Add files via upload

knn.ipynb

@@ -62,7 +62,7 @@
     "  \n",
     "# data (as pandas dataframes) \n",
     "X = data.drop(columns='Classification')\n",
-    "y = data['Classification'].map({2: 1, 1: 0}) # Map 2 to 1 and 1 to 0, 1 = pacient healthy, 0 = pacient sick\n",
+    "y = data['Classification'].map({2: 1, 1: 0}) # Map 2 to 1 and 1 to 0, 1 = sick patient, 0 = healthy patient\n",
     "  \n",
     "print(\"Dataset shape:\", data.shape)\n",
     "print(data.head())"
@@ -81,7 +81,7 @@
    "id": "082c143b",
    "metadata": {},
    "source": [
-    "### 1) No curse of dimention "
+    "### 1) No curse of dimension "
    ]
   },
   {
@@ -111,7 +111,7 @@
    "id": "01bb817a",
    "metadata": {},
    "source": [
-    "Then d is small enough to insure that we are not in the curse of dimention"
+    "Then d is small enough to ensure that we do not suffer under the curse of dimension"
    ]
   },
   {
@@ -138,7 +138,7 @@
    ],
    "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 )  # considering 1/4 of the samples as neighbors is large enough for k-NN not to overfit\n",
     "\n",
     "\n",
     "for k in K_list:\n",
@@ -167,7 +167,7 @@
    "id": "9f74eaee",
    "metadata": {},
    "source": [
-    "### 3) train-test split and rescaling of the feature "
+    "### 3) train-test split and rescaling of the features"
    ]
   },
   {
@@ -205,7 +205,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 10,
    "id": "064a5aa7",
    "metadata": {},
    "outputs": [
@@ -250,7 +250,7 @@
     }
    ],
    "source": [
-    "knn = KNeighborsClassifier(n_neighbors=k_optimal) # using the best k founded earlier\n",
+    "knn = KNeighborsClassifier(n_neighbors=k_optimal) # using the best k found earlier\n",
     "knn.fit(X_train_scaled, y_train)\n",
     "\n",
     "y_pred = knn.predict(X_test_scaled)\n",
@@ -267,7 +267,7 @@
     "print(\"Classification Report:\\n\", class_report)\n",
     "\n",
     "# Plotting the confusion matrix\n",
-    "cm = confusion_matrix(y_test, y_pred)\n",
+    "cm = confusion_matrix(y_true=y_test,y_pred= y_pred)\n",
     "plt.figure(figsize=(8, 6))\n",
     "plt.imshow(cm, interpolation='nearest', cmap=plt.cm.Blues)\n",
     "plt.title('Confusion Matrix')\n",
@@ -321,7 +321,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.9.6"
   }
  },
  "nbformat": 4,