finlab.ml

from finlab import data
from finlab.ml import feature as mlf, label as mll
import finlab.ml.qlib as q
from finlab.backtest import sim

# 步驟 1：建立特徵集
print("建立特徵...")
features = mlf.combine(
    {
        # 基本面特徵
        'pb': data.get('price_earning_ratio:股價淨值比'),
        'pe': data.get('price_earning_ratio:本益比'),
        'roe': data.get('fundamental_features:ROE稅後'),
        # 技術指標（使用少量指標避免過擬合）
        'technical': mlf.ta(mlf.ta_names(n=1)[:20]),  # 只取前 20 個
    },
    resample='W',
)

# 步驟 2：生成標籤
print("生成標籤...")
label = mll.return_percentage(features.index, resample='W', period=1)

# 步驟 3：切分訓練/測試集
print("切分資料...")
is_train = features.index.get_level_values('datetime') < '2023-01-01'
X_train, y_train = features[is_train], label[is_train]
X_test = features[~is_train]

# 步驟 4：訓練模型
print("訓練模型...")
model = q.LGBModel()
model.fit(X_train, y_train)

# 步驟 5：預測
print("生成預測...")
pred = model.predict(X_test)

# 步驟 6：轉換為交易訊號
print("生成交易訊號...")
position = pred.is_largest(30)  # 買入預測報酬率最高的 30 檔

# 步驟 7：回測
print("執行回測...")
report = sim(position, resample='W')
report.display()

# 步驟 8：分析特徵重要性（如果是樹模型）
if hasattr(model, 'feature_importances_'):
    import pandas as pd

    feature_importance = pd.Series(
        model.feature_importances_, index=features.columns.get_level_values(1).unique()
    ).sort_values(ascending=False)

    print("\n前 10 重要特徵:")
    print(feature_importance.head(10))

from finlab import data
from finlab.ml import feature as mlf

close = data.get('price:收盤價')
pb = data.get('price_earning_ratio:股價淨值比')
pe = data.get('price_earning_ratio:本益比')

# 範例 1：合併基本面特徵
features = mlf.combine(
    {
        'pb': pb,
        'pe': pe,
        'roe': data.get('fundamental_features:ROE稅後'),
    },
    resample='W',
)

# 範例 2：合併技術指標
indicators = [
    'talib.RSI__real__timeperiod__14__',
    'talib.MACD__macd__fastperiod__12__slowperiod__26__signalperiod__9__',
]
technical = mlf.ta(indicators)
features = mlf.combine({'talib': technical}, resample='D')

# 範例 3：混合多種特徵
features = mlf.combine(
    {
        'fundamental': mlf.combine({'pb': pb, 'pe': pe}),
        'technical': technical,
        'custom': close / close.average(20),  # 股價相對 20 日均線
    },
    resample='W',
)

import pandas as pd
from finlab import data
from finlab.ml import feature as mlf, label as mll

rsi = data.indicator('RSI')
calendar = rsi.index
weekly = pd.DatetimeIndex(calendar.to_series().resample('W').last().dropna())
features = mlf.combine({'rsi': rsi}, resample=weekly)
labels = mll.return_percentage(features.index, resample=weekly, period=2)

from finlab.ml import feature as mlf

# 計算特定指標
indicators = mlf.ta(
    [
        'talib.RSI__real__timeperiod__14__',
        'talib.MACD__macd__fastperiod__12__slowperiod__26__signalperiod__9__',
        'talib.BBANDS__upperband__timeperiod__20__nbdevup__2.0__nbdevdn__2.0__matype__0__',
    ],
    resample='W',
)

# 指定指標的隨機參數組合
names = [
    name
    for name in mlf.ta_names(n=3)
    if name.startswith(('talib.RSI__', 'talib.MACD__', 'talib.ATR__'))
]
random_indicators = mlf.ta(names, resample='W')

from finlab.ml import feature as mlf

# 生成 10 種隨機參數組合的所有 TA-Lib 指標
indicator_names = mlf.ta_names(n=10)
print(f"共 {len(indicator_names)} 個指標")

# 查看範例
for name in indicator_names[:5]:
    print(name)
# 輸出（參數隨機抽取；沒有參數的指標只出現一次）:
# talib.HT_DCPERIOD__real__
# talib.HT_DCPHASE__real__
# talib.HT_PHASOR__inphase__
# talib.HT_PHASOR__quadrature__
# talib.HT_SINE__sine__

from finlab import data
from finlab.ml import feature as mlf, label as mll

features = mlf.combine({'pb': data.get('price_earning_ratio:股價淨值比')}, resample='W')

# 生成標籤：預測未來 1 週報酬率
label = mll.return_percentage(features.index, resample='W', period=1)

# 生成標籤：預測未來 4 週報酬率
label_4w = mll.return_percentage(features.index, resample='W', period=4)

from finlab import data
from finlab.ml import feature as mlf, label as mll

# 建立日頻特徵
features = mlf.combine({'rsi': data.indicator('RSI')}, resample='D')

# 生成標籤：下一個交易日開盤買、收盤賣的報酬率
label = mll.daytrading_percentage(features.index)

from finlab import data
from finlab.ml import feature as mlf, label as mll

features = mlf.combine({'rsi': data.indicator('RSI')}, resample='D')

# 計算未來 N 期的最大跌幅
mae_label = mll.maximum_adverse_excursion(features.index, period=5)

# 可用於訓練風險預測模型
# 負值越大表示風險越高

from finlab import data
from finlab.ml import feature as mlf, label as mll
import finlab.ml.qlib as q

# 1. 準備特徵
features = mlf.combine(
    {
        'pb': data.get('price_earning_ratio:股價淨值比'),
        'pe': data.get('price_earning_ratio:本益比'),
    },
    resample='W',
)

# 2. 準備標籤
label = mll.return_percentage(features.index, resample='W', period=1)

# 3. 切分訓練/測試集
is_train = features.index.get_level_values('datetime') < '2020-01-01'
X_train, y_train = features[is_train], label[is_train]
X_test = features[~is_train]

# 4. 建立並訓練模型
model = q.XGBModel()  # 可選: q.LGBModel(), q.CatBoostModel(), q.LinearModel()
model.fit(X_train, y_train)

# 5. 預測
y_pred = model.predict(X_test)