Fix/warning if revlog_history.tsv is empty (#330)

fsrs4anki_optimizer.ipynb

@@ -5,9 +5,9 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "# FSRS4Anki v3.25.8 Optimizer\n",
+        "# FSRS4Anki v3.25.9 Optimizer\n",
         "\n",
-        "[![open in colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/open-spaced-repetition/fsrs4anki/blob/v3.25.8/fsrs4anki_optimizer.ipynb)\n",
+        "[![open in colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/open-spaced-repetition/fsrs4anki/blob/v3.25.9/fsrs4anki_optimizer.ipynb)\n",
         "\n",
         "↑ Click the above button to open the optimizer on Google Colab.\n",
         "\n",
@@ -103,7 +103,7 @@
         }
       ],
       "source": [
-        "%pip install -q fsrs4anki_optimizer==3.25.8\n",
+        "%pip install -q fsrs4anki_optimizer==3.25.9\n",
         "# for local development\n",
         "# import os\n",
         "# import sys\n",

package/fsrs4anki_optimizer/fsrs4anki_optimizer.py

@@ -108,7 +108,7 @@ def lineToTensor(line: str) -> Tensor:
 
 class RevlogDataset(Dataset):
     def __init__(self, dataframe: pd.DataFrame):
-        if len(dataframe) == 0:
+        if dataframe.empty:
             raise ValueError('Training data is inadequate.')
         padded = pad_sequence(dataframe['tensor'].to_list(), batch_first=True, padding_value=0)
         self.x_train = padded.int()
@@ -483,6 +483,8 @@ def train(self, lr: float = 4e-2, n_epoch: int = 3, n_splits: int = 3, batch_siz
         """Step 4"""
         self.dataset = pd.read_csv("./revlog_history.tsv", sep='\t', index_col=None, dtype={'r_history': str ,'t_history': str} )
         self.dataset = self.dataset[(self.dataset['i'] > 1) & (self.dataset['delta_t'] > 0) & (self.dataset['t_history'].str.count(',0') == 0)]
+        if self.dataset.empty:
+            raise ValueError('Training data is inadequate.')
         self.dataset['tensor'] = self.dataset.progress_apply(lambda x: lineToTensor(list(zip([x['t_history']], [x['r_history']]))[0]), axis=1)
         self.dataset['group'] = self.dataset['r_history'] + self.dataset['t_history']
         print("Tensorized!")

package/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "fsrs4anki_optimizer"
-version = "3.25.8"
+version = "3.25.9"
 readme = "README.md"
 dependencies = [
     "matplotlib>=3.7.0",