(6) Add filter synsets by pos

6/6.1.BO_synsets_classifier.ipynb

@@ -230,6 +230,35 @@
                 "print(get_synsets(1))"
             ]
         },
+        {
+            "cell_type": "code",
+            "execution_count": 9,
+            "metadata": {},
+            "outputs": [
+                {
+                    "name": "stdout",
+                    "output_type": "stream",
+                    "text": [
+                        "My skin has been peeling, especially on my knees, elbows, and scalp. This peeling is often accompanied by a burning or stinging sensation.\n",
+                        "skin.n.01 skin.n.02 hide.n.02 skin.n.04 peel.n.02 skin.n.06 skin.v.04 peel_off.v.04 undress.v.01 particularly.r.01 specially.r.01 knee.n.01 stifle.n.01 knee.n.03 elbow.n.01 elbow.n.02 elbow.n.03 elbow.n.04 elbow.n.05 scalp.n.01 desquamation.n.01 frequently.r.01 much.r.05 often.r.03 attach_to.v.01 accompany.v.02 play_along.v.02 company.v.01 burning.n.01 burn.n.01 combustion.n.01 electrocution.n.01 burning.n.05 burning.n.06 cutting.s.01 sensation.n.01 ace.n.03 sensation.n.03 sensation.n.04 sense.n.03\n"
+                    ]
+                }
+            ],
+            "source": [
+                "def get_filtered_synsets(text_id):\n",
+                "    words = get_text_tokens(text_id)\n",
+                "    pos_tags = get_wordnet_pos(text_id)\n",
+                "    synsets = []\n",
+                "    for word, pos in pos_tags:\n",
+                "        if pos:  # Filter by WordNet-compatible POS\n",
+                "            syns = wn.synsets(word, pos=pos)\n",
+                "            if syns:\n",
+                "                synsets.extend([syn.name() for syn in syns])\n",
+                "    return \" \".join(synsets)\n",
+                "print(get_doc_by_id(1).text)\n",
+                "print(get_filtered_synsets(1))"
+            ]
+        },
         {
             "cell_type": "markdown",
             "metadata": {},
@@ -240,7 +269,7 @@
         },
         {
             "cell_type": "code",
-            "execution_count": 9,
+            "execution_count": 10,
             "metadata": {},
             "outputs": [],
             "source": [
@@ -262,7 +291,7 @@
         },
         {
             "cell_type": "code",
-            "execution_count": 10,
+            "execution_count": 11,
             "metadata": {},
             "outputs": [],
             "source": [
@@ -329,7 +358,7 @@
         },
         {
             "cell_type": "code",
-            "execution_count": 11,
+            "execution_count": 12,
             "metadata": {},
             "outputs": [],
             "source": [
@@ -350,7 +379,7 @@
         },
         {
             "cell_type": "code",
-            "execution_count": 12,
+            "execution_count": 13,
             "metadata": {},
             "outputs": [],
             "source": [
@@ -390,7 +419,7 @@
         },
         {
             "cell_type": "code",
-            "execution_count": 13,
+            "execution_count": 14,
             "metadata": {},
             "outputs": [],
             "source": [
@@ -408,7 +437,7 @@
         },
         {
             "cell_type": "code",
-            "execution_count": 14,
+            "execution_count": 15,
             "metadata": {},
             "outputs": [
                 {
@@ -430,7 +459,7 @@
         },
         {
             "cell_type": "code",
-            "execution_count": 15,
+            "execution_count": 16,
             "metadata": {},
             "outputs": [],
             "source": [
@@ -447,7 +476,7 @@
         },
         {
             "cell_type": "code",
-            "execution_count": 16,
+            "execution_count": 17,
             "metadata": {},
             "outputs": [
                 {
@@ -484,7 +513,7 @@
         },
         {
             "cell_type": "code",
-            "execution_count": 17,
+            "execution_count": 18,
             "metadata": {},
             "outputs": [
                 {
@@ -521,7 +550,7 @@
         },
         {
             "cell_type": "code",
-            "execution_count": 18,
+            "execution_count": 19,
             "metadata": {},
             "outputs": [
                 {
@@ -569,6 +598,122 @@
                 "model = MultinomialNB(alpha=0.01)\n",
                 "evaluate_model(X_train, X_test, y_train, y_test, chi2, 1500, model)"
             ]
+        },
+        {
+            "cell_type": "markdown",
+            "metadata": {},
+            "source": [
+                "# ***Use synsets as Features with filtering by POS***\n"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 20,
+            "metadata": {},
+            "outputs": [
+                {
+                    "name": "stdout",
+                    "output_type": "stream",
+                    "text": [
+                        "Train set shape after features extraction: (4320, 3739)\n",
+                        "Test set shape after features extraction: (480, 3739)\n"
+                    ]
+                }
+            ],
+            "source": [
+                "train_df[\"features\"] = train_df[\"Id\"].apply(get_filtered_synsets)\n",
+                "test_df[\"features\"] = test_df[\"Id\"].apply(get_filtered_synsets)\n",
+                "\n",
+                "vectorizer = TfidfVectorizer()\n",
+                "X_train = vectorizer.fit_transform(train_df['features'])\n",
+                "X_test = vectorizer.transform(test_df['features'])\n",
+                "print(f\"Train set shape after features extraction: {X_train.shape}\")\n",
+                "print(f\"Test set shape after features extraction: {X_test.shape}\")\n",
+                "\n",
+                "y_train = train_df[\"label\"]\n",
+                "y_test = test_df[\"label\"]"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 21,
+            "metadata": {},
+            "outputs": [
+                {
+                    "name": "stdout",
+                    "output_type": "stream",
+                    "text": [
+                        "Closest Point 1: Number of Features = 1250, Train Accuracy = 0.9655092592592592, Test Accuracy = 0.91875\n",
+                        "Closest Point 2: Number of Features = 2000, Train Accuracy = 0.9664351851851852, Test Accuracy = 0.9166666666666666\n",
+                        "Closest Point 3: Number of Features = 500, Train Accuracy = 0.9428240740740741, Test Accuracy = 0.8916666666666667\n"
+                    ]
+                },
+                {
+                    "data": {
+                        "image/png": "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",
+                        "text/plain": [
+                            "<Figure size 1000x600 with 1 Axes>"
+                        ]
+                    },
+                    "metadata": {},
+                    "output_type": "display_data"
+                }
+            ],
+            "source": [
+                "model = MultinomialNB(alpha=0.1)\n",
+                "plot_accuracies(X_train, X_test, y_train, y_test, model, k_end=3500)"
+            ]
+        },
+        {
+            "cell_type": "code",
+            "execution_count": 22,
+            "metadata": {},
+            "outputs": [
+                {
+                    "name": "stdout",
+                    "output_type": "stream",
+                    "text": [
+                        "Train Accuracy: 0.9798611111111111\n",
+                        "Test Accuracy: 0.9208333333333333\n",
+                        "Difference: 0.05902777777777779\n",
+                        "+---------------------------------+--------------------+--------------------+------------+-----------+\n",
+                        "| Class                           | Precision          | Recall             |   F1-score | Support   |\n",
+                        "|---------------------------------+--------------------+--------------------+------------+-----------|\n",
+                        "| Acne                            | 1.0                | 0.9523809523809523 |   0.97561  | 21.0      |\n",
+                        "| Arthritis                       | 0.9090909090909091 | 1.0                |   0.952381 | 20.0      |\n",
+                        "| Bronchial Asthma                | 1.0                | 1.0                |   1        | 19.0      |\n",
+                        "| Cervical spondylosis            | 1.0                | 0.9523809523809523 |   0.97561  | 21.0      |\n",
+                        "| Chicken pox                     | 0.6086956521739131 | 0.9333333333333333 |   0.736842 | 15.0      |\n",
+                        "| Common Cold                     | 0.8636363636363636 | 0.9047619047619048 |   0.883721 | 21.0      |\n",
+                        "| Dengue                          | 0.8461538461538461 | 0.5                |   0.628571 | 22.0      |\n",
+                        "| Dimorphic Hemorrhoids           | 0.95               | 1.0                |   0.974359 | 19.0      |\n",
+                        "| Fungal infection                | 1.0                | 0.9615384615384616 |   0.980392 | 26.0      |\n",
+                        "| Hypertension                    | 1.0                | 0.8333333333333334 |   0.909091 | 18.0      |\n",
+                        "| Impetigo                        | 0.92               | 1.0                |   0.958333 | 23.0      |\n",
+                        "| Jaundice                        | 1.0                | 1.0                |   1        | 22.0      |\n",
+                        "| Malaria                         | 1.0                | 1.0                |   1        | 17.0      |\n",
+                        "| Migraine                        | 1.0                | 0.9583333333333334 |   0.978723 | 24.0      |\n",
+                        "| Pneumonia                       | 0.9565217391304348 | 1.0                |   0.977778 | 22.0      |\n",
+                        "| Psoriasis                       | 0.9285714285714286 | 0.7647058823529411 |   0.83871  | 17.0      |\n",
+                        "| Typhoid                         | 0.8947368421052632 | 0.9444444444444444 |   0.918919 | 18.0      |\n",
+                        "| Varicose Veins                  | 0.9565217391304348 | 0.88               |   0.916667 | 25.0      |\n",
+                        "| allergy                         | 0.8                | 0.8                |   0.8      | 15.0      |\n",
+                        "| diabetes                        | 0.85               | 1.0                |   0.918919 | 17.0      |\n",
+                        "| drug reaction                   | 0.7894736842105263 | 0.9375             |   0.857143 | 16.0      |\n",
+                        "| gastroesophageal reflux disease | 0.9130434782608695 | 1.0                |   0.954545 | 21.0      |\n",
+                        "| peptic ulcer disease            | 1.0                | 0.8333333333333334 |   0.909091 | 18.0      |\n",
+                        "| urinary tract infection         | 0.9130434782608695 | 0.9130434782608695 |   0.913043 | 23.0      |\n",
+                        "| accuracy                        |                    |                    |   0.920833 |           |\n",
+                        "| macro avg                       | 0.9208120483635359 | 0.9195453920605775 |   0.914935 |           |\n",
+                        "| weighted avg                    | 0.927868734145336  | 0.9208333333333333 |   0.919441 |           |\n",
+                        "+---------------------------------+--------------------+--------------------+------------+-----------+\n"
+                    ]
+                }
+            ],
+            "source": [
+                "model = MultinomialNB(alpha=0.01)\n",
+                "evaluate_model(X_train, X_test, y_train, y_test, chi2, 1250, model)"
+            ]
         }
     ],
     "metadata": {