low = df['low']
close = df['close']
typical_price = (high + low + close) / 3
for i in range(len(df)):
if df.index.hour[i] == 23 and df.index.minute[i] == 0:
df.loc[i:, 'vwap'] = (
volume[i:] * typical_price[i:]).cumsum() / volume[i:].cumsum()
# EMA
ema200 = btalib.ema(df.close, period=200)
# MACD
macd = btalib.macd(df.close, pfast=12, pslow=26, psignal=9)
df = df.join([ema200.df, macd.df])
# Export RAW calculated file
df.to_csv('{}_history_indicator_{}.csv'.format(symbol_pair, time_step))
# Remove blank data from calculated file
df_plot = df[199:-1]
df_plot.to_csv('{}_history_indicator_cutted_{}.csv'.format(
symbol_pair, time_step))
return df_plot
# get the highest closing price in 2020 max_val = btc_df.close['2020'].max() print(mean) print(max_val) # technical indicators using bta-lib # sma sma = btalib.sma(btc_df.close) print(sma.df) # create sma and attach as column to original df btc_df['sma'] = btalib.sma(btc_df.close, period=20).df print(btc_df.tail()) # calculate rsi and macd rsi = btalib.rsi(btc_df, period=14) macd = btalib.macd(btc_df, pfast=20, pslow=50, psignal=13) print(rsi.df) print(macd.df) # access last rsi value print(rsi.df.rsi[-1]) # join the rsi and macd calculations as columns in original df btc_df = btc_df.join([rsi.df, macd.df]) print(btc_df.tail())
def tech_ind_features(data):
"""
Generate technical indicators
* :param data(pd.DataFrame): Raw data for processing
:return transformed_df(pd.DataFrame): Dataframe of features, sample balanced and normalised
"""
data['smoothed_close'] = data.close.rolling(9).mean().rolling(21).mean().shift(-15)
data['dx'] = np.diff(data['smoothed_close'], prepend=data['smoothed_close'][0])
data['dx_signal'] = pd.Series(data['dx']).rolling(9).mean()
data['ddx'] = np.diff(np.diff(data['smoothed_close']), prepend=data['smoothed_close'][0:2])
data['labels'] = np.zeros(len(data))
data['labels'].iloc[[(data.ddx < 0.1) & (data.dx <= 0) & (data.dx_signal > 0)]] = 1
data['labels'].iloc[[(data.ddx > -0.075) & (data.dx >= 0) & (data.dx_signal < 0)]] = 2
#Filter and drop all columns except close price, volume and date (for indexing)
relevant_cols = list(
compress(
data.columns,
[False if i in [1, 3, 4, 5, 6, len(data.columns)-1] else True for i in range(len(data.columns))]
)
)
data = data.drop(columns=relevant_cols).rename(columns={'open_date_time': 'date'})
data.set_index('date', inplace = True)
#Define relevant periods for lookback/feature engineering
periods = [
9, 14, 21,
30, 45, 60,
90, 100, 120
]
#Construct technical features for image synthesis
for period in periods:
data[f'ema_{period}'] = btalib.ema(
data.close,
period = period
).df['ema']
data[f'ema_{period}_dx'] = np.append(np.nan, np.diff(btalib.ema(
data.close,
period = period
).df['ema']))
data[f'rsi_{period}'] = btalib.rsi(
data.close,
period = period
).df['rsi']
data[f'cci_{period}'] = btalib.cci(
data.high,
data.low,
data.close,
period = period
).df['cci']
data[f'macd_{period}'] = btalib.macd(
data.close,
pfast = period,
pslow = period*2,
psignal = int(period/3)
).df['macd']
data[f'signal_{period}'] = btalib.macd(
data.close,
pfast = period,
pslow = period*2,
psignal = int(period/3)
).df['signal']
data[f'hist_{period}'] = btalib.macd(
data.close,
pfast = period,
pslow = period*2,
psignal = int(period/3)
).df['histogram']
data[f'volume_{period}'] = btalib.sma(
data.volume,
period = period
).df['sma']
data[f'change_{period}'] = data.close.pct_change(periods = period)
data = data.drop(data.query('labels == 0').sample(frac=.90).index)
data = data.replace([np.inf, -np.inf], np.nan).dropna()
data_trimmed = data.loc[:, 'ema_9':]
data_trimmed = pd.concat(
[data_trimmed,
data_trimmed.shift(1),
data_trimmed.shift(2)],
axis = 1
)
mm_scaler = MinMaxScaler(feature_range=(0, 1))
transformed_data = mm_scaler.fit_transform(data_trimmed[24:])
transformed_data = np.c_[
transformed_data,
pd.to_numeric(
data.labels[24:],
downcast = 'signed'
).to_list()
]
return transformed_data
def create_indicator(cls, klines: pd.DataFrame) -> pd.DataFrame:
macd = btalib.macd(klines.copy())
return macd.df