Pythonでtsfreshを利用して超簡単に株価データ特徴量を自動抽出

1. ツールインストール

＄ pip install scikit-learn xgboost pandas-datareader tsfresh

2. ファイル作成

pred.py

import pandas_datareader as pdr
from sklearn.model_selection import train_test_split
import xgboost as xgb
from sklearn.metrics import accuracy_score
from tsfresh import extract_features

df = pdr.get_data_yahoo("AAPL", "2010-11-01", "2020-11-01")
df["Diff"] = df.Close.diff()
df["y"] = df["Diff"].apply(lambda x: 1 if x > 0 else 0).shift(-1)
df = df.drop(
  ["Diff", "Adj Close"],
  axis=1,
).dropna()
# print(df)
df["id"] = df.index
X = extract_features(df.drop(["y"], axis=1), column_id="id").values
y = df["y"].values
X_train, X_test, y_train, y_test = train_test_split(
  X,
  y,
  test_size=0.2,
  shuffle=False,
)
clf = xgb.XGBClassifier()
clf.fit(
  X_train,
  y_train,
)
y_pred = clf.predict(X_test)
print(accuracy_score(y_test, y_pred))

3. 実行

$ python pred.py

0.47619047619047616

以上、超簡単！

4. 参考

5. 関連記事