mark down math functions \ Finance-data

! pip install finance-datareader
! pip install beautifulsoup4

In [1]:

%matplotlib inline
%config InlineBackend.figure_format = 'retina'
# Loading ... Visualization Modules
import matplotlib.pyplot as plt
import warnings
plt.style.use('seaborn')
warnings.simplefilter(action='ignore', category=FutureWarning)

from matplotlib.font_manager import fontManager as fm # 한글폰트 확인 및 추가
font_list_check  = ['D2Coding', 'NanumGothicCoding', 'NanumGothic']
for _ in font_list_check:
    font_counts = [f  for f in font_list_check if _ in [_.name for _ in fm.ttflist]]
    if len(font_counts) > 1: print(f"found : {_}"); plt.rc('font', family=_); break 

found : D2Coding

In [2]:

# S&P 500 지수와 VIX 지수를 다운로드 합니다
import yfinance as yf
df = yf.download(['^GSPC', '^VIX'], 
                 start='1999-01-01', 
                 end='2022-12-31',
                 progress=False)
df = df[['Adj Close']].copy()
df.columns = df.columns.droplevel(0)
df = df.rename(columns={'^GSPC': 'sp500', '^VIX': 'vix'})

In [3]:

# yahoo finance 를 활용한 주가수집
# loading ... the Financial DataSet
import os
import pandas as pd

def fd_csv(file_name, code='', date_start='', date_end=''):
    if os.path.isfile(file_name):     # Checking the File exist
        data = pd.read_csv(file_name)
        data['Date'] = pd.to_datetime(data['Date']) # datetime 포맷
        data = data.set_index('Date') # 변경된 컬럼을 Index 로 설정
    else:                             # if not, download the data
        from FinanceDataReader import DataReader as fdr
        data = fdr(code, date_start, date_end).reset_index()
        data.to_csv(file_name, index=None)
        data = data.set_index('Date')
    return data

# Finance DataSet 생성하기
file_name = './data/stock-msft.csv'
data_csv = fd_csv(file_name, 'MSFT', date_start='2020-1-1', date_end='2021-3-31')
data_csv.tail(3)

Out[3]:

	Close	Open	High	Low	Volume	Change
Date
2021-03-25	232.34	235.34	236.90	231.60	34060000.0	-0.0133
2021-03-26	236.48	231.55	236.71	231.55	25480000.0	0.0178
2021-03-29	232.24	236.69	236.69	231.91	5490000.0	-0.0179

In [4]:

# yahoo finance 를 활용한 주가수집
# loading ... the Financial DataSet
import os
import pandas as pd

def yf_csv(file_name, code='', date_start='', date_end=''):
    if os.path.isfile(file_name):  # Checking the File exist
        data = pd.read_csv(file_name)
        data['Date'] = pd.to_datetime(data['Date']) # datetime 포맷 변경
        data = data.set_index('Date')               # 변경된 컬럼을 Index 로 설정
    else:  # if not, download the data
        import yfinance as yf
        data = yf.download(code, start=date_start, end=date_end,
            progress=False, auto_adjust=True).reset_index()
        data.to_csv(file_name, index=None)
        data = data.set_index('Date')
    return data

# Finance DataSet 생성하기
file_name = './data/stock-samsung.csv'
data_csv = yf_csv(file_name, '005930', date_start='2020-1-1', date_end='2021-3-31')
data_csv.tail(3)

Out[4]:

	Open	High	Low	Close	Volume	Change
Date
2021-03-25	81000	82100	80800	81200	14758826	0.002469
2021-03-26	81400	81600	81000	81500	12845778	0.003695
2021-03-29	81700	81700	81000	81600	14835336	0.001227

In [12]:

data_csv['2021-MAR-1':'2021-MAY-1'].tail()

Out[12]:

	Open	High	Low	Close	Volume	Change
Date
2021-03-23	82600	82900	81800	81800	13299907	-0.002439
2021-03-24	81000	81600	80700	81000	17926638	-0.009780
2021-03-25	81000	82100	80800	81200	14758826	0.002469
2021-03-26	81400	81600	81000	81500	12845778	0.003695
2021-03-29	81700	81700	81000	81600	14835336	0.001227

In [ ]:

data_csv

In [6]:

import os
import pandas as pd

class StockCSV:
    
    #def __init__(self):
    #    self.code = '005930'
        
    def finance(self, code='', date_start='', date_end='', file_name=None):
        r'''Finance Data Reacer : CSV file save & loader
        https://github.com/FinanceData/FinanceDataReader/blob/master/README.md'''
        # case 1 : 파일을 지정한 경우
        if file_name:
            ## 01 Loading from CSV
            if os.path.isfile(file_name):     # Checking the File exist
                data = pd.read_csv(file_name)
                data['Date'] = pd.to_datetime(data['Date']) # datetime 포맷
                data = data.set_index('Date') # 변경된 컬럼을 Index 로 설정
            ## 02 Loading from Py Module API
            else:                             # if not, download the data
                from FinanceDataReader import DataReader as fdr
                data = fdr(code, date_start, date_end).reset_index()
                data.to_csv(file_name, index=None)
                data = data.set_index('Date')
        # case 2 : 파일을 지정하지 않은경우
        else:
            from FinanceDataReader import DataReader as fdr
            data = fdr(code, date_start, date_end)            
        return data
    
    
    def yahoo(self, code='', date_start='', date_end='', file_name=None):
        r'''Yahoo Finance : CSV file save & loader'''
        # case 1 : 파일을 지정한 경우
        if file_name:
            ## 01 Loading from CSV
            if os.path.isfile(file_name):  # Checking the File exist
                data = pd.read_csv(file_name)
                data['Date'] = pd.to_datetime(data['Date']) # datetime 포맷 변경
                data = data.set_index('Date')               # 변경된 컬럼을 Index 로 설정
            ## 02 Loading from Py Module API
            else:  # if not, download the data
                import yfinance as yf
                data = yf.download(code, start=date_start, end=date_end,
                    progress=False, auto_adjust=True).reset_index()
                data.to_csv(file_name, index=None)
                data = data.set_index('Date')
        # case 2 : 파일을 지정하지 않은경우
        else:
            import yfinance as yf
            data = yf.download(code, start=date_start, end=date_end,
                progress=False, auto_adjust=True) #.reset_index()
        return data  

In [7]:

reader = StockCSV()
# reader.finance('005930', '2020-01-01','2021-01-01', './data/test.csv')
reader.finance('005930', '2020-01-01','2021-01-01').tail()

Out[7]:

	Open	High	Low	Close	Volume	Change
Date
2020-01-02	55500	56000	55000	55200	12993228	-0.010753
2020-01-03	56000	56600	54900	55500	15422255	0.005435
2020-01-06	54900	55600	54600	55500	10278951	0.000000
2020-01-07	55700	56400	55600	55800	10009778	0.005405
2020-01-08	56200	57400	55900	56800	23501171	0.017921
...	...	...	...	...	...	...
2020-12-23	72400	74000	72300	73900	19411326	0.022130
2020-12-24	74100	78800	74000	77800	32502870	0.052774
2020-12-28	79000	80100	78200	78700	40085044	0.011568
2020-12-29	78800	78900	77300	78300	30339449	-0.005083
2020-12-30	77400	81300	77300	81000	29417421	0.034483

248 rows × 6 columns

2) BOK EOS 한국은행 통계정보 API¶

In [8]:

# https://bjecondata.blogspot.com/2019/08/open-api-ecos-ii.html
import pandas as pd
code_table = pd.read_csv('./data/BOK_ECOS_EXAMPLE.csv')
code_table.head(3)

Out[8]:

	통계명	항목명1	통계코드	항목코드1	항목코드2	항목명2	항목코드3	항목명3	단위	URL
0	1.1.주요 통화금융지표	예금은행요구불예금회전율	010Y002	AAAA5	NaN	NaN	NaN	NaN	회/월	http://ecos.bok.or.kr/api/StatisticSearch/APIC...
1	1.1.주요 통화금융지표	화폐발행잔액(말잔)	010Y002	AAAA11	NaN	NaN	NaN	NaN	십억원	http://ecos.bok.or.kr/api/StatisticSearch/APIC...
2	1.1.주요 통화금융지표	화폐발행잔액(평잔)	010Y002	AAAA12	NaN	NaN	NaN	NaN	십억원	http://ecos.bok.or.kr/api/StatisticSearch/APIC...

In [9]:

# 필요한 자료코드 추출하기
search_text = '인플레'
code_index = [no   for no, _ in enumerate(code_table['통계명'].to_list())
              if _.find(search_text) != -1]
code_example = code_table.iloc[code_index, :].reset_index(drop=True)
code_example.head(3)
# code_example['URL'][:3].to_list()

Out[9]:

	통계명	항목명1	통계코드	항목코드1	항목코드2	항목명2	항목코드3	항목명3	단위	URL
0	9.2.3 소비자동향조사(기대 인플레이션율)(전국)	물가인식	040Y003	FMA	NaN	NaN	NaN	NaN	NaN	http://ecos.bok.or.kr/api/StatisticSearch/APIC...
1	9.2.3 소비자동향조사(기대 인플레이션율)(전국)	<0%	040Y003	FMAAA	NaN	NaN	NaN	NaN	NaN	http://ecos.bok.or.kr/api/StatisticSearch/APIC...
2	9.2.3 소비자동향조사(기대 인플레이션율)(전국)	0~1%	040Y003	FMAAB	NaN	NaN	NaN	NaN	NaN	http://ecos.bok.or.kr/api/StatisticSearch/APIC...

In [10]:

from data.finance import bok_eos_api
eos_table = bok_eos_api('040Y003', date_end='20210101', code2='FMB')  # 7년 단위로만 추출가능
eos_table['DATA_VALUE'] = list(map(lambda x : float(x),  eos_table['DATA_VALUE']))
eos_table = eos_table.rename(columns={'DATA_VALUE':'cpi', 'TIME':'Date'})

eos_table['Date'] = pd.to_datetime(eos_table['Date'], format='%Y%m')
eos_table = eos_table.set_index('Date')  # eos_table.head(3)
eos_table = eos_table[['cpi']]
# ploting the DataSet
eos_table.head(3)

Out[10]:

	cpi
Date
2002-02-01	4.4
2002-03-01	4.3
2002-04-01	4.3