ENH: Add lib.random_ohlc_data(frac=)

Author: kernc

backtesting/lib.py

@@ -287,12 +287,16 @@ def wrap_func(resampled, *args, **kwargs):
     return array
 
 
-def random_ohlc_data(example_data: pd.DataFrame, random_state: int = None) -> pd.DataFrame:
+def random_ohlc_data(example_data: pd.DataFrame, *,
+                     frac=1., random_state: int = None) -> pd.DataFrame:
     """
     OHLC data generator. The generated OHLC data has basic
     [descriptive statistics](https://en.wikipedia.org/wiki/Descriptive_statistics)
     similar to the provided `example_data`.
 
+    `frac` is a fraction of data to sample (with replacement). Values greater
+    than 1 result in oversampling.
+
     Such random data can be effectively used for stress testing trading
     strategy robustness, Monte Carlo simulations, significance testing, etc.
 
@@ -304,7 +308,7 @@ def random_ohlc_data(example_data: pd.DataFrame, random_state: int = None) -> pd
     ...
     """
     def shuffle(x):
-        return x.sample(frac=1, random_state=random_state)
+        return x.sample(frac=frac, replace=frac > 1, random_state=random_state)
 
     if len(example_data.columns & {'Open', 'High', 'Low', 'Close'}) != 4:
         raise ValueError("`data` must be a pandas.DataFrame with columns "

backtesting/test/_test.py

@@ -729,7 +729,7 @@ def test_plot_heatmaps(self):
             time.sleep(5)
 
     def test_random_ohlc_data(self):
-        generator = random_ohlc_data(GOOG)
+        generator = random_ohlc_data(GOOG, frac=1)
         new_data = next(generator)
         self.assertEqual(list(new_data.index), list(GOOG.index))
         self.assertEqual(new_data.shape, GOOG.shape)