from tqdm import tqdm
os.chdir(path_code)
import util
os.chdir(path_data)
##############################################################################
# 0. 데이터 로드 & 클렌징
##############################################################################
'''
재무데이터 : 퀀티와이즈
가격데이터 : 퀀트DB
'''
# 재무정보
ocf = util.data_cleansing(pd.read_excel('fin.xlsx', sheet_name='ocf_Q'))
cfTTM = util.data_cleansing(pd.read_excel('fin.xlsx', sheet_name='cfTTM_Q'))
ocfTTM = util.data_cleansing(pd.read_excel('fin.xlsx', sheet_name='ocfTTM_Q'))
opmTTM = util.data_cleansing(pd.read_excel('fin.xlsx', sheet_name='opm_Q'))
# 수급 및 유동성 정보 (20일 거래대금, 20일누적 기관순매수수량, 시가총액, 상장주식수)
vol_20MA = util.data_cleansing_ts(
pd.read_excel('liq.xlsx', sheet_name='vol_20MA_M'))
netbuy20 = util.data_cleansing_ts(
pd.read_excel('liq.xlsx', sheet_name='netbuy20_M'))
mktcap = util.data_cleansing_ts(
pd.read_excel('liq.xlsx', sheet_name='mktcap_M'))
numStock = util.data_cleansing_ts(
pd.read_excel('liq.xlsx', sheet_name='numStock_M'))
# 상장시장, 섹터, 거래정지 여부 등 기본 정보
- Crash / Jackpot
-
'''
import os
import pandas as pd
import numpy as np
import datetime
path = 'C:/Woojin/###. Git/Project_Q/V. Small Cap strategy'
os.chdir(path)
import util as ut
rdata = pd.ExcelFile(path + '/Data/data.xlsx')
mkt_info = ut.data_cleansing(pd.read_excel(rdata, 'market_info'))
mktcap = ut.data_cleansing(pd.read_excel(rdata, 'mktcap'))
net_income = ut.data_cleansing_as(pd.read_excel(rdata, 'net_income'))
vol = ut.data_cleansing(pd.read_excel(rdata, 'volume'))
caution_1 = ut.data_cleansing(pd.read_excel(rdata, '거래정지'))
caution_2 = ut.data_cleansing(pd.read_excel(rdata, '투자유의'))
caution_3 = ut.data_cleansing(pd.read_excel(rdata, '관리종목'))
per = ut.data_cleansing(pd.read_excel(rdata, 'PER'))
psr = ut.data_cleansing(pd.read_excel(rdata, 'PSR'))
pbr = ut.data_cleansing(pd.read_excel(rdata, 'PBR'))
def get_universe(rebalDate, df_info, df_mktcap, df_netincome, df_vol, df_caution_1, df_caution_2, df_caution_3):
# 코스피 소형주 대상
lookback_info = df_info.loc[:rebalDate, :].tail(1).transpose()
lookback_info = lookback_info[lookback_info == 3].dropna().index.values
start_invest = pd.datetime(start_year, start_month, start_day)
end_invest = pd.datetime(end_year, end_month, end_day)
rebal_sche = pd.date_range(start_invest, end_invest, freq='M')
# Load market info data
marketInfo = util.data_cleansing_ts(
pd.read_excel('factorData.xlsx', sheet_name='market'))
mktcap = util.data_cleansing_ts(
pd.read_excel('factorData.xlsx', sheet_name='mktcap'))
risk_1 = util.data_cleansing_ts(
pd.read_excel('factorData.xlsx', sheet_name='risk_1'))
risk_2 = util.data_cleansing_ts(
pd.read_excel('factorData.xlsx', sheet_name='risk_2'))
# Load factor data
factor_book = util.data_cleansing(
pd.read_excel('factorData.xlsx', sheet_name='book'))
factor_size = util.data_cleansing(
pd.read_excel('factorData.xlsx', sheet_name='size'))
factor_yield = util.data_cleansing(
pd.read_excel('factorData.xlsx', sheet_name='dividend'))
current_asset = util.data_cleansing(
pd.read_excel('factorData.xlsx', sheet_name='CA'))
current_liability = util.data_cleansing(
pd.read_excel('factorData.xlsx', sheet_name='CL'))
total_liability = util.data_cleansing(
pd.read_excel('factorData.xlsx', sheet_name='TL'))
accural_ratio = (current_asset - current_liability).pct_change()
earnings = util.data_cleansing(
pd.read_excel('factorData.xlsx', sheet_name='earnings'))
start_invest = pd.datetime(start_year, start_month, start_day)
end_invest = pd.datetime(end_year, end_month, end_day)
rebal_sche = pd.date_range(start_invest, end_invest, freq='M')
# Load market info data
marketInfo = util.data_cleansing_ts(
pd.read_excel('testData.xlsx', sheet_name='market'))
mktcap = util.data_cleansing_ts(
pd.read_excel('testData.xlsx', sheet_name='mktcap'))
risk_1 = util.data_cleansing_ts(
pd.read_excel('testData.xlsx', sheet_name='risk_1'))
risk_2 = util.data_cleansing_ts(
pd.read_excel('testData.xlsx', sheet_name='risk_2'))
# Load factor data
factor_PSR = util.data_cleansing(
pd.read_excel('testData.xlsx', sheet_name='sales'))
factor_PBR = util.data_cleansing(
pd.read_excel('testData.xlsx', sheet_name='book'))
factor_PER = util.data_cleansing(
pd.read_excel('testData.xlsx', sheet_name='earnings'))
# I. Cross-sectional
'''
ex. Value & Momentum (Sales to Price, Book to Price, Momentum)
'''
def get_priceRatio_multi(factorData, mktcapData):
code_f = factorData.index.values
code_p = mktcapData.columns.values
code = list(set(code_f).intersection(code_p))
import matplotlib.pylab as plt
from datetime import datetime
import statsmodels.api as sm
from pykalman import KalmanFilter
from math import sqrt
path = 'C:/Woojin/###. Git/Project_Q/III. Factor Exposed Pairs Trading'
os.chdir(path)
#import backtest_pipeline_ver2 as bt
import util
codes = pd.read_excel('firmCode.xlsx')['Code'].values
price = util.get_stock_price(codes, pd.to_datetime('2010-01-01'),
pd.to_datetime('2019-06-30'))
size = util.data_cleansing(pd.read_excel('firmSize.xlsx'))
#NOTE CRITICAL LEVEL HAS BEEN SET TO 5% FOR COINTEGRATION TEST
def find_cointegrated_pairs(dataframe, critial_level=0.05):
n = dataframe.shape[1] # the length of dateframe
pvalue_matrix = np.ones((n, n)) # initialize the matrix of p
keys = dataframe.columns # get the column names
pairs = [] # initilize the list for cointegration
for i in range(n):
for j in range(i + 1, n): # for j bigger than i
stock1 = dataframe[keys[i]] # obtain the price of "stock1"
stock2 = dataframe[keys[j]] # obtain the price of "stock2"
result = sm.tsa.stattools.coint(stock1,
stock2) # get conintegration
pvalue = result[1] # get the pvalue