Merge pull request #15 from PaskalSunari/Ml-CodeSpace-1

claffification 1 finished

4-Classification/2-Classifiers-1/notebook.ipynb

@@ -16,7 +16,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -214,7 +214,7 @@
        "[5 rows x 382 columns]"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 1,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -227,7 +227,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -240,7 +240,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -254,7 +254,7 @@
        "Name: cuisine, dtype: object"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -266,7 +266,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -464,7 +464,7 @@
        "[5 rows x 380 columns]"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -476,7 +476,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -485,7 +485,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -513,7 +513,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -529,6 +529,121 @@
     "print(f'ingredients: {X_test.iloc[50][X_test.iloc[50]!=0].keys()}')\n",
     "print(f'cuisine: {y_test.iloc[50]}')"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/workspaces/ML-For-Beginners/.venv/lib/python3.11/site-packages/sklearn/utils/validation.py:2739: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>0</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>thai</th>\n",
+       "      <td>0.839568</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>japanese</th>\n",
+       "      <td>0.134624</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>chinese</th>\n",
+       "      <td>0.014531</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>korean</th>\n",
+       "      <td>0.008383</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>indian</th>\n",
+       "      <td>0.002894</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                 0\n",
+       "thai      0.839568\n",
+       "japanese  0.134624\n",
+       "chinese   0.014531\n",
+       "korean    0.008383\n",
+       "indian    0.002894"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test= X_test.iloc[50].values.reshape(-1, 1).T\n",
+    "proba = model.predict_proba(test)\n",
+    "classes = model.classes_\n",
+    "resultdf = pd.DataFrame(data=proba, columns=classes)\n",
+    "\n",
+    "topPrediction = resultdf.T.sort_values(by=[0], ascending = [False])\n",
+    "topPrediction.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "     chinese       0.69      0.69      0.69       236\n",
+      "      indian       0.91      0.91      0.91       245\n",
+      "    japanese       0.73      0.72      0.73       231\n",
+      "      korean       0.81      0.76      0.78       242\n",
+      "        thai       0.78      0.84      0.81       245\n",
+      "\n",
+      "    accuracy                           0.79      1199\n",
+      "   macro avg       0.79      0.78      0.78      1199\n",
+      "weighted avg       0.79      0.79      0.79      1199\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "y_pred = model.predict(X_test)\n",
+    "print(classification_report(y_test, y_pred))"
+   ]
   }
  ],
  "metadata": {