From 22ffb188ce45024f28c2a817420edbddd825bc5e Mon Sep 17 00:00:00 2001
From: Daniel Svitan <daniel.svitan.team7274dev@gmail.com>
Date: Sun, 15 Dec 2024 11:50:05 +0100
Subject: [PATCH] :zap: Adds sex owanova

---
 analyze_sex.py | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)
 create mode 100644 analyze_sex.py

diff --git a/analyze_sex.py b/analyze_sex.py
new file mode 100644
index 0000000..50c763b
--- /dev/null
+++ b/analyze_sex.py
@@ -0,0 +1,29 @@
+import numpy as np
+import scipy.stats as stats
+
+dataset = np.load("clean.npy")
+print(f"dataset shape: {dataset.shape}, analyzing column 1 (sex)")
+print("\t0 - female")
+print("\t1 - male")
+print("")
+
+
+def analyze(name: str, col: np.ndarray):
+    sex_col = dataset[:, 1]
+    F, p = stats.f_oneway(col[sex_col == 0], col[sex_col == 1])
+    print(f"F-stats for {name}: {F}")
+    print(f"p-value for {name}: {p}")
+
+    if p > 0.05:
+        print("statistically insignificant\n")
+        return
+
+    print("statistically significant")
+    tukey_results = stats.tukey_hsd(col[sex_col == 0], col[sex_col == 1])
+    print(tukey_results)
+
+
+analyze("gpa", dataset[:, 2])
+analyze("math", dataset[:, 3])
+analyze("slovak", dataset[:, 4])
+analyze("english", dataset[:, 5])