为回溯测试和机器学习指定测试行。

Question

我想用一个机器学习来预测一个资产的价格走势.到目前为止,我得到了数据和结果.现在我想回测这个模型.前提很简单:只要预测值是1就买入,然后持有. 我想应用预测模型，从下往上迭代测试行，直到指定的数字，检查预测的输出是否符合相应的标签（这里的标签是-1,1），然后进行一些计算。

这里是代码。

def backtest():
    x = df[['open', 'high', 'low', 'close', 'vol']]
    y = df['label']
    z = np.array(df['log_ret'].values)

test_size = 366
rf = RandomForestClassifier(n_estimators = 100)
rf.fit(x[:-test_size],y[:-test_size])

invest_amount = 1000
trade_qty = 0
correct_count = 0

for i in range(1, test_size):
    if rf.predict(x[-i])[0] == y[-i]:
    correct_count += 1

if rf.predict(x[-i])[0] == 1:
    invest_return = invest_amount + (invest_amount * (z[-i]/100))
    trade_qty += 1


print('accuracy:', (correct_count/test_size)*100)
print('total trades:', trade_qty)
print('profits:', invest_return)

backtest()

到目前为止，我还卡在这上面。

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
~\anaconda3\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
   2645             try:
-> 2646                 return self._engine.get_loc(key)
   2647             except KeyError:

pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

KeyError: -1

During handling of the above exception, another exception occurred:

KeyError                                  Traceback (most recent call last)
<ipython-input-29-feab89792f26> in <module>
     22 
     23 for i in range(1, test_size):
---> 24     if rf.predict(x[-i])[0] == y[-i]:
     25         correct_count += 1
     26 

~\anaconda3\lib\site-packages\pandas\core\frame.py in __getitem__(self, key)
   2798             if self.columns.nlevels > 1:
   2799                 return self._getitem_multilevel(key)
-> 2800             indexer = self.columns.get_loc(key)
   2801             if is_integer(indexer):
   2802                 indexer = [indexer]

~\anaconda3\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
   2646                 return self._engine.get_loc(key)
   2647             except KeyError:
-> 2648                 return self._engine.get_loc(self._maybe_cast_indexer(key))
   2649         indexer = self.get_indexer([key], method=method, tolerance=tolerance)
   2650         if indexer.ndim > 1 or indexer.size > 1:

pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

KeyError: -1

Answer 1

下面这段代码，解决了这个问题，做了一些修改。

def backtest():
    x = df[['open', 'high', 'low', 'close', 'vol']]
    y = df['label']
    z = np.array(df['log_ret'].values)

    test_size = 366
    rf = RandomForestClassifier(n_estimators = 100)
    rf.fit(x[:-test_size],y[:-test_size])

    invest_amount = 1000
    trade_qty = 0
    correct_count = 0

    for i in range(1, test_size)[::-1]:
        if rf.predict(x[x.index == i])[0] == y[i]:
            correct_count += 1

        if rf.predict(x[x.index == i])[0] == 1:
            invest_return = invest_amount + (invest_amount * (z[i]/100))
            trade_qty += 1

    print('accuracy:', (correct_count/test_size)*100)
    print('total trades:', trade_qty)
    print('profits:', invest_return)

backtest()

解释一下这些修改

1. 通过过滤索引来访问数据框架行

   x[x.index ==
   i]

   ;
2. 修改适应性较差的后退幅度的负指数。range(1, test_size)[::-1];

生成一个测试用例。

import numpy as np
import pandas as pd
from sklearn.ensemble import RandomForestClassifier

data = {'open': np.random.rand(1000), 
        'high': np.random.rand(1000), 
        'low': np.random.rand(1000), 
        'close': np.random.rand(1000), 
        'vol': np.random.rand(1000),
        'log_ret': np.random.rand(1000),
        'label': np.random.choice([-1,1], 1000)}

df = pd.DataFrame(data)

这将产生以下结果。

>> backtest()
accuracy: 99.72677595628416
total trades: 181
profits: 1006.8351193358026