Upload Football Winner Prediction.ipynb

Football Winner Prediction.ipynb

@@ -0,0 +1,481 @@
+{
+ "cells": [
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-01T10:05:00.890729Z",
+     "start_time": "2024-12-01T10:05:00.885464Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import LabelEncoder, StandardScaler\n",
+    "import tensorflow as tf\n",
+    "from tensorflow.keras.models import Sequential\n",
+    "from tensorflow.keras.layers import Dense, Dropout"
+   ],
+   "id": "e8f9a90ff28c2228",
+   "outputs": [],
+   "execution_count": 36
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-01T10:05:06.623390Z",
+     "start_time": "2024-12-01T10:05:06.605514Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# Load the dataset\n",
+    "data = pd.read_csv(\"data/large_mock_football_data.csv\")"
+   ],
+   "id": "bcba25fa701b7739",
+   "outputs": [],
+   "execution_count": 37
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-01T10:05:08.311068Z",
+     "start_time": "2024-12-01T10:05:08.301297Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# Encode categorical features\n",
+    "encoder = LabelEncoder()\n",
+    "data[\"team_a_name\"] = encoder.fit_transform(data[\"team_a_name\"])\n",
+    "data[\"team_b_name\"] = encoder.fit_transform(data[\"team_b_name\"])\n",
+    "data[\"match_location\"] = encoder.fit_transform(data[\"match_location\"])\n",
+    "data[\"weather_condition\"] = encoder.fit_transform(data[\"weather_condition\"])"
+   ],
+   "id": "6163fdf4954bdff9",
+   "outputs": [],
+   "execution_count": 38
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-01T10:05:10.847483Z",
+     "start_time": "2024-12-01T10:05:10.841396Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# Encode the target (result)\n",
+    "data[\"result\"] = data[\"result\"].map({\"team_a_win\": 0, \"team_b_win\": 1, \"draw\": 2})"
+   ],
+   "id": "c2c51d8074b763ed",
+   "outputs": [],
+   "execution_count": 39
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-01T10:05:12.607454Z",
+     "start_time": "2024-12-01T10:05:12.602100Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# Split features and labels\n",
+    "X = data.drop(\"result\", axis=1)\n",
+    "y = data[\"result\"]\n"
+   ],
+   "id": "426d1dd68fae7b22",
+   "outputs": [],
+   "execution_count": 40
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-01T10:05:14.519744Z",
+     "start_time": "2024-12-01T10:05:14.511091Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# Normalize features\n",
+    "scaler = StandardScaler()\n",
+    "X = scaler.fit_transform(X)"
+   ],
+   "id": "69a891f01254baa",
+   "outputs": [],
+   "execution_count": 41
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-01T10:05:17.798320Z",
+     "start_time": "2024-12-01T10:05:17.793462Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
+   "id": "ef4b241b01411c02",
+   "outputs": [],
+   "execution_count": 43
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-01T10:05:19.045325Z",
+     "start_time": "2024-12-01T10:05:19.038713Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "y_train",
+   "id": "2e9b7472e92eb8b4",
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "642     1\n",
+       "700     1\n",
+       "226     2\n",
+       "1697    0\n",
+       "1010    0\n",
+       "       ..\n",
+       "1638    2\n",
+       "1095    1\n",
+       "1130    2\n",
+       "1294    1\n",
+       "860     0\n",
+       "Name: result, Length: 2400, dtype: int64"
+      ]
+     },
+     "execution_count": 44,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "execution_count": 44
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-01T10:05:22.750495Z",
+     "start_time": "2024-12-01T10:05:22.713793Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# Build the model\n",
+    "model = Sequential([\n",
+    "    Dense(64, input_dim=X_train.shape[1], activation='relu'),\n",
+    "    Dropout(0.2),\n",
+    "    Dense(32, activation='relu'),\n",
+    "    Dropout(0.2),\n",
+    "    Dense(3, activation='softmax')  # 3 classes (team_a_win, team_b_win, draw)\n",
+    "])"
+   ],
+   "id": "35dbd98020d0a9c3",
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\ProgramData\\miniconda3\\Lib\\site-packages\\keras\\src\\layers\\core\\dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
+      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
+     ]
+    }
+   ],
+   "execution_count": 45
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-01T10:05:27.003568Z",
+     "start_time": "2024-12-01T10:05:26.997249Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# Compile the model\n",
+    "model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])"
+   ],
+   "id": "97b5c68fc4d3c5ae",
+   "outputs": [],
+   "execution_count": 47
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-01T10:06:52.058005Z",
+     "start_time": "2024-12-01T10:06:01.184361Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# Train the model\n",
+    "model.fit(X_train, y_train, epochs=64, batch_size=2, validation_split=0.3)"
+   ],
+   "id": "dd3ca9f254babc99",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 1ms/step - accuracy: 0.4704 - loss: 1.0244 - val_accuracy: 0.4500 - val_loss: 1.0509\n",
+      "Epoch 2/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 884us/step - accuracy: 0.4727 - loss: 1.0207 - val_accuracy: 0.4361 - val_loss: 1.0620\n",
+      "Epoch 3/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 863us/step - accuracy: 0.5057 - loss: 1.0105 - val_accuracy: 0.4486 - val_loss: 1.0561\n",
+      "Epoch 4/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 862us/step - accuracy: 0.4966 - loss: 1.0121 - val_accuracy: 0.4347 - val_loss: 1.0440\n",
+      "Epoch 5/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 854us/step - accuracy: 0.4839 - loss: 1.0113 - val_accuracy: 0.4528 - val_loss: 1.0354\n",
+      "Epoch 6/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 856us/step - accuracy: 0.4945 - loss: 1.0043 - val_accuracy: 0.4444 - val_loss: 1.0351\n",
+      "Epoch 7/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 848us/step - accuracy: 0.4748 - loss: 1.0203 - val_accuracy: 0.4639 - val_loss: 1.0314\n",
+      "Epoch 8/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 849us/step - accuracy: 0.4846 - loss: 1.0112 - val_accuracy: 0.4556 - val_loss: 1.0310\n",
+      "Epoch 9/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 864us/step - accuracy: 0.5166 - loss: 0.9906 - val_accuracy: 0.4681 - val_loss: 1.0361\n",
+      "Epoch 10/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 865us/step - accuracy: 0.4985 - loss: 1.0013 - val_accuracy: 0.4667 - val_loss: 1.0279\n",
+      "Epoch 11/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 860us/step - accuracy: 0.4991 - loss: 0.9903 - val_accuracy: 0.4792 - val_loss: 1.0265\n",
+      "Epoch 12/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 874us/step - accuracy: 0.5300 - loss: 0.9713 - val_accuracy: 0.4806 - val_loss: 1.0167\n",
+      "Epoch 13/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 871us/step - accuracy: 0.4900 - loss: 1.0010 - val_accuracy: 0.4722 - val_loss: 1.0248\n",
+      "Epoch 14/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 887us/step - accuracy: 0.5145 - loss: 0.9902 - val_accuracy: 0.4542 - val_loss: 1.0213\n",
+      "Epoch 15/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 889us/step - accuracy: 0.5230 - loss: 0.9829 - val_accuracy: 0.4764 - val_loss: 1.0165\n",
+      "Epoch 16/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 885us/step - accuracy: 0.5011 - loss: 0.9831 - val_accuracy: 0.4681 - val_loss: 1.0130\n",
+      "Epoch 17/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 894us/step - accuracy: 0.5148 - loss: 0.9639 - val_accuracy: 0.4667 - val_loss: 1.0168\n",
+      "Epoch 18/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 871us/step - accuracy: 0.5430 - loss: 0.9641 - val_accuracy: 0.4847 - val_loss: 1.0200\n",
+      "Epoch 19/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 893us/step - accuracy: 0.5125 - loss: 0.9657 - val_accuracy: 0.4750 - val_loss: 1.0127\n",
+      "Epoch 20/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 874us/step - accuracy: 0.5236 - loss: 0.9596 - val_accuracy: 0.4681 - val_loss: 1.0147\n",
+      "Epoch 21/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 874us/step - accuracy: 0.5505 - loss: 0.9198 - val_accuracy: 0.4889 - val_loss: 1.0084\n",
+      "Epoch 22/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 874us/step - accuracy: 0.5658 - loss: 0.9277 - val_accuracy: 0.4792 - val_loss: 1.0109\n",
+      "Epoch 23/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 877us/step - accuracy: 0.5364 - loss: 0.9530 - val_accuracy: 0.4903 - val_loss: 1.0087\n",
+      "Epoch 24/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 880us/step - accuracy: 0.5316 - loss: 0.9524 - val_accuracy: 0.4889 - val_loss: 1.0065\n",
+      "Epoch 25/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 876us/step - accuracy: 0.5616 - loss: 0.9233 - val_accuracy: 0.4778 - val_loss: 1.0001\n",
+      "Epoch 26/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 900us/step - accuracy: 0.5465 - loss: 0.9409 - val_accuracy: 0.4875 - val_loss: 1.0036\n",
+      "Epoch 27/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 886us/step - accuracy: 0.5188 - loss: 0.9549 - val_accuracy: 0.4722 - val_loss: 1.0039\n",
+      "Epoch 28/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 883us/step - accuracy: 0.5414 - loss: 0.9478 - val_accuracy: 0.4750 - val_loss: 0.9998\n",
+      "Epoch 29/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 919us/step - accuracy: 0.5261 - loss: 0.9438 - val_accuracy: 0.4903 - val_loss: 0.9995\n",
+      "Epoch 30/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 1ms/step - accuracy: 0.5610 - loss: 0.9234 - val_accuracy: 0.4708 - val_loss: 0.9909\n",
+      "Epoch 31/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 1ms/step - accuracy: 0.5621 - loss: 0.9041 - val_accuracy: 0.4931 - val_loss: 0.9888\n",
+      "Epoch 32/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 930us/step - accuracy: 0.5543 - loss: 0.9295 - val_accuracy: 0.4917 - val_loss: 0.9921\n",
+      "Epoch 33/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 1ms/step - accuracy: 0.5428 - loss: 0.9415 - val_accuracy: 0.4889 - val_loss: 0.9916\n",
+      "Epoch 34/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 897us/step - accuracy: 0.5690 - loss: 0.9042 - val_accuracy: 0.4889 - val_loss: 0.9945\n",
+      "Epoch 35/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 1ms/step - accuracy: 0.5439 - loss: 0.9190 - val_accuracy: 0.5028 - val_loss: 0.9796\n",
+      "Epoch 36/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 1ms/step - accuracy: 0.5537 - loss: 0.9207 - val_accuracy: 0.5000 - val_loss: 0.9795\n",
+      "Epoch 37/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 1ms/step - accuracy: 0.5909 - loss: 0.8891 - val_accuracy: 0.4903 - val_loss: 0.9821\n",
+      "Epoch 38/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 891us/step - accuracy: 0.5790 - loss: 0.9119 - val_accuracy: 0.5000 - val_loss: 0.9860\n",
+      "Epoch 39/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 909us/step - accuracy: 0.5792 - loss: 0.8886 - val_accuracy: 0.5083 - val_loss: 0.9821\n",
+      "Epoch 40/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 1ms/step - accuracy: 0.5800 - loss: 0.8886 - val_accuracy: 0.5194 - val_loss: 0.9789\n",
+      "Epoch 41/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 1ms/step - accuracy: 0.5486 - loss: 0.9242 - val_accuracy: 0.4750 - val_loss: 0.9924\n",
+      "Epoch 42/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 899us/step - accuracy: 0.5455 - loss: 0.9287 - val_accuracy: 0.5014 - val_loss: 0.9734\n",
+      "Epoch 43/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 882us/step - accuracy: 0.5582 - loss: 0.9184 - val_accuracy: 0.5069 - val_loss: 0.9686\n",
+      "Epoch 44/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 896us/step - accuracy: 0.5596 - loss: 0.8958 - val_accuracy: 0.4972 - val_loss: 0.9699\n",
+      "Epoch 45/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 944us/step - accuracy: 0.5755 - loss: 0.8973 - val_accuracy: 0.4847 - val_loss: 0.9818\n",
+      "Epoch 46/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 904us/step - accuracy: 0.5888 - loss: 0.8730 - val_accuracy: 0.5069 - val_loss: 0.9762\n",
+      "Epoch 47/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 877us/step - accuracy: 0.5845 - loss: 0.8735 - val_accuracy: 0.5167 - val_loss: 0.9596\n",
+      "Epoch 48/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 907us/step - accuracy: 0.5763 - loss: 0.9182 - val_accuracy: 0.4986 - val_loss: 0.9675\n",
+      "Epoch 49/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 887us/step - accuracy: 0.5833 - loss: 0.8793 - val_accuracy: 0.5028 - val_loss: 0.9629\n",
+      "Epoch 50/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 930us/step - accuracy: 0.5736 - loss: 0.8905 - val_accuracy: 0.5056 - val_loss: 0.9613\n",
+      "Epoch 51/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 914us/step - accuracy: 0.6091 - loss: 0.8598 - val_accuracy: 0.5153 - val_loss: 0.9531\n",
+      "Epoch 52/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 948us/step - accuracy: 0.5823 - loss: 0.8932 - val_accuracy: 0.5236 - val_loss: 0.9497\n",
+      "Epoch 53/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 931us/step - accuracy: 0.5771 - loss: 0.8799 - val_accuracy: 0.5208 - val_loss: 0.9505\n",
+      "Epoch 54/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 894us/step - accuracy: 0.5840 - loss: 0.8816 - val_accuracy: 0.5250 - val_loss: 0.9399\n",
+      "Epoch 55/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 897us/step - accuracy: 0.6086 - loss: 0.8647 - val_accuracy: 0.5264 - val_loss: 0.9441\n",
+      "Epoch 56/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 910us/step - accuracy: 0.5963 - loss: 0.8471 - val_accuracy: 0.5250 - val_loss: 0.9377\n",
+      "Epoch 57/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 889us/step - accuracy: 0.5881 - loss: 0.8731 - val_accuracy: 0.5139 - val_loss: 0.9503\n",
+      "Epoch 58/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 898us/step - accuracy: 0.5963 - loss: 0.8609 - val_accuracy: 0.5417 - val_loss: 0.9359\n",
+      "Epoch 59/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 900us/step - accuracy: 0.6087 - loss: 0.8495 - val_accuracy: 0.5319 - val_loss: 0.9465\n",
+      "Epoch 60/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 940us/step - accuracy: 0.5941 - loss: 0.8887 - val_accuracy: 0.5250 - val_loss: 0.9467\n",
+      "Epoch 61/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 918us/step - accuracy: 0.5583 - loss: 0.8744 - val_accuracy: 0.5181 - val_loss: 0.9463\n",
+      "Epoch 62/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 950us/step - accuracy: 0.5815 - loss: 0.8637 - val_accuracy: 0.5181 - val_loss: 0.9486\n",
+      "Epoch 63/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 915us/step - accuracy: 0.6214 - loss: 0.8448 - val_accuracy: 0.5361 - val_loss: 0.9427\n",
+      "Epoch 64/64\n",
+      "\u001B[1m840/840\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m1s\u001B[0m 911us/step - accuracy: 0.6034 - loss: 0.8680 - val_accuracy: 0.5264 - val_loss: 0.9538\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.src.callbacks.history.History at 0x1db010a2150>"
+      ]
+     },
+     "execution_count": 49,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "execution_count": 49
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-01T10:06:56.633427Z",
+     "start_time": "2024-12-01T10:06:56.562087Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# Evaluate the model\n",
+    "loss, accuracy = model.evaluate(X_test, y_test)\n",
+    "print(f\"Test Accuracy: {accuracy:.2f}\")"
+   ],
+   "id": "33799f9e7377c32c",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001B[1m19/19\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 820us/step - accuracy: 0.5235 - loss: 0.9529\n",
+      "Test Accuracy: 0.49\n"
+     ]
+    }
+   ],
+   "execution_count": 50
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-01T10:07:59.256655Z",
+     "start_time": "2024-12-01T10:07:59.198211Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# Predict for a new match\n",
+    "new_match = np.array([[8, 1, 8, 9, 1, 1, 1, 1]])  # Example data\n",
+    "new_match = scaler.transform(new_match)\n",
+    "prediction = model.predict(new_match)\n",
+    "predicted_class = np.argmax(prediction)\n",
+    "result_mapping = {0: \"team_a_win\", 1: \"team_b_win\", 2: \"draw\"}\n",
+    "print(f\"Predicted Result: {result_mapping[predicted_class]}\")"
+   ],
+   "id": "8afcc0c67d20c53d",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001B[1m1/1\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 22ms/step\n",
+      "Predicted Result: team_a_win\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\3176\\AppData\\Roaming\\Python\\Python312\\site-packages\\sklearn\\base.py:493: UserWarning: X does not have valid feature names, but StandardScaler was fitted with feature names\n",
+      "  warnings.warn(\n"
+     ]
+    }
+   ],
+   "execution_count": 73
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-01T10:13:49.624661Z",
+     "start_time": "2024-12-01T10:13:49.605519Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "model.save(\"data/Football_Winner_Model.h5\")",
+   "id": "a314f0dcbe19c8de",
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
+     ]
+    }
+   ],
+   "execution_count": 75
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": "",
+   "id": "3a11d48c49cb7314"
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}