🧪 Add tests for create_labels_multi_bar

Implement tests for `create_labels_multi_bar` within `features/labeling_schemes.py` to ensure it accurately generates multi-bar classification labels according to future return horizons and thresholds.

These tests improve overall codebase coverage and reliability by correctly covering boundaries and trailing returns.

Co-authored-by: maghdam <63883156+maghdam@users.noreply.github.com>

tests/test_labeling_schemes.py

@@ -1,67 +1,64 @@
 import pandas as pd
 import numpy as np
-import pytest
 from features.labeling_schemes import create_labels_multi_bar
 
 def test_create_labels_multi_bar():
-    """
-    Test create_labels_multi_bar correctly assigns labels based on future returns.
-    """
-    # Create a simple dummy dataframe
-    # We want future returns over horizon=2 to be:
-    # index 0: (10.5 / 10.0) - 1 = 0.05 (should be +1, since >= 0.05 is not met if threshold=0.06, wait let's use exact)
-
+    # Toy dataframe with close prices
     df = pd.DataFrame({
-        "close": [100.0, 100.0, 105.0, 95.0, 100.0, 100.0]
+        "close": [100.0, 102.0, 99.0, 99.0, 105.0]
     })
 
-    # Let's set horizon=2, threshold=0.04
-    # future returns for horizon=2:
-    # i=0: (105.0 - 100.0)/100.0 = 0.05 => >= 0.04 => 1
-    # i=1: (95.0 - 100.0)/100.0 = -0.05 => <= -0.04 => -1
-    # i=2: (100.0 - 105.0)/105.0 = -0.0476 => <= -0.04 => -1
-    # i=3: (100.0 - 95.0)/95.0 = 0.0526 => >= 0.04 => 1
-    # i=4: NaN
-    # i=5: NaN
+    # horizon = 1, threshold = 0.01
+    # row 0: close = 100, future = 102, return = 0.02 >= 0.01 -> label = 1
+    # row 1: close = 102, future = 99, return = -3/102 = -0.0294 <= -0.01 -> label = -1
+    # row 2: close = 99, future = 99, return = 0.00 -> label = 0
+    # row 3: close = 99, future = 105, return = 6/99 = 0.0606 >= 0.01 -> label = 1
+    # row 4: close = 105, future = NaN
 
-    labeled_df = create_labels_multi_bar(df, horizon=2, threshold=0.04)
+    res = create_labels_multi_bar(df, horizon=1, threshold=0.01)
 
-    # Check that df wasn't modified in place
-    assert "multi_bar_label" not in df.columns
+    # Should have 4 rows because the last row is dropped due to NaN future return
+    assert len(res) == 4
 
-    # Ensure correct columns exist in result
-    assert "future_return_h" in labeled_df.columns
-    assert "multi_bar_label" in labeled_df.columns
+    expected_labels = [1, -1, 0, 1]
+    np.testing.assert_array_equal(res["multi_bar_label"].values, expected_labels)
 
-    # Since the original drops NaN, it should have 4 rows
-    assert len(labeled_df) == 4
+    # Check returns
+    expected_returns = [0.02, -3/102, 0.0, 6/99]
+    np.testing.assert_array_almost_equal(res["future_return_h"].values, expected_returns)
 
-    # Check calculated future returns roughly match expected
-    expected_returns = [0.05, -0.05, -0.047619047619047616, 0.052631578947368474]
-    np.testing.assert_allclose(labeled_df["future_return_h"].values, expected_returns, rtol=1e-5)
+def test_create_labels_multi_bar_custom_horizon():
+    # Test with horizon=2, threshold=0.05
+    df = pd.DataFrame({
+        "close": [100.0, 101.0, 105.0, 90.0, 95.0, 100.0]
+    })
 
-    # Check assigned labels
+    # horizon = 2
+    # row 0: close 100, future 105 (idx 2), return 0.05 >= 0.05 -> 1
+    # row 1: close 101, future 90 (idx 3), return -11/101 = -0.1089 <= -0.05 -> -1
+    # row 2: close 105, future 95 (idx 4), return -10/105 = -0.0952 <= -0.05 -> -1
+    # row 3: close 90,  future 100 (idx 5), return 10/90 = 0.1111 >= 0.05 -> 1
+    # row 4: NaN
+    # row 5: NaN
+
+    res = create_labels_multi_bar(df, horizon=2, threshold=0.05)
+
+    assert len(res) == 4
     expected_labels = [1, -1, -1, 1]
-    np.testing.assert_array_equal(labeled_df["multi_bar_label"].values, expected_labels)
+    np.testing.assert_array_equal(res["multi_bar_label"].values, expected_labels)
 
-
-def test_create_labels_multi_bar_neutral():
-    """
-    Test create_labels_multi_bar handles neutral labels correctly (returns inside threshold).
-    """
+def test_create_labels_multi_bar_exact_threshold():
+    # Check boundary condition where return is exactly the threshold
     df = pd.DataFrame({
-        "close": [100.0, 101.0, 102.0, 99.0, 100.0]
+        "close": [100.0, 105.0, 95.0]
     })
 
-    # Let's set horizon=1, threshold=0.02
-    # future returns for horizon=1:
-    # i=0: (101 - 100)/100 = 0.01 (neutral -> 0)
-    # i=1: (102 - 101)/101 = 0.0099 (neutral -> 0)
-    # i=2: (99 - 102)/102 = -0.0294 (down -> -1)
-    # i=3: (100 - 99)/99 = 0.0101 (neutral -> 0)
+    # threshold = 0.05, horizon = 1
+    # row 0: return 0.05 -> 1
+    # row 1: return -10/105 = -0.0952 -> -1
+    res = create_labels_multi_bar(df, horizon=1, threshold=0.05)
+    assert res.iloc[0]["multi_bar_label"] == 1
 
-    labeled_df = create_labels_multi_bar(df, horizon=1, threshold=0.02)
-
-    assert len(labeled_df) == 4
-    expected_labels = [0, 0, -1, 0]
-    np.testing.assert_array_equal(labeled_df["multi_bar_label"].values, expected_labels)
+    res = create_labels_multi_bar(df, horizon=1, threshold=0.1)
+    # return is 0.05, which is < 0.1 and > -0.1
+    assert res.iloc[0]["multi_bar_label"] == 0