Change on cross validation

This commit is contained in:
AntoninDurousseau
2025-06-03 13:10:06 +02:00
parent dfc0cd48c6
commit 044f875728

View File

@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
"execution_count": 26,
"execution_count": 35,
"id": "4e6f6cb1",
"metadata": {},
"outputs": [],
@@ -20,7 +20,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 36,
"id": "4dd5223b",
"metadata": {},
"outputs": [],
@@ -31,7 +31,7 @@
},
{
"cell_type": "code",
"execution_count": 29,
"execution_count": 37,
"id": "c1ab7ec9",
"metadata": {},
"outputs": [
@@ -89,7 +89,7 @@
},
{
"cell_type": "code",
"execution_count": 30,
"execution_count": 38,
"id": "754dce9b",
"metadata": {},
"outputs": [
@@ -117,7 +117,7 @@
},
{
"cell_type": "code",
"execution_count": 31,
"execution_count": 43,
"id": "feb42adf",
"metadata": {},
"outputs": [
@@ -125,19 +125,17 @@
"name": "stdout",
"output_type": "stream",
"text": [
"The best k for k-NN is k = 5\n"
"The best k for k-NN is k = 6\n"
]
}
],
"source": [
"k_scores = []\n",
"K_list = np.arange(1, X.shape[0] // 4) # concidering 1/4 of the samples as neaighbors is large enough for k-NN to don't overfit\n",
"K_list = np.arange(1, X.shape[0] // 4 ) # concidering 1/4 of the samples as neaighbors is large enough for k-NN to don't overfit\n",
"\n",
"for k in K_list:\n",
" knn = KNeighborsClassifier(n_neighbors=k)\n",
" score_acc = cross_val_score(knn, X, y, cv=5, scoring='accuracy')\n",
" score_f1 = cross_val_score(knn, X, y, cv=5, scoring='f1')\n",
" score = (score_acc + score_f1) / 2 \n",
" score = cross_val_score(knn, X, y, cv=5, scoring='accuracy')\n",
" k_scores.append(score.mean())\n",
"\n",
"k_scores = np.array(k_scores)\n",
@@ -147,7 +145,7 @@
},
{
"cell_type": "code",
"execution_count": 34,
"execution_count": 40,
"id": "fa8a7166",
"metadata": {},
"outputs": [