{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# import our dataset\n\nimport pandas as pd\n\ntrain = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\nX = train.values[:, 1:]\ny = train.values[:, :1].reshape(42000)\n\nprint(X.shape)\nprint(y.shape)","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-07-26T18:58:38.613629Z","iopub.execute_input":"2022-07-26T18:58:38.614660Z","iopub.status.idle":"2022-07-26T18:58:41.720964Z","shell.execute_reply.started":"2022-07-26T18:58:38.614603Z","shell.execute_reply":"2022-07-26T18:58:41.719409Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from pandas import get_dummies\nfrom matplotlib import pyplot as plt\n\nX = X.astype(\"float32\")\nX /= 225.0\nX = X.reshape(42000, 28, 28, 1)\n\ny = get_dummies(y)\n\nprint(y.head())\n\nplt.imshow(X[3], cmap=\"gray\")","metadata":{"execution":{"iopub.status.busy":"2022-07-26T18:58:41.723674Z","iopub.execute_input":"2022-07-26T18:58:41.724470Z","iopub.status.idle":"2022-07-26T18:58:42.003127Z","shell.execute_reply.started":"2022-07-26T18:58:41.724418Z","shell.execute_reply":"2022-07-26T18:58:42.001864Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Flatten\n\nmodel = Sequential()\nmodel.add(Conv2D(16, (5, 5), activation=\"relu\", input_shape=(28, 28, 1), padding=\"same\"))\nmodel.add(Conv2D(16, (5, 5), activation=\"relu\", padding=\"same\"))\nmodel.add(MaxPooling2D(2, 2))\nmodel.add(Conv2D(16, (3, 3), activation=\"relu\", padding=\"same\"))\nmodel.add(Conv2D(16, (3, 3), activation=\"relu\", padding=\"same\"))\nmodel.add(MaxPooling2D(2, 2))\nmodel.add(Flatten())\nmodel.add(Dense(128, activation=\"relu\"))\nmodel.add(Dense(10, activation=\"softmax\"))\n\nmodel.summary()\n\nfrom tensorflow.keras.losses import categorical_crossentropy\nmodel.compile(loss=categorical_crossentropy, optimizer=\"Adam\", metrics=[\"accuracy\"])","metadata":{"execution":{"iopub.status.busy":"2022-07-26T18:58:42.004747Z","iopub.execute_input":"2022-07-26T18:58:42.007220Z","iopub.status.idle":"2022-07-26T18:58:42.096361Z","shell.execute_reply.started":"2022-07-26T18:58:42.007158Z","shell.execute_reply":"2022-07-26T18:58:42.095302Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.125)\n\nmodel_stats = model.fit(\n    X_train,\n    y_train,\n    batch_size=196,\n    epochs=6,\n    verbose=1,\n    validation_data=(X_test, y_test)\n)\n","metadata":{"execution":{"iopub.status.busy":"2022-07-26T18:58:42.098536Z","iopub.execute_input":"2022-07-26T18:58:42.098914Z","iopub.status.idle":"2022-07-26T19:00:17.029444Z","shell.execute_reply.started":"2022-07-26T18:58:42.098874Z","shell.execute_reply":"2022-07-26T19:00:17.028417Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.plot(model_stats.history[\"loss\"])\nplt.plot(model_stats.history[\"val_loss\"])\nplt.legend([\"train loss\", \"test loss\"], loc=\"upper left\")","metadata":{"execution":{"iopub.status.busy":"2022-07-26T19:01:14.873581Z","iopub.execute_input":"2022-07-26T19:01:14.874013Z","iopub.status.idle":"2022-07-26T19:01:15.082050Z","shell.execute_reply.started":"2022-07-26T19:01:14.873980Z","shell.execute_reply":"2022-07-26T19:01:15.080964Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np\n\nX_pred = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")\n\nX_pred = np.asarray(X_pred)\nX_pred = X_pred.astype(\"float32\")\nX_pred /= 225.0\nX_pred = X_pred.reshape(X_pred.shape[0], 28, 28, 1)\n\ny_pred = model.predict(X_pred)\ny_pred = [np.argmax(v) for v in y_pred]\n\ndata = {\n    \"ImageId\": [x for x in range(1, 28001)],\n    \"Label\": y_pred\n}\nsubmission = pd.DataFrame(data)\n\nsubmission.to_csv(\"submission.csv\", index=False)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T19:08:45.681691Z","iopub.execute_input":"2022-07-26T19:08:45.682581Z","iopub.status.idle":"2022-07-26T19:08:53.038922Z","shell.execute_reply.started":"2022-07-26T19:08:45.682543Z","shell.execute_reply":"2022-07-26T19:08:53.037811Z"},"trusted":true},"execution_count":null,"outputs":[]}]}