feat(math): do not normalize chi_square value.

onekey-sec · Oct 27, 2024 · 6bf4da7 · 6bf4da7
1 parent 7adbdf9
commit 6bf4da7
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 9 deletions.
diff --git a/src/math_tools.rs b/src/math_tools.rs
@@ -49,9 +49,7 @@ pub fn chi_square(data: &[u8]) -> f64 {
         })
         .sum();
 
-    // Normalize chi-square by the maximum possible value
-    let chi_square_max = (num_bins as f64) * (data.len() as f64 - 1.0);
-    chi_square / chi_square_max
+    chi_square
 }
 /// Calculates Chi Square of data
 #[pyfunction(name = "chi_square")]
@@ -105,7 +103,7 @@ mod tests {
 
             // Expect chi-square to be relatively low for uniform random data
             assert!(
-                chi_square_value < 0.2,
+                chi_square_value < 300.0,
                 "Chi-square for random data was too high: {}",
                 chi_square_value
             );
@@ -117,9 +115,8 @@ mod tests {
             let non_random_data = vec![42u8; 4096];
             let chi_square_value = chi_square(&non_random_data);
 
-            // Expect chi-square to be close to 1 for non-random data
             assert!(
-                chi_square_value > 0.8,
+                chi_square_value == 1044480.0,
                 "Chi-square for non-random data was too low: {}",
                 chi_square_value
             );
@@ -134,7 +131,7 @@ mod tests {
 
             // Check chi-square for partially random data
             assert!(
-                chi_square_value > 0.2 && chi_square_value < 0.8,
+                chi_square_value < 275000.0,
                 "Chi-square for partial random data was outside expected range: {}",
                 chi_square_value
             );

diff --git a/tests/test_math.py b/tests/test_math.py
@@ -25,10 +25,10 @@ def test_shannon_entropy(data: bytes, entropy: float):
     [
         pytest.param(b"", 0, id="empty"),
         pytest.param(UNIFORM_DISTRIBUTION, 0.0, id="uniform distribution"),
-        pytest.param(NON_UNIFORM_DISTRIBUTION, 1.0, id="non uniform distribution"),
+        pytest.param(NON_UNIFORM_DISTRIBUTION, 65280.0, id="non uniform distribution"),
         pytest.param(
             UNIFORM_DISTRIBUTION + NON_UNIFORM_DISTRIBUTION,
-            0.2495,
+            32640.0,
             id="partially uniform distribution",
         ),
     ],