{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","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":30732,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"<h3>Import Libraries</h3>","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport keras\nfrom keras.models import Sequential\nfrom keras.layers import Dense,Dropout\nfrom keras.utils import to_categorical\nfrom keras.datasets import mnist\nimport matplotlib.pyplot as plt\nfrom keras.layers import Conv2D\nfrom keras.layers import MaxPooling2D\nfrom keras.layers import Flatten","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-06-22T09:43:21.518817Z","iopub.execute_input":"2024-06-22T09:43:21.519373Z","iopub.status.idle":"2024-06-22T09:43:21.527473Z","shell.execute_reply.started":"2024-06-22T09:43:21.519328Z","shell.execute_reply":"2024-06-22T09:43:21.525981Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h3>Build Model</h3>","metadata":{}},{"cell_type":"code","source":"def convolutional_model():\n  model=Sequential()\n  model.add(Conv2D(16, (4, 4), activation='relu', input_shape=(28, 28, 1)))#Convolution layer\n  model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2)))#Pooling layer\n  model.add(Conv2D(16, (4, 4), activation='relu', input_shape=(28, 28, 1)))#Convolution layer\n  model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2)))#Pooling layer\n  model.add(Dense(128, activation='relu',))\n  model.add(Dropout(0.5))\n  model.add(Flatten())#flatter\n  model.add(Dense(100, activation='relu'))#fully connected layer\n  model.add(Dropout(0.3))\n  model.add(Dense(10, activation='softmax'))#output layer\n  \n  model.compile(optimizer='adam', loss='categorical_crossentropy',  metrics=['accuracy'])\n  return model","metadata":{"execution":{"iopub.status.busy":"2024-06-22T09:43:21.529719Z","iopub.execute_input":"2024-06-22T09:43:21.530140Z","iopub.status.idle":"2024-06-22T09:43:21.542893Z","shell.execute_reply.started":"2024-06-22T09:43:21.530106Z","shell.execute_reply":"2024-06-22T09:43:21.541498Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h3>Load Dataset</h3>","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nfrom sklearn.model_selection import train_test_split\n\ntrain = pd.read_csv(\"../input/digit-recognizer/train.csv\")\ntest = pd.read_csv(\"../input/digit-recognizer/test.csv\")\n\n# Preprocess the data\nX_train = train.drop(columns=['label']).values.reshape(-1, 28, 28, 1)\ny_train = to_categorical(train['label'].values, num_classes=10)\n\n\n# Normalize the data\nX_train = X_train / 255.0\n\n# Split the data into training and validation sets\nX_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.2, random_state=42)","metadata":{"execution":{"iopub.status.busy":"2024-06-22T09:43:21.544623Z","iopub.execute_input":"2024-06-22T09:43:21.545129Z","iopub.status.idle":"2024-06-22T09:43:27.323464Z","shell.execute_reply.started":"2024-06-22T09:43:21.545085Z","shell.execute_reply":"2024-06-22T09:43:27.322374Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h3>Train</h3>","metadata":{}},{"cell_type":"code","source":"model = convolutional_model()\n\n# fit the model\nmodel.fit(X_train, y_train, epochs=10, batch_size=64, validation_data=(X_val, y_val))\n\n","metadata":{"execution":{"iopub.status.busy":"2024-06-22T09:43:27.326266Z","iopub.execute_input":"2024-06-22T09:43:27.326751Z","iopub.status.idle":"2024-06-22T09:45:34.141946Z","shell.execute_reply.started":"2024-06-22T09:43:27.326692Z","shell.execute_reply":"2024-06-22T09:45:34.140568Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_test = test.values.reshape(-1, 28, 28, 1)\nX_test = X_test / 255.0\npredictions = model.predict(X_test)\npredictions = np.argmax(predictions, axis=1)\n\n# Create a submission DataFrame\nsubmission = pd.DataFrame({'ImageId': np.arange(1, len(predictions) + 1), 'Label': predictions})\n\n# Save to CSV\nsubmission.to_csv('submission.csv', index=False)\n\nprint('All done!')","metadata":{"execution":{"iopub.status.busy":"2024-06-22T09:45:34.143280Z","iopub.execute_input":"2024-06-22T09:45:34.143734Z","iopub.status.idle":"2024-06-22T09:45:39.351337Z","shell.execute_reply.started":"2024-06-22T09:45:34.143677Z","shell.execute_reply":"2024-06-22T09:45:39.349947Z"},"trusted":true},"execution_count":null,"outputs":[]}]}