From 13495af3f034974610e381f518d0488b57cadb9d Mon Sep 17 00:00:00 2001
From: David Rotermund <54365609+davrot@users.noreply.github.com>
Date: Fri, 26 Jan 2024 15:10:40 +0100
Subject: [PATCH] Update README.md

Signed-off-by: David Rotermund <54365609+davrot@users.noreply.github.com>
---
 numpy/roc/README.md | 81 ++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 80 insertions(+), 1 deletion(-)

diff --git a/numpy/roc/README.md b/numpy/roc/README.md
index 3932296..612d77d 100644
--- a/numpy/roc/README.md
+++ b/numpy/roc/README.md
@@ -76,9 +76,88 @@ plt.show()
 ```
 ![Image2](image2.png)
 
-
+## How to create an estimate from ROC
 
 ```python
+import numpy as np
+import matplotlib.pyplot as plt
+
+rng = np.random.default_rng(1)
+
+a_x = rng.normal(1.5, 1.0, size=(5000))
+b_x = rng.normal(0.0, 1.0, size=(5000))
+
+data_data = np.concatenate([a_x, b_x])
+data_class = np.concatenate([np.full_like(a_x, -1), np.full_like(b_x, +1)])
+idx = np.argsort(data_data)
+
+data_data = data_data[idx]
+data_class = data_class[idx]
+
+data_cumsum = np.cumsum(data_class)
+border = np.argmax(data_cumsum)
+
+variant_a = (data_class[:border] == -1).sum() + (data_class[border:] == +1).sum()
+
+variant_b = (data_class[:border] == +1).sum() + (data_class[border:] == -1).sum()
+
+estimate_a = np.concatenate(
+    (np.full_like(data_class[:border], -1), np.full_like(data_class[border:], +1))
+)
+
+estimate_b = np.concatenate(
+    (np.full_like(data_class[:border], +1), np.full_like(data_class[border:], -1))
+)
+
+if variant_a > variant_b:
+    print("We will use: Estimate A")
+    estimate = estimate_a
+
+else:
+    print("We will use: Estimate B")
+    estimate = estimate_b
+
+performance = 100.0 * (data_class == estimate).sum() / data_class.shape[0]
+print(f"Performance: {performance}% correct")
+
+plt.subplot(3, 1, 1)
+idx_a = np.where(data_class == -1)[0]
+idx_b = np.where(data_class == +1)[0]
+idx = np.arange(0, data_class.shape[0])
+
+plt.plot(data_data[idx_a], np.zeros_like(idx_a), "c*")
+plt.plot(data_data[idx_b], np.zeros_like(idx_b), "m.")
+plt.yticks([])
+plt.title("Data")
+
+plt.subplot(3, 1, 2)
+idx_a = np.where(estimate_a == -1)[0]
+idx_b = np.where(estimate_a == +1)[0]
+idx = np.arange(0, estimate_a.shape[0])
+
+plt.plot(data_data[idx_a], np.zeros_like(idx_a), "c*")
+plt.plot(data_data[idx_b], np.zeros_like(idx_b), "m.")
+plt.yticks([])
+plt.title("Estimate A")
+
+plt.subplot(3, 1, 3)
+idx_a = np.where(estimate_b == -1)[0]
+idx_b = np.where(estimate_b == +1)[0]
+idx = np.arange(0, estimate_b.shape[0])
+
+plt.plot(data_data[idx_a], np.zeros_like(idx_a), "c*")
+plt.plot(data_data[idx_b], np.zeros_like(idx_b), "m.")
+plt.yticks([])
+
+plt.title("Estimate B")
+plt.xlabel("Data Value")
+plt.show()
 ```
 
+Output:
+```python
+We will use: Estimate B
+Performance: 77.3% correct
+```
 
+![Image3](image3.png)