Nasdaq vs Commodity Features(Corration 0.868)

validation.py

import yfinance as yf
import pandas as pd

class Data:
    def __init__(self, symbol, start_date, end_date):
        self.symbol = symbol
        self.start_date = start_date
        self.end_date = end_date
    
    def get_data(self):
        data = yf.download(self.symbol, start=self.start_date, end=self.end_date)
        return data

# カカオのデータの取得
cacao_instance = Data("CC=F", "1990-01-01", "2024-03-31")
cacao_data = cacao_instance.get_data()

# アルミニウムのデータの取得
aluminum_instance = Data("ALI=F", "1990-01-01", "2024-03-31")
aluminum_data = aluminum_instance.get_data()

# 銅のデータの取得
copper_instance = Data("HG=F", "1990-01-01", "2024-03-31")
copper_data = copper_instance.get_data()

# 銀のデータの取得
silver_instance = Data("SI=F", "1990-01-01", "2024-03-31")
silver_data = silver_instance.get_data()

# 金のデータの取得
gold_instance = Data("GC=F", "1990-01-01", "2024-03-31")
gold_data = gold_instance.get_data()

# 砂糖のデータの取得
sugar_instance = Data("SB=F", "1990-01-01", "2024-03-31")
sugar_data = sugar_instance.get_data()

# コーヒーのデータの取得
coffee_instance = Data("KC=F", "1990-01-01", "2024-03-31")
coffee_data = coffee_instance.get_data()

# ナスダックのデータの取得
nasdaq_instance = Data("^IXIC", "1990-01-01", "2024-03-31")
nasdaq_data = nasdaq_instance.get_data()

# 終値の列のみを抽出してデータフレームに結合
merged_data = pd.concat([
    cacao_data["Close"].rename("Cacao_Close"),
    aluminum_data["Close"].rename("Aluminum_Close"),
    copper_data["Close"].rename("Copper_Close"),
    silver_data["Close"].rename("Silver_Close"),
    gold_data["Close"].rename("Gold_Close"),
    sugar_data["Close"].rename("Sugar_Close"),
    coffee_data["Close"].rename("Coffee_Close"),
    nasdaq_data["Close"].rename("Nasdaq_Close")
], axis=1).dropna()

# 列名を変数として定義
cacao_close_col = "Cacao_Close"
aluminum_close_col = "Aluminum_Close"
copper_close_col = "Copper_Close"
silver_close_col = "Silver_Close"
gold_close_col = "Gold_Close"
sugar_close_col = "Sugar_Close"
coffee_close_col = "Coffee_Close"
nasdaq_close_col = "Nasdaq_Close"

# 終値の列のみを抽出してデータフレームに結合
merged_data = pd.concat([
    cacao_data["Close"].rename(cacao_close_col),
    aluminum_data["Close"].rename(aluminum_close_col),
    copper_data["Close"].rename(copper_close_col),
    silver_data["Close"].rename(silver_close_col),
    gold_data["Close"].rename(gold_close_col),
    sugar_data["Close"].rename(sugar_close_col),
    coffee_data["Close"].rename(coffee_close_col),
    nasdaq_data["Close"].rename(nasdaq_close_col)
], axis=1).dropna()

#print(merged_data.tail())

mixed = merged_data['Coffee_Close'] ** -0.45 * \
        merged_data['Cacao_Close'] ** 0.105 * \
        (merged_data['Aluminum_Close'] + \
        merged_data['Copper_Close'] + \
        merged_data['Silver_Close'] + \
        merged_data['Gold_Close'] ** 3.35) - \
        merged_data['Sugar_Close']

testCorrelation = mixed.corr(merged_data["Nasdaq_Close"])
print(testCorrelation)