255 lines
12 KiB
Python
255 lines
12 KiB
Python
# https://bibot.tistory.com/63
|
|
# https://nonmeyet.tistory.com/entry/Python-TALib%EB%A5%BC-%ED%99%9C%EC%9A%A9%ED%95%9C-%EB%B9%84%ED%8A%B8%EC%BD%94%EC%9D%B8%EC%A3%BC%EA%B0%80%EA%B8%B0%EC%88%A0%EB%B6%84%EC%84%9D-%EB%B3%B4%EC%A1%B0%EC%A7%80%ED%91%9C-%EC%B6%94%EA%B0%80
|
|
# https://lunadaddy.tistory.com/122
|
|
# https://wikidocs.net/186885
|
|
|
|
import os
|
|
from scipy.signal import savgol_filter
|
|
import numpy as np
|
|
np.seterr(divide='ignore', invalid='ignore')
|
|
# https://www.lfd.uci.edu/~gohlke/pythonlibs/#ta-lib
|
|
# https://lunadaddy.tistory.com/122
|
|
import talib
|
|
import pandas as pd
|
|
from datetime import datetime, timedelta
|
|
|
|
from JSDPattern import JSDPattern
|
|
|
|
class JSDPattern_realtime (JSDPattern):
|
|
|
|
def __init__(self, stockFileName=None):
|
|
super().__init__(stockFileName)
|
|
return
|
|
|
|
def analyze(self, result):
|
|
result["volume"] = [result["volume"][i] if 0 < result["volume"][i] else 1 for i in range(len(result["volume"]))]
|
|
# 기본 캔들 정보
|
|
open_df = pd.DataFrame(result["open"])
|
|
close_df = pd.DataFrame(result["close"])
|
|
high_df = pd.DataFrame(result["high"])
|
|
low_df = pd.DataFrame(result["low"])
|
|
volume_df = pd.DataFrame(result["volume"])
|
|
|
|
# 중복 제거
|
|
ymd_df = pd.DataFrame(result["ymd"])
|
|
data_dup = pd.concat([ymd_df, open_df, close_df, high_df, low_df, volume_df], axis=1)
|
|
data_dup.columns = ["ymd", "open", "close", "high", "low", "volume"]
|
|
data_dup.index = pd.DatetimeIndex(result["ymd"])
|
|
data_dup_sorted = data_dup.sort_index(ascending=True)
|
|
data_dup_sorted = data_dup_sorted.drop_duplicates()
|
|
|
|
ymd_df = data_dup_sorted["ymd"]
|
|
open_df = data_dup_sorted["open"]
|
|
close_df = data_dup_sorted["close"]
|
|
high_df = data_dup_sorted["high"]
|
|
low_df = data_dup_sorted["low"]
|
|
volume_df = data_dup_sorted["volume"]
|
|
|
|
ymd = ymd_df.tolist()
|
|
open = open_df.tolist()
|
|
close = close_df.tolist()
|
|
high = high_df.tolist()
|
|
low = low_df.tolist()
|
|
volume = volume_df.tolist()
|
|
|
|
# ichimokuCloud
|
|
df = pd.concat([ymd_df, open_df, close_df, high_df, low_df, volume_df], axis=1)
|
|
column_names = ['DATE', 'open', 'close', 'high', 'low', 'volume']
|
|
df.columns = column_names
|
|
c, b, l, s = 9, 26, 52, 26
|
|
# 1. 전환선 = (과거 9일 동안 최고가 + 최저가) / 2
|
|
# 당일을 포함한 9일 동안의 최고가와 최저가의 중간 값을 평균으로 나타낸다.
|
|
changeLine = (df.high.rolling(c).max() + df.low.rolling(c).min()) / 2
|
|
# 2. 기준선 = 과거 26일 동안 최고가 + 최저가) / 2
|
|
# 당일을 포함한 26일 동안의 최고가와 최저가의 중간 값을 평균으로 나타낸다.
|
|
baseLine = (df.high.rolling(b).max() + df.low.rolling(b).min()) / 2
|
|
|
|
# 3. 후행스팬 = 현재 close가격의 26일전 반영
|
|
laggingSpan = [df.close.values[i + s] for i in range(len(df.close) - s)]
|
|
laggingSpan += [None for i in range(s)]
|
|
laggingSpan = np.array(laggingSpan)
|
|
|
|
# 4. 선행스팬 1 = ((기준선 + 전환선) / 2)를 26일 선행하여 배치
|
|
# 전환선과 기준선의 평균값을 구해 당일 포함 26일 앞으로 이동시킨 선 (중-단기 구간의 힘을 보여줌)
|
|
tmp_leadingSpan1 = (changeLine + baseLine) / 2
|
|
""" S: 26일 선행시킴 """
|
|
leadingSpan1 = list(tmp_leadingSpan1.values)
|
|
for i in range(b - 1):
|
|
leadingSpan1.insert(0, None)
|
|
""" E: 26일 선행시킴 """
|
|
|
|
# 5. 선행스팬 2 = ((최근 52일 동안 최고가 + 최저가) / 2)를 26일 선행하여 배치
|
|
# 당일을 포함한 52일 동안의 최고가와 최저가의 평균을 26일 앞으로 이동시킨 선 (장기으로 형성된 선이기 때문에 가장 느리게 변함)
|
|
tmp_leadingSpan2 = (df.high.rolling(l).max() + df.low.rolling(l).min()) / 2
|
|
""" S: 52일 선행시킴 """
|
|
leadingSpan2 = list(tmp_leadingSpan2.values)
|
|
for i in range(l - 1):
|
|
leadingSpan2.insert(0, None)
|
|
""" S: 52일 선행시킴 """
|
|
|
|
baseLine = baseLine.tolist()
|
|
changeLine = changeLine.tolist()
|
|
laggingSpan = list(laggingSpan)
|
|
current_index = len(ymd)
|
|
for i in range(51):
|
|
if len(ymd) < len(leadingSpan2):
|
|
ymd.append(ymd[-1] + timedelta(days=1))
|
|
if len(open) < len(leadingSpan2):
|
|
open.append(None)
|
|
if len(close) < len(leadingSpan2):
|
|
close.append(None)
|
|
if len(high) < len(leadingSpan2):
|
|
high.append(None)
|
|
if len(low) < len(leadingSpan2):
|
|
low.append(None)
|
|
if len(volume) < len(leadingSpan2):
|
|
volume.append(None)
|
|
if len(baseLine) < len(leadingSpan2):
|
|
baseLine.append(None)
|
|
if len(changeLine) < len(leadingSpan2):
|
|
changeLine.append(None)
|
|
if len(laggingSpan) < len(leadingSpan2):
|
|
laggingSpan.append(None)
|
|
for i in range(26):
|
|
if len(leadingSpan1) < len(leadingSpan2):
|
|
leadingSpan1.append(leadingSpan1[-1])
|
|
|
|
# 9일 신고가
|
|
new_high_9 = [0 for c in range(8)] + [1 if (changeLine[c-1] is not None and changeLine[c] is not None and changeLine[c-1] < changeLine[c]) and None not in close[c-8:c+1] and max(close[c-8:c]) < close[c] else 0 for c in range(8, len(close))]
|
|
# 26일 신고가
|
|
new_high_26 = [0 for c in range(25)] + [1 if (baseLine[c-1] is not None and baseLine[c] is not None and baseLine[c-1] < baseLine[c]) and None not in close[c-8:c+1] and max(close[c-25:c]) < close[c] else 0 for c in range(25, len(close))]
|
|
|
|
# 9일 신저가
|
|
new_low_9 = [0 for c in range(8)] + [1 if (changeLine[c-1] is not None and changeLine[c] is not None and changeLine[c-1] < changeLine[c]) and None not in close[c-8:c+1] and close[c-9] < min(close[c-8:c+1]) else 0 for c in range(8, len(close))]
|
|
# 26일 신저가
|
|
new_low_26 = [0 for c in range(25)] + [1 if (baseLine[c-1] is not None and baseLine[c] is not None and baseLine[c-1] < baseLine[c]) and None not in close[c-8:c+1] and close[c-26] < min(close[c-25:c+1]) else 0 for c in range(25, len(close))]
|
|
|
|
|
|
# 이동 평균
|
|
close_df = pd.DataFrame(close)
|
|
avg5 = list(np.reshape(close_df.ewm(5).mean().values, -1))
|
|
avg10 = list(np.reshape(close_df.ewm(10).mean().values, -1))
|
|
avg20 = list(np.reshape(close_df.ewm(20).mean().values, -1))
|
|
avg60 = list(np.reshape(close_df.ewm(60).mean().values, -1))
|
|
avg90 = list(np.reshape(close_df.ewm(90).mean().values, -1))
|
|
avg120 = list(np.reshape(close_df.ewm(120).mean().values, -1))
|
|
avg240 = list(np.reshape(close_df.ewm(240).mean().values, -1))
|
|
avg360 = list(np.reshape(close_df.ewm(360).mean().values, -1))
|
|
avg480 = list(np.reshape(close_df.ewm(480).mean().values, -1))
|
|
|
|
np_high, np_low, np_close = np.array(high, dtype=np.float64), np.array(low, dtype=np.float64), np.array(close, dtype=np.float64)
|
|
slowk_12_df, slowd_12_df = talib.STOCH(np_high, np_low, np_close, fastk_period=12, slowk_period=5, slowk_matype=0, slowd_period=5, slowd_matype=0)
|
|
slowk_26_df, slowd_26_df = talib.STOCH(np_high, np_low, np_close, fastk_period=26, slowk_period=16, slowk_matype=0, slowd_period=16, slowd_matype=0)
|
|
slowk_52_df, slowd_52_df = talib.STOCH(np_high, np_low, np_close, fastk_period=52, slowk_period=32, slowk_matype=0, slowd_period=32, slowd_matype=0)
|
|
|
|
|
|
# 볼린저 밴드
|
|
n, t = 10, 2
|
|
max_10 = close_df.rolling(window=n).mean()
|
|
stddev_10 = close_df.rolling(window=n).std()
|
|
upper_10 = max_10 + (stddev_10 * t) # 상단 볼리저 밴드
|
|
lower_10 = max_10 - (stddev_10 * t) # 하단 볼리저 밴드
|
|
middle_10 = (upper_10 + lower_10) / 2
|
|
upper_10 = list(np.reshape(upper_10.values, -1))
|
|
lower_10 = list(np.reshape(lower_10.values, -1))
|
|
middle_10 = list(np.reshape(middle_10.values, -1))
|
|
|
|
n, t = 20, 2
|
|
max_20 = close_df.rolling(window=n).mean()
|
|
stddev_20 = close_df.rolling(window=n).std()
|
|
upper_20 = max_20 + (stddev_20 * t) # 상단 볼리저 밴드
|
|
lower_20 = max_20 - (stddev_20 * t) # 하단 볼리저 밴드
|
|
middle_20 = (upper_20 + lower_20) / 2
|
|
upper_20 = list(np.reshape(upper_20.values, -1))
|
|
lower_20 = list(np.reshape(lower_20.values, -1))
|
|
middle_20 = list(np.reshape(middle_20.values, -1))
|
|
|
|
duration = 360
|
|
laggingSpan_close_diff, laggingSpan_close_diff_rate = self.getDiff_Rate(laggingSpan, close, duration=duration)
|
|
laggingSpan_avg60_diff, laggingSpan_avg60_diff_rate = self.getDiff_Rate(laggingSpan, avg60, duration=duration)
|
|
leadingSpan1_leadingSpan2_diff, leadingSpan1_leadingSpan2_diff_rate = self.getDiff_Rate(leadingSpan1, leadingSpan2, duration=duration)
|
|
|
|
df_list = [
|
|
pd.DataFrame(ymd),
|
|
pd.DataFrame(open), pd.DataFrame(close), pd.DataFrame(high), pd.DataFrame(low), pd.DataFrame(volume),
|
|
pd.DataFrame(changeLine), pd.DataFrame(baseLine), pd.DataFrame(laggingSpan), pd.DataFrame(leadingSpan1), pd.DataFrame(leadingSpan2),
|
|
|
|
pd.DataFrame(laggingSpan_close_diff),
|
|
pd.DataFrame(laggingSpan_avg60_diff),
|
|
pd.DataFrame(leadingSpan1_leadingSpan2_diff),
|
|
|
|
pd.DataFrame(laggingSpan_close_diff_rate),
|
|
pd.DataFrame(laggingSpan_avg60_diff_rate),
|
|
pd.DataFrame(leadingSpan1_leadingSpan2_diff_rate),
|
|
|
|
pd.DataFrame(avg5), pd.DataFrame(avg10), pd.DataFrame(avg20), pd.DataFrame(avg60), pd.DataFrame(avg90), pd.DataFrame(avg120), pd.DataFrame(avg240), pd.DataFrame(avg360), pd.DataFrame(avg480),
|
|
pd.DataFrame(upper_10), pd.DataFrame(lower_10), pd.DataFrame(middle_10),
|
|
pd.DataFrame(upper_20), pd.DataFrame(lower_20), pd.DataFrame(middle_20),
|
|
|
|
pd.DataFrame(new_high_9), pd.DataFrame(new_high_26),
|
|
pd.DataFrame(new_low_9), pd.DataFrame(new_low_26),
|
|
pd.DataFrame(slowk_12_df), pd.DataFrame(slowd_12_df),
|
|
pd.DataFrame(slowk_26_df), pd.DataFrame(slowd_26_df),
|
|
pd.DataFrame(slowk_52_df), pd.DataFrame(slowd_52_df),
|
|
|
|
]
|
|
|
|
data = pd.concat(df_list, axis=1)
|
|
column_names = [
|
|
'ymd',
|
|
'open', 'close', 'high', 'low', 'volume',
|
|
'changeLine', 'baseLine', 'laggingSpan', 'leadingSpan1', 'leadingSpan2',
|
|
|
|
'laggingSpan_close_diff',
|
|
'laggingSpan_avg60_diff',
|
|
'leadingSpan1_leadingSpan2_diff',
|
|
|
|
'laggingSpan_close_diff_rate',
|
|
'laggingSpan_avg60_diff_rate',
|
|
'leadingSpan1_leadingSpan2_diff_rate',
|
|
|
|
'avg5', 'avg10', 'avg20', 'avg60', 'avg90', 'avg120', 'avg240', 'avg360', 'avg480',
|
|
|
|
'upper_10', 'lower_10', 'middle_10',
|
|
'upper_20', 'lower_20', 'middle_20',
|
|
|
|
'new_high_9', 'new_high_26',
|
|
'new_low_9', 'new_low_26',
|
|
|
|
'slowk_12', 'slowd_12',
|
|
'slowk_26', 'slowd_26',
|
|
'slowk_52', 'slowd_52',
|
|
]
|
|
data.columns = column_names
|
|
data.index = pd.DatetimeIndex(ymd)
|
|
|
|
return data, current_index
|
|
|
|
def getData(self, ticker, ymd=None, get_days=14):
|
|
if ymd is None:
|
|
result = self.getCoinData(ticker, get_days=get_days)
|
|
else:
|
|
result = self.getCoinData(ticker, ymd=ymd, get_days=get_days)
|
|
|
|
if len(result['ymd']) < 1:
|
|
return None, None
|
|
|
|
#result_tic = self.makeTickData(result_m1, mins=minute)
|
|
data, current_index = self.analyze(result)
|
|
return data, current_index
|
|
|
|
if __name__ == "__main__":
|
|
def min_max_normalize(data):
|
|
min_val = min(data)
|
|
max_val = max(data)
|
|
normalized_data = [(x - min_val) / (max_val - min_val) for x in data]
|
|
return normalized_data
|
|
|
|
|
|
# 예시 데이터
|
|
original_data = [-4, -3, -2, -1, 0]
|
|
normalized_data = min_max_normalize(original_data)
|
|
print(np.asarray(normalized_data)-1)
|
|
original_data = [0, 2,4,6,8,10]
|
|
normalized_data = min_max_normalize(original_data)
|
|
print(normalized_data) |