{"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":"markdown","source":"# Topicos Especiais II - Bruno Simões","metadata":{}},{"cell_type":"markdown","source":"# Bibliotecas e Dados","metadata":{}},{"cell_type":"code","source":"# Bibliotecas necessárias\n# Manipulação de dados\nimport pandas as pd\n# Redes Neurais\nfrom tensorflow import keras\nfrom tensorflow.keras.datasets import mnist\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Dropout, Conv2D, MaxPooling2D, Flatten\nfrom tensorflow.keras.optimizers import RMSprop\n# Plot\nimport matplotlib.pyplot as plt\n%matplotlib inline\n# Avaliação\nfrom sklearn.metrics import classification_report, confusion_matrix\n","metadata":{"ExecuteTime":{"end_time":"2019-01-16T20:39:41.500258Z","start_time":"2019-01-16T20:39:39.261856Z"},"execution":{"iopub.status.busy":"2022-03-11T00:54:32.868607Z","iopub.execute_input":"2022-03-11T00:54:32.869126Z","iopub.status.idle":"2022-03-11T00:54:32.878106Z","shell.execute_reply.started":"2022-03-11T00:54:32.869087Z","shell.execute_reply":"2022-03-11T00:54:32.877111Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Lendo o dataset Kaggle\ntrain = pd.read_csv(\"../input/digit-recognizer/train.csv\")\n\n#Alternativa ler do próprio keras\n#(x_train, y_train), (x_test, y_test) = mnist.load_data()\n","metadata":{"execution":{"iopub.status.busy":"2022-03-11T00:54:32.879784Z","iopub.execute_input":"2022-03-11T00:54:32.880281Z","iopub.status.idle":"2022-03-11T00:54:35.443568Z","shell.execute_reply.started":"2022-03-11T00:54:32.880251Z","shell.execute_reply":"2022-03-11T00:54:35.442450Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Analisando o dataset\nprint(\"Quantidade de elementos de treino: {}\". format(len(train)))\nprint(train.head())","metadata":{"execution":{"iopub.status.busy":"2022-03-11T00:54:35.444961Z","iopub.execute_input":"2022-03-11T00:54:35.445243Z","iopub.status.idle":"2022-03-11T00:54:35.456411Z","shell.execute_reply.started":"2022-03-11T00:54:35.445216Z","shell.execute_reply":"2022-03-11T00:54:35.455545Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Separando x_train e y_train\nY = train[\"label\"]\nX = train.drop(labels = [\"label\"],axis = 1)\nprint(X.head())\n# Em formato numpy array de imagens 28 x 28\n#x = X.values.reshape(-1,28,28,1)\n#print(x[0])","metadata":{"execution":{"iopub.status.busy":"2022-03-11T00:54:35.458383Z","iopub.execute_input":"2022-03-11T00:54:35.458660Z","iopub.status.idle":"2022-03-11T00:54:35.612376Z","shell.execute_reply.started":"2022-03-11T00:54:35.458631Z","shell.execute_reply":"2022-03-11T00:54:35.611594Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(X.shape)","metadata":{"execution":{"iopub.status.busy":"2022-03-11T00:54:35.614358Z","iopub.execute_input":"2022-03-11T00:54:35.614817Z","iopub.status.idle":"2022-03-11T00:54:35.624776Z","shell.execute_reply.started":"2022-03-11T00:54:35.614779Z","shell.execute_reply":"2022-03-11T00:54:35.623973Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Transformando a imagem 2d em um numpy array (imagem 28*28)\nx = X.values.reshape(42000, 28, 28, 1)\n\n#Normalizando para valores entre 0 e 1\nx = x.astype('float32')\nx /= 255\n\n#print(x[0])","metadata":{"ExecuteTime":{"end_time":"2019-01-08T20:49:57.425537Z","start_time":"2019-01-08T20:49:57.272377Z"},"execution":{"iopub.status.busy":"2022-03-11T00:54:35.625942Z","iopub.execute_input":"2022-03-11T00:54:35.626395Z","iopub.status.idle":"2022-03-11T00:54:35.741932Z","shell.execute_reply.started":"2022-03-11T00:54:35.626356Z","shell.execute_reply":"2022-03-11T00:54:35.740932Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Vamos ajustar o formato da saida\nnum_classes = 10\n\n# Convertendo para um vetor de saida com 10 dimensoes\n# ex. 8 => [0,0,0,0,0,0,0,0,1,0]\ny = keras.utils.to_categorical(Y, num_classes)\nprint(y[0])","metadata":{"ExecuteTime":{"end_time":"2019-01-08T20:50:48.007428Z","start_time":"2019-01-08T20:50:47.986527Z"},"execution":{"iopub.status.busy":"2022-03-11T00:54:35.743081Z","iopub.execute_input":"2022-03-11T00:54:35.743508Z","iopub.status.idle":"2022-03-11T00:54:35.750399Z","shell.execute_reply.started":"2022-03-11T00:54:35.743478Z","shell.execute_reply":"2022-03-11T00:54:35.749556Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Separando uma parte para treino (90%) e outra para validação (10%)\nfrom sklearn.model_selection import train_test_split\nx_train, x_val, y_train, y_val = train_test_split(x, y, test_size = 0.1, random_state=5)\nprint('Qtde de treino: {}'.format(len(x_train)))\nprint('Qtde de validação: {}'.format(len(x_val)))","metadata":{"execution":{"iopub.status.busy":"2022-03-11T00:54:35.751671Z","iopub.execute_input":"2022-03-11T00:54:35.752531Z","iopub.status.idle":"2022-03-11T00:54:36.277906Z","shell.execute_reply.started":"2022-03-11T00:54:35.752488Z","shell.execute_reply":"2022-03-11T00:54:36.277055Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Criando e treinando o Modelo","metadata":{}},{"cell_type":"code","source":"# Alterações feitas nesse trabalho:\n# Conv2d: \n#    Filtros (Tamanho das camadas de saída) = 1º: 30, 2º: 35\n#    kernel_size = 1º: (5, 5), 2º: (5, 5)\n#    1ª função de ativação = 'softmax'\n# Pooling\n#    pool_size = (3, 3)\n# Penultima camada Dense: funcao de ativacao = 'relu'\n# Dropout: 0.3\n# Ultima funcao de ativacao: sigmoid\n\nmodel = Sequential()\nmodel.add(Conv2D(30, kernel_size=(5, 5),\n                 activation='softmax',\n                 input_shape=(28,28,1)))\n\nmodel.add(MaxPooling2D(pool_size=(3, 3)))\nmodel.add(Conv2D(35, kernel_size=(3,3), activation='relu'))\nmodel.add(Flatten())\n\nmodel.add(Dense(50, activation='relu'))\nmodel.add(Dropout(0.3))\nmodel.add(Dense(num_classes, activation='sigmoid'))\nmodel.summary()","metadata":{"ExecuteTime":{"end_time":"2019-01-08T21:38:00.233865Z","start_time":"2019-01-08T21:38:00.15079Z"},"scrolled":true,"execution":{"iopub.status.busy":"2022-03-11T00:54:36.279014Z","iopub.execute_input":"2022-03-11T00:54:36.279419Z","iopub.status.idle":"2022-03-11T00:54:36.350794Z","shell.execute_reply.started":"2022-03-11T00:54:36.279390Z","shell.execute_reply":"2022-03-11T00:54:36.349955Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Compila o modelo\nmodel.compile(loss='categorical_crossentropy',\n              optimizer=RMSprop(),\n              metrics=['accuracy'])","metadata":{"ExecuteTime":{"end_time":"2019-01-08T21:33:17.184644Z","start_time":"2019-01-08T21:33:17.129141Z"},"execution":{"iopub.status.busy":"2022-03-11T00:54:36.351852Z","iopub.execute_input":"2022-03-11T00:54:36.352275Z","iopub.status.idle":"2022-03-11T00:54:36.384912Z","shell.execute_reply.started":"2022-03-11T00:54:36.352247Z","shell.execute_reply":"2022-03-11T00:54:36.384087Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Alterações feitas nesse trabalho:\n#   Epocas = 20\n#   batch_size = 40\n\nbatch_size = 40\nepochs = 20\n\n#Salvar o melhor modelo\ncallbacks_list = [\n    keras.callbacks.ModelCheckpoint(\n        filepath='model.h5',\n        monitor='val_loss', save_best_only=True, verbose=1),\n    keras.callbacks.EarlyStopping(monitor='val_loss', patience=10,verbose=1)\n]\n\nhistory = model.fit(x_train, y_train,\n                    batch_size=batch_size,\n                    epochs=epochs,\n                    callbacks = callbacks_list,\n                    verbose=1,\n                    validation_data=(x_val, y_val))","metadata":{"ExecuteTime":{"end_time":"2019-01-08T21:36:15.501168Z","start_time":"2019-01-08T21:33:19.322895Z"},"execution":{"iopub.status.busy":"2022-03-11T00:54:36.385956Z","iopub.execute_input":"2022-03-11T00:54:36.386370Z","iopub.status.idle":"2022-03-11T01:00:38.281909Z","shell.execute_reply.started":"2022-03-11T00:54:36.386341Z","shell.execute_reply":"2022-03-11T01:00:38.280731Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Vamos ver como foi o treino?\n\nfig, ax = plt.subplots(1,2, figsize=(16,8))\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)","metadata":{"ExecuteTime":{"end_time":"2019-01-08T21:36:20.243921Z","start_time":"2019-01-08T21:36:20.064201Z"},"execution":{"iopub.status.busy":"2022-03-11T01:00:38.283975Z","iopub.execute_input":"2022-03-11T01:00:38.284310Z","iopub.status.idle":"2022-03-11T01:00:38.613237Z","shell.execute_reply.started":"2022-03-11T01:00:38.284278Z","shell.execute_reply":"2022-03-11T01:00:38.611908Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras.models import load_model\n# Load the best saved model\nmodel = load_model('model.h5')","metadata":{"execution":{"iopub.status.busy":"2022-03-11T01:00:38.614853Z","iopub.execute_input":"2022-03-11T01:00:38.615293Z","iopub.status.idle":"2022-03-11T01:00:39.104965Z","shell.execute_reply.started":"2022-03-11T01:00:38.615236Z","shell.execute_reply":"2022-03-11T01:00:39.103948Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Testa\nscore = model.evaluate(x_val, y_val, verbose=0)\nprint('Test loss:', score[0])\nprint('Test accuracy:', score[1])","metadata":{"ExecuteTime":{"end_time":"2019-01-08T21:36:39.779842Z","start_time":"2019-01-08T21:36:38.946173Z"},"execution":{"iopub.status.busy":"2022-03-11T01:00:39.106476Z","iopub.execute_input":"2022-03-11T01:00:39.107107Z","iopub.status.idle":"2022-03-11T01:00:39.947038Z","shell.execute_reply.started":"2022-03-11T01:00:39.107058Z","shell.execute_reply":"2022-03-11T01:00:39.945765Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Testando uma entrada qualquer\nprint(y_train[10])\nprint(model.predict(x_train[10].reshape((1,28,28,1))))\nprint(model.predict_classes(x_train[10].reshape((1,28,28,1))))","metadata":{"ExecuteTime":{"end_time":"2019-01-08T21:06:04.363715Z","start_time":"2019-01-08T21:06:04.27849Z"},"execution":{"iopub.status.busy":"2022-03-11T01:00:39.948582Z","iopub.execute_input":"2022-03-11T01:00:39.948983Z","iopub.status.idle":"2022-03-11T01:00:40.057867Z","shell.execute_reply.started":"2022-03-11T01:00:39.948939Z","shell.execute_reply":"2022-03-11T01:00:40.056871Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Avaliando o Modelo","metadata":{}},{"cell_type":"code","source":"import itertools\n\n#Plot the confusion matrix. Set Normalize = True/False\ndef plot_confusion_matrix(cm, classes, normalize=True, title='Confusion matrix', 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.figure(figsize=(10,10))\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    if normalize:\n        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]\n        cm = np.around(cm, decimals=2)\n        cm[np.isnan(cm)] = 0.0\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    plt.tight_layout()\n    plt.ylabel('True label')\n    plt.xlabel('Predicted label')","metadata":{"execution":{"iopub.status.busy":"2022-03-11T01:00:40.059514Z","iopub.execute_input":"2022-03-11T01:00:40.059810Z","iopub.status.idle":"2022-03-11T01:00:40.070624Z","shell.execute_reply.started":"2022-03-11T01:00:40.059780Z","shell.execute_reply":"2022-03-11T01:00:40.069563Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Vendo alguns reports# Vendo alguns reports\n# Usando sklearn\nimport numpy as np\n\n# Classificando toda base de teste\ny_pred = model.predict_classes(x_val)\n# voltando pro formato de classes\ny_test_c = np.argmax(y_val, axis=1)\ntarget_names = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9']\n\n#Confution Matrix\ncm = confusion_matrix(y_test_c, y_pred)\nplot_confusion_matrix(cm, target_names, normalize=False, title='Confusion Matrix')\n\nprint('Classification Report')\nprint(classification_report(y_test_c, y_pred, target_names=target_names))","metadata":{"ExecuteTime":{"end_time":"2019-01-08T21:24:57.7654Z","start_time":"2019-01-08T21:24:57.220867Z"},"execution":{"iopub.status.busy":"2022-03-11T01:00:40.072119Z","iopub.execute_input":"2022-03-11T01:00:40.072422Z","iopub.status.idle":"2022-03-11T01:00:41.334936Z","shell.execute_reply.started":"2022-03-11T01:00:40.072393Z","shell.execute_reply":"2022-03-11T01:00:41.333716Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Gerando Saída","metadata":{}},{"cell_type":"code","source":"# Gerando saída para dataset de teste\n\n#Carrega dataset de teste\ntest = pd.read_csv(\"../input/digit-recognizer/test.csv\")\nprint(\"Qtde de testes: {}\".format(len(test)))\n# Bota no formato numpy e normaliza\nx_test = test.values.reshape(len(test),28,28,1)\nx_test = x_test.astype('float32')\nx_test /= 255\n\n# Faz classificação para dataset de teste\ny_pred = model.predict_classes(x_test)\n\n# Verficando algum exemplo\ni = 0\nplt.imshow(test.values[i].reshape(28,28), cmap=plt.cm.binary)\nplt.show()\nprint('Previsto: {}'.format(y_pred[i]))\n\n# Botando no formato de saída (competição Kaggle)\nresults = pd.Series(y_pred,name=\"Label\")\nsubmission = pd.concat([pd.Series(range(1,len(y_pred)+1),name = \"ImageId\"),results],axis = 1)\nprint(submission.head(10))\n#Salvando Arquivo\nsubmission.to_csv(\"submission.csv\",index=False)","metadata":{"execution":{"iopub.status.busy":"2022-03-11T01:00:41.336629Z","iopub.execute_input":"2022-03-11T01:00:41.337055Z","iopub.status.idle":"2022-03-11T01:00:47.943020Z","shell.execute_reply.started":"2022-03-11T01:00:41.336990Z","shell.execute_reply":"2022-03-11T01:00:47.941935Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Teste Adicional: Com ruído","metadata":{}},{"cell_type":"code","source":"#introduzindo ruido\nimport numpy as np\nmean = 0.\nstddev = 0.2\nnoise = np.random.normal(mean, stddev, (4200, 28, 28,1))\nx_te = x_val + noise\nx_te = np.clip(x_te, 0., 1.)\n\nplt.imshow(x_te.reshape(4200, 28,28)[0], cmap=plt.cm.binary)\nplt.show()\n\n# Testa\nscore = model.evaluate(x_te, y_val, verbose=0)\nprint('Test loss:', score[0])\nprint('Test accuracy:', score[1])","metadata":{"execution":{"iopub.status.busy":"2022-03-11T01:00:47.946265Z","iopub.execute_input":"2022-03-11T01:00:47.946577Z","iopub.status.idle":"2022-03-11T01:00:49.089913Z","shell.execute_reply.started":"2022-03-11T01:00:47.946545Z","shell.execute_reply":"2022-03-11T01:00:49.088972Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Com ruído, percebemos que a acurácia dos exemplos de validação caiu, mas muito menos que o modelo MLP clássico (ver exemplo de MLP).\nUm modelo Convolucional (CNN) captura melhor regiões, ou padrões espaciais de pixels, tornando o modelo mais robusto.","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}