Test_Pedro

Author: pericotronic

test/test_Chi.py

@@ -0,0 +1,28 @@
+
+
+
+def test_chi_squared_test():
+    from Chi import chi_squared_test
+    import pandas as pd
+    import scipy.stats as stats
+    import pytest
+    import numpy as np
+    # Create a sample DataFrame
+    data = {'feature': ['A', 'B', 'C', 'D', 'E'],
+            'target': np.random.randint(2, size=5)}
+    df = pd.DataFrame(data)
+
+    # Perform the chi-squared test
+    chi2, p = chi_squared_test(df, 'feature', 'target')
+
+    # Verify the results
+    assert isinstance(chi2, float)
+    assert isinstance(p, float)
+    assert chi2 == pytest.approx(5.0, rel=1e-3)
+    assert p == pytest.approx(0.287, rel=0.2872974951836458)
+
+
+    
+
+
+

test/test_balance.py

@@ -0,0 +1,22 @@
+
+from balance import balance_binary_target
+
+import pytest
+import pandas as pd
+import numpy as np
+from imblearn.over_sampling import SMOTE
+import math
+
+def test_balance_binary_target_min_ratio():
+    # Create a sample DataFrame with a binary target variable.
+    data = {'feature1': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
+            'feature2': [10, 9, 8, 7, 6, 5, 4, 3, 2, 1],
+            'target': [1, 1, 1, 1, 0, 0, 0, 0, 0, 0]}
+    df = pd.DataFrame(data)
+
+    # Perform the oversampling using SMOTE and minority_ratio of 0.4
+    df_resampled = balance_binary_target(df, strategy='smote', minority_ratio=0.4)
+
+    # Verify that the resulting DataFrame has the expected ratio of minority samples
+    ratio = df_resampled['target'].mean()
+    assert math.isclose(ratio, 0.4, rel_tol=1)

test/test_smoth.py

@@ -0,0 +1,18 @@
+from smoth import _exponential_smooth
+import pandas as pd
+def test_exponential_smooth():
+    # Define a sample dataset to test with
+    data = pd.Series([1, 3, 4, 6, 7, 8, 9, 10])
+
+    # Apply the exponential smoothing function with alpha=0.3
+    smoothed_data = _exponential_smooth(data, alpha=0.65)
+
+    # Check that the length of the smoothed data is the same as the original data
+    assert len(smoothed_data) == len(data)
+
+    # Check that the first and last values of the smoothed data are the same as the original data
+    assert smoothed_data.iloc[0] == data.iloc[0]
+    assert smoothed_data.iloc[-1] == data.iloc[-1]
+
+    # Check that the smoothed data is less 'rigid' than the original data
+    assert smoothed_data.diff().var() < data.diff().var()