{"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":30664,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-03-13T11:51:00.556701Z","iopub.execute_input":"2024-03-13T11:51:00.557210Z","iopub.status.idle":"2024-03-13T11:51:01.047632Z","shell.execute_reply.started":"2024-03-13T11:51:00.557167Z","shell.execute_reply":"2024-03-13T11:51:01.046736Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"mnist_train = pd.read_csv(\"../input/digit-recognizer/train.csv\")\nmnist_test = pd.read_csv(\"../input/digit-recognizer/test.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-03-13T11:51:03.903295Z","iopub.execute_input":"2024-03-13T11:51:03.903897Z","iopub.status.idle":"2024-03-13T11:51:10.575356Z","shell.execute_reply.started":"2024-03-13T11:51:03.903861Z","shell.execute_reply":"2024-03-13T11:51:10.574206Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_train1 = pd.get_dummies(mnist_train.label)\nprint(y_train1.shape)","metadata":{"execution":{"iopub.status.busy":"2024-03-13T11:51:12.249906Z","iopub.execute_input":"2024-03-13T11:51:12.250320Z","iopub.status.idle":"2024-03-13T11:51:12.266330Z","shell.execute_reply.started":"2024-03-13T11:51:12.250284Z","shell.execute_reply":"2024-03-13T11:51:12.265138Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"npx = mnist_train.drop(['label'], axis=1)\nx_train1 = np.array(npx).reshape(42000,28,28,1)/255\nprint(x_train1.shape)","metadata":{"execution":{"iopub.status.busy":"2024-03-13T11:51:18.430690Z","iopub.execute_input":"2024-03-13T11:51:18.431071Z","iopub.status.idle":"2024-03-13T11:51:18.809202Z","shell.execute_reply.started":"2024-03-13T11:51:18.431040Z","shell.execute_reply":"2024-03-13T11:51:18.808311Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split #to split our dataset\nx_train, x_val, y_train, y_val = train_test_split(x_train1, y_train1, test_size=0.1, random_state=33)","metadata":{"execution":{"iopub.status.busy":"2024-03-13T11:51:22.627994Z","iopub.execute_input":"2024-03-13T11:51:22.628614Z","iopub.status.idle":"2024-03-13T11:51:23.803010Z","shell.execute_reply.started":"2024-03-13T11:51:22.628581Z","shell.execute_reply":"2024-03-13T11:51:23.801713Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"npx = mnist_test\nx_test = np.array(npx).reshape(28000,28,28,1)/255\nprint(x_test.shape)","metadata":{"execution":{"iopub.status.busy":"2024-03-13T11:51:25.475999Z","iopub.execute_input":"2024-03-13T11:51:25.476870Z","iopub.status.idle":"2024-03-13T11:51:25.636398Z","shell.execute_reply.started":"2024-03-13T11:51:25.476822Z","shell.execute_reply":"2024-03-13T11:51:25.635226Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import keras\nfrom keras.models import Sequential\nfrom keras.optimizers import Adam\nfrom keras.utils import to_categorical\nfrom keras.layers import Dense, Dropout, Flatten, BatchNormalization\nfrom keras.layers import Conv2D, MaxPooling2D\nfrom keras.preprocessing import image\nfrom keras.callbacks import ReduceLROnPlateau\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport cv2\nfrom PIL import Image\n\nnp.random.seed(33)","metadata":{"execution":{"iopub.status.busy":"2024-03-13T11:51:28.990705Z","iopub.execute_input":"2024-03-13T11:51:28.991209Z","iopub.status.idle":"2024-03-13T11:51:44.236114Z","shell.execute_reply.started":"2024-03-13T11:51:28.991168Z","shell.execute_reply":"2024-03-13T11:51:44.234896Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def display(img):\n  plt.figure(figsize=(5,5))\n  plt.axis(\"off\")\n  plt.imshow(img,cmap=\"gray\")\n\ndisplay(x_train[0])","metadata":{"execution":{"iopub.status.busy":"2024-03-13T08:25:50.546262Z","iopub.execute_input":"2024-03-13T08:25:50.546705Z","iopub.status.idle":"2024-03-13T08:25:50.615537Z","shell.execute_reply.started":"2024-03-13T08:25:50.546673Z","shell.execute_reply":"2024-03-13T08:25:50.614239Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def Conv_Net_model():\n  model = Sequential()\n  model.add(Conv2D(32,(3,3), input_shape=(28,28,1), padding=\"same\", activation=\"relu\"))\n  model.add(MaxPooling2D(pool_size=(2,2)))\n  model.add(BatchNormalization(axis = -1))\n  model.add(Conv2D(64,(3,3), activation=\"relu\", padding=\"same\"))\n  model.add(MaxPooling2D(pool_size=(2,2)))\n  model.add(BatchNormalization(axis = -1))\n  model.add(Conv2D(128,(3,3), activation=\"relu\", padding=\"same\"))\n  model.add(MaxPooling2D(pool_size=(2,2)))\n  model.add(BatchNormalization(axis = -1))\n  model.add(Conv2D(256,(3,3), activation=\"relu\", padding=\"same\"))\n  model.add(MaxPooling2D(pool_size=(2,2)))\n  model.add(BatchNormalization(axis = -1))\n  model.add(Flatten())\n  model.add(Dense(400, activation=\"relu\"))\n  model.add(Dense(300, activation=\"relu\"))\n  model.add(Dense(200, activation=\"relu\"))\n  model.add(Dense(100, activation=\"relu\"))\n  model.add(Dense(10, activation=\"softmax\"))\n  return model\n\nmodel = Conv_Net_model()\nprint(model.summary())","metadata":{"execution":{"iopub.status.busy":"2024-03-13T12:48:24.790326Z","iopub.execute_input":"2024-03-13T12:48:24.791570Z","iopub.status.idle":"2024-03-13T12:48:25.308485Z","shell.execute_reply.started":"2024-03-13T12:48:24.791524Z","shell.execute_reply":"2024-03-13T12:48:25.307102Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Compile model\nmodel.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])\n\n# Train model\nmodel.fit(x_train, y_train, validation_data=(x_val, y_val), epochs=3, batch_size=100)\n\n# Evaluate model\ncnn_score = model.evaluate(x_val, y_val)","metadata":{"execution":{"iopub.status.busy":"2024-03-13T12:51:52.387217Z","iopub.execute_input":"2024-03-13T12:51:52.387639Z","iopub.status.idle":"2024-03-13T12:56:05.995238Z","shell.execute_reply.started":"2024-03-13T12:51:52.387607Z","shell.execute_reply":"2024-03-13T12:56:05.994029Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_pred=model.predict(x_test)\ny_test = np.argmax(y_pred,axis=1)\nprint(y_test.shape)","metadata":{"execution":{"iopub.status.busy":"2024-03-13T12:56:21.131915Z","iopub.execute_input":"2024-03-13T12:56:21.132383Z","iopub.status.idle":"2024-03-13T12:56:35.126399Z","shell.execute_reply.started":"2024-03-13T12:56:21.132348Z","shell.execute_reply":"2024-03-13T12:56:35.125068Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample = pd.read_csv(\"../input/digit-recognizer/sample_submission.csv\")\ni = sample.ImageId\n\noutput = pd.DataFrame({'ImageId' : i,'Label': y_test})\noutput.head(20)","metadata":{"execution":{"iopub.status.busy":"2024-03-13T12:56:38.413912Z","iopub.execute_input":"2024-03-13T12:56:38.414311Z","iopub.status.idle":"2024-03-13T12:56:38.441285Z","shell.execute_reply.started":"2024-03-13T12:56:38.414280Z","shell.execute_reply":"2024-03-13T12:56:38.440108Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"output.to_csv('submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2024-03-13T12:56:51.866300Z","iopub.execute_input":"2024-03-13T12:56:51.868487Z","iopub.status.idle":"2024-03-13T12:56:51.914130Z","shell.execute_reply.started":"2024-03-13T12:56:51.868429Z","shell.execute_reply":"2024-03-13T12:56:51.912779Z"},"trusted":true},"execution_count":null,"outputs":[]}]}