def genTA(data, y, t): #t is timeperiod
indicators = {}
y_ind = copy.deepcopy(y)
for ticker in data:
## Overlap
indicators[ticker] = ta.SMA(data[ticker].iloc[:,3], timeperiod=t).to_frame()
indicators[ticker]['EMA'] = ta.EMA(data[ticker].iloc[:,3], timeperiod=t)
indicators[ticker]['BBAND_Upper'], indicators[ticker]['BBAND_Middle' ], indicators[ticker]['BBAND_Lower' ] = ta.BBANDS(data[ticker].iloc[:,3], timeperiod=t, nbdevup=2, nbdevdn=2, matype=0)
indicators[ticker]['HT_TRENDLINE'] = ta.HT_TRENDLINE(data[ticker].iloc[:,3])
indicators[ticker]['SAR'] = ta.SAR(data[ticker].iloc[:,1], data[ticker].iloc[:,2], acceleration=0, maximum=0)
#rename SMA column
indicators[ticker].rename(columns={indicators[ticker].columns[0]: "SMA"}, inplace=True)
## Momentum
indicators[ticker]['RSI'] = ta.RSI(data[ticker].iloc[:,3], timeperiod=(t-1))
indicators[ticker]['MOM'] = ta.MOM(data[ticker].iloc[:,3], timeperiod=(t-1))
indicators[ticker]['ROC'] = ta.ROC(data[ticker].iloc[:,3], timeperiod=(t-1))
indicators[ticker]['ROCP']= ta.ROCP(data[ticker].iloc[:,3],timeperiod=(t-1))
indicators[ticker]['STOCH_SLOWK'], indicators[ticker]['STOCH_SLOWD'] = ta.STOCH(data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3], fastk_period=t, slowk_period=int(.6*t), slowk_matype=0, slowd_period=int(.6*t), slowd_matype=0)
indicators[ticker]['MACD'], indicators[ticker]['MACDSIGNAL'], indicators[ticker]['MACDHIST'] = ta.MACD(data[ticker].iloc[:,3], fastperiod=t,slowperiod=2*t,signalperiod=int(.7*t))
## Volume
indicators[ticker]['OBV'] = ta.OBV(data[ticker].iloc[:,3], data[ticker].iloc[:,4])
indicators[ticker]['AD'] = ta.AD(data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3], data[ticker].iloc[:,4])
indicators[ticker]['ADOSC'] = ta.ADOSC(data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3], data[ticker].iloc[:,4], fastperiod=int(.3*t), slowperiod=t)
## Cycle
indicators[ticker]['HT_DCPERIOD'] = ta.HT_DCPERIOD(data[ticker].iloc[:,3])
indicators[ticker]['HT_TRENDMODE']= ta.HT_TRENDMODE(data[ticker].iloc[:,3])
## Price
indicators[ticker]['AVGPRICE'] = ta.AVGPRICE(data[ticker].iloc[:,0], data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3])
indicators[ticker]['TYPPRICE'] = ta.TYPPRICE(data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3])
## Volatility
indicators[ticker]['ATR'] = ta.ATR(data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3], timeperiod=(t-1))
## Statistics
indicators[ticker]['BETA'] = ta.BETA(data[ticker].iloc[:,1], data[ticker].iloc[:,2], timeperiod=(t-1))
indicators[ticker]['LINEARREG'] = ta.LINEARREG(data[ticker].iloc[:,3], timeperiod=t)
indicators[ticker]['VAR'] = ta.VAR(data[ticker].iloc[:,3], timeperiod=t, nbdev=1)
## Math Transform
indicators[ticker]['EXP'] = ta.EXP(data[ticker].iloc[:,3])
indicators[ticker]['LN'] = ta.LN(data[ticker].iloc[:,3])
## Patterns (returns integers - but norming might not really do anything but wondering if they should be normed)
indicators[ticker]['CDLENGULFING'] = ta.CDLENGULFING(data[ticker].iloc[:,0], data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3])
indicators[ticker]['CDLDOJI'] = ta.CDLDOJI(data[ticker].iloc[:,0], data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3])
indicators[ticker]['CDLHAMMER'] = ta.CDLHAMMER(data[ticker].iloc[:,0], data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3])
indicators[ticker]['CDLHANGINGMAN']= ta.CDLHANGINGMAN(data[ticker].iloc[:,0], data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3])
#drop 'nan' values
indicators[ticker].drop(indicators[ticker].index[np.arange(0,63)], inplace=True)
y_ind[ticker].drop(y_ind[ticker].index[np.arange(0,63)], inplace=True)
#Normalize Features
indicators_norm = normData(indicators)
return indicators_norm, indicators, y_ind
def avgprice(
client,
symbol,
timeframe="6m",
opencol="open",
highcol="high",
lowcol="low",
closecol="close",
):
"""This will return a dataframe of average price for the given symbol across
the given timeframe
Args:
client (pyEX.Client): Client
symbol (string): Ticker
timeframe (string): timeframe to use, for pyEX.chart
opencol (string): column to use to calculate
highcol (string): column to use to calculate
lowcol (string): column to use to calculate
closecol (string): column to use to calculate
Returns:
DataFrame: result
"""
df = client.chartDF(symbol, timeframe)
avg = t.AVGPRICE(df[opencol].values, df[highcol].values, df[lowcol].values,
df[closecol].values)
return pd.DataFrame({
opencol: df[opencol].values,
highcol: df[highcol].values,
lowcol: df[lowcol].values,
closecol: df[closecol].values,
"avgprice": avg,
})
def update(self, data, N):
self.clear()
self.series.attachAxis(self.chart.ax)
self.series.attachAxis(self.chart.ay)
price_average = talib.AVGPRICE(data[1], data[2], data[3], data[4])
for i, val in enumerate(price_average[-N:]):
self.series.append(i + 0.5, val)
def AVGPRICE(open, high, low, close):
''' Average Price 平均价格
分组: Price Transform 价格指标
简介:
real = AVGPRICE(open, high, low, close)
'''
return talib.AVGPRICE(open, high, low, close)
def getPriceTransforms(df):
high = df['High']
low = df['Low']
close = df['Close']
open = df['Open']
volume = df['Volume']
df['AVGPRICE'] = ta.AVGPRICE(open, high, low, close)
df['MEDPRICE'] = ta.MEDPRICE(high, low)
df['TYPPRICE'] = ta.TYPPRICE(high, low, close)
df['WCLPRICE'] = ta.WCLPRICE(high, low, close)
def add_technical_indicators(dataframe):
# Overlap Studies Functions
dataframe["SMA"] = talib.SMA(dataframe["Close"])
dataframe["BBANDS_up"], dataframe["BBANDS_md"], dataframe[
"BBANDS_dw"] = talib.BBANDS(dataframe["Close"],
timeperiod=5,
nbdevup=2,
nbdevdn=2,
matype=0)
dataframe["EMA"] = talib.EMA(dataframe["Close"], timeperiod=30)
dataframe["HT_TRENDLINE"] = talib.HT_TRENDLINE(dataframe["Close"])
dataframe["WMA"] = talib.WMA(dataframe["Close"], timeperiod=30)
# Momentum Indicator Functions
dataframe["ADX"] = talib.ADX(dataframe["High"],
dataframe["Low"],
dataframe["Close"],
timeperiod=14)
dataframe["MACD"], _, _ = talib.MACD(dataframe["Close"],
fastperiod=12,
slowperiod=26,
signalperiod=9)
dataframe["MOM"] = talib.MOM(dataframe["Close"], timeperiod=5)
dataframe["RSI"] = talib.RSI(dataframe["Close"], timeperiod=14)
# Volume Indicator Functions
# dataframe["OBV"] = talib.OBV(dataframe["Close"], dataframe["Volume"])
# Volatility Indicator Functions
dataframe["ATR"] = talib.ATR(dataframe["High"],
dataframe["Low"],
dataframe["Close"],
timeperiod=14)
dataframe["TRANGE"] = talib.TRANGE(dataframe["High"], dataframe["Low"],
dataframe["Close"])
# Price Transform Functions
dataframe["AVGPRICE"] = talib.AVGPRICE(dataframe["Open"],
dataframe["High"], dataframe["Low"],
dataframe["Close"])
dataframe["MEDPRICE"] = talib.MEDPRICE(dataframe["High"], dataframe["Low"])
dataframe["WCLPRICE"] = talib.WCLPRICE(dataframe["High"], dataframe["Low"],
dataframe["Close"])
# Statistic Functions
dataframe["LINEARREG_SLOPE"] = talib.LINEARREG_SLOPE(dataframe["Close"],
timeperiod=14)
dataframe["STDDEV"] = talib.STDDEV(dataframe["Close"],
timeperiod=5,
nbdev=1)
dataframe = dataframe.dropna()
return dataframe
def get_price_studies(open, low, high, close, df):
# https://mrjbq7.github.io/ta-lib/func_groups/price_transform.html
df["AVGPRICE"] = talib.AVGPRICE(open, high, low, close)
df["MEDPRICE"] = talib.MEDPRICE(high, low)
df["TYPPRICE"] = talib.TYPPRICE(high, low, close)
df["WCLPRICE"] = talib.WCLPRICE(high, low, close)
df["ATR-5"] = talib.ATR(high, low, close, timeperiod=5)
df["ATR-10"] = talib.ATR(high, low, close, timeperiod=10)
df["ATR-20"] = talib.ATR(high, low, close, timeperiod=20)
df["ATR-50"] = talib.ATR(high, low, close, timeperiod=50)
df["ATR-200"] = talib.ATR(high, low, close, timeperiod=200)
def Other_test():
data_table["AVGPRICE"] = talib.AVGPRICE(data_table.open, data_table.high,
data_table.low, data_table.close)
print("AVGPRICE", data_table["AVGPRICE"])
data_table["MEDPRICE"] = talib.MEDPRICE(data_table.high, data_table.low)
print("MEDPRICE", data_table["MEDPRICE"])
data_table["BETA"] = talib.BETA(data_table.high,
data_table.low,
timeperiod=4)
print("BETA", data_table["BETA"])
data_table["VAR"] = talib.VAR(data_table.close, timeperiod=5, nbdev=1)
print("VAR", data_table["VAR"])
def avg_price(self, sym, frequency):
if not self.kbars_ready(sym, frequency):
return []
opens = self.open(sym, frequency)
highs = self.high(sym, frequency)
lows = self.low(sym, frequency)
closes = self.close(sym, frequency)
v = ta.AVGPRICE(opens, highs, lows, closes)
return v
def main():
# read csv file and transform it to datafeed (df):
df = pd.read_csv(current_dir+"/"+base_dir+"/"+in_dir+"/"+in_dir+'_'+stock_symbol+'.csv')
# set numpy datafeed from df:
df_numpy = {
'Date': np.array(df['date']),
'Open': np.array(df['open'], dtype='float'),
'High': np.array(df['high'], dtype='float'),
'Low': np.array(df['low'], dtype='float'),
'Close': np.array(df['close'], dtype='float'),
'Volume': np.array(df['volume'], dtype='float')
}
date = df_numpy['Date']
openp = df_numpy['Open']
high = df_numpy['High']
low = df_numpy['Low']
close = df_numpy['Close']
volume = df_numpy['Volume']
#########################################
##### Price Transform Functions #####
#########################################
#AVGPRICE - Average Price
avgprice = ta.AVGPRICE(openp, high, low, close)
#MEDPRICE - Median Price
medprice = ta.MEDPRICE(high, low)
#TYPPRICE - Typical Price
typprice = ta.TYPPRICE(high, low, close)
#WCLPRICE - Weighted Close Price
wclprice = ta.WCLPRICE(high, low, close)
df_save = pd.DataFrame(data ={
'date': np.array(df['date']),
'avgprice':avgprice,
'medprice':medprice,
'typprice':typprice,
'wclprice':wclprice
})
df_save.to_csv(current_dir+"/"+base_dir+"/"+out_dir+'/'+stock_symbol+"/"+out_dir+'_ta_price_transform_'+stock_symbol+'.csv',index=False)
def avgprice(candles: np.ndarray,
sequential: bool = False) -> Union[float, np.ndarray]:
"""
AVGPRICE - Average Price
:param candles: np.ndarray
:param sequential: bool - default: False
:return: float | np.ndarray
"""
candles = slice_candles(candles, sequential)
res = talib.AVGPRICE(candles[:, 1], candles[:, 3], candles[:, 4],
candles[:, 2])
return res if sequential else res[-1]
def get_additional_factors(open, high, low, close, volume):
# Overlap Studies Functions
mat = get_all_factors(open, high, low, close, volume)
mat = np.column_stack((mat, talib.HT_TRENDLINE(close))) ## close
mat = np.column_stack((mat, talib.KAMA(close, timeperiod=30))) ##close
#Momentum Indicator Functions
mat = np.column_stack((mat, talib.ADX(high, low, close, timeperiod=14)))
mat = np.column_stack((mat, talib.ADXR(high, low, close, timeperiod=14)))
mat = np.column_stack(
(mat, talib.APO(close, fastperiod=12, slowperiod=26, matype=0)))
mat = np.column_stack((mat, talib.AROONOSC(high, low, timeperiod=14)))
mat = np.column_stack((mat, talib.BOP(open, high, low, close)))
mat = np.column_stack((mat, talib.MOM(close, timeperiod=10)))
#Volume Indicator Functions
mat = np.column_stack((mat, talib.AD(high, low, close, volume)))
mat = np.column_stack(
(mat, talib.ADOSC(high,
low,
close,
volume,
fastperiod=3,
slowperiod=10)))
mat = np.column_stack((mat, talib.OBV(close, volume)))
#Volatility Indicator Functions
mat = np.column_stack((mat, talib.NATR(high, low, close, timeperiod=14)))
mat = np.column_stack((mat, talib.TRANGE(high, low, close)))
#Price Transform Functions
mat = np.column_stack((mat, talib.AVGPRICE(open, high, low, close)))
mat = np.column_stack((mat, talib.MEDPRICE(high, low)))
mat = np.column_stack((mat, talib.TYPPRICE(high, low, close)))
mat = np.column_stack((mat, talib.WCLPRICE(high, low, close)))
#Cycle Indicator Functions
mat = np.column_stack((mat, talib.HT_DCPERIOD(close)))
mat = np.column_stack((mat, talib.HT_DCPHASE(close)))
mat = np.column_stack((mat, talib.HT_TRENDMODE(close)))
# 20
return mat
def add_price_transform_indicators(data_list):
for data in data_list:
# 1) AVGPRICE - Average Price
real = talib.AVGPRICE(data.Open, data.High, data.Low, data.Close)
data['AVERAGE'] = real
# 2) MEDPRICE - Median Price
real = talib.MEDPRICE(data.High, data.Low)
data['MEDPRICE'] = real
# 3) TYPPRICE - Typical Price
real = talib.TYPPRICE(data.High, data.Low, data.Close)
data['TYPPRICE'] = real
# 4) WCLPRICE - Weighted Close Price
real = talib.WCLPRICE(data.High, data.Low, data.Close)
data['WCLPRICE'] = real
return data_list
def avgprice(candles: np.ndarray, sequential: bool = False) -> Union[float, np.ndarray]:
"""
AVGPRICE - Average Price
:param candles: np.ndarray
:param sequential: bool - default=False
:return: float | np.ndarray
"""
warmup_candles_num = get_config('env.data.warmup_candles_num', 240)
if not sequential and len(candles) > warmup_candles_num:
candles = candles[-warmup_candles_num:]
res = talib.AVGPRICE(candles[:, 1], candles[:, 3], candles[:, 4], candles[:, 2])
if sequential:
return res
else:
return None if np.isnan(res[-1]) else res[-1]
def Price_Transform(dataframe):
"""
Price Transform
AVGPRICE Average Price
MEDPRICE Median Price
TYPPRICE Typical Price
WCLPRICE Weighted Close Price
"""
#Price Transform Functions
#AVGPRICE - Average Price
df[f'{ratio}_AVGPRICE'] = talib.AVGPRICE(Open, High, Low, Close)
#MEDPRICE - Median Price
df[f'{ratio}_MEDPRICE'] = talib.MEDPRICE(High, Low)
#TYPPRICE - Typical Price
df[f'{ratio}_TYPPRICE'] = talib.TYPPRICE(High, Low, Close)
#WCLPRICE - Weighted Close Price
df[f'{ratio}_WCLPRICE'] = talib.WCLPRICE(High, Low, Close)
return
def avgprice(candles: np.ndarray,
sequential=False) -> Union[float, np.ndarray]:
"""
AVGPRICE - Average Price
:param candles: np.ndarray
:param sequential: bool - default=False
:return: float | np.ndarray
"""
if not sequential and len(candles) > 240:
candles = candles[-240:]
res = talib.AVGPRICE(candles[:, 1], candles[:, 3], candles[:, 4],
candles[:, 2])
if sequential:
return res
else:
return None if np.isnan(res[-1]) else res[-1]
def kakakutai_dekidaka(self, df):
OPEN = df['open']
HIGH = df['high']
LOW = df['low']
CLOSE = df['close']
VOLUME = df['volume']
#1日の平均価格を計算
ave = talib.AVGPRICE(OPEN, HIGH, LOW, CLOSE)
#価格のレンジを確認
minimum = np.floor(LOW.min())
maximum = np.ceil(HIGH.max())
# print('価格のレンジ：{}-{}'.format(minimum,maximum))
#価格のレンジをビン分割する
supposed_bin_num = 20
bin_range = int(np.ceil((maximum - minimum) / supposed_bin_num))
# print('各価格帯の刻み：{}'.format(bin_range))
#ビン分割の境界値のリストとリストの長さ
bins = np.arange(minimum, maximum, bin_range)
# print('境界値リスト：{}'.format(bins))
# print('境界値リスト長さ：{}'.format(len(bins)))
#1日の平均価格をビン分割
cut = pd.cut(ave, bins)
#出来高データと統合
data = pd.DataFrame()
data['cut'] = cut
data['axis'] = cut.apply(lambda x: x.mid)
data['volume'] = VOLUME
#価格帯別の出来高を合計する
dekidaka = data.groupby('axis').sum()
dekidaka.fillna(0)
return minimum, maximum, dekidaka
def handle_price_transform(args, kax, klines_df, close_times, display_count):
os_key = 'AVGPRICE'
if args.AVGPRICE:
real = talib.AVGPRICE(klines_df["open"], klines_df["high"],
klines_df["low"], klines_df["close"])
kax.plot(close_times, real[-display_count:], "y", label=os_key)
os_key = 'MEDPRICE'
if args.MEDPRICE:
real = talib.MEDPRICE(klines_df["high"], klines_df["low"])
kax.plot(close_times, real[-display_count:], "y", label=os_key)
os_key = 'TYPPRICE'
if args.TYPPRICE:
real = talib.TYPPRICE(klines_df["high"], klines_df["low"],
klines_df["close"])
kax.plot(close_times, real[-display_count:], "y", label=os_key)
os_key = 'WCLPRICE'
if args.WCLPRICE:
real = talib.WCLPRICE(klines_df["high"], klines_df["low"],
klines_df["close"])
kax.plot(close_times, real[-display_count:], "y", label=os_key)
def Set_multiple_timeframe_indicators(data, begin, end, verbose=True):
"""
:param @data: dataframe containing ohlcv prices and indexed with date
:param @begin: first timeframe used to calculate indicators
:param @end: last timeframe used to calculate indicators
:return: dataframe of Technical indicators of different timeframes from @begin to @end
"""
if verbose:
print("Extracting TA ...")
df = pd.DataFrame(index=data.index)
for timeframe in range(begin, end):
d = Set_indicators(data, timeframe)
df = pd.concat([df, d], axis=1, join='inner')
if verbose:
print(str(timeframe) + "timeframe TA done")
#AD - Chaikin A/D Line
df["AD"] = talib.AD(data["High"], data["Low"], data[USED_CLOSE_PRICE],
data["Volume"])
df["OBV"] = talib.OBV(data[USED_CLOSE_PRICE], data["Volume"])
#BOP - Balance Of Power
df["BOP"] = talib.BOP(data["Open"], data["High"], data["Low"],
data[USED_CLOSE_PRICE])
df["priceAvg"] = talib.AVGPRICE(data.Open, data["High"], data["Low"],
data[USED_CLOSE_PRICE])
#Adding date column
df["Date"] = data["Date"]
return df
def talib_AVGPRICE(DataFrame):
"""AVGPRICE - Average Price 平均价格函数"""
res = talib.AVGPRICE(DataFrame.open.values, DataFrame.high.values,
DataFrame.low.values, DataFrame.close.values)
return pd.DataFrame({'AVGPRICE': res}, index=DataFrame.index)
def AVGPRICE(DataFrame):
res = talib.AVGPRICE(DataFrame.open.values, DataFrame.high.values,
DataFrame.low.values, DataFrame.close.values)
return pd.DataFrame({'AVGPRICE': res}, index=DataFrame.index)
def main():
ohlcv = api_ohlcv('20191017')
open, high, low, close, volume, timestamp = [], [], [], [], [], []
for i in ohlcv:
open.append(int(i[0]))
high.append(int(i[1]))
low.append(int(i[2]))
close.append(int(i[3]))
volume.append(float(i[4]))
time_str = str(i[5])
timestamp.append(
datetime.fromtimestamp(int(
time_str[:10])).strftime('%Y/%m/%d %H:%M:%M'))
date_time_index = pd.to_datetime(
timestamp) # convert to DateTimeIndex type
df = pd.DataFrame(
{
'open': open,
'high': high,
'low': low,
'close': close,
'volume': volume
},
index=date_time_index)
# df.index += pd.offsets.Hour(9) # adjustment for JST if required
print(df.shape)
print(df.columns)
# pct_change
f = lambda x: 1 if x > 0.0001 else -1 if x < -0.0001 else 0 if -0.0001 <= x <= 0.0001 else np.nan
y = df.rename(columns={
'close': 'y'
}).loc[:, 'y'].pct_change(1).shift(-1).fillna(0)
X = df.copy()
y_ = pd.DataFrame(y.map(f), columns=['y'])
y = df.rename(columns={'close': 'y'}).loc[:, 'y'].pct_change(1).fillna(0)
df_ = pd.concat([X, y_], axis=1)
# check the shape
print(
'----------------------------------------------------------------------------------------'
)
print('X shape: (%i,%i)' % X.shape)
print('y shape: (%i,%i)' % y_.shape)
print(
'----------------------------------------------------------------------------------------'
)
print(y_.groupby('y').size())
print('y=1 up, y=0 stay, y=-1 down')
print(
'----------------------------------------------------------------------------------------'
)
# feature calculation
open = pd.Series(df['open'])
high = pd.Series(df['high'])
low = pd.Series(df['low'])
close = pd.Series(df['close'])
volume = pd.Series(df['volume'])
# pct_change for new column
X['diff'] = y
# Exponential Moving Average
ema = talib.EMA(close, timeperiod=3)
ema = ema.fillna(ema.mean())
# Momentum
momentum = talib.MOM(close, timeperiod=5)
momentum = momentum.fillna(momentum.mean())
# RSI
rsi = talib.RSI(close, timeperiod=14)
rsi = rsi.fillna(rsi.mean())
# ADX
adx = talib.ADX(high, low, close, timeperiod=14)
adx = adx.fillna(adx.mean())
# ADX change
adx_change = adx.pct_change(1).shift(-1)
adx_change = adx_change.fillna(adx_change.mean())
# AD
ad = talib.AD(high, low, close, volume)
ad = ad.fillna(ad.mean())
X_ = pd.concat([X, ema, momentum, rsi, adx_change, ad],
axis=1).drop(['open', 'high', 'low', 'close'], axis=1)
X_.columns = ['volume', 'diff', 'ema', 'momentum', 'rsi', 'adx', 'ad']
X_.join(y_).head(10)
# default parameter models
X_train, X_test, y_train, y_test = train_test_split(X_,
y_,
test_size=0.33,
random_state=42)
print('X_train shape: {}'.format(X_train.shape))
print('X_test shape: {}'.format(X_test.shape))
print('y_train shape: {}'.format(y_train.shape))
print('y_test shape: {}'.format(y_test.shape))
pipe_knn = Pipeline([('scl', StandardScaler()),
('est', KNeighborsClassifier(n_neighbors=3))])
pipe_logistic = Pipeline([('scl', StandardScaler()),
('est',
LogisticRegression(solver='lbfgs',
multi_class='multinomial',
random_state=39))])
pipe_rf = Pipeline([('scl', StandardScaler()),
('est', RandomForestClassifier(random_state=39))])
pipe_gb = Pipeline([('scl', StandardScaler()),
('est', GradientBoostingClassifier(random_state=39))])
pipe_names = ['KNN', 'Logistic', 'RandomForest', 'GradientBoosting']
pipe_lines = [pipe_knn, pipe_logistic, pipe_rf, pipe_gb]
for (i, pipe) in enumerate(pipe_lines):
pipe.fit(X_train, y_train.values.ravel())
print(pipe)
print('%s: %.3f' %
(pipe_names[i] + ' Train Accuracy',
accuracy_score(y_train.values.ravel(), pipe.predict(X_train))))
print('%s: %.3f' %
(pipe_names[i] + ' Test Accuracy',
accuracy_score(y_test.values.ravel(), pipe.predict(X_test))))
print('%s: %.3f' % (pipe_names[i] + ' Train F1 Score',
f1_score(y_train.values.ravel(),
pipe.predict(X_train),
average='micro')))
print('%s: %.3f' % (pipe_names[i] + ' Test F1 Score',
f1_score(y_test.values.ravel(),
pipe.predict(X_test),
average='micro')))
for (i, pipe) in enumerate(pipe_lines):
predict = pipe.predict(X_test)
cm = confusion_matrix(y_test.values.ravel(),
predict,
labels=[-1, 0, 1])
print('{} Confusion Matrix'.format(pipe_names[i]))
print(cm)
## Overlap Studies Functions
# DEMA - Double Exponential Moving Average
dema = talib.DEMA(close, timeperiod=3)
dema = dema.fillna(dema.mean())
print('DEMA - Double Exponential Moving Average shape: {}'.format(
dema.shape))
# EMA - Exponential Moving Average
ema = talib.EMA(close, timeperiod=3)
ema = ema.fillna(ema.mean())
print('EMA - Exponential Moving Average shape: {}'.format(ema.shape))
# HT_TRENDLINE - Hilbert Transform - Instantaneous Trendline
hilbert = talib.HT_TRENDLINE(close)
hilbert = hilbert.fillna(hilbert.mean())
print(
'HT_TRENDLINE - Hilbert Transform - Instantaneous Trendline shape: {}'.
format(hilbert.shape))
# KAMA - Kaufman Adaptive Moving Average
kama = talib.KAMA(close, timeperiod=3)
kama = kama.fillna(kama.mean())
print('KAMA - Kaufman Adaptive Moving Average shape: {}'.format(
kama.shape))
# MA - Moving average
ma = talib.MA(close, timeperiod=3, matype=0)
ma = ma.fillna(ma.mean())
print('MA - Moving average shape: {}'.format(kama.shape))
# MIDPOINT - MidPoint over period
midpoint = talib.MIDPOINT(close, timeperiod=7)
midpoint = midpoint.fillna(midpoint.mean())
print('MIDPOINT - MidPoint over period shape: {}'.format(midpoint.shape))
# MIDPRICE - Midpoint Price over period
midprice = talib.MIDPRICE(high, low, timeperiod=7)
midprice = midprice.fillna(midprice.mean())
print('MIDPRICE - Midpoint Price over period shape: {}'.format(
midprice.shape))
# SAR - Parabolic SAR
sar = talib.SAR(high, low, acceleration=0, maximum=0)
sar = sar.fillna(sar.mean())
print('SAR - Parabolic SAR shape: {}'.format(sar.shape))
# SAREXT - Parabolic SAR - Extended
sarext = talib.SAREXT(high,
low,
startvalue=0,
offsetonreverse=0,
accelerationinitlong=0,
accelerationlong=0,
accelerationmaxlong=0,
accelerationinitshort=0,
accelerationshort=0,
accelerationmaxshort=0)
sarext = sarext.fillna(sarext.mean())
print('SAREXT - Parabolic SAR - Extended shape: {}'.format(sarext.shape))
# SMA - Simple Moving Average
sma = talib.SMA(close, timeperiod=3)
sma = sma.fillna(sma.mean())
print('SMA - Simple Moving Average shape: {}'.format(sma.shape))
# T3 - Triple Exponential Moving Average (T3)
t3 = talib.T3(close, timeperiod=5, vfactor=0)
t3 = t3.fillna(t3.mean())
print('T3 - Triple Exponential Moving Average shape: {}'.format(t3.shape))
# TEMA - Triple Exponential Moving Average
tema = talib.TEMA(close, timeperiod=3)
tema = tema.fillna(tema.mean())
print('TEMA - Triple Exponential Moving Average shape: {}'.format(
tema.shape))
# TRIMA - Triangular Moving Average
trima = talib.TRIMA(close, timeperiod=3)
trima = trima.fillna(trima.mean())
print('TRIMA - Triangular Moving Average shape: {}'.format(trima.shape))
# WMA - Weighted Moving Average
wma = talib.WMA(close, timeperiod=3)
wma = wma.fillna(wma.mean())
print('WMA - Weighted Moving Average shape: {}'.format(wma.shape))
## Momentum Indicator Functions
# ADX - Average Directional Movement Index
adx = talib.ADX(high, low, close, timeperiod=14)
adx = adx.fillna(adx.mean())
print('ADX - Average Directional Movement Index shape: {}'.format(
adx.shape))
# ADXR - Average Directional Movement Index Rating
adxr = talib.ADXR(high, low, close, timeperiod=7)
adxr = adxr.fillna(adxr.mean())
print('ADXR - Average Directional Movement Index Rating shape: {}'.format(
adxr.shape))
# APO - Absolute Price Oscillator
apo = talib.APO(close, fastperiod=12, slowperiod=26, matype=0)
apo = apo.fillna(apo.mean())
print('APO - Absolute Price Oscillator shape: {}'.format(apo.shape))
# AROONOSC - Aroon Oscillator
aroon = talib.AROONOSC(high, low, timeperiod=14)
aroon = aroon.fillna(aroon.mean())
print('AROONOSC - Aroon Oscillator shape: {}'.format(apo.shape))
# BOP - Balance Of Power
bop = talib.BOP(open, high, low, close)
bop = bop.fillna(bop.mean())
print('BOP - Balance Of Power shape: {}'.format(apo.shape))
# CCI - Commodity Channel Index
cci = talib.CCI(high, low, close, timeperiod=7)
cci = cci.fillna(cci.mean())
print('CCI - Commodity Channel Index shape: {}'.format(cci.shape))
# CMO - Chande Momentum Oscillator
cmo = talib.CMO(close, timeperiod=7)
cmo = cmo.fillna(cmo.mean())
print('CMO - Chande Momentum Oscillator shape: {}'.format(cmo.shape))
# DX - Directional Movement Index
dx = talib.DX(high, low, close, timeperiod=7)
dx = dx.fillna(dx.mean())
print('DX - Directional Movement Index shape: {}'.format(dx.shape))
# MFI - Money Flow Index
mfi = talib.MFI(high, low, close, volume, timeperiod=7)
mfi = mfi.fillna(mfi.mean())
print('MFI - Money Flow Index shape: {}'.format(mfi.shape))
# MINUS_DI - Minus Directional Indicator
minusdi = talib.MINUS_DI(high, low, close, timeperiod=14)
minusdi = minusdi.fillna(minusdi.mean())
print('MINUS_DI - Minus Directional Indicator shape: {}'.format(
minusdi.shape))
# MINUS_DM - Minus Directional Movement
minusdm = talib.MINUS_DM(high, low, timeperiod=14)
minusdm = minusdm.fillna(minusdm.mean())
print('MINUS_DM - Minus Directional Movement shape: {}'.format(
minusdm.shape))
# MOM - Momentum
mom = talib.MOM(close, timeperiod=5)
mom = mom.fillna(mom.mean())
print('MOM - Momentum shape: {}'.format(mom.shape))
# PLUS_DI - Plus Directional Indicator
plusdi = talib.PLUS_DI(high, low, close, timeperiod=14)
plusdi = plusdi.fillna(plusdi.mean())
print('PLUS_DI - Plus Directional Indicator shape: {}'.format(
plusdi.shape))
# PLUS_DM - Plus Directional Movement
plusdm = talib.PLUS_DM(high, low, timeperiod=14)
plusdm = plusdm.fillna(plusdm.mean())
print('PLUS_DM - Plus Directional Movement shape: {}'.format(plusdi.shape))
# PPO - Percentage Price Oscillator
ppo = talib.PPO(close, fastperiod=12, slowperiod=26, matype=0)
ppo = ppo.fillna(ppo.mean())
print('PPO - Percentage Price Oscillator shape: {}'.format(ppo.shape))
# ROC - Rate of change:((price/prevPrice)-1)*100
roc = talib.ROC(close, timeperiod=10)
roc = roc.fillna(roc.mean())
print('ROC - Rate of change : ((price/prevPrice)-1)*100 shape: {}'.format(
roc.shape))
# RSI - Relative Strength Index
rsi = talib.RSI(close, timeperiod=14)
rsi = rsi.fillna(rsi.mean())
print('RSI - Relative Strength Index shape: {}'.format(rsi.shape))
# TRIX - 1-day Rate-Of-Change (ROC) of a Triple Smooth EMA
trix = talib.TRIX(close, timeperiod=30)
trix = trix.fillna(trix.mean())
print('TRIX - 1-day Rate-Of-Change (ROC) of a Triple Smooth EMA shape: {}'.
format(trix.shape))
# ULTOSC - Ultimate Oscillator
ultosc = talib.ULTOSC(high,
low,
close,
timeperiod1=7,
timeperiod2=14,
timeperiod3=28)
ultosc = ultosc.fillna(ultosc.mean())
print('ULTOSC - Ultimate Oscillator shape: {}'.format(ultosc.shape))
# WILLR - Williams'%R
willr = talib.WILLR(high, low, close, timeperiod=7)
willr = willr.fillna(willr.mean())
print("WILLR - Williams'%R shape: {}".format(willr.shape))
## Volume Indicator Functions
# AD - Chaikin A/D Line
ad = talib.AD(high, low, close, volume)
ad = ad.fillna(ad.mean())
print('AD - Chaikin A/D Line shape: {}'.format(ad.shape))
# ADOSC - Chaikin A/D Oscillator
adosc = talib.ADOSC(high, low, close, volume, fastperiod=3, slowperiod=10)
adosc = adosc.fillna(adosc.mean())
print('ADOSC - Chaikin A/D Oscillator shape: {}'.format(adosc.shape))
# OBV - On Balance Volume
obv = talib.OBV(close, volume)
obv = obv.fillna(obv.mean())
print('OBV - On Balance Volume shape: {}'.format(obv.shape))
## Volatility Indicator Functions
# ATR - Average True Range
atr = talib.ATR(high, low, close, timeperiod=7)
atr = atr.fillna(atr.mean())
print('ATR - Average True Range shape: {}'.format(atr.shape))
# NATR - Normalized Average True Range
natr = talib.NATR(high, low, close, timeperiod=7)
natr = natr.fillna(natr.mean())
print('NATR - Normalized Average True Range shape: {}'.format(natr.shape))
# TRANGE - True Range
trange = talib.TRANGE(high, low, close)
trange = trange.fillna(trange.mean())
print('TRANGE - True Range shape: {}'.format(natr.shape))
## Price Transform Functions
# AVGPRICE - Average Price
avg = talib.AVGPRICE(open, high, low, close)
avg = avg.fillna(avg.mean())
print('AVGPRICE - Average Price shape: {}'.format(natr.shape))
# MEDPRICE - Median Price
medprice = talib.MEDPRICE(high, low)
medprice = medprice.fillna(medprice.mean())
print('MEDPRICE - Median Price shape: {}'.format(medprice.shape))
# TYPPRICE - Typical Price
typ = talib.TYPPRICE(high, low, close)
typ = typ.fillna(typ.mean())
print('TYPPRICE - Typical Price shape: {}'.format(typ.shape))
# WCLPRICE - Weighted Close Price
wcl = talib.WCLPRICE(high, low, close)
wcl = wcl.fillna(wcl.mean())
print('WCLPRICE - Weighted Close Price shape: {}'.format(wcl.shape))
## Cycle Indicator Functions
# HT_DCPERIOD - Hilbert Transform - Dominant Cycle Period
dcperiod = talib.HT_DCPERIOD(close)
dcperiod = dcperiod.fillna(dcperiod.mean())
print('HT_DCPERIOD - Hilbert Transform - Dominant Cycle Period shape: {}'.
format(dcperiod.shape))
# HT_DCPHASE - Hilbert Transform - Dominant Cycle Phase
dcphase = talib.HT_DCPHASE(close)
dcphase = dcphase.fillna(dcphase.mean())
print('HT_DCPHASE - Hilbert Transform - Dominant Cycle Phase shape: {}'.
format(dcperiod.shape))
## Statistic Functions
# BETA - Beta
beta = talib.BETA(high, low, timeperiod=3)
beta = beta.fillna(beta.mean())
print('BETA - Beta shape: {}'.format(beta.shape))
# CORREL - Pearson's Correlation Coefficient(r)
correl = talib.CORREL(high, low, timeperiod=30)
correl = correl.fillna(correl.mean())
print("CORREL - Pearson's Correlation Coefficient(r) shape: {}".format(
beta.shape))
# LINEARREG - Linear Regression
linreg = talib.LINEARREG(close, timeperiod=7)
linreg = linreg.fillna(linreg.mean())
print("LINEARREG - Linear Regression shape: {}".format(linreg.shape))
# STDDEV - Standard Deviation
stddev = talib.STDDEV(close, timeperiod=5, nbdev=1)
stddev = stddev.fillna(stddev.mean())
print("STDDEV - Standard Deviation shape: {}".format(stddev.shape))
# TSF - Time Series Forecast
tsf = talib.TSF(close, timeperiod=7)
tsf = tsf.fillna(tsf.mean())
print("TSF - Time Series Forecast shape: {}".format(tsf.shape))
# VAR - Variance
var = talib.VAR(close, timeperiod=5, nbdev=1)
var = var.fillna(var.mean())
print("VAR - Variance shape: {}".format(var.shape))
## Feature DataFrame
X_full = pd.concat([
X, dema, ema, hilbert, kama, ma, midpoint, midprice, sar, sarext, sma,
t3, tema, trima, wma, adx, adxr, apo, aroon, bop, cci, cmo, mfi,
minusdi, minusdm, mom, plusdi, plusdm, ppo, roc, rsi, trix, ultosc,
willr, ad, adosc, obv, atr, natr, trange, avg, medprice, typ, wcl,
dcperiod, dcphase, beta, correl, linreg, stddev, tsf, var
],
axis=1).drop(['open', 'high', 'low', 'close'], axis=1)
X_full.columns = [
'volume', 'diff', 'dema', 'ema', 'hilbert', 'kama', 'ma', 'midpoint',
'midprice', 'sar', 'sarext', 'sma', 't3', 'tema', 'trima', 'wma',
'adx', 'adxr', 'apo', 'aroon', 'bop', 'cci', 'cmo', 'mfi', 'minusdi',
'minusdm', 'mom', 'plusdi', 'plusdm', 'ppo', 'roc', 'rsi', 'trix',
'ultosc', 'willr', 'ad', 'adosc', 'obv', 'atr', 'natr', 'trange',
'avg', 'medprice', 'typ', 'wcl', 'dcperiod', 'dcphase', 'beta',
'correl', 'linreg', 'stddev', 'tsf', 'var'
]
X_full.join(y_).head(10)
# full feature models
X_train_full, X_test_full, y_train_full, y_test_full = train_test_split(
X_full, y_, test_size=0.33, random_state=42)
print('X_train shape: {}'.format(X_train_full.shape))
print('X_test shape: {}'.format(X_test_full.shape))
print('y_train shape: {}'.format(y_train_full.shape))
print('y_test shape: {}'.format(y_test_full.shape))
pipe_knn_full = Pipeline([('scl', StandardScaler()),
('est', KNeighborsClassifier(n_neighbors=3))])
pipe_logistic_full = Pipeline([
('scl', StandardScaler()),
('est',
LogisticRegression(solver='lbfgs',
multi_class='multinomial',
random_state=39))
])
pipe_rf_full = Pipeline([('scl', StandardScaler()),
('est', RandomForestClassifier(random_state=39))])
pipe_gb_full = Pipeline([('scl', StandardScaler()),
('est',
GradientBoostingClassifier(random_state=39))])
pipe_names = ['KNN', 'Logistic', 'RandomForest', 'GradientBoosting']
pipe_lines_full = [
pipe_knn_full, pipe_logistic_full, pipe_rf_full, pipe_gb_full
]
for (i, pipe) in enumerate(pipe_lines_full):
pipe.fit(X_train_full, y_train_full.values.ravel())
print(pipe)
print('%s: %.3f' % (pipe_names[i] + ' Train Accuracy',
accuracy_score(y_train_full.values.ravel(),
pipe.predict(X_train_full))))
print('%s: %.3f' % (pipe_names[i] + ' Test Accuracy',
accuracy_score(y_test_full.values.ravel(),
pipe.predict(X_test_full))))
print('%s: %.3f' % (pipe_names[i] + ' Train F1 Score',
f1_score(y_train_full.values.ravel(),
pipe.predict(X_train_full),
average='micro')))
print('%s: %.3f' % (pipe_names[i] + ' Test F1 Score',
f1_score(y_test_full.values.ravel(),
pipe.predict(X_test_full),
average='micro')))
# Univariate Statistics
select = SelectPercentile(percentile=25)
select.fit(X_train_full, y_train_full.values.ravel())
X_train_selected = select.transform(X_train_full)
X_test_selected = select.transform(X_test_full)
# GradientBoost Classifier
print(
'--------------------------Without Univariate Statistics-------------------------------------'
)
pipe_gb = Pipeline([('scl', StandardScaler()),
('est', GradientBoostingClassifier(random_state=39))])
pipe_gb.fit(X_train_full, y_train_full.values.ravel())
print('Train Accuracy: {:.3f}'.format(
accuracy_score(y_train_full.values.ravel(),
pipe_gb.predict(X_train_full))))
print('Test Accuracy: {:.3f}'.format(
accuracy_score(y_test_full.values.ravel(),
pipe_gb.predict(X_test_full))))
print('Train F1 Score: {:.3f}'.format(
f1_score(y_train_full.values.ravel(),
pipe_gb.predict(X_train_full),
average='micro')))
print('Test F1 Score: {:.3f}'.format(
f1_score(y_test_full.values.ravel(),
pipe_gb.predict(X_test_full),
average='micro')))
# GradientBoost Cllassifier with Univariate Statistics
print(
'---------------------------With Univariate Statistics--------------------------------------'
)
pipe_gb_percentile = Pipeline([
('scl', StandardScaler()),
('est', GradientBoostingClassifier(random_state=39))
])
pipe_gb_percentile.fit(X_train_selected, y_train_full.values.ravel())
print('Train Accuracy: {:.3f}'.format(
accuracy_score(y_train_full.values.ravel(),
pipe_gb_percentile.predict(X_train_selected))))
print('Test Accuracy: {:.3f}'.format(
accuracy_score(y_test_full.values.ravel(),
pipe_gb_percentile.predict(X_test_selected))))
print('Train F1 Score: {:.3f}'.format(
f1_score(y_train_full.values.ravel(),
pipe_gb_percentile.predict(X_train_selected),
average='micro')))
print('Test F1 Score: {:.3f}'.format(
f1_score(y_test_full.values.ravel(),
pipe_gb_percentile.predict(X_test_selected),
average='micro')))
# Model-based Selection
select = SelectFromModel(RandomForestClassifier(n_estimators=100,
random_state=42),
threshold="1.25*mean")
select.fit(X_train_full, y_train_full.values.ravel())
X_train_model = select.transform(X_train_full)
X_test_model = select.transform(X_test_full)
# GradientBoost Classifier
print(
'--------------------------Without Model-based Selection--------------------------------------'
)
pipe_gb = Pipeline([('scl', StandardScaler()),
('est', GradientBoostingClassifier(random_state=39))])
pipe_gb.fit(X_train_full, y_train_full.values.ravel())
print('Train Accuracy: {:.3f}'.format(
accuracy_score(y_train_full.values.ravel(),
pipe_gb.predict(X_train_full))))
print('Test Accuracy: {:.3f}'.format(
accuracy_score(y_test_full.values.ravel(),
pipe_gb.predict(X_test_full))))
print('Train F1 Score: {:.3f}'.format(
f1_score(y_train_full.values.ravel(),
pipe_gb.predict(X_train_full),
average='micro')))
print('Test F1 Score: {:.3f}'.format(
f1_score(y_test_full.values.ravel(),
pipe_gb.predict(X_test_full),
average='micro')))
# GradientBoost Classifier with Model-based Selection
print(
'----------------------------With Model-based Selection--------------------------------------'
)
pipe_gb_model = Pipeline([('scl', StandardScaler()),
('est',
GradientBoostingClassifier(random_state=39))])
pipe_gb_model.fit(X_train_model, y_train_full.values.ravel())
print('Train Accuracy: {:.3f}'.format(
accuracy_score(y_train_full.values.ravel(),
pipe_gb_model.predict(X_train_model))))
print('Test Accuracy: {:.3f}'.format(
accuracy_score(y_test_full.values.ravel(),
pipe_gb_model.predict(X_test_model))))
print('Train F1 Score: {:.3f}'.format(
f1_score(y_train_full.values.ravel(),
pipe_gb_model.predict(X_train_model),
average='micro')))
print('Test F1 Score: {:.3f}'.format(
f1_score(y_test_full.values.ravel(),
pipe_gb_model.predict(X_test_model),
average='micro')))
# Recursive Feature Elimination
select = RFE(RandomForestClassifier(n_estimators=100, random_state=42),
n_features_to_select=15)
select.fit(X_train_full, y_train_full.values.ravel())
X_train_rfe = select.transform(X_train_full)
X_test_rfe = select.transform(X_test_full)
# GradientBoost Classifier
print(
'--------------------------Without Recursive Feature Elimination-------------------------------------'
)
pipe_gb = Pipeline([('scl', StandardScaler()),
('est', GradientBoostingClassifier(random_state=39))])
pipe_gb.fit(X_train_full, y_train_full.values.ravel())
print('Train Accuracy: {:.3f}'.format(
accuracy_score(y_train_full.values.ravel(),
pipe_gb.predict(X_train_full))))
print('Test Accuracy: {:.3f}'.format(
accuracy_score(y_test_full.values.ravel(),
pipe_gb.predict(X_test_full))))
print('Train F1 Score: {:.3f}'.format(
f1_score(y_train_full.values.ravel(),
pipe_gb.predict(X_train_full),
average='micro')))
print('Test F1 Score: {:.3f}'.format(
f1_score(y_test_full.values.ravel(),
pipe_gb.predict(X_test_full),
average='micro')))
# GradientBoost Classifier with Recursive Feature Elimination
print(
'----------------------------With Recursive Feature Elimination--------------------------------------'
)
pipe_gb_rfe = Pipeline([('scl', StandardScaler()),
('est',
GradientBoostingClassifier(random_state=39))])
pipe_gb_rfe.fit(X_train_rfe, y_train_full.values.ravel())
print('Train Accuracy: {:.3f}'.format(
accuracy_score(y_train_full.values.ravel(),
pipe_gb_rfe.predict(X_train_rfe))))
print('Test Accuracy: {:.3f}'.format(
accuracy_score(y_test_full.values.ravel(),
pipe_gb_rfe.predict(X_test_rfe))))
print('Train F1 Score: {:.3f}'.format(
f1_score(y_train_full.values.ravel(),
pipe_gb_rfe.predict(X_train_rfe),
average='micro')))
print('Test F1 Score: {:.3f}'.format(
f1_score(y_test_full.values.ravel(),
pipe_gb_rfe.predict(X_test_rfe),
average='micro')))
cv = cross_val_score(pipe_gb,
X_,
y_.values.ravel(),
cv=StratifiedKFold(n_splits=10,
shuffle=True,
random_state=39))
print('Cross validation with StratifiedKFold scores: {}'.format(cv))
print('Cross Validation with StatifiedKFold mean: {}'.format(cv.mean()))
# GridSearch
n_features = len(df.columns)
param_grid = {
'learning_rate': [0.01, 0.1, 1, 10],
'n_estimators': [1, 10, 100, 200, 300],
'max_depth': [1, 2, 3, 4, 5]
}
stratifiedcv = StratifiedKFold(n_splits=10, shuffle=True, random_state=39)
X_train, X_test, y_train, y_test = train_test_split(X_,
y_,
test_size=0.33,
random_state=42)
grid_search = GridSearchCV(GradientBoostingClassifier(),
param_grid,
cv=stratifiedcv)
grid_search.fit(X_train, y_train.values.ravel())
print('GridSearch Train Accuracy: {:.3f}'.format(
accuracy_score(y_train.values.ravel(), grid_search.predict(X_train))))
print('GridSearch Test Accuracy: {:.3f}'.format(
accuracy_score(y_test.values.ravel(), grid_search.predict(X_test))))
print('GridSearch Train F1 Score: {:.3f}'.format(
f1_score(y_train.values.ravel(),
grid_search.predict(X_train),
average='micro')))
print('GridSearch Test F1 Score: {:.3f}'.format(
f1_score(y_test.values.ravel(),
grid_search.predict(X_test),
average='micro')))
# GridSearch results
print("Best params:\n{}".format(grid_search.best_params_))
print("Best cross-validation score: {:.2f}".format(
grid_search.best_score_))
results = pd.DataFrame(grid_search.cv_results_)
corr_params = results.drop(results.columns[[
0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 19, 20
]],
axis=1)
corr_params.head()
# GridSearch in nested
cv_gb = cross_val_score(grid_search,
X_,
y_.values.ravel(),
cv=StratifiedKFold(n_splits=3,
shuffle=True,
random_state=39))
print('Grid Search with nested cross validation scores: {}'.format(cv_gb))
print('Grid Search with nested cross validation mean: {}'.format(
cv_gb.mean()))
def add_ta_features(df, ta_settings):
"""Add technial analysis features from typical financial dataset that
typically include columns such as "open", "high", "low", "price" and
"volume".
http://mrjbq7.github.io/ta-lib/
Args:
df(pandas.DataFrame): original DataFrame.
ta_settings(dict): configuration.
Returns:
pandas.DataFrame: DataFrame with new features included.
"""
open = df['open']
high = df['high']
low = df['low']
close = df['price']
volume = df['volume']
if ta_settings['overlap']:
df['ta_overlap_bbands_upper'], df['ta_overlap_bbands_middle'], df[
'ta_overlap_bbands_lower'] = ta.BBANDS(close,
timeperiod=5,
nbdevup=2,
nbdevdn=2,
matype=0)
df['ta_overlap_dema'] = ta.DEMA(
close, timeperiod=15) # NOTE: Changed to avoid a lot of Nan values
df['ta_overlap_ema'] = ta.EMA(close, timeperiod=30)
df['ta_overlap_kama'] = ta.KAMA(close, timeperiod=30)
df['ta_overlap_ma'] = ta.MA(close, timeperiod=30, matype=0)
df['ta_overlap_mama_mama'], df['ta_overlap_mama_fama'] = ta.MAMA(close)
period = np.random.randint(10, 20, size=len(close)).astype(float)
df['ta_overlap_mavp'] = ta.MAVP(close,
period,
minperiod=2,
maxperiod=30,
matype=0)
df['ta_overlap_midpoint'] = ta.MIDPOINT(close, timeperiod=14)
df['ta_overlap_midprice'] = ta.MIDPRICE(high, low, timeperiod=14)
df['ta_overlap_sar'] = ta.SAR(high, low, acceleration=0, maximum=0)
df['ta_overlap_sarext'] = ta.SAREXT(high,
low,
startvalue=0,
offsetonreverse=0,
accelerationinitlong=0,
accelerationlong=0,
accelerationmaxlong=0,
accelerationinitshort=0,
accelerationshort=0,
accelerationmaxshort=0)
df['ta_overlap_sma'] = ta.SMA(close, timeperiod=30)
df['ta_overlap_t3'] = ta.T3(close, timeperiod=5, vfactor=0)
df['ta_overlap_tema'] = ta.TEMA(
close, timeperiod=12) # NOTE: Changed to avoid a lot of Nan values
df['ta_overlap_trima'] = ta.TRIMA(close, timeperiod=30)
df['ta_overlap_wma'] = ta.WMA(close, timeperiod=30)
# NOTE: Commented to avoid a lot of Nan values
# df['ta_overlap_ht_trendline'] = ta.HT_TRENDLINE(close)
if ta_settings['momentum']:
df['ta_momentum_adx'] = ta.ADX(high, low, close, timeperiod=14)
df['ta_momentum_adxr'] = ta.ADXR(high, low, close, timeperiod=14)
df['ta_momentum_apo'] = ta.APO(close,
fastperiod=12,
slowperiod=26,
matype=0)
df['ta_momentum_aroondown'], df['ta_momentum_aroonup'] = ta.AROON(
high, low, timeperiod=14)
df['ta_momentum_aroonosc'] = ta.AROONOSC(high, low, timeperiod=14)
df['ta_momentum_bop'] = ta.BOP(open, high, low, close)
df['ta_momentum_cci'] = ta.CCI(high, low, close, timeperiod=14)
df['ta_momentum_cmo'] = ta.CMO(close, timeperiod=14)
df['ta_momentum_dx'] = ta.DX(high, low, close, timeperiod=14)
df['ta_momentum_macd_macd'], df['ta_momentum_macd_signal'], df[
'ta_momentum_macd_hist'] = ta.MACD(close,
fastperiod=12,
slowperiod=26,
signalperiod=9)
df['ta_momentum_macdext_macd'], df['ta_momentum_macdext_signal'], df[
'ta_momentum_macdext_hist'] = ta.MACDEXT(close,
fastperiod=12,
fastmatype=0,
slowperiod=26,
slowmatype=0,
signalperiod=9,
signalmatype=0)
df['ta_momentum_macdfix_macd'], df['ta_momentum_macdfix_signal'], df[
'ta_momentum_macdfix_hist'] = ta.MACDFIX(close, signalperiod=9)
df['ta_momentum_mfi'] = ta.MFI(high, low, close, volume, timeperiod=14)
df['ta_momentum_minus_di'] = ta.MINUS_DI(high,
low,
close,
timeperiod=14)
df['ta_momentum_minus_dm'] = ta.MINUS_DM(high, low, timeperiod=14)
df['ta_momentum_mom'] = ta.MOM(close, timeperiod=10)
df['ta_momentum_plus_di'] = ta.PLUS_DI(high, low, close, timeperiod=14)
df['ta_momentum_plus_dm'] = ta.PLUS_DM(high, low, timeperiod=14)
df['ta_momentum_ppo'] = ta.PPO(close,
fastperiod=12,
slowperiod=26,
matype=0)
df['ta_momentum_roc'] = ta.ROC(close, timeperiod=10)
df['ta_momentum_rocp'] = ta.ROCP(close, timeperiod=10)
df['ta_momentum_rocr'] = ta.ROCR(close, timeperiod=10)
df['ta_momentum_rocr100'] = ta.ROCR100(close, timeperiod=10)
df['ta_momentum_rsi'] = ta.RSI(close, timeperiod=14)
df['ta_momentum_slowk'], df['ta_momentum_slowd'] = ta.STOCH(
high,
low,
close,
fastk_period=5,
slowk_period=3,
slowk_matype=0,
slowd_period=3,
slowd_matype=0)
df['ta_momentum_fastk'], df['ta_momentum_fastd'] = ta.STOCHF(
high, low, close, fastk_period=5, fastd_period=3, fastd_matype=0)
df['ta_momentum_fastk'], df['ta_momentum_fastd'] = ta.STOCHRSI(
close,
timeperiod=14,
fastk_period=5,
fastd_period=3,
fastd_matype=0)
df['ta_momentum_trix'] = ta.TRIX(
close, timeperiod=12) # NOTE: Changed to avoid a lot of Nan values
df['ta_momentum_ultosc'] = ta.ULTOSC(high,
low,
close,
timeperiod1=7,
timeperiod2=14,
timeperiod3=28)
df['ta_momentum_willr'] = ta.WILLR(high, low, close, timeperiod=14)
if ta_settings['volume']:
df['ta_volume_ad'] = ta.AD(high, low, close, volume)
df['ta_volume_adosc'] = ta.ADOSC(high,
low,
close,
volume,
fastperiod=3,
slowperiod=10)
df['ta_volume_obv'] = ta.OBV(close, volume)
if ta_settings['volatility']:
df['ta_volatility_atr'] = ta.ATR(high, low, close, timeperiod=14)
df['ta_volatility_natr'] = ta.NATR(high, low, close, timeperiod=14)
df['ta_volatility_trange'] = ta.TRANGE(high, low, close)
if ta_settings['price']:
df['ta_price_avgprice'] = ta.AVGPRICE(open, high, low, close)
df['ta_price_medprice'] = ta.MEDPRICE(high, low)
df['ta_price_typprice'] = ta.TYPPRICE(high, low, close)
df['ta_price_wclprice'] = ta.WCLPRICE(high, low, close)
if ta_settings['cycle']:
df['ta_cycle_ht_dcperiod'] = ta.HT_DCPERIOD(close)
df['ta_cycle_ht_phasor_inphase'], df[
'ta_cycle_ht_phasor_quadrature'] = ta.HT_PHASOR(close)
df['ta_cycle_ht_trendmode'] = ta.HT_TRENDMODE(close)
# NOTE: Commented to avoid a lot of Nan values
# df['ta_cycle_ht_dcphase'] = ta.HT_DCPHASE(close)
# df['ta_cycle_ht_sine_sine'], df['ta_cycle_ht_sine_leadsine'] = ta.HT_SINE(close)
if ta_settings['pattern']:
df['ta_pattern_cdl2crows'] = ta.CDL2CROWS(open, high, low, close)
df['ta_pattern_cdl3blackrows'] = ta.CDL3BLACKCROWS(
open, high, low, close)
df['ta_pattern_cdl3inside'] = ta.CDL3INSIDE(open, high, low, close)
df['ta_pattern_cdl3linestrike'] = ta.CDL3LINESTRIKE(
open, high, low, close)
df['ta_pattern_cdl3outside'] = ta.CDL3OUTSIDE(open, high, low, close)
df['ta_pattern_cdl3starsinsouth'] = ta.CDL3STARSINSOUTH(
open, high, low, close)
df['ta_pattern_cdl3whitesoldiers'] = ta.CDL3WHITESOLDIERS(
open, high, low, close)
df['ta_pattern_cdlabandonedbaby'] = ta.CDLABANDONEDBABY(open,
high,
low,
close,
penetration=0)
df['ta_pattern_cdladvanceblock'] = ta.CDLADVANCEBLOCK(
open, high, low, close)
df['ta_pattern_cdlbelthold'] = ta.CDLBELTHOLD(open, high, low, close)
df['ta_pattern_cdlbreakaway'] = ta.CDLBREAKAWAY(open, high, low, close)
df['ta_pattern_cdlclosingmarubozu'] = ta.CDLCLOSINGMARUBOZU(
open, high, low, close)
df['ta_pattern_cdlconcealbabyswall'] = ta.CDLCONCEALBABYSWALL(
open, high, low, close)
df['ta_pattern_cdlcounterattack'] = ta.CDLCOUNTERATTACK(
open, high, low, close)
df['ta_pattern_cdldarkcloudcover'] = ta.CDLDARKCLOUDCOVER(
open, high, low, close, penetration=0)
df['ta_pattern_cdldoji'] = ta.CDLDOJI(open, high, low, close)
df['ta_pattern_cdldojistar'] = ta.CDLDOJISTAR(open, high, low, close)
df['ta_pattern_cdldragonflydoji'] = ta.CDLDRAGONFLYDOJI(
open, high, low, close)
df['ta_pattern_cdlengulfing'] = ta.CDLENGULFING(open, high, low, close)
df['ta_pattern_cdleveningdojistar'] = ta.CDLEVENINGDOJISTAR(
open, high, low, close, penetration=0)
df['ta_pattern_cdleveningstar'] = ta.CDLEVENINGSTAR(open,
high,
low,
close,
penetration=0)
df['ta_pattern_cdlgapsidesidewhite'] = ta.CDLGAPSIDESIDEWHITE(
open, high, low, close)
df['ta_pattern_cdlgravestonedoji'] = ta.CDLGRAVESTONEDOJI(
open, high, low, close)
df['ta_pattern_cdlhammer'] = ta.CDLHAMMER(open, high, low, close)
df['ta_pattern_cdlhangingman'] = ta.CDLHANGINGMAN(
open, high, low, close)
df['ta_pattern_cdlharami'] = ta.CDLHARAMI(open, high, low, close)
df['ta_pattern_cdlharamicross'] = ta.CDLHARAMICROSS(
open, high, low, close)
df['ta_pattern_cdlhighwave'] = ta.CDLHIGHWAVE(open, high, low, close)
df['ta_pattern_cdlhikkake'] = ta.CDLHIKKAKE(open, high, low, close)
df['ta_pattern_cdlhikkakemod'] = ta.CDLHIKKAKEMOD(
open, high, low, close)
df['ta_pattern_cdlhomingpigeon'] = ta.CDLHOMINGPIGEON(
open, high, low, close)
df['ta_pattern_cdlidentical3crows'] = ta.CDLIDENTICAL3CROWS(
open, high, low, close)
df['ta_pattern_cdlinneck'] = ta.CDLINNECK(open, high, low, close)
df['ta_pattern_cdlinvertedhammer'] = ta.CDLINVERTEDHAMMER(
open, high, low, close)
df['ta_pattern_cdlkicking'] = ta.CDLKICKING(open, high, low, close)
df['ta_pattern_cdlkickingbylength'] = ta.CDLKICKINGBYLENGTH(
open, high, low, close)
df['ta_pattern_cdlladderbottom'] = ta.CDLLADDERBOTTOM(
open, high, low, close)
df['ta_pattern_cdllongleggeddoji'] = ta.CDLLONGLEGGEDDOJI(
open, high, low, close)
df['ta_pattern_cdllongline'] = ta.CDLLONGLINE(open, high, low, close)
df['ta_pattern_cdlmarubozu'] = ta.CDLMARUBOZU(open, high, low, close)
df['ta_pattern_cdlmatchinglow'] = ta.CDLMATCHINGLOW(
open, high, low, close)
df['ta_pattern_cdlmathold'] = ta.CDLMATHOLD(open,
high,
low,
close,
penetration=0)
df['ta_pattern_cdlmorningdojistar'] = ta.CDLMORNINGDOJISTAR(
open, high, low, close, penetration=0)
df['ta_pattern_cdlmorningstar'] = ta.CDLMORNINGSTAR(open,
high,
low,
close,
penetration=0)
df['ta_pattern_cdllonneck'] = ta.CDLONNECK(open, high, low, close)
df['ta_pattern_cdlpiercing'] = ta.CDLPIERCING(open, high, low, close)
df['ta_pattern_cdlrickshawman'] = ta.CDLRICKSHAWMAN(
open, high, low, close)
df['ta_pattern_cdlrisefall3methods'] = ta.CDLRISEFALL3METHODS(
open, high, low, close)
df['ta_pattern_cdlseparatinglines'] = ta.CDLSEPARATINGLINES(
open, high, low, close)
df['ta_pattern_cdlshootingstar'] = ta.CDLSHOOTINGSTAR(
open, high, low, close)
df['ta_pattern_cdlshortline'] = ta.CDLSHORTLINE(open, high, low, close)
df['ta_pattern_cdlspinningtop'] = ta.CDLSPINNINGTOP(
open, high, low, close)
df['ta_pattern_cdlstalledpattern'] = ta.CDLSTALLEDPATTERN(
open, high, low, close)
df['ta_pattern_cdlsticksandwich'] = ta.CDLSTICKSANDWICH(
open, high, low, close)
df['ta_pattern_cdltakuri'] = ta.CDLTAKURI(open, high, low, close)
df['ta_pattern_cdltasukigap'] = ta.CDLTASUKIGAP(open, high, low, close)
df['ta_pattern_cdlthrusting'] = ta.CDLTHRUSTING(open, high, low, close)
df['ta_pattern_cdltristar'] = ta.CDLTRISTAR(open, high, low, close)
df['ta_pattern_cdlunique3river'] = ta.CDLUNIQUE3RIVER(
open, high, low, close)
df['ta_pattern_cdlupsidegap2crows'] = ta.CDLUPSIDEGAP2CROWS(
open, high, low, close)
df['ta_pattern_cdlxsidegap3methods'] = ta.CDLXSIDEGAP3METHODS(
open, high, low, close)
if ta_settings['statistic']:
df['ta_statistic_beta'] = ta.BETA(high, low, timeperiod=5)
df['ta_statistic_correl'] = ta.CORREL(high, low, timeperiod=30)
df['ta_statistic_linearreg'] = ta.LINEARREG(close, timeperiod=14)
df['ta_statistic_linearreg_angle'] = ta.LINEARREG_ANGLE(close,
timeperiod=14)
df['ta_statistic_linearreg_intercept'] = ta.LINEARREG_INTERCEPT(
close, timeperiod=14)
df['ta_statistic_linearreg_slope'] = ta.LINEARREG_SLOPE(close,
timeperiod=14)
df['ta_statistic_stddev'] = ta.STDDEV(close, timeperiod=5, nbdev=1)
df['ta_statistic_tsf'] = ta.TSF(close, timeperiod=14)
df['ta_statistic_var'] = ta.VAR(close, timeperiod=5, nbdev=1)
if ta_settings['math_transforms']:
df['ta_math_transforms_atan'] = ta.ATAN(close)
df['ta_math_transforms_ceil'] = ta.CEIL(close)
df['ta_math_transforms_cos'] = ta.COS(close)
df['ta_math_transforms_floor'] = ta.FLOOR(close)
df['ta_math_transforms_ln'] = ta.LN(close)
df['ta_math_transforms_log10'] = ta.LOG10(close)
df['ta_math_transforms_sin'] = ta.SIN(close)
df['ta_math_transforms_sqrt'] = ta.SQRT(close)
df['ta_math_transforms_tan'] = ta.TAN(close)
if ta_settings['math_operators']:
df['ta_math_operators_add'] = ta.ADD(high, low)
df['ta_math_operators_div'] = ta.DIV(high, low)
df['ta_math_operators_min'], df['ta_math_operators_max'] = ta.MINMAX(
close, timeperiod=30)
df['ta_math_operators_minidx'], df[
'ta_math_operators_maxidx'] = ta.MINMAXINDEX(close, timeperiod=30)
df['ta_math_operators_mult'] = ta.MULT(high, low)
df['ta_math_operators_sub'] = ta.SUB(high, low)
df['ta_math_operators_sum'] = ta.SUM(close, timeperiod=30)
return df
def TALIB_AVGPRICE(close, timeperiod=14):
'''00333,2,1'''
return talib.AVGPRICE(close, timeperiod)
def calculate(self, para):
self.t = self.inputdata[:, 0]
self.op = self.inputdata[:, 1]
self.high = self.inputdata[:, 2]
self.low = self.inputdata[:, 3]
self.close = self.inputdata[:, 4]
#adjusted close
self.close1 = self.inputdata[:, 5]
self.volume = self.inputdata[:, 6]
#Overlap study
#Overlap Studies
#Overlap Studies
if para is 'BBANDS': #Bollinger Bands
upperband, middleband, lowerband = ta.BBANDS(self.close,
timeperiod=self.tp,
nbdevup=2,
nbdevdn=2,
matype=0)
self.output = [upperband, middleband, lowerband]
elif para is 'DEMA': #Double Exponential Moving Average
self.output = ta.DEMA(self.close, timeperiod=self.tp)
elif para is 'EMA': #Exponential Moving Average
self.output = ta.EMA(self.close, timeperiod=self.tp)
elif para is 'HT_TRENDLINE': #Hilbert Transform - Instantaneous Trendline
self.output = ta.HT_TRENDLINE(self.close)
elif para is 'KAMA': #Kaufman Adaptive Moving Average
self.output = ta.KAMA(self.close, timeperiod=self.tp)
elif para is 'MA': #Moving average
self.output = ta.MA(self.close, timeperiod=self.tp, matype=0)
elif para is 'MAMA': #MESA Adaptive Moving Average
mama, fama = ta.MAMA(self.close, fastlimit=0, slowlimit=0)
elif para is 'MAVP': #Moving average with variable period
self.output = ta.MAVP(self.close,
periods=10,
minperiod=self.tp,
maxperiod=self.tp1,
matype=0)
elif para is 'MIDPOINT': #MidPoint over period
self.output = ta.MIDPOINT(self.close, timeperiod=self.tp)
elif para is 'MIDPRICE': #Midpoint Price over period
self.output = ta.MIDPRICE(self.high, self.low, timeperiod=self.tp)
elif para is 'SAR': #Parabolic SAR
self.output = ta.SAR(self.high,
self.low,
acceleration=0,
maximum=0)
elif para is 'SAREXT': #Parabolic SAR - Extended
self.output = ta.SAREXT(self.high,
self.low,
startvalue=0,
offsetonreverse=0,
accelerationinitlong=0,
accelerationlong=0,
accelerationmaxlong=0,
accelerationinitshort=0,
accelerationshort=0,
accelerationmaxshort=0)
elif para is 'SMA': #Simple Moving Average
self.output = ta.SMA(self.close, timeperiod=self.tp)
elif para is 'T3': #Triple Exponential Moving Average (T3)
self.output = ta.T3(self.close, timeperiod=self.tp, vfactor=0)
elif para is 'TEMA': #Triple Exponential Moving Average
self.output = ta.TEMA(self.close, timeperiod=self.tp)
elif para is 'TRIMA': #Triangular Moving Average
self.output = ta.TRIMA(self.close, timeperiod=self.tp)
elif para is 'WMA': #Weighted Moving Average
self.output = ta.WMA(self.close, timeperiod=self.tp)
#Momentum Indicators
elif para is 'ADX': #Average Directional Movement Index
self.output = ta.ADX(self.high,
self.low,
self.close,
timeperiod=self.tp)
elif para is 'ADXR': #Average Directional Movement Index Rating
self.output = ta.ADXR(self.high,
self.low,
self.close,
timeperiod=self.tp)
elif para is 'APO': #Absolute Price Oscillator
self.output = ta.APO(self.close,
fastperiod=12,
slowperiod=26,
matype=0)
elif para is 'AROON': #Aroon
aroondown, aroonup = ta.AROON(self.high,
self.low,
timeperiod=self.tp)
self.output = [aroondown, aroonup]
elif para is 'AROONOSC': #Aroon Oscillator
self.output = ta.AROONOSC(self.high, self.low, timeperiod=self.tp)
elif para is 'BOP': #Balance Of Power
self.output = ta.BOP(self.op, self.high, self.low, self.close)
elif para is 'CCI': #Commodity Channel Index
self.output = ta.CCI(self.high,
self.low,
self.close,
timeperiod=self.tp)
elif para is 'CMO': #Chande Momentum Oscillator
self.output = ta.CMO(self.close, timeperiod=self.tp)
elif para is 'DX': #Directional Movement Index
self.output = ta.DX(self.high,
self.low,
self.close,
timeperiod=self.tp)
elif para is 'MACD': #Moving Average Convergence/Divergence
macd, macdsignal, macdhist = ta.MACD(self.close,
fastperiod=12,
slowperiod=26,
signalperiod=9)
self.output = [macd, macdsignal, macdhist]
elif para is 'MACDEXT': #MACD with controllable MA type
macd, macdsignal, macdhist = ta.MACDEXT(self.close,
fastperiod=12,
fastmatype=0,
slowperiod=26,
slowmatype=0,
signalperiod=9,
signalmatype=0)
self.output = [macd, macdsignal, macdhist]
elif para is 'MACDFIX': #Moving Average Convergence/Divergence Fix 12/26
macd, macdsignal, macdhist = ta.MACDFIX(self.close, signalperiod=9)
self.output = [macd, macdsignal, macdhist]
elif para is 'MFI': #Money Flow Index
self.output = ta.MFI(self.high,
self.low,
self.close,
self.volume,
timeperiod=self.tp)
elif para is 'MINUS_DI': #Minus Directional Indicator
self.output = ta.MINUS_DI(self.high,
self.low,
self.close,
timeperiod=self.tp)
elif para is 'MINUS_DM': #Minus Directional Movement
self.output = ta.MINUS_DM(self.high, self.low, timeperiod=self.tp)
elif para is 'MOM': #Momentum
self.output = ta.MOM(self.close, timeperiod=10)
elif para is 'PLUS_DI': #Plus Directional Indicator
self.output = ta.PLUS_DI(self.high,
self.low,
self.close,
timeperiod=self.tp)
elif para is 'PLUS_DM': #Plus Directional Movement
self.output = ta.PLUS_DM(self.high, self.low, timeperiod=self.tp)
elif para is 'PPO': #Percentage Price Oscillator
self.output = ta.PPO(self.close,
fastperiod=12,
slowperiod=26,
matype=0)
elif para is 'ROC': #Rate of change : ((price/prevPrice)-1)*100
self.output = ta.ROC(self.close, timeperiod=10)
elif para is 'ROCP': #Rate of change Percentage: (price-prevPrice)/prevPrice
self.output = ta.ROCP(self.close, timeperiod=10)
elif para is 'ROCR': #Rate of change ratio: (price/prevPrice)
self.output = ta.ROCR(self.close, timeperiod=10)
elif para is 'ROCR100': #Rate of change ratio 100 scale: (price/prevPrice)*100
self.output = ta.ROCR100(self.close, timeperiod=10)
elif para is 'RSI': #Relative Strength Index
self.output = ta.RSI(self.close, timeperiod=self.tp)
elif para is 'STOCH': #Stochastic
slowk, slowd = ta.STOCH(self.high,
self.low,
self.close,
fastk_period=5,
slowk_period=3,
slowk_matype=0,
slowd_period=3,
slowd_matype=0)
self.output = [slowk, slowd]
elif para is 'STOCHF': #Stochastic Fast
fastk, fastd = ta.STOCHF(self.high,
self.low,
self.close,
fastk_period=5,
fastd_period=3,
fastd_matype=0)
self.output = [fastk, fastd]
elif para is 'STOCHRSI': #Stochastic Relative Strength Index
fastk, fastd = ta.STOCHRSI(self.close,
timeperiod=self.tp,
fastk_period=5,
fastd_period=3,
fastd_matype=0)
self.output = [fastk, fastd]
elif para is 'TRIX': #1-day Rate-Of-Change (ROC) of a Triple Smooth EMA
self.output = ta.TRIX(self.close, timeperiod=self.tp)
elif para is 'ULTOSC': #Ultimate Oscillator
self.output = ta.ULTOSC(self.high,
self.low,
self.close,
timeperiod1=self.tp,
timeperiod2=self.tp1,
timeperiod3=self.tp2)
elif para is 'WILLR': #Williams' %R
self.output = ta.WILLR(self.high,
self.low,
self.close,
timeperiod=self.tp)
# Volume Indicators : #
elif para is 'AD': #Chaikin A/D Line
self.output = ta.AD(self.high, self.low, self.close, self.volume)
elif para is 'ADOSC': #Chaikin A/D Oscillator
self.output = ta.ADOSC(self.high,
self.low,
self.close,
self.volume,
fastperiod=3,
slowperiod=10)
elif para is 'OBV': #On Balance Volume
self.output = ta.OBV(self.close, self.volume)
# Volatility Indicators: #
elif para is 'ATR': #Average True Range
self.output = ta.ATR(self.high,
self.low,
self.close,
timeperiod=self.tp)
elif para is 'NATR': #Normalized Average True Range
self.output = ta.NATR(self.high,
self.low,
self.close,
timeperiod=self.tp)
elif para is 'TRANGE': #True Range
self.output = ta.TRANGE(self.high, self.low, self.close)
#Price Transform : #
elif para is 'AVGPRICE': #Average Price
self.output = ta.AVGPRICE(self.op, self.high, self.low, self.close)
elif para is 'MEDPRICE': #Median Price
self.output = ta.MEDPRICE(self.high, self.low)
elif para is 'TYPPRICE': #Typical Price
self.output = ta.TYPPRICE(self.high, self.low, self.close)
elif para is 'WCLPRICE': #Weighted Close Price
self.output = ta.WCLPRICE(self.high, self.low, self.close)
#Cycle Indicators : #
elif para is 'HT_DCPERIOD': #Hilbert Transform - Dominant Cycle Period
self.output = ta.HT_DCPERIOD(self.close)
elif para is 'HT_DCPHASE': #Hilbert Transform - Dominant Cycle Phase
self.output = ta.HT_DCPHASE(self.close)
elif para is 'HT_PHASOR': #Hilbert Transform - Phasor Components
inphase, quadrature = ta.HT_PHASOR(self.close)
self.output = [inphase, quadrature]
elif para is 'HT_SINE': #Hilbert Transform - SineWave #2
sine, leadsine = ta.HT_SINE(self.close)
self.output = [sine, leadsine]
elif para is 'HT_TRENDMODE': #Hilbert Transform - Trend vs Cycle Mode
self.integer = ta.HT_TRENDMODE(self.close)
#Pattern Recognition : #
elif para is 'CDL2CROWS': #Two Crows
self.integer = ta.CDL2CROWS(self.op, self.high, self.low,
self.close)
elif para is 'CDL3BLACKCROWS': #Three Black Crows
self.integer = ta.CDL3BLACKCROWS(self.op, self.high, self.low,
self.close)
elif para is 'CDL3INSIDE': #Three Inside Up/Down
self.integer = ta.CDL3INSIDE(self.op, self.high, self.low,
self.close)
elif para is 'CDL3LINESTRIKE': #Three-Line Strike
self.integer = ta.CDL3LINESTRIKE(self.op, self.high, self.low,
self.close)
elif para is 'CDL3OUTSIDE': #Three Outside Up/Down
self.integer = ta.CDL3OUTSIDE(self.op, self.high, self.low,
self.close)
elif para is 'CDL3STARSINSOUTH': #Three Stars In The South
self.integer = ta.CDL3STARSINSOUTH(self.op, self.high, self.low,
self.close)
elif para is 'CDL3WHITESOLDIERS': #Three Advancing White Soldiers
self.integer = ta.CDL3WHITESOLDIERS(self.op, self.high, self.low,
self.close)
elif para is 'CDLABANDONEDBABY': #Abandoned Baby
self.integer = ta.CDLABANDONEDBABY(self.op,
self.high,
self.low,
self.close,
penetration=0)
elif para is 'CDLBELTHOLD': #Belt-hold
self.integer = ta.CDLBELTHOLD(self.op, self.high, self.low,
self.close)
elif para is 'CDLBREAKAWAY': #Breakaway
self.integer = ta.CDLBREAKAWAY(self.op, self.high, self.low,
self.close)
elif para is 'CDLCLOSINGMARUBOZU': #Closing Marubozu
self.integer = ta.CDLCLOSINGMARUBOZU(self.op, self.high, self.low,
self.close)
elif para is 'CDLCONCEALBABYSWALL': #Concealing Baby Swallow
self.integer = ta.CDLCONCEALBABYSWALL(self.op, self.high, self.low,
self.close)
elif para is 'CDLCOUNTERATTACK': #Counterattack
self.integer = ta.CDLCOUNTERATTACK(self.op, self.high, self.low,
self.close)
elif para is 'CDLDARKCLOUDCOVER': #Dark Cloud Cover
self.integer = ta.CDLDARKCLOUDCOVER(self.op,
self.high,
self.low,
self.close,
penetration=0)
elif para is 'CDLDOJI': #Doji
self.integer = ta.CDLDOJI(self.op, self.high, self.low, self.close)
elif para is 'CDLDOJISTAR': #Doji Star
self.integer = ta.CDLDOJISTAR(self.op, self.high, self.low,
self.close)
elif para is 'CDLDRAGONFLYDOJI': #Dragonfly Doji
self.integer = ta.CDLDRAGONFLYDOJI(self.op, self.high, self.low,
self.close)
elif para is 'CDLENGULFING': #Engulfing Pattern
self.integer = ta.CDLENGULFING(self.op, self.high, self.low,
self.close)
elif para is 'CDLEVENINGDOJISTAR': #Evening Doji Star
self.integer = ta.CDLEVENINGDOJISTAR(self.op,
self.high,
self.low,
self.close,
penetration=0)
elif para is 'CDLEVENINGSTAR': #Evening Star
self.integer = ta.CDLEVENINGSTAR(self.op,
self.high,
self.low,
self.close,
penetration=0)
elif para is 'CDLGAPSIDESIDEWHITE': #Up/Down-gap side-by-side white lines
self.integer = ta.CDLGAPSIDESIDEWHITE(self.op, self.high, self.low,
self.close)
elif para is 'CDLGRAVESTONEDOJI': #Gravestone Doji
self.integer = ta.CDLGRAVESTONEDOJI(self.op, self.high, self.low,
self.close)
elif para is 'CDLHAMMER': #Hammer
self.integer = ta.CDLHAMMER(self.op, self.high, self.low,
self.close)
elif para is 'CDLHANGINGMAN': #Hanging Man
self.integer = ta.CDLHANGINGMAN(self.op, self.high, self.low,
self.close)
elif para is 'CDLHARAMI': #Harami Pattern
self.integer = ta.CDLHARAMI(self.op, self.high, self.low,
self.close)
elif para is 'CDLHARAMICROSS': #Harami Cross Pattern
self.integer = ta.CDLHARAMICROSS(self.op, self.high, self.low,
self.close)
elif para is 'CDLHIGHWAVE': #High-Wave Candle
self.integer = ta.CDLHIGHWAVE(self.op, self.high, self.low,
self.close)
elif para is 'CDLHIKKAKE': #Hikkake Pattern
self.integer = ta.CDLHIKKAKE(self.op, self.high, self.low,
self.close)
elif para is 'CDLHIKKAKEMOD': #Modified Hikkake Pattern
self.integer = ta.CDLHIKKAKEMOD(self.op, self.high, self.low,
self.close)
elif para is 'CDLHOMINGPIGEON': #Homing Pigeon
self.integer = ta.CDLHOMINGPIGEON(self.op, self.high, self.low,
self.close)
elif para is 'CDLIDENTICAL3CROWS': #Identical Three Crows
self.integer = ta.CDLIDENTICAL3CROWS(self.op, self.high, self.low,
self.close)
elif para is 'CDLINNECK': #In-Neck Pattern
self.integer = ta.CDLINNECK(self.op, self.high, self.low,
self.close)
elif para is 'CDLINVERTEDHAMMER': #Inverted Hammer
self.integer = ta.CDLINVERTEDHAMMER(self.op, self.high, self.low,
self.close)
elif para is 'CDLKICKING': #Kicking
self.integer = ta.CDLKICKING(self.op, self.high, self.low,
self.close)
elif para is 'CDLKICKINGBYLENGTH': #Kicking - bull/bear determined by the longer marubozu
self.integer = ta.CDLKICKINGBYLENGTH(self.op, self.high, self.low,
self.close)
elif para is 'CDLLADDERBOTTOM': #Ladder Bottom
self.integer = ta.CDLLADDERBOTTOM(self.op, self.high, self.low,
self.close)
elif para is 'CDLLONGLEGGEDDOJI': #Long Legged Doji
self.integer = ta.CDLLONGLEGGEDDOJI(self.op, self.high, self.low,
self.close)
elif para is 'CDLLONGLINE': #Long Line Candle
self.integer = ta.CDLLONGLINE(self.op, self.high, self.low,
self.close)
elif para is 'CDLMARUBOZU': #Marubozu
self.integer = ta.CDLMARUBOZU(self.op, self.high, self.low,
self.close)
elif para is 'CDLMATCHINGLOW': #Matching Low
self.integer = ta.CDLMATCHINGLOW(self.op, self.high, self.low,
self.close)
elif para is 'CDLMATHOLD': #Mat Hold
self.integer = ta.CDLMATHOLD(self.op,
self.high,
self.low,
self.close,
penetration=0)
elif para is 'CDLMORNINGDOJISTAR': #Morning Doji Star
self.integer = ta.CDLMORNINGDOJISTAR(self.op,
self.high,
self.low,
self.close,
penetration=0)
elif para is 'CDLMORNINGSTAR': #Morning Star
self.integer = ta.CDLMORNINGSTAR(self.op,
self.high,
self.low,
self.close,
penetration=0)
elif para is 'CDLONNECK': #On-Neck Pattern
self.integer = ta.CDLONNECK(self.op, self.high, self.low,
self.close)
elif para is 'CDLPIERCING': #Piercing Pattern
self.integer = ta.CDLPIERCING(self.op, self.high, self.low,
self.close)
elif para is 'CDLRICKSHAWMAN': #Rickshaw Man
self.integer = ta.CDLRICKSHAWMAN(self.op, self.high, self.low,
self.close)
elif para is 'CDLRISEFALL3METHODS': #Rising/Falling Three Methods
self.integer = ta.CDLRISEFALL3METHODS(self.op, self.high, self.low,
self.close)
elif para is 'CDLSEPARATINGLINES': #Separating Lines
self.integer = ta.CDLSEPARATINGLINES(self.op, self.high, self.low,
self.close)
elif para is 'CDLSHOOTINGSTAR': #Shooting Star
self.integer = ta.CDLSHOOTINGSTAR(self.op, self.high, self.low,
self.close)
elif para is 'CDLSHORTLINE': #Short Line Candle
self.integer = ta.CDLSHORTLINE(self.op, self.high, self.low,
self.close)
elif para is 'CDLSPINNINGTOP': #Spinning Top
self.integer = ta.CDLSPINNINGTOP(self.op, self.high, self.low,
self.close)
elif para is 'CDLSTALLEDPATTERN': #Stalled Pattern
self.integer = ta.CDLSTALLEDPATTERN(self.op, self.high, self.low,
self.close)
elif para is 'CDLSTICKSANDWICH': #Stick Sandwich
self.integer = ta.CDLSTICKSANDWICH(self.op, self.high, self.low,
self.close)
elif para is 'CDLTAKURI': #Takuri (Dragonfly Doji with very long lower shadow)
self.integer = ta.CDLTAKURI(self.op, self.high, self.low,
self.close)
elif para is 'CDLTASUKIGAP': #Tasuki Gap
self.integer = ta.CDLTASUKIGAP(self.op, self.high, self.low,
self.close)
elif para is 'CDLTHRUSTING': #Thrusting Pattern
self.integer = ta.CDLTHRUSTING(self.op, self.high, self.low,
self.close)
elif para is 'CDLTRISTAR': #Tristar Pattern
self.integer = ta.CDLTRISTAR(self.op, self.high, self.low,
self.close)
elif para is 'CDLUNIQUE3RIVER': #Unique 3 River
self.integer = ta.CDLUNIQUE3RIVER(self.op, self.high, self.low,
self.close)
elif para is 'CDLUPSIDEGAP2CROWS': #Upside Gap Two Crows
self.integer = ta.CDLUPSIDEGAP2CROWS(self.op, self.high, self.low,
self.close)
elif para is 'CDLXSIDEGAP3METHODS': #Upside/Downside Gap Three Methods
self.integer = ta.CDLXSIDEGAP3METHODS(self.op, self.high, self.low,
self.close)
#Statistic Functions : #
elif para is 'BETA': #Beta
self.output = ta.BETA(self.high, self.low, timeperiod=5)
elif para is 'CORREL': #Pearson's Correlation Coefficient (r)
self.output = ta.CORREL(self.high, self.low, timeperiod=self.tp)
elif para is 'LINEARREG': #Linear Regression
self.output = ta.LINEARREG(self.close, timeperiod=self.tp)
elif para is 'LINEARREG_ANGLE': #Linear Regression Angle
self.output = ta.LINEARREG_ANGLE(self.close, timeperiod=self.tp)
elif para is 'LINEARREG_INTERCEPT': #Linear Regression Intercept
self.output = ta.LINEARREG_INTERCEPT(self.close,
timeperiod=self.tp)
elif para is 'LINEARREG_SLOPE': #Linear Regression Slope
self.output = ta.LINEARREG_SLOPE(self.close, timeperiod=self.tp)
elif para is 'STDDEV': #Standard Deviation
self.output = ta.STDDEV(self.close, timeperiod=5, nbdev=1)
elif para is 'TSF': #Time Series Forecast
self.output = ta.TSF(self.close, timeperiod=self.tp)
elif para is 'VAR': #Variance
self.output = ta.VAR(self.close, timeperiod=5, nbdev=1)
else:
print('You issued command:' + para)
# Volume Indicator Functions
df['AD'] = ta.AD(np.array(df['High'].shift(1)), np.array(df['Low'].shift(1)),
np.array(df['Adj Close'].shift(1)),
np.array(df['Volume'].shift(1)))
df['ADOSC'] = ta.ADOSC(np.array(df['High'].shift(1)),
np.array(df['Low'].shift(1)),
np.array(df['Adj Close'].shift(1)),
np.array(df['Volume'].shift(1)),
fastperiod=3,
slowperiod=10)
df['OBV'] = ta.OBV(np.array(df['Adj Close'].shift(1)),
np.array(df['Volume'].shift(1)))
# Price Transform Functions
df['AVGPRICE'] = ta.AVGPRICE(np.array(df['Open'].shift(1)),
np.array(df['High'].shift(1)),
np.array(df['Low'].shift(1)),
np.array(df['Adj Close'].shift(1)))
df['MEDPRICE'] = ta.MEDPRICE(np.array(df['High'].shift(1)),
np.array(df['Low'].shift(1)))
df['TYPPRICE'] = ta.TYPPRICE(np.array(df['High'].shift(1)),
np.array(df['Low'].shift(1)),
np.array(df['Adj Close'].shift(1)))
df['WCLPRICE'] = ta.WCLPRICE(np.array(df['High'].shift(1)),
np.array(df['Low'].shift(1)),
np.array(df['Adj Close'].shift(1)))
# Pattern Recognition Fuction
df['Two_Crows'] = ta.CDL2CROWS(np.array(df['Open']), np.array(df['High']),
np.array(df['Low']), np.array(df['Adj Close']))
df['Three_Crows'] = ta.CDL3BLACKCROWS(np.array(df['Open']),
np.array(df['High']),
def talib_035(self):
data_AVGPRICE = copy.deepcopy(self.close)
for symbol in symbols:
data_AVGPRICE[symbol] = ta.AVGPRICE(self.open[symbol].values, self.high[symbol].values, self.low[symbol].values, self.close[symbol].values)
return data_AVGPRICE
def avg_price(open, high, low, close):
"""
also found in tradingview as ohlc4 source
"""
return talib.AVGPRICE(open, high, low, close)
def AVGPRICE(data, **kwargs):
_check_talib_presence()
popen, phigh, plow, pclose, pvolume = _extract_ohlc(data)
return talib.AVGPRICE(popen, phigh, plow, pclose, **kwargs)
def get_talib_stock_daily(
stock_code,
s,
e,
append_ori_close=False,
norms=['volume', 'amount', 'ht_dcphase', 'obv', 'adosc', 'ad', 'cci']):
"""获取经过talib处理后的股票日线数据"""
stock_data = QA.QA_fetch_stock_day_adv(stock_code, s, e)
stock_df = stock_data.to_qfq().data
if append_ori_close:
stock_df['o_close'] = stock_data.data['close']
# stock_df['high_qfq'] = stock_data.to_qfq().data['high']
# stock_df['low_hfq'] = stock_data.to_hfq().data['low']
close = np.array(stock_df['close'])
high = np.array(stock_df['high'])
low = np.array(stock_df['low'])
_open = np.array(stock_df['open'])
_volume = np.array(stock_df['volume'])
stock_df['dema'] = talib.DEMA(close)
stock_df['ema'] = talib.EMA(close)
stock_df['ht_tradeline'] = talib.HT_TRENDLINE(close)
stock_df['kama'] = talib.KAMA(close)
stock_df['ma'] = talib.MA(close)
stock_df['mama'], stock_df['fama'] = talib.MAMA(close)
# MAVP
stock_df['midpoint'] = talib.MIDPOINT(close)
stock_df['midprice'] = talib.MIDPRICE(high, low)
stock_df['sar'] = talib.SAR(high, low)
stock_df['sarext'] = talib.SAREXT(high, low)
stock_df['sma'] = talib.SMA(close)
stock_df['t3'] = talib.T3(close)
stock_df['tema'] = talib.TEMA(close)
stock_df['trima'] = talib.TRIMA(close)
stock_df['wma'] = talib.WMA(close)
stock_df['adx'] = talib.ADX(high, low, close)
stock_df['adxr'] = talib.ADXR(high, low, close)
stock_df['apo'] = talib.APO(close)
stock_df['aroondown'], stock_df['aroonup'] = talib.AROON(high, low)
stock_df['aroonosc'] = talib.AROONOSC(high, low)
stock_df['bop'] = talib.BOP(_open, high, low, close)
stock_df['cci'] = talib.CCI(high, low, close)
stock_df['cmo'] = talib.CMO(close)
stock_df['dx'] = talib.DX(high, low, close)
# MACD
stock_df['macd'], stock_df['macdsignal'], stock_df[
'macdhist'] = talib.MACDEXT(close)
# MACDFIX
stock_df['mfi'] = talib.MFI(high, low, close, _volume)
stock_df['minus_di'] = talib.MINUS_DI(high, low, close)
stock_df['minus_dm'] = talib.MINUS_DM(high, low)
stock_df['mom'] = talib.MOM(close)
stock_df['plus_di'] = talib.PLUS_DI(high, low, close)
stock_df['plus_dm'] = talib.PLUS_DM(high, low)
stock_df['ppo'] = talib.PPO(close)
stock_df['roc'] = talib.ROC(close)
stock_df['rocp'] = talib.ROCP(close)
stock_df['rocr'] = talib.ROCR(close)
stock_df['rocr100'] = talib.ROCR100(close)
stock_df['rsi'] = talib.RSI(close)
stock_df['slowk'], stock_df['slowd'] = talib.STOCH(high, low, close)
stock_df['fastk'], stock_df['fastd'] = talib.STOCHF(high, low, close)
# STOCHRSI - Stochastic Relative Strength Index
stock_df['trix'] = talib.TRIX(close)
stock_df['ultosc'] = talib.ULTOSC(high, low, close)
stock_df['willr'] = talib.WILLR(high, low, close)
stock_df['ad'] = talib.AD(high, low, close, _volume)
stock_df['adosc'] = talib.ADOSC(high, low, close, _volume)
stock_df['obv'] = talib.OBV(close, _volume)
stock_df['ht_dcperiod'] = talib.HT_DCPERIOD(close)
stock_df['ht_dcphase'] = talib.HT_DCPHASE(close)
stock_df['inphase'], stock_df['quadrature'] = talib.HT_PHASOR(close)
stock_df['sine'], stock_df['leadsine'] = talib.HT_PHASOR(close)
stock_df['ht_trendmode'] = talib.HT_TRENDMODE(close)
stock_df['avgprice'] = talib.AVGPRICE(_open, high, low, close)
stock_df['medprice'] = talib.MEDPRICE(high, low)
stock_df['typprice'] = talib.TYPPRICE(high, low, close)
stock_df['wclprice'] = talib.WCLPRICE(high, low, close)
stock_df['atr'] = talib.ATR(high, low, close)
stock_df['natr'] = talib.NATR(high, low, close)
stock_df['trange'] = talib.TRANGE(high, low, close)
stock_df['beta'] = talib.BETA(high, low)
stock_df['correl'] = talib.CORREL(high, low)
stock_df['linearreg'] = talib.LINEARREG(close)
stock_df['linearreg_angle'] = talib.LINEARREG_ANGLE(close)
stock_df['linearreg_intercept'] = talib.LINEARREG_INTERCEPT(close)
stock_df['linearreg_slope'] = talib.LINEARREG_SLOPE(close)
stock_df['stddev'] = talib.STDDEV(close)
stock_df['tsf'] = talib.TSF(close)
stock_df['var'] = talib.VAR(close)
stock_df = stock_df.reset_index().set_index('date')
if norms:
x = stock_df[norms].values # returns a numpy array
x_scaled = MinMaxScaler().fit_transform(x)
stock_df = stock_df.drop(columns=norms).join(
pd.DataFrame(x_scaled, columns=norms, index=stock_df.index))
# stock_df = stock_df.drop(columns=['code', 'open', 'high', 'low'])
stock_df = stock_df.dropna()
stock_df = stock_df.drop(columns=['code'])
return stock_df
