{"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","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# handwritten number detector challange \nimport pandas as pd \nimport numpy as np\nfrom tensorflow import keras\nfrom tensorflow.keras import layers\nfrom tensorflow.keras.layers.experimental import preprocessing\nfrom sklearn.model_selection import train_test_split\nimport tensorflow as tf\nfrom tensorflow.keras.preprocessing import image_dataset_from_directory\n\n\nX_data = pd.read_csv('../input/digit-recognizer/train.csv')\nX_data_test = pd.read_csv('../input/digit-recognizer/test.csv')\n\ny = X_data.label          \nX_data.drop(['label'], axis=1, inplace=True)\n\n# print(X_data_train.head())\n# print()\n# print(y.head())\n\nX_train, X_valid, y_train, y_valid = train_test_split(X_data, y, train_size=0.75, test_size=0.25,\n                                                                random_state=0)\n\n# for x in X_train:\n#     x = tf.image.convert_image_dtype(x, dtype=tf.float32)\n# for x in X_valid:\n#     x = tf.image.convert_image_dtype(x, dtype=tf.float32)\n#X_train = np.expand_dims(X_train, axis=-1)\n#X_valid = np.expand_dims(X_valid, axis=-1)\nX_train = tf.reshape(X_train, (-1, 28, 28, 1))\nX_valid = tf.reshape(X_valid, (-1, 28, 28, 1))\n    \n# def convert_to_float(image):\n#     image = tf.image.convert_image_dtype(image, dtype=tf.float32)\n#     return image\n\n# AUTOTUNE = tf.data.experimental.AUTOTUNE\n# X_train = (\n#     X_train\n#     .map(convert_to_float)\n#     .cache()\n#     .prefetch(buffer_size=AUTOTUNE)\n# )\n# X_valid = (\n#     X_valid\n#     .map(convert_to_float)\n#     .cache()\n#     .prefetch(buffer_size=AUTOTUNE)\n# )\n\nmodel = keras.Sequential([\n    \n    layers.InputLayer(input_shape=[28, 28, 1]),\n    \n    preprocessing.RandomContrast(factor=0.10),\n    preprocessing.RandomTranslation(height_factor=0.02, width_factor=0.02),\n    preprocessing.RandomRotation(factor=0.04),\n    \n    \n    layers.Conv2D(filters=64, kernel_size=3, activation='relu', padding='same'),\n    #,input_shape=[28, 28, 1]\n    layers.MaxPool2D(),\n    \n    layers.BatchNormalization(renorm=True),\n    layers.Conv2D(filters=64, kernel_size=3, activation='relu', padding='same',input_shape=[28, 28, 1]),\n    layers.MaxPool2D(),\n    layers.Flatten(),\n    layers.BatchNormalization(renorm=True),\n    layers.Dense(100, activation='relu'),\n    #layers.Dropout(0.2),\n    layers.Dense(30, activation='relu'),    \n    layers.Dense(10, activation='softmax'),\n])\n\nmodel.compile(\n    optimizer='adam',\n    loss='sparse_categorical_crossentropy',\n    metrics=['accuracy'],\n)\n\n\nearly_stopping = keras.callbacks.EarlyStopping(\n    patience=10,\n    min_delta=0.01,\n    restore_best_weights=True,\n)\n\nhistory = model.fit(\n    X_train, y_train,\n    validation_data=(X_valid, y_valid),\n    batch_size=512,\n    epochs=30,\n    callbacks=[early_stopping],\n    #verbose=1,\n)\n\nhistory_df = pd.DataFrame(history.history)\n# Start the plot at epoch 1\nhistory_df.loc[1:, ['loss', 'val_loss']].plot()\nhistory_df.loc[1:, ['accuracy', 'val_accuracy']].plot()\n\n# print((\"Best Validation Loss: {:0.4f}\" +\\\n#       \"\\nBest Validation Accuracy: {:0.4f}\")\\\n#       .format(history_df['val_loss'].min(), \n#               history_df['val_binary_accuracy'].max()))\n\npredictions = model.predict(X_data_test)","metadata":{"execution":{"iopub.status.busy":"2021-12-16T09:54:11.372133Z","iopub.status.idle":"2021-12-16T09:54:11.372589Z","shell.execute_reply.started":"2021-12-16T09:54:11.372345Z","shell.execute_reply":"2021-12-16T09:54:11.37237Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}