{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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 5GB 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","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Data preprocessing**","execution_count":null},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_df = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')\ntest_df = pd.read_csv('/kaggle/input/digit-recognizer/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = train_df['label']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = train_df.drop('label',axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = X.values.reshape(-1,28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from matplotlib import pyplot as plt","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y[45]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = X / 255","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y[23]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.utils import to_categorical","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_cat = to_categorical(y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_cat[0].shape","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Making an CNN**\n","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Activation, Dropout, Flatten, Dense, Conv2D, MaxPooling2D","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(filters=16, kernel_size=(2,2),input_shape=(28,28,1), activation='relu',))\nmodel.add(MaxPooling2D(pool_size=(1, 1)))\n\nmodel.add(Conv2D(filters=32, kernel_size=(2,2),input_shape=(28,28,1), activation='relu',))\nmodel.add(MaxPooling2D(pool_size=(1, 1)))\n\nmodel.add(Conv2D(filters=64, kernel_size=(2,2),input_shape=(28,28,1), activation='relu',))\nmodel.add(MaxPooling2D(pool_size=(1, 1)))\n\n\nmodel.add(Flatten())\n\nmodel.add(Dense(128))\nmodel.add(Activation('relu'))\nmodel.add(Dropout(0.5))\n\nmodel.add(Dense(10))\nmodel.add(Activation('softmax'))\n\nmodel.compile(loss='categorical_crossentropy',\n              optimizer='adam',\n              metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(X,y_cat,epochs=5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df = test_df/255","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df = test_df.values.reshape(-1,28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_pred = model.predict(test_df)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Preparing for submission**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions = np.argmax(test_pred,axis = 1)\npredictions = pd.Series(predictions,name=\"Label\")\nsubmission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),predictions],axis = 1)\n\nsubmission.to_csv(\"submission_final.csv\",index=False)\n\n","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}