{"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":"# 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":"2023-01-03T16:41:14.06623Z","iopub.execute_input":"2023-01-03T16:41:14.066847Z","iopub.status.idle":"2023-01-03T16:41:14.095775Z","shell.execute_reply.started":"2023-01-03T16:41:14.066718Z","shell.execute_reply":"2023-01-03T16:41:14.094421Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h2>TensorFlow :3 Import Libraries<h/2>","metadata":{}},{"cell_type":"code","source":"pip install tensorflow","metadata":{"execution":{"iopub.status.busy":"2023-01-03T16:41:57.699354Z","iopub.execute_input":"2023-01-03T16:41:57.699866Z","iopub.status.idle":"2023-01-03T16:42:37.023028Z","shell.execute_reply.started":"2023-01-03T16:41:57.699829Z","shell.execute_reply":"2023-01-03T16:42:37.021306Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np\nfrom tensorflow.keras.models import load_model\nfrom tkinter import *\nimport tkinter as tk\nfrom PIL import ImageGrab, Image\n\nfrom tensorflow import keras \nfrom tensorflow.keras.datasets import mnist\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Dropout, Flatten\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D\nfrom tensorflow.keras import backend as K\n\nimport pandas as pd\nimport tensorflow_datasets as tfds\nfrom sklearn.model_selection import train_test_split\nimport matplotlib.pyplot as plt","metadata":{"execution":{"iopub.status.busy":"2023-01-03T17:12:46.179176Z","iopub.execute_input":"2023-01-03T17:12:46.17966Z","iopub.status.idle":"2023-01-03T17:12:46.18974Z","shell.execute_reply.started":"2023-01-03T17:12:46.179622Z","shell.execute_reply":"2023-01-03T17:12:46.187657Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\ntest = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")","metadata":{"execution":{"iopub.status.busy":"2023-01-03T17:20:19.248291Z","iopub.execute_input":"2023-01-03T17:20:19.248834Z","iopub.status.idle":"2023-01-03T17:20:23.587987Z","shell.execute_reply.started":"2023-01-03T17:20:19.248794Z","shell.execute_reply":"2023-01-03T17:20:23.586695Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()","metadata":{"execution":{"iopub.status.busy":"2023-01-03T17:20:23.590344Z","iopub.execute_input":"2023-01-03T17:20:23.590894Z","iopub.status.idle":"2023-01-03T17:20:23.609759Z","shell.execute_reply.started":"2023-01-03T17:20:23.590854Z","shell.execute_reply":"2023-01-03T17:20:23.608823Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x = train.drop(['label'], axis = 1).values\ny = train[\"label\"]\n","metadata":{"execution":{"iopub.status.busy":"2023-01-03T17:34:59.259273Z","iopub.execute_input":"2023-01-03T17:34:59.259735Z","iopub.status.idle":"2023-01-03T17:34:59.381675Z","shell.execute_reply.started":"2023-01-03T17:34:59.2597Z","shell.execute_reply":"2023-01-03T17:34:59.379962Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=4, stratify=y)","metadata":{"execution":{"iopub.status.busy":"2023-01-03T17:35:00.100079Z","iopub.execute_input":"2023-01-03T17:35:00.100616Z","iopub.status.idle":"2023-01-03T17:35:00.579278Z","shell.execute_reply.started":"2023-01-03T17:35:00.100567Z","shell.execute_reply":"2023-01-03T17:35:00.576498Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(x_train.shape, y_train.shape)","metadata":{"execution":{"iopub.status.busy":"2023-01-03T17:35:00.668191Z","iopub.execute_input":"2023-01-03T17:35:00.669452Z","iopub.status.idle":"2023-01-03T17:35:00.679144Z","shell.execute_reply.started":"2023-01-03T17:35:00.66939Z","shell.execute_reply":"2023-01-03T17:35:00.676712Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.imshow(train.iloc[0,1:].values.reshape(28,28))\n","metadata":{"execution":{"iopub.status.busy":"2023-01-03T17:35:02.255983Z","iopub.execute_input":"2023-01-03T17:35:02.256659Z","iopub.status.idle":"2023-01-03T17:35:02.440908Z","shell.execute_reply.started":"2023-01-03T17:35:02.256622Z","shell.execute_reply":"2023-01-03T17:35:02.43956Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.imshow(test.iloc[0,:].values.reshape(28,28))","metadata":{"execution":{"iopub.status.busy":"2023-01-03T17:35:03.266356Z","iopub.execute_input":"2023-01-03T17:35:03.266864Z","iopub.status.idle":"2023-01-03T17:35:03.509224Z","shell.execute_reply.started":"2023-01-03T17:35:03.266826Z","shell.execute_reply":"2023-01-03T17:35:03.507971Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x_train.reshape(-1,28,28,1)\nx_test.reshape(-1,28,28,1)\ninput_shape = (28,28,1)\n","metadata":{"execution":{"iopub.status.busy":"2023-01-03T17:35:04.141304Z","iopub.execute_input":"2023-01-03T17:35:04.141788Z","iopub.status.idle":"2023-01-03T17:35:04.148715Z","shell.execute_reply.started":"2023-01-03T17:35:04.141753Z","shell.execute_reply":"2023-01-03T17:35:04.147539Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x_train = x_train.reshape(x_train.shape[0], 28, 28, 1)\nx_test = x_test.reshape(x_test.shape[0], 28, 28, 1)\ny_test = y_test.values.reshape(y_test.shape[0], 1)","metadata":{"execution":{"iopub.status.busy":"2023-01-03T17:35:04.949148Z","iopub.execute_input":"2023-01-03T17:35:04.949619Z","iopub.status.idle":"2023-01-03T17:35:04.956824Z","shell.execute_reply.started":"2023-01-03T17:35:04.949582Z","shell.execute_reply":"2023-01-03T17:35:04.955217Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_train = keras.utils.to_categorical(y_train, 10)\ny_test = keras.utils.to_categorical(y_test, 10)\nx_train = x_train.astype('float32')\nx_test = x_test.astype('float32')\nx_train /= 255\nx_test /= 255\nprint('x_train shape:', x_train.shape)\nprint(x_train.shape[0], 'train samples')\nprint(x_test.shape[0], 'test samples')","metadata":{"execution":{"iopub.status.busy":"2023-01-03T17:35:06.573008Z","iopub.execute_input":"2023-01-03T17:35:06.573501Z","iopub.status.idle":"2023-01-03T17:35:06.674921Z","shell.execute_reply.started":"2023-01-03T17:35:06.573448Z","shell.execute_reply":"2023-01-03T17:35:06.673423Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"batch_size = 128\nnum_classes = 10\nepochs = 30\nmodel = Sequential()\nmodel.add(Conv2D(32, kernel_size=(3, 3),\n                    activation='relu',\n                    input_shape=input_shape))\nmodel.add(Conv2D(64, (3, 3), activation='relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(num_classes, activation='softmax'))\n\nmodel.compile(loss=keras.losses.categorical_crossentropy,\n                optimizer=keras.optimizers.Adadelta(),\n                metrics=['accuracy'])\n\nmodel.fit(x_train, y_train,\n            batch_size=batch_size,\n            epochs=epochs,\n            verbose=1,\n            validation_data=(x_test, y_test))\n\nprint(\"The model has successfully trained\")\nscore = model.evaluate(x_test, y_test, verbose=0)\nprint('Test loss:', score[0])\nprint('Test accuracy:', score[1])","metadata":{"execution":{"iopub.status.busy":"2023-01-03T17:35:11.863212Z","iopub.execute_input":"2023-01-03T17:35:11.864066Z","iopub.status.idle":"2023-01-03T17:51:29.230446Z","shell.execute_reply.started":"2023-01-03T17:35:11.864025Z","shell.execute_reply":"2023-01-03T17:51:29.229063Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = pd.read_csv('../input/digit-recognizer/sample_submission.csv')\ny_pred = model.predict(test)\ny_pred = np.argmax(y_pred, axis=1)\nsubmission['Label'] = y_pred\nsubmission.to_csv('submission.csv', index=False)\n    \n\n#check the first image\nplt.imshow(test[0])","metadata":{"execution":{"iopub.status.busy":"2023-01-03T17:56:45.201286Z","iopub.execute_input":"2023-01-03T17:56:45.202743Z","iopub.status.idle":"2023-01-03T17:56:54.176722Z","shell.execute_reply.started":"2023-01-03T17:56:45.202692Z","shell.execute_reply":"2023-01-03T17:56:54.17553Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission.head()","metadata":{"execution":{"iopub.status.busy":"2023-01-03T17:56:56.842507Z","iopub.execute_input":"2023-01-03T17:56:56.842974Z","iopub.status.idle":"2023-01-03T17:56:56.855752Z","shell.execute_reply.started":"2023-01-03T17:56:56.842937Z","shell.execute_reply":"2023-01-03T17:56:56.853792Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"batch_size = 128\nnum_classes = 10\nepochs = 50\nmodel = Sequential()\nmodel.add(Conv2D(32, kernel_size=(3, 3),\n                    activation='relu',\n                    input_shape=input_shape))\nmodel.add(Conv2D(64, (3, 3), activation='relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.35))\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(num_classes, activation='softmax'))\n\nmodel.compile(loss=keras.losses.categorical_crossentropy,\n                optimizer=keras.optimizers.Adadelta(),\n                metrics=['accuracy'])\n\nmodel.fit(x_train, y_train,\n            batch_size=batch_size,\n            epochs=epochs,\n            verbose=1,\n            validation_data=(x_test, y_test))\n\nprint(\"The model has successfully trained\")\nscore = model.evaluate(x_test, y_test, verbose=0)\nprint('Test loss:', score[0])\nprint('Test accuracy:', score[1])","metadata":{"execution":{"iopub.status.busy":"2023-01-03T17:59:15.393213Z","iopub.execute_input":"2023-01-03T17:59:15.393749Z","iopub.status.idle":"2023-01-03T18:25:36.956448Z","shell.execute_reply.started":"2023-01-03T17:59:15.39371Z","shell.execute_reply":"2023-01-03T18:25:36.955535Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = pd.read_csv('../input/digit-recognizer/sample_submission.csv')\ny_pred2 = model.predict(test)\ny_pred2= np.argmax(y_pred2, axis=1)\nsubmission['Label'] = y_pred2\nsubmission.to_csv('submission2.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2023-01-03T18:25:40.318728Z","iopub.execute_input":"2023-01-03T18:25:40.319509Z","iopub.status.idle":"2023-01-03T18:25:48.322547Z","shell.execute_reply.started":"2023-01-03T18:25:40.319457Z","shell.execute_reply":"2023-01-03T18:25:48.321563Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}