{"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":"markdown","source":"## Library Imports","metadata":{}},{"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom keras.models import Sequential\nfrom keras.layers import Dense,MaxPool2D,Conv2D,Dropout,Flatten,Activation,Dropout\nfrom tensorflow.keras.callbacks import EarlyStopping\nfrom sklearn.model_selection import train_test_split\nfrom tensorflow import keras\nfrom sklearn.model_selection import train_test_split\nimport matplotlib.pyplot as plt","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"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')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Data Preprocessing","metadata":{}},{"cell_type":"code","source":"train_df.shape","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df['label'].unique()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X = train_df.drop('label',axis=1)\ny = train_df['label']","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Scale images to the [0, 1] range\nX = X.astype(\"float32\")/255.0","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Reshape images\nX = X.values.reshape(-1, 28, 28, 1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"NumClass = 10\nInputShape = (28, 28, 1)","metadata":{"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=0.25, random_state=101)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Convert class vectors to binary class matrices\ny_train = keras.utils.to_categorical(y_train, NumClass)\ny_test = keras.utils.to_categorical(y_test, NumClass)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Model Building","metadata":{}},{"cell_type":"code","source":"model = Sequential()\nmodel.add(Conv2D(input_shape=(InputShape), filters=64, kernel_size=(3,3), padding='same', activation='relu'))\nmodel.add(Conv2D(filters=64, kernel_size=(3,3), padding='same', activation='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\n\nmodel.add(Conv2D(filters=64, kernel_size=(3,3), padding='same', activation='relu'))\nmodel.add(Conv2D(filters=64, kernel_size=(3,3), padding='same', activation='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\n\nmodel.add(Conv2D(filters=64, kernel_size=(3,3), padding='same', activation='relu'))\nmodel.add(Conv2D(filters=64, kernel_size=(3,3), padding='same', activation='relu'))\nmodel.add(Conv2D(filters=64, kernel_size=(3,3), padding='same', activation='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\n\nmodel.add(Conv2D(filters=64, kernel_size=(3,3), padding='same', activation='relu'))\nmodel.add(Conv2D(filters=64, kernel_size=(3,3), padding='same', activation='relu'))\nmodel.add(Conv2D(filters=64, kernel_size=(3,3), padding='same', activation='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\n\nmodel.add(Flatten())\n\nmodel.add(Dense(units=4080, activation='relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(units=4080, activation='relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(units=10, activation='softmax'))\nmodel.summary()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"early_stop = EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=25)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=[\"accuracy\"])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"BatchSize = 64\nEpochs = 100","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"history = model.fit(X_train, y_train, batch_size=BatchSize, epochs=Epochs,validation_data=(X_test,y_test), callbacks=[early_stop])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"loss_df = pd.DataFrame(history.history)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"acuracy = history.history['accuracy']\nval_accuracy = history.history['val_accuracy']\nloss = history.history['loss']\nval_loss = history.history['val_loss']\n\nplt.figure(figsize=(6,5))\nplt.plot(acuracy, color='green', label = 'Training Accuracy')\nplt.plot(val_accuracy, color='red', label = 'Validation Accuracy')\nplt.legend()\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"loss = history.history['loss']\nval_loss = history.history['val_loss']\n\nplt.figure(figsize=(6,5))\nplt.plot(loss, color='green', label = 'Training Loss')\nplt.plot(val_loss, color='red', label = 'Validation Loss')\nplt.legend()\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 99% Accuracy On Train Set","metadata":{}},{"cell_type":"code","source":"model.evaluate(X_train,y_train)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 98% Accuracy On Test Set","metadata":{}},{"cell_type":"code","source":"model.evaluate(X_test,y_test)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Test code for Submission","metadata":{}},{"cell_type":"code","source":"X_submit = test_df","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Scale images in 0,1\nX_submit = X_submit.astype('float32')/255.0","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Reshape images\nX_new = X_submit.values.reshape(-1, 28, 28, 1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predict = model.predict(X_new)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_pred = np.argmax(predict,axis=1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(test_pred.shape)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predict = keras.utils.to_categorical(predict, NumClass)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample_submission = pd.read_csv('/kaggle/input/digit-recognizer/sample_submission.csv')\nsample_submission","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"index = sample_submission.ImageId\ndata = {'ImageId':index, 'Label':test_pred}\nfinal_df = pd.DataFrame(data)\nfinal_df.head","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"final_df.to_csv('submission.csv', index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"os.listdir('/kaggle/working')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}