【Python】 「Sweetviz」探索的データ解析EDAでの使い方。仮想通貨の分析。

conda install -c conda-forge sweetviz

import pandas as pd  
from pandas_datareader import data as pdr 
import datetime
import yfinance as yf
import mplfinance as mpl

#BTCのチャートを取得
tickers = ['BTC-USD','^IXIC','^GSPC','^DJI','^TNX','DX-Y.NYB','GC=F']

#取得開始日を入力
start = "2022-01-01"

#取得終了日を入力
end = datetime.date.today()

#Yahoofinanceから取得するように設定
yf.pdr_override()

#データの取得を実行
data = pdr.get_data_yahoo(tickers, start, end)

data = data.dropna()
data

# 必要なライブラリーのインポート
import numpy as np
import sweetviz as sv
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split

df = data['Adj Close']

# 学習データと評価データを作成
x_train, x_test, y_train, y_test = train_test_split(df.iloc[:, 1:7], df.iloc[:, 0],
                                                    test_size=0.2, random_state=1)

df_train = pd.concat([x_train, y_train], axis=1)
df_test = pd.concat([x_test, y_test], axis=1)

my_report = sv.compare([df_train, "Train"], [df_test, "Test"], "BTC-USD")

#直接ブラウザに表示
my_report.show_html("sweetviz_report_2col.html")

from sklearn.ensemble import RandomForestRegressor as RFR

rg = RFR(n_jobs=-1, random_state=2525)
rg.fit(x_train, y_train)
predicted = rg.predict(x_test)
rg.score(x_test, y_test)

fti = rg.feature_importances_

print('Feature Importances:')
for i in range(len(df.columns)):
    print(df.columns[i+1],fti [i])