{"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":"import tensorflow as tf\nimport matplotlib.pyplot as plt","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')\ntrain.head(3)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_labels = train['label']\ntrain_pixels = train.drop('label', axis=1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_pixels.shape","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_pixels = np.array(train_pixels)\ntrain_pixels = train_pixels.reshape(42000, 28, 28)\ntrain_pixels.shape","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.imshow(train_pixels[1])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = tf.keras.models.Sequential([\n  tf.keras.layers.Flatten(input_shape=(28, 28)),\n  tf.keras.layers.Dense(128, activation='relu'),\n  tf.keras.layers.Dropout(0.2),\n  tf.keras.layers.Dense(10)\n])\n\nloss_fn = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)\nmodel.compile(optimizer='adam', loss=loss_fn, metrics=['accuracy'])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.fit(train_pixels, train_labels, epochs=20)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test = pd.read_csv('/kaggle/input/digit-recognizer/test.csv')\ntest.shape","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test = np.array(test)\ntest = test.reshape(28000, 28, 28)\ntest.shape","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"prediction = model(test)\nprediction = tf.nn.softmax(prediction).numpy() #Shows probabilities\nprediction[0]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"prediction = [np.argmax(predict) for predict in prediction]\nprint(prediction[0])\nplt.imshow(test[0])  #The prediction correspond to the image","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission_df = {'ImageId' : range(1, len(prediction)+1), 'Label' : prediction}\nsubmission_df = pd.DataFrame(data=submission_df)\nsubmission_df.head(3)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission_df.to_csv('./submission.csv', index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}