diff --git a/Airlinepassengerreferral_predicton__1_.ipynb b/Airlinepassengerreferral_predicton__1_.ipynb
index 187d0c57ec2f354790941fdd1e6e0c0c0893d8a4..d8c07394d71277eac6eb7a60e3e35134518e453e 100644
--- a/Airlinepassengerreferral_predicton__1_.ipynb
+++ b/Airlinepassengerreferral_predicton__1_.ipynb
@@ -11,7 +11,7 @@
},
{
"cell_type": "code",
- "execution_count": 115,
+ "execution_count": null,
"metadata": {
"id": "xI1O-udM7sJj"
},
@@ -52,13 +52,15 @@
{
"cell_type": "code",
"execution_count": null,
- "metadata": {},
+ "metadata": {
+ "id": "wz7IlGTZS6Nw"
+ },
"outputs": [],
"source": []
},
{
"cell_type": "code",
- "execution_count": 232,
+ "execution_count": null,
"metadata": {
"id": "5O2Is-Q772Lh"
},
@@ -78,7 +80,7 @@
},
{
"cell_type": "code",
- "execution_count": 233,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
@@ -281,7 +283,7 @@
},
{
"cell_type": "code",
- "execution_count": 234,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
@@ -477,7 +479,7 @@
},
{
"cell_type": "code",
- "execution_count": 235,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -503,7 +505,7 @@
},
{
"cell_type": "code",
- "execution_count": 236,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -533,7 +535,7 @@
},
{
"cell_type": "code",
- "execution_count": 237,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -576,7 +578,7 @@
},
{
"cell_type": "code",
- "execution_count": 238,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -622,7 +624,7 @@
},
{
"cell_type": "code",
- "execution_count": 239,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
@@ -780,7 +782,7 @@
},
{
"cell_type": "code",
- "execution_count": 240,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -823,7 +825,7 @@
},
{
"cell_type": "code",
- "execution_count": 241,
+ "execution_count": null,
"metadata": {
"id": "p5IU6nNYQwfg"
},
@@ -853,7 +855,7 @@
},
{
"cell_type": "code",
- "execution_count": 242,
+ "execution_count": null,
"metadata": {
"id": "jos6N2yhQ5yz"
},
@@ -887,7 +889,7 @@
},
{
"cell_type": "code",
- "execution_count": 127,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -914,7 +916,7 @@
},
{
"cell_type": "code",
- "execution_count": 128,
+ "execution_count": null,
"metadata": {
"id": "Gt5N46PWRZDx"
},
@@ -939,7 +941,7 @@
},
{
"cell_type": "code",
- "execution_count": 129,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -975,7 +977,7 @@
},
{
"cell_type": "code",
- "execution_count": 132,
+ "execution_count": null,
"metadata": {
"id": "Xvlrzz4VTxXw"
},
@@ -986,7 +988,7 @@
},
{
"cell_type": "code",
- "execution_count": 133,
+ "execution_count": null,
"metadata": {
"id": "mVYxrShFR0A2"
},
@@ -1009,7 +1011,7 @@
},
{
"cell_type": "code",
- "execution_count": 134,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -1054,7 +1056,7 @@
},
{
"cell_type": "code",
- "execution_count": 245,
+ "execution_count": null,
"metadata": {
"id": "NO-AVUrNSF76"
},
@@ -1065,7 +1067,7 @@
},
{
"cell_type": "code",
- "execution_count": 246,
+ "execution_count": null,
"metadata": {
"id": "bXS94JOMUu-r"
},
@@ -1076,7 +1078,7 @@
},
{
"cell_type": "code",
- "execution_count": 247,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -1115,7 +1117,7 @@
},
{
"cell_type": "code",
- "execution_count": 248,
+ "execution_count": null,
"metadata": {
"id": "6nNZ2T2VRbXO"
},
@@ -1127,7 +1129,7 @@
},
{
"cell_type": "code",
- "execution_count": 249,
+ "execution_count": null,
"metadata": {
"id": "tT04SGgTU4BI"
},
@@ -1138,7 +1140,7 @@
},
{
"cell_type": "code",
- "execution_count": 250,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -1186,7 +1188,7 @@
},
{
"cell_type": "code",
- "execution_count": 251,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -1237,7 +1239,7 @@
},
{
"cell_type": "code",
- "execution_count": 252,
+ "execution_count": null,
"metadata": {
"id": "tQN7gZhOW9nO"
},
@@ -1248,7 +1250,7 @@
},
{
"cell_type": "code",
- "execution_count": 253,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
@@ -1357,7 +1359,7 @@
},
{
"cell_type": "code",
- "execution_count": 243,
+ "execution_count": null,
"metadata": {
"id": "BxDfAo9lKAFS",
"outputId": "61329e86-0f5a-4950-d5e0-36f63afc3c6f"
@@ -1385,7 +1387,7 @@
},
{
"cell_type": "code",
- "execution_count": 145,
+ "execution_count": null,
"metadata": {
"id": "8Q68S13iKAFS",
"outputId": "30ddf4fe-9e66-4c41-a29b-b0408adda5f8"
@@ -1420,7 +1422,7 @@
},
{
"cell_type": "code",
- "execution_count": 254,
+ "execution_count": null,
"metadata": {
"id": "nJhc3zaPKAFS",
"outputId": "36c2536e-d5d7-4926-ffbb-f7f8a441841d"
@@ -1480,7 +1482,7 @@
},
{
"cell_type": "code",
- "execution_count": 148,
+ "execution_count": null,
"metadata": {
"id": "CV5g7Vp0KAFT",
"outputId": "9ae286b0-2701-4944-dd6a-1df953d3639b"
@@ -1511,7 +1513,9 @@
},
{
"cell_type": "markdown",
- "metadata": {},
+ "metadata": {
+ "id": "4CzDU-jIS6N6"
+ },
"source": [
"* So, economy class have more recomandation and first class have minimum.\n"
]
@@ -1528,7 +1532,7 @@
},
{
"cell_type": "code",
- "execution_count": 149,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
@@ -1566,7 +1570,9 @@
},
{
"cell_type": "markdown",
- "metadata": {},
+ "metadata": {
+ "id": "2bZZsNbFS6N7"
+ },
"source": [
"The bar plot shows the count of reviews categorized by traveler type (Business, Family Leisure, Solo Leisure, Couple Leisure). Here's what the graph suggests:\n",
"\n",
@@ -1600,7 +1606,7 @@
},
{
"cell_type": "code",
- "execution_count": 150,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
@@ -1637,7 +1643,9 @@
},
{
"cell_type": "markdown",
- "metadata": {},
+ "metadata": {
+ "id": "ZAYwYB7rS6N8"
+ },
"source": [
"This graph shows maximum trips by planes . British airways has the most."
]
@@ -1653,7 +1661,7 @@
},
{
"cell_type": "code",
- "execution_count": 151,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -1685,7 +1693,7 @@
},
{
"cell_type": "code",
- "execution_count": 228,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
@@ -1739,7 +1747,7 @@
},
{
"cell_type": "code",
- "execution_count": 153,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
@@ -1770,15 +1778,17 @@
},
{
"cell_type": "markdown",
- "metadata": {},
+ "metadata": {
+ "id": "H8ImLkRRS6N9"
+ },
"source": [
- "* As we have seen earlier 'British Airways' is the topmost Airline. \n",
+ "* As we have seen earlier 'British Airways' is the topmost Airline.\n",
"* 'Tunisair','Germanwings' etc are the lowest number of trips."
]
},
{
"cell_type": "code",
- "execution_count": 154,
+ "execution_count": null,
"metadata": {
"id": "rE-4TENmin-P"
},
@@ -1790,7 +1800,7 @@
},
{
"cell_type": "code",
- "execution_count": 155,
+ "execution_count": null,
"metadata": {
"id": "N5ANZppMfsKq"
},
@@ -1810,7 +1820,7 @@
},
{
"cell_type": "code",
- "execution_count": 156,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
@@ -1842,7 +1852,9 @@
},
{
"cell_type": "markdown",
- "metadata": {},
+ "metadata": {
+ "id": "weOxkRcKS6N-"
+ },
"source": [
"Correlation matrix heatmap, which illustrates the relationships between different aspects of airline services, such as seat comfort, cabin service, food and beverages, entertainment, ground service, value for money, and how these factors correlate with overall customer satisfaction and recommendation rates.\n",
"\n",
@@ -1866,7 +1878,7 @@
},
{
"cell_type": "code",
- "execution_count": 157,
+ "execution_count": null,
"metadata": {
"id": "94xRV2gKjXPo"
},
@@ -1877,7 +1889,7 @@
},
{
"cell_type": "code",
- "execution_count": 158,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -1906,7 +1918,7 @@
},
{
"cell_type": "code",
- "execution_count": 159,
+ "execution_count": null,
"metadata": {
"id": "8T6q-4DM79HM"
},
@@ -1926,7 +1938,7 @@
},
{
"cell_type": "code",
- "execution_count": 160,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
@@ -2103,7 +2115,7 @@
},
{
"cell_type": "code",
- "execution_count": 161,
+ "execution_count": null,
"metadata": {
"id": "bGT9lH07Jslz"
},
@@ -2125,7 +2137,7 @@
},
{
"cell_type": "code",
- "execution_count": 162,
+ "execution_count": null,
"metadata": {
"id": "wYLkkdmxJ6ZE"
},
@@ -2151,9 +2163,10 @@
},
{
"cell_type": "code",
- "execution_count": 163,
+ "execution_count": null,
"metadata": {
- "id": "C2WHHqiRDD_r"
+ "id": "C2WHHqiRDD_r",
+ "outputId": "eaf7cf23-ec3d-458f-9b37-7ff67593cf36"
},
"outputs": [
{
@@ -2176,7 +2189,7 @@
},
{
"cell_type": "code",
- "execution_count": 164,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -2202,7 +2215,7 @@
},
{
"cell_type": "code",
- "execution_count": 165,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -2228,7 +2241,7 @@
},
{
"cell_type": "code",
- "execution_count": 166,
+ "execution_count": null,
"metadata": {
"id": "nJ9rTJjYHvJv"
},
@@ -2240,7 +2253,7 @@
},
{
"cell_type": "code",
- "execution_count": 167,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -2267,18 +2280,14 @@
"cell_type": "code",
"execution_count": null,
"metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "FLwVC70GH528",
- "outputId": "7b8b329b-250f-4cfb-cb37-35e49bf7190e"
+ "id": "FLwVC70GH528"
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
- "execution_count": 168,
+ "execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -2324,7 +2333,7 @@
},
{
"cell_type": "code",
- "execution_count": 169,
+ "execution_count": null,
"metadata": {
"id": "kULpJOi8H8Sx"
},
@@ -2337,7 +2346,7 @@
},
{
"cell_type": "code",
- "execution_count": 170,
+ "execution_count": null,
"metadata": {
"id": "cQbmgg_ZIHD3"
},
@@ -2366,9 +2375,10 @@
},
{
"cell_type": "code",
- "execution_count": 171,
+ "execution_count": null,
"metadata": {
- "id": "ANv9nzxoh9Nk"
+ "id": "ANv9nzxoh9Nk",
+ "outputId": "f86f6d15-9cfc-435d-81a7-cc4ce1897726"
},
"outputs": [
{
@@ -2393,7 +2403,7 @@
},
{
"cell_type": "code",
- "execution_count": 172,
+ "execution_count": null,
"metadata": {
"id": "b235fa57",
"outputId": "dbeba9ca-8145-4516-a3d8-2d66e8587c5f",
@@ -2416,7 +2426,7 @@
},
{
"cell_type": "code",
- "execution_count": 173,
+ "execution_count": null,
"metadata": {
"id": "ab8bfa30",
"outputId": "f0b726bd-92fe-4f09-8acb-fc857cd35af7",
@@ -2443,7 +2453,7 @@
},
{
"cell_type": "code",
- "execution_count": 174,
+ "execution_count": null,
"metadata": {
"id": "33629d40"
},
@@ -2455,7 +2465,7 @@
},
{
"cell_type": "code",
- "execution_count": 175,
+ "execution_count": null,
"metadata": {
"id": "b424a17b",
"outputId": "2486b767-d83f-4e1e-a35e-5a6eb55a0922"
@@ -2498,7 +2508,7 @@
},
{
"cell_type": "code",
- "execution_count": 176,
+ "execution_count": null,
"metadata": {
"id": "1f18bc90",
"outputId": "1a49b7c0-2fda-451f-bd6c-4868fa41fd99"
@@ -2524,7 +2534,7 @@
},
{
"cell_type": "code",
- "execution_count": 177,
+ "execution_count": null,
"metadata": {
"id": "d0505bf0",
"outputId": "ab3c3433-5864-4b51-ae80-ab40560d62ac"
@@ -2547,7 +2557,7 @@
},
{
"cell_type": "code",
- "execution_count": 178,
+ "execution_count": null,
"metadata": {
"id": "d4af37e2",
"outputId": "d571539f-3e83-44d1-8271-19d570f77915"
@@ -2578,8 +2588,10 @@
},
{
"cell_type": "code",
- "execution_count": 256,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "ePmCbKZfS6OF"
+ },
"outputs": [],
"source": [
"Y_pred_tree = tree_classify.predict(X_test)\n",
@@ -2588,7 +2600,7 @@
},
{
"cell_type": "code",
- "execution_count": 179,
+ "execution_count": null,
"metadata": {
"id": "40e897f8",
"outputId": "1b4cf01c-00d9-4417-d7a2-9f1610355dd8"
@@ -2619,8 +2631,11 @@
},
{
"cell_type": "code",
- "execution_count": 180,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "GvFc6gOCS6OG",
+ "outputId": "71302171-ee3f-488c-dd42-fd12bd2cd14f"
+ },
"outputs": [
{
"name": "stdout",
@@ -2651,8 +2666,10 @@
},
{
"cell_type": "code",
- "execution_count": 181,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "awnXzmfyS6OG"
+ },
"outputs": [],
"source": [
"metrics_df = add_metrics_details(\"Decision Tree Model\", Y_test, Y_pred, metrics_df)"
@@ -2669,7 +2686,7 @@
},
{
"cell_type": "code",
- "execution_count": 182,
+ "execution_count": null,
"metadata": {
"id": "eed30370",
"outputId": "dd496ed7-40d8-43fe-89ac-37f78f6dd762"
@@ -2697,7 +2714,7 @@
},
{
"cell_type": "code",
- "execution_count": 183,
+ "execution_count": null,
"metadata": {
"id": "5371acc9",
"outputId": "9b4391ef-d576-47ae-dbb3-116391332514"
@@ -2719,9 +2736,10 @@
},
{
"cell_type": "code",
- "execution_count": 184,
+ "execution_count": null,
"metadata": {
- "id": "545ac715"
+ "id": "545ac715",
+ "outputId": "aacd46a4-747c-49a4-a87a-87bf3781f9bc"
},
"outputs": [
{
@@ -2744,10 +2762,9 @@
},
{
"cell_type": "code",
- "execution_count": 185,
+ "execution_count": null,
"metadata": {
- "id": "c9443b7b",
- "outputId": "09c20dd7-7e4d-4407-d1a9-9d23a80f418a"
+ "id": "c9443b7b"
},
"outputs": [],
"source": [
@@ -2758,7 +2775,7 @@
},
{
"cell_type": "code",
- "execution_count": 186,
+ "execution_count": null,
"metadata": {
"id": "dc7a01e5",
"outputId": "2cc84915-7e2a-4c8c-cb66-d7249a873006"
@@ -2800,9 +2817,10 @@
},
{
"cell_type": "code",
- "execution_count": 187,
+ "execution_count": null,
"metadata": {
- "id": "487d5448"
+ "id": "487d5448",
+ "outputId": "b94cf1ba-9543-481d-e277-c579ff4cefc5"
},
"outputs": [
{
@@ -2822,8 +2840,11 @@
},
{
"cell_type": "code",
- "execution_count": 188,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "W27rY6ccS6OH",
+ "outputId": "08d3141a-ca8d-4d03-8dd3-68fba295e9b7"
+ },
"outputs": [
{
"data": {
@@ -2842,8 +2863,11 @@
},
{
"cell_type": "code",
- "execution_count": 189,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "KI1YLu5bS6OI",
+ "outputId": "4875dc4e-616d-4aad-8189-03bcec9327b4"
+ },
"outputs": [
{
"data": {
@@ -2866,8 +2890,11 @@
},
{
"cell_type": "code",
- "execution_count": 190,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "3nzBCwpZS6OI",
+ "outputId": "d594e6c3-4913-4ead-c3f8-1ee5f4fd0df7"
+ },
"outputs": [
{
"name": "stdout",
@@ -2893,8 +2920,10 @@
},
{
"cell_type": "code",
- "execution_count": 257,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "BS_1G24LS6OI"
+ },
"outputs": [],
"source": [
"Y_pred_knn = knn_classify.predict(X_test)\n",
@@ -2903,8 +2932,11 @@
},
{
"cell_type": "code",
- "execution_count": 191,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "9PYQW1sJS6OI",
+ "outputId": "21f762ee-929f-46b7-9723-8f8c411ff2e9"
+ },
"outputs": [
{
"name": "stdout",
@@ -2935,8 +2967,10 @@
},
{
"cell_type": "code",
- "execution_count": 192,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "RF7V-j_yS6OJ"
+ },
"outputs": [],
"source": [
"metrics_df = add_metrics_details(\"KNN Model\", Y_test, Y_pred, metrics_df)"
@@ -2953,7 +2987,7 @@
},
{
"cell_type": "code",
- "execution_count": 259,
+ "execution_count": null,
"metadata": {
"id": "e0f3952f",
"outputId": "19a0bf12-4e8f-428c-e89a-5910214e57b4"
@@ -2982,8 +3016,11 @@
},
{
"cell_type": "code",
- "execution_count": 194,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "oX78sbkGS6OJ",
+ "outputId": "553f2f3f-185c-4170-94c8-5b1376584e4f"
+ },
"outputs": [
{
"name": "stdout",
@@ -3002,8 +3039,11 @@
},
{
"cell_type": "code",
- "execution_count": 195,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "RYC1C7xCS6OJ",
+ "outputId": "525b3cfd-952a-4a4b-88ff-e9b6528eeb41"
+ },
"outputs": [
{
"name": "stdout",
@@ -3025,8 +3065,11 @@
},
{
"cell_type": "code",
- "execution_count": 196,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "-BA3Sgs4S6OK",
+ "outputId": "e314985a-f9c7-41d6-e5f3-30ecc831ac3c"
+ },
"outputs": [
{
"data": {
@@ -3060,8 +3103,11 @@
},
{
"cell_type": "code",
- "execution_count": 197,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "0zClFEJUS6OK",
+ "outputId": "bba4f5eb-06e9-4272-84fc-c15428613bf2"
+ },
"outputs": [
{
"name": "stdout",
@@ -3081,8 +3127,11 @@
},
{
"cell_type": "code",
- "execution_count": 198,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "beDs3TwNS6OK",
+ "outputId": "ed3dea6a-c039-44dc-ae4b-5aadca7454ba"
+ },
"outputs": [
{
"data": {
@@ -3106,7 +3155,7 @@
},
{
"cell_type": "code",
- "execution_count": 199,
+ "execution_count": null,
"metadata": {
"id": "919bf13d",
"outputId": "9e0b8e70-3ea0-4cd9-9c32-b8657ad993a1"
@@ -3136,8 +3185,10 @@
},
{
"cell_type": "code",
- "execution_count": 260,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "wCE00a0SS6OL"
+ },
"outputs": [],
"source": [
"Y_pred_svm = svm_model.predict(X_test)\n",
@@ -3146,8 +3197,11 @@
},
{
"cell_type": "code",
- "execution_count": 200,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "jRhDJr9RS6OL",
+ "outputId": "9f76bbb4-434f-4513-ead4-b85226ac2f9e"
+ },
"outputs": [
{
"data": {
@@ -3171,8 +3225,11 @@
},
{
"cell_type": "code",
- "execution_count": 201,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "XEU8o_w4S6OL",
+ "outputId": "a78ebac7-bf14-4d63-b69e-36cae258f358"
+ },
"outputs": [
{
"name": "stdout",
@@ -3193,8 +3250,11 @@
},
{
"cell_type": "code",
- "execution_count": 261,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "bLyaLcpsS6OL",
+ "outputId": "5d8ce848-5ef6-4a42-b2ae-37e559356017"
+ },
"outputs": [
{
"data": {
@@ -3236,8 +3296,11 @@
},
{
"cell_type": "code",
- "execution_count": 202,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "Tj9z8YrHS6OM",
+ "outputId": "dca83d84-b37e-4f86-ebfd-4134ca0f4a0c"
+ },
"outputs": [
{
"name": "stdout",
@@ -3296,8 +3359,11 @@
},
{
"cell_type": "code",
- "execution_count": 215,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "FjrYsCFoS6OM",
+ "outputId": "a12d2dc5-4986-46b0-b234-496810a4c7e7"
+ },
"outputs": [
{
"data": {
@@ -3461,8 +3527,11 @@
},
{
"cell_type": "code",
- "execution_count": 203,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "jQ0zzcoQS6OM",
+ "outputId": "962c6a24-2c9c-49bf-c706-6d5336ab914e"
+ },
"outputs": [
{
"name": "stdout",
@@ -3484,9 +3553,18 @@
]
},
{
- "cell_type": "code",
- "execution_count": 205,
+ "cell_type": "markdown",
"metadata": {},
+ "source": [
+ "# Q learning"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "sHCGJZHGS6ON"
+ },
"outputs": [],
"source": [
"# Load the dataset\n",
@@ -3498,15 +3576,17 @@
"numerical_features = ['overall', 'seat_comfort', 'cabin_service', 'food_bev', 'entertainment', 'ground_service', 'value_for_money']\n",
"dataset[numerical_features] = scaler.fit_transform(dataset[numerical_features])\n",
"\n",
- "# Convert boolean features to integers\n",
+ "\n",
"boolean_features = ['Couple Leisure', 'Family Leisure', 'Solo Leisure', 'Economy Class', 'First Class', 'Premium Economy']\n",
"dataset[boolean_features] = dataset[boolean_features].astype(int)"
]
},
{
"cell_type": "code",
- "execution_count": 206,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "dQdJ9gKxS6ON"
+ },
"outputs": [],
"source": [
"# Define states and actions\n",
@@ -3520,28 +3600,33 @@
},
{
"cell_type": "code",
- "execution_count": 207,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "L-dVzpcYS6ON"
+ },
"outputs": [],
"source": [
"# Hyperparameters\n",
"alpha = 0.1\n",
"gamma = 0.95\n",
"epsilon = 0.1\n",
- "num_episodes = 10000\n",
+ "num_episodes = 10000 #i have incresed this after i got accuracy 51%\n",
"\n",
"\n",
"def choose_action(state_index):\n",
" if np.random.uniform(0, 1) < epsilon:\n",
- " return np.random.choice(actions) \n",
+ " return np.random.choice(actions)\n",
" else:\n",
- " return np.argmax(q_table[state_index, :]) "
+ " return np.argmax(q_table[state_index, :])"
]
},
{
"cell_type": "code",
- "execution_count": 209,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "73jWTg9xS6ON",
+ "outputId": "30ce35b8-8600-4881-eb85-8ffda6f5435b"
+ },
"outputs": [
{
"name": "stdout",
@@ -3554,20 +3639,20 @@
"source": [
"# Training the agent\n",
"for episode in range(num_episodes):\n",
- " \n",
+ "\n",
" state_index = np.random.randint(0, len(states))\n",
" done = False\n",
- " \n",
+ "\n",
" while not done:\n",
" action = choose_action(state_index)\n",
- " \n",
+ "\n",
" next_state_index = (state_index + 1) % len(states)\n",
" reward = dataset.iloc[next_state_index]['recommended']\n",
- " \n",
+ "\n",
" # Q-learning update\n",
" q_table[state_index, action] = q_table[state_index, action] + alpha * (\n",
" reward + gamma * np.max(q_table[next_state_index, :]) - q_table[state_index, action])\n",
- " \n",
+ "\n",
" state_index = next_state_index\n",
" done = state_index == 0\n",
"\n",
@@ -3576,8 +3661,11 @@
},
{
"cell_type": "code",
- "execution_count": 210,
- "metadata": {},
+ "execution_count": null,
+ "metadata": {
+ "id": "IKnPseuKS6ON",
+ "outputId": "2c457e79-7ecc-4673-eaa1-9213e7653b77"
+ },
"outputs": [
{
"name": "stdout",
@@ -3591,11 +3679,11 @@
"def evaluate_policy(q_table, states, actions):\n",
" correct_predictions = 0\n",
" total_predictions = len(states)\n",
- " \n",
+ "\n",
" for state_index in range(total_predictions):\n",
" action = np.argmax(q_table[state_index, :])\n",
" correct_predictions += int(action == dataset.iloc[state_index]['recommended'])\n",
- " \n",
+ "\n",
" accuracy = correct_predictions / total_predictions\n",
" return accuracy\n",
"\n",
@@ -3603,131 +3691,104 @@
"print(f\"Policy accuracy: {accuracy:.2f}\")"
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "WlOhu_l4TJ9B"
+ },
+ "source": [
+ "# ILP For Airline Data"
+ ]
+ },
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
- "source": []
+ "source": [
+ "#!pip install PyILP\n",
+ "#!pip install texttable"
+ ]
},
{
"cell_type": "code",
- "execution_count": 219,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Facts have been successfully generated and saved to 'facts.pl'.\n"
- ]
- }
- ],
+ "execution_count": 31,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "8H74hLUPTP3B",
+ "outputId": "4f5fd7ea-dbd5-43d9-f9a6-4d58f295077e"
+ },
+ "outputs": [],
"source": [
- "# Load the dataset\n",
- "df2 = pd.read_csv('cleanedairline_pred_data.csv')\n",
- "df2.head()\n",
- "\n",
- "\n",
- "# Fill numerical NaNs with the mean\n",
- "numerical_features = ['overall', 'seat_comfort', 'cabin_service', 'food_bev', 'entertainment', 'ground_service', 'value_for_money']\n",
- "df2[numerical_features] = df2[numerical_features].fillna(df2[numerical_features].mean())\n",
- "\n",
- "# Convert `recommended` to binary\n",
- "df2['recommended'] = df2['recommended'].apply(lambda x: 1 if x == 'yes' else 0)\n",
- "\n",
- "# Define mappings for traveller type and cabin based on the one-hot encoded columns\n",
- "traveller_type_columns = ['Couple Leisure', 'Family Leisure', 'Solo Leisure']\n",
- "cabin_columns = ['Economy Class', 'First Class', 'Premium Economy']\n",
- "\n",
- "def get_traveller_type(row):\n",
- " for col in traveller_type_columns:\n",
- " if row[col]:\n",
- " return col.replace(' ', '_')\n",
- " return 'Unknown'\n",
- "\n",
- "def get_cabin_type(row):\n",
- " for col in cabin_columns:\n",
- " if row[col]:\n",
- " return col.replace(' ', '_')\n",
- " return 'Unknown'\n",
+ "import numpy as np\n",
+ "import pandas as pd\n",
+ "# Load the clean airline dataset\n",
+ "cleaned_airline_data = pd.read_csv('cleanedairline_pred_data.csv')\n",
"\n",
- "# Save facts to a Prolog file\n",
- "with open('facts.pl', 'w') as f:\n",
- " for _, row in df2.iterrows():\n",
- " traveller_type = get_traveller_type(row)\n",
- " cabin = get_cabin_type(row)\n",
- " fact = f\"recommended({traveller_type}, {cabin}, {int(row['seat_comfort'])}, {int(row['cabin_service'])}, {int(row['food_bev'])}, {int(row['entertainment'])}, {int(row['ground_service'])}, {int(row['value_for_money'])}).\\n\"\n",
- " f.write(fact)\n",
- "print(\"Facts have been successfully generated and saved to 'facts.pl'.\")"
+ "facts = open(\"facts.pl\",'w')\n",
+ "positives_file = open(\"positives_file.pl\",'w')\n",
+ "negatives_file = open(\"negatives_file.pl\",'w')\n",
+ "for i,data in cleaned_airline_data.iterrows():\n",
+ " facts.write('ground_service('+str(i)+\",\"+str(data[\"ground_service\"])+\").\\n\")\n",
+ " facts.write('value_for_money('+str(i)+\",\"+str(data[\"value_for_money\"])+\").\\n\")\n",
+ " if data[\"recommended\"]==0:\n",
+ " negatives_file.write(\"recommended(\"+str(i)+\").\\n\")\n",
+ " else:\n",
+ " positives_file.write(\"recommended(\"+str(i)+\").\\n\")\n",
+ " if i>200 :break\n",
+ "facts.close()\n",
+ "positives_file.close()\n",
+ "negatives_file.close()"
]
},
{
"cell_type": "code",
- "execution_count": 220,
- "metadata": {},
+ "execution_count": 33,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 351
+ },
+ "id": "snsE7NpOTQG7",
+ "outputId": "0113b939-0485-42a2-ce54-5f38f1f35055"
+ },
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "Number of positive examples: 0\n",
- "Number of negative examples: 29731\n",
- "Positive and negative examples have been successfully generated and saved to 'positiveexamples.f' and 'negativeexamples.n'.\n"
+ "['recommended(0).recommended(A) :- value_for_money(A,5.0).recommended(8).recommended(15).recommended(16).recommended(17).recommended(18).recommended(32).recommended(A) :- ground_service(A,5.0), value_for_money(A,4.0).recommended(36).recommended(53).recommended(77).recommended(80).recommended(82).recommended(83).recommended(84).recommended(91).recommended(94).recommended(95).recommended(117).recommended(121).recommended(138).recommended(141).']\n",
+ "+----------+ Testing +----------+\n",
+ "+---------------------+------------------+------------------+\n",
+ "| n = 61 | Positive(Actual) | Negative(Actual) |\n",
+ "+=====================+==================+==================+\n",
+ "| Positive(Predicted) | 21 | 1 |\n",
+ "+---------------------+------------------+------------------+\n",
+ "| Negative(Predicted) | 0 | 39 |\n",
+ "+---------------------+------------------+------------------+\n",
+ "+-------------+-------+\n",
+ "| Metric | # |\n",
+ "+=============+=======+\n",
+ "| Accuracy | 0.984 |\n",
+ "+-------------+-------+\n",
+ "| Precision | 0.955 |\n",
+ "+-------------+-------+\n",
+ "| Sensitivity | 1 |\n",
+ "+-------------+-------+\n",
+ "| Specificity | 0.975 |\n",
+ "+-------------+-------+\n",
+ "| F1 Score | 0.977 |\n",
+ "+-------------+-------+\n"
]
}
],
"source": [
- "traveller_type_columns = ['Couple Leisure', 'Family Leisure', 'Solo Leisure']\n",
- "cabin_columns = ['Economy Class', 'First Class', 'Premium Economy']\n",
"\n",
- "def get_traveller_type(row):\n",
- " for col in traveller_type_columns:\n",
- " if row[col]:\n",
- " return col.replace(' ', '_').lower()\n",
- " return 'unknown'\n",
- "\n",
- "def get_cabin_type(row):\n",
- " for col in cabin_columns:\n",
- " if row[col]:\n",
- " return col.replace(' ', '_').lower()\n",
- " return 'unknown'\n",
- "\n",
- "\n",
- "positive_examples = []\n",
- "negative_examples = []\n",
- "\n",
- "for _, row in df2.iterrows():\n",
- " traveller_type = get_traveller_type(row)\n",
- " cabin = get_cabin_type(row)\n",
- " fact = f\"recommended({traveller_type}, {cabin}, {int(row['seat_comfort'])}, {int(row['cabin_service'])}, {int(row['food_bev'])}, {int(row['entertainment'])}, {int(row['ground_service'])}, {int(row['value_for_money'])}).\"\n",
- " if row['recommended'] == 1:\n",
- " positive_examples.append(fact)\n",
- " else:\n",
- " negative_examples.append(fact)\n",
- "\n",
- "print(\"Number of positive examples:\", len(positive_examples))\n",
- "print(\"Number of negative examples:\", len(negative_examples))\n",
- "\n",
- "# Save positive examples to file\n",
- "with open('positiveexamples.f', 'w') as f:\n",
- " for example in positive_examples:\n",
- " f.write(example + '\\n')\n",
- "\n",
- "# Save negative examples to file\n",
- "with open('negativeexamples.n', 'w') as f:\n",
- " for example in negative_examples:\n",
- " f.write(example + '\\n')\n",
- "\n",
- "print(\"Positive and negative examples have been successfully generated and saved to 'positiveexamples.f' and 'negativeexamples.n'.\")"
+ "from PyILP.PyILP import *\n",
+ "model_2=aleph_learn(file=\"facts.pl\", positive_example=\"positives_file.pl\", negative_example=\"negatives_file.pl\", test_size=0.3)"
]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
}
],
"metadata": {
@@ -3753,5 +3814,5 @@
}
},
"nbformat": 4,
- "nbformat_minor": 4
+ "nbformat_minor": 1
}