Issue 115

ctgan/data_sampler.py

@@ -41,7 +41,7 @@ def is_discrete_column(column_info):
         # Prepare an interval matrix for efficiently sample conditional vector
         max_category = max(
             [column_info[0].dim for column_info in output_info
-             if is_discrete_column(column_info)])
+             if is_discrete_column(column_info)], default=0)
 
         self._discrete_column_cond_st = np.zeros(n_discrete_columns, dtype='int32')
         self._discrete_column_n_category = np.zeros(
@@ -133,7 +133,7 @@ def sample_data(self, n, col, opt):
             n rows of matrix data.
         """
         if col is None:
-            idx = np.random.randint(len(self._data), n)
+            idx = np.random.randint(len(self._data), size=n)
             return self._data[idx]
 
         idx = []

tests/integration/test_ctgan.py

@@ -15,6 +15,21 @@
 from ctgan.synthesizers.ctgan import CTGANSynthesizer
 
 
+def test_ctgan_no_categoricals():
+    data = pd.DataFrame({
+        'continuous': np.random.random(1000)
+    })
+
+    ctgan = CTGANSynthesizer(epochs=1)
+    ctgan.fit(data, [])
+
+    sampled = ctgan.sample(100)
+
+    assert sampled.shape == (100, 1)
+    assert isinstance(sampled, pd.DataFrame)
+    assert set(sampled.columns) == {'continuous'}
+
+
 def test_ctgan_dataframe():
     data = pd.DataFrame({
         'continuous': np.random.random(100),