기본 데이터.csv → 분석 데이터로 계산 하기

 

특정 종목의 기본 데이터 가져오기

 

■분석 데이터로 변환

기술지표 계산 코드. 먼저 analysis.py의 역할을 명확히 정의하겠습니다.

• 5일 이동평균선
• 20일 이동평균선
• 60일 이동평균선
• 120일 이동평균선
• 240일 이동평균선
• 거래량 5일 평균
• 거래량 20일 평균
• EMA12
• EMA26
• MACD
• Signal
• Histogram : MACD 오실레이터(Oscillator)
• RSI(14)
• Bollinger Band(20)

 

 

이동평균선 이란?

 

MACD (Moving Average Convergence Divergence) 란?

 

 

RSI(Relative Strength Index, 상대강도지수)

 

 

볼린저 밴드(Bollinger Bands)?

 

 

추천 컬럼

최종 CSV는 아래처럼 구성하는 것을 추천합니다.  날짜별 계산 항목들

• 날짜
• 종가
• 시가
• 고가
• 저가
• 거래량
• MA5
• MA20
• MA60
• MA120
• MA240
• VOL_MA5
• VOL_MA20
• EMA12
• EMA26
• MACD
• Signal
• Histogram
• RSI14
• BB_Middle
• BB_Upper
• BB_Lower

---

▶ 파이썬 코드

설치해야 하는 패키지

pip install pandas numpy matplotlib openpyxl requests beautifulsoup4 lxml

import os
import glob
import pandas as pd


INPUT_FOLDER = "StockData"
OUTPUT_FOLDER = "Output"

os.makedirs(OUTPUT_FOLDER, exist_ok=True)


############################################################
# RSI
############################################################

def calculate_rsi(close, period=14):

    delta = close.diff()

    gain = delta.clip(lower=0)

    loss = -delta.clip(upper=0)

    avg_gain = gain.ewm(alpha=1/period, adjust=False).mean()

    avg_loss = loss.ewm(alpha=1/period, adjust=False).mean()

    rs = avg_gain / avg_loss

    rsi = 100 - (100 / (1 + rs))

    return rsi


############################################################
# Bollinger Band
############################################################

def calculate_bollinger(close):

    middle = close.rolling(20).mean()

    std = close.rolling(20).std()

    upper = middle + std * 2

    lower = middle - std * 2

    return middle, upper, lower


############################################################
# Analysis
############################################################

def analyze(df):

    df["날짜"] = pd.to_datetime(df["날짜"])

    df = df.sort_values("날짜").reset_index(drop=True)

    cols = ["종가", "시가", "고가", "저가", "거래량"]

    for c in cols:

        df[c] = (
            df[c]
            .astype(str)
            .str.replace(",", "", regex=False)
            .astype(float)
        )

    #######################################################
    # Moving Average
    #######################################################

    df["MA5"] = df["종가"].rolling(5).mean()

    df["MA20"] = df["종가"].rolling(20).mean()

    df["MA60"] = df["종가"].rolling(60).mean()

    df["MA120"] = df["종가"].rolling(120).mean()

    df["MA240"] = df["종가"].rolling(240).mean()

    #######################################################
    # Volume MA
    #######################################################

    df["VOL_MA5"] = df["거래량"].rolling(5).mean()

    df["VOL_MA20"] = df["거래량"].rolling(20).mean()

    #######################################################
    # EMA
    #######################################################

    df["EMA12"] = df["종가"].ewm(
        span=12,
        adjust=False
    ).mean()

    df["EMA26"] = df["종가"].ewm(
        span=26,
        adjust=False
    ).mean()

    #######################################################
    # MACD
    #######################################################

    df["MACD"] = df["EMA12"] - df["EMA26"]

    df["Signal"] = df["MACD"].ewm(
        span=9,
        adjust=False
    ).mean()

    df["Histogram"] = df["MACD"] - df["Signal"]

    #######################################################
    # RSI
    #######################################################

    df["RSI14"] = calculate_rsi(df["종가"])

    #######################################################
    # Bollinger
    #######################################################

    middle, upper, lower = calculate_bollinger(df["종가"])

    df["BB_Middle"] = middle

    df["BB_Upper"] = upper

    df["BB_Lower"] = lower

    #######################################################

    df["날짜"] = df["날짜"].dt.strftime("%Y-%m-%d")

    return df


############################################################
# Main
############################################################

def main():

    files = glob.glob(
        os.path.join(INPUT_FOLDER, "*.csv")
    )

    if len(files) == 0:

        print("CSV가 없습니다.")

        return

    for file in files:

        if "_Analysis" in file:

            continue

        print("--------------------------------")

        print(os.path.basename(file))

        try:

            df = pd.read_csv(
                file,
                encoding="utf-8-sig"
            )

            result = analyze(df)

            name = os.path.splitext(
                os.path.basename(file)
            )[0]

            save = os.path.join(
                OUTPUT_FOLDER,
                name + "_Analysis.csv"
            )

            result.to_csv(
                save,
                index=False,
                encoding="utf-8-sig"
            )

            print("저장 :", save)

        except Exception as e:

            print(e)

    print()

    print("완료")


if __name__ == "__main__":

    main()

analysis.py

0.00MB

---

by korealionkk@gmail.com