{"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":"# **1.0** Importing libraries and Datasets ","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"**1.1 Importing Libraries **","execution_count":null},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import pandas as ps \nimport numpy as np \nimport seaborn as sns \nimport matplotlib.pyplot as plt \nimport seaborn as sns \nimport tensorflow as tf \nfrom tensorflow.keras.preprocessing.image  import ImageDataGenerator  ","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**1.2 Importing Datasets **","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\ntest = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train = train['label'] \nx_train = train.drop(labels=['label'],axis = 1)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**1.3 Normalization **","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = x_train/255\ntest = test/255 ","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**1.3 Reshaping the data matrix **","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = x_train.values.reshape(-1,28,28,1)\ntest = test.values.reshape(-1,28,28,1)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**1.4 Label encoding **","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train = tf.keras.utils.to_categorical(y_train)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**1.5 Spliting The Dataset**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nx_train , x_val,y_train, y_val = train_test_split(x_train,y_train,random_state=8,test_size = 0.1)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**1.6 Data Visvalization**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"for i in range (10) :\n    plt.imshow(x_train[i][:,:,0])\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# 3.0 CNN Model","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"**3.1 Defining model Archictect**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"model = tf.keras.models.Sequential()\nmodel.add(tf.keras.layers.Conv2D(filters=32,kernel_size=(5,5),padding=\"Same\",activation='relu',input_shape=(28,28,1)))\nmodel.add(tf.keras.layers.Conv2D(filters=32,kernel_size=(5,5),padding=\"Same\",activation='relu'))\nmodel.add(tf.keras.layers.MaxPool2D(pool_size=(2,2)))\nmodel.add(tf.keras.layers.Conv2D(filters=32,kernel_size=(5,5),padding=\"Same\",activation='relu'))\nmodel.add(tf.keras.layers.Conv2D(filters=32,kernel_size=(5,5),padding=\"Same\",activation='relu'))\nmodel.add(tf.keras.layers.MaxPool2D(pool_size=(2,2),strides=(2,2)))\nmodel.add(tf.keras.layers.Flatten())\nmodel.add(tf.keras.layers.Dense(256, activation = \"relu\"))\nmodel.add(tf.keras.layers.Dense(10, activation = \"softmax\"))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer = 'adam' , loss = \"categorical_crossentropy\", metrics=[\"accuracy\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"datagen = ImageDataGenerator(\n        featurewise_center=False,  # set input mean to 0 over the dataset\n        samplewise_center=False,  # set each sample mean to 0\n        featurewise_std_normalization=False,  # divide inputs by std of the dataset\n        samplewise_std_normalization=False,  # divide each input by its std\n        zca_whitening=False,  # apply ZCA whitening\n        rotation_range=10,  # randomly rotate images in the range (degrees, 0 to 180)\n        zoom_range = 0.1, # Randomly zoom image \n        width_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)\n        height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)\n        horizontal_flip=False,  # randomly flip images\n        vertical_flip=False)  # randomly flip images\n\n\ndatagen.fit(x_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit_generator(datagen.flow(x_train,y_train, batch_size=86),\n                              epochs = 30, validation_data = (x_val,y_val),\n                              verbose = 2, steps_per_epoch=x_train.shape[0] // 86)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**3.2 checking how accuracy increases **","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, ax = plt.subplots(2,1)\nax[0].plot(history.history['loss'], color='b', label=\"Training loss\")\nax[0].plot(history.history['val_loss'], color='r', label=\"validation loss\",axes =ax[0])\nlegend = ax[0].legend(loc='best', shadow=True)\n\nax[1].plot(history.history['accuracy'], color='b', label=\"Training accuracy\")\nax[1].plot(history.history['val_accuracy'], color='r',label=\"Validation accuracy\")\nlegend = ax[1].legend(loc='best', shadow=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import itertools\nfrom sklearn.metrics import confusion_matrix\ndef plot_confusion_matrix(cm, classes,\n                          normalize=False,\n                          title='Confusion matrix',\n                          cmap=plt.cm.Blues):\n    \"\"\"\n    This function prints and plots the confusion matrix.\n    Normalization can be applied by setting `normalize=True`.\n    \"\"\"\n    plt.imshow(cm, interpolation='nearest', cmap=cmap)\n    plt.title(title)\n    plt.colorbar()\n    tick_marks = np.arange(len(classes))\n    plt.xticks(tick_marks, classes, rotation=45)\n    plt.yticks(tick_marks, classes)\n\n    if normalize:\n        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]\n\n    thresh = cm.max() / 2.\n    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):\n        plt.text(j, i, cm[i, j],\n                 horizontalalignment=\"center\",\n                 color=\"white\" if cm[i, j] > thresh else \"black\")\n\n    plt.tight_layout()\n    plt.ylabel('True label')\n    plt.xlabel('Predicted label')\n# Predict the values from the validation dataset\nY_pred = model.predict(x_val)\n# Convert predictions classes to one hot vectors \nY_pred_classes = np.argmax(Y_pred,axis = 1) \n# Convert validation observations to one hot vectors\nY_true = np.argmax(y_val,axis = 1) \n# compute the confusion matrix\nconfusion_mtx = confusion_matrix(Y_true, Y_pred_classes) \n# plot the confusion matrix\nplot_confusion_matrix(confusion_mtx, classes = range(10)) \n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Display some error results \n\n# Errors are difference between predicted labels and true labels\nerrors = (Y_pred_classes - Y_true != 0)\n\nY_pred_classes_errors = Y_pred_classes[errors]\nY_pred_errors = Y_pred[errors]\nY_true_errors = Y_true[errors]\nX_val_errors = x_val[errors]\n\ndef display_errors(errors_index,img_errors,pred_errors, obs_errors):\n    \"\"\" This function shows 6 images with their predicted and real labels\"\"\"\n    n = 0\n    nrows = 2\n    ncols = 3\n    fig, ax = plt.subplots(nrows,ncols,sharex=True,sharey=True)\n    for row in range(nrows):\n        for col in range(ncols):\n            error = errors_index[n]\n            ax[row,col].imshow((img_errors[error]).reshape((28,28)))\n            ax[row,col].set_title(\"Predicted label :{}\\nTrue label :{}\".format(pred_errors[error],obs_errors[error]))\n            n += 1\n# Probabilities of the wrong predicted numbers\nY_pred_errors_prob = np.max(Y_pred_errors,axis = 1)\n\n# Predicted probabilities of the true values in the error set\ntrue_prob_errors = np.diagonal(np.take(Y_pred_errors, Y_true_errors, axis=1))\n\n# Difference between the probability of the predicted label and the true label\ndelta_pred_true_errors = Y_pred_errors_prob - true_prob_errors\n\n# Sorted list of the delta prob errors\nsorted_dela_errors = np.argsort(delta_pred_true_errors)\n\n# Top 6 errors \nmost_important_errors = sorted_dela_errors[-6:]\n\n# Show the top 6 errors\ndisplay_errors(most_important_errors, X_val_errors, Y_pred_classes_errors, Y_true_errors)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# predict results\nresults = model.predict(test)\n\n# select the indix with the maximum probability\nresults = np.argmax(results,axis = 1)\n\nresults = pd.Series(results,name=\"Label\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),results],axis = 1)\n\nsubmission.to_csv(\"cnn_mnist_datagen.csv\",index=False)","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}