{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":3004,"databundleVersionId":861823,"sourceType":"competition"}],"dockerImageVersionId":30786,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Conv2D, Flatten, MaxPooling2D\nfrom tensorflow.keras.utils import to_categorical\nfrom sklearn.model_selection import train_test_split\n\n# Load the dataset.\ntrain = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')\nX = train.drop('label', axis=1).values\ny = train['label'].values\n\n# Preprocess the data.\nX = X.reshape(-1, 28, 28, 1).astype('float32') / 255.0  # Normalize.\ny = to_categorical(y, num_classes=10)\n\n# Split into training and validation sets.\nX_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)\n\n# Build the model.\nmodel = Sequential()\nmodel.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(28, 28, 1)))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Conv2D(64, kernel_size=(3, 3), activation='relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu'))\nmodel.add(Dense(10, activation='softmax'))\n\n# Compile the model.\nmodel.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])\n\n# Train the model.\nhistory = model.fit(X_train, y_train, validation_data=(X_val, y_val), epochs=20, batch_size=128)\n\n# Plot training & validation accuracy values.\nplt.plot(history.history['accuracy'], label='train accuracy')\nplt.plot(history.history['val_accuracy'], label='validation accuracy')\nplt.title('Model accuracy')\nplt.ylabel('Accuracy')\nplt.xlabel('Epoch')\nplt.legend()\nplt.show()\n\n# Prepare test data.\ntest = pd.read_csv('../input/digit-recognizer/test.csv')\nX_test = test.values.reshape(-1, 28, 28, 1).astype('float32') / 255.0\n\n# Make predictions.\npredictions = model.predict(X_test)\npredicted_classes = np.argmax(predictions, axis=1)\n\n# Prepare submission.\nsubmission = pd.DataFrame({'ImageId': np.arange(1, len(predicted_classes) + 1), 'Label': predicted_classes})\nsubmission.to_csv('submission.csv', index=False)","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-10-16T16:05:04.755720Z","iopub.execute_input":"2024-10-16T16:05:04.756513Z","iopub.status.idle":"2024-10-16T16:10:51.166979Z","shell.execute_reply.started":"2024-10-16T16:05:04.756451Z","shell.execute_reply":"2024-10-16T16:10:51.165778Z"},"trusted":true},"execution_count":null,"outputs":[]}]}