{"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":"# Introdução","metadata":{}},{"cell_type":"markdown","source":"**Resumo:**\n\nO exemplo aqui desenvolvido tem como objetivo apresentar conceitos iniciais de implementação de redes neurais com python e tensorflow/keras. Esse modelo apresenta um modelo MLP básico que pode ser expandido mudando o número de neurônios e camadas. Em adaptações mais avançadas, pode-se estudar possibilidade de otimização de hyperparâmetros e outras técnincas como aumento de dados.\n\n**Não é objetivo nosso desenvolver e otimizar o modelo de classificação**. O exemplo tem objetivo meramente didático.\n\n---\n\n**Para saber mais:**\n* [Palestras e cursos do Ocean](http://www.oceanbrasil.com/)\n* François Chollet. Deep Learning with Python. Manning Publications, 2017.\n* Ian Goodfellow and Yoshua Bengio and Aaron Courville. [Deep Learning](https://www.deeplearningbook.org/). MIT Press, 2016.","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\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","metadata":{"ExecuteTime":{"end_time":"2019-01-16T20:39:41.500258Z","start_time":"2019-01-16T20:39:39.261856Z"},"execution":{"iopub.status.busy":"2021-10-24T23:29:57.847320Z","iopub.execute_input":"2021-10-24T23:29:57.847994Z","iopub.status.idle":"2021-10-24T23:29:57.860800Z","shell.execute_reply.started":"2021-10-24T23:29:57.847952Z","shell.execute_reply":"2021-10-24T23:29:57.859764Z"},"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":"2021-10-24T23:29:57.863134Z","iopub.execute_input":"2021-10-24T23:29:57.863447Z","iopub.status.idle":"2021-10-24T23:30:00.886721Z","shell.execute_reply.started":"2021-10-24T23:29:57.863414Z","shell.execute_reply":"2021-10-24T23:30:00.885903Z"},"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":"2021-10-24T23:30:00.888157Z","iopub.execute_input":"2021-10-24T23:30:00.888703Z","iopub.status.idle":"2021-10-24T23:30:00.902184Z","shell.execute_reply.started":"2021-10-24T23:30:00.888668Z","shell.execute_reply":"2021-10-24T23:30:00.901099Z"},"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":"2021-10-24T23:30:00.903621Z","iopub.execute_input":"2021-10-24T23:30:00.903959Z","iopub.status.idle":"2021-10-24T23:30:01.006984Z","shell.execute_reply.started":"2021-10-24T23:30:00.903898Z","shell.execute_reply":"2021-10-24T23:30:01.005968Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(Y)","metadata":{"execution":{"iopub.status.busy":"2021-10-24T23:30:01.010383Z","iopub.execute_input":"2021-10-24T23:30:01.010821Z","iopub.status.idle":"2021-10-24T23:30:01.026244Z","shell.execute_reply.started":"2021-10-24T23:30:01.010780Z","shell.execute_reply":"2021-10-24T23:30:01.024680Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Numtendi nada!\n# Bora ver com matplotlib\nplt.imshow(X.values[100].reshape(28,28), cmap=plt.cm.binary)\nplt.show()\nprint('Label: {}'.format(Y[100]))","metadata":{"ExecuteTime":{"end_time":"2019-01-08T20:49:47.144492Z","start_time":"2019-01-08T20:49:47.016025Z"},"execution":{"iopub.status.busy":"2021-10-24T23:30:01.028066Z","iopub.execute_input":"2021-10-24T23:30:01.028537Z","iopub.status.idle":"2021-10-24T23:30:01.184380Z","shell.execute_reply.started":"2021-10-24T23:30:01.028484Z","shell.execute_reply":"2021-10-24T23:30:01.183414Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Transformando a imagem 2d em um numpy array (imagem 28*28 = 784 pixels)\nx = X.values.reshape(42000, 784)\n\n#Normalizando para valores entre 0 e 1\nx = x.astype('float32')\nx /= 255\n\nprint(x[0])","metadata":{"ExecuteTime":{"end_time":"2019-01-08T20:49:57.425537Z","start_time":"2019-01-08T20:49:57.272377Z"},"execution":{"iopub.status.busy":"2021-10-24T23:30:01.185840Z","iopub.execute_input":"2021-10-24T23:30:01.186191Z","iopub.status.idle":"2021-10-24T23:30:01.277955Z","shell.execute_reply.started":"2021-10-24T23:30:01.186156Z","shell.execute_reply":"2021-10-24T23:30:01.277063Z"},"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":"2021-10-24T23:30:01.279319Z","iopub.execute_input":"2021-10-24T23:30:01.279647Z","iopub.status.idle":"2021-10-24T23:30:01.286518Z","shell.execute_reply.started":"2021-10-24T23:30:01.279613Z","shell.execute_reply":"2021-10-24T23:30:01.285614Z"},"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=9)\nprint('Qtde de treino: {}'.format(len(x_train)))\nprint('Qtde de validação: {}'.format(len(x_val)))","metadata":{"execution":{"iopub.status.busy":"2021-10-24T23:30:01.287852Z","iopub.execute_input":"2021-10-24T23:30:01.288215Z","iopub.status.idle":"2021-10-24T23:30:01.680798Z","shell.execute_reply.started":"2021-10-24T23:30:01.288174Z","shell.execute_reply":"2021-10-24T23:30:01.679810Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Criando e treinando o Modelo","metadata":{}},{"cell_type":"code","source":"# Criando o modelo Sequential\n# Sequential: Modelo Keras de ir adicionando camadas (como um lego)\n# Dense: Camada onde todas as entradas estão conectadas em cada neurônio (totalmente conectada)\n# Dropout: Camada usa durante treino que descarta aleatoriamente um percentual de conexões (reduz overfitting)\n\nmodel = Sequential()\n# Camada com 30 neurônios\nmodel.add(Dense(30, activation='linear', input_shape=(784,)))\n# Dropout de 20%\nmodel.add(Dropout(0.1))\n# Camada de 20 neurônios\nmodel.add(Dense(30, activation='relu'))\n\nmodel.add(Dropout(0.1))\n# Camada de 20 neurônios\nmodel.add(Dense(30, activation='relu'))\n\nmodel.add(Dropout(0.1))\n# Camada de 20 neurônios\nmodel.add(Dense(20, activation='relu'))\n\nmodel.add(Dropout(0.1))\n# Camada de 20 neurônios\nmodel.add(Dense(10, activation='relu'))\n# Dropout de 20%\n# model.add(Dropout(0.5))\n# Camda de classificação final, com 1 neurônio para cada classe de saída. Softmax divide a probabilidade de cada classe.\nmodel.add(Dense(num_classes, activation='softmax'))\n\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":"2021-10-24T23:30:01.682222Z","iopub.execute_input":"2021-10-24T23:30:01.682544Z","iopub.status.idle":"2021-10-24T23:30:01.817555Z","shell.execute_reply.started":"2021-10-24T23:30:01.682510Z","shell.execute_reply":"2021-10-24T23:30:01.816271Z"},"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":"2021-10-24T23:30:01.819039Z","iopub.execute_input":"2021-10-24T23:30:01.819354Z","iopub.status.idle":"2021-10-24T23:30:01.865569Z","shell.execute_reply.started":"2021-10-24T23:30:01.819325Z","shell.execute_reply":"2021-10-24T23:30:01.864375Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Treina com os parte dos dados\nbatch_size = 32\nepochs = 50\n#Salvar o melhor modelo\n\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":"2021-10-24T23:30:01.866958Z","iopub.execute_input":"2021-10-24T23:30:01.867269Z","iopub.status.idle":"2021-10-24T23:32:25.042843Z","shell.execute_reply.started":"2021-10-24T23:30:01.867233Z","shell.execute_reply":"2021-10-24T23:32:25.041435Z"},"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":"2021-10-24T23:32:25.044867Z","iopub.execute_input":"2021-10-24T23:32:25.045255Z","iopub.status.idle":"2021-10-24T23:32:25.454447Z","shell.execute_reply.started":"2021-10-24T23:32:25.045221Z","shell.execute_reply":"2021-10-24T23:32:25.453100Z"},"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":"2021-10-24T23:32:25.456429Z","iopub.execute_input":"2021-10-24T23:32:25.456781Z","iopub.status.idle":"2021-10-24T23:32:25.664333Z","shell.execute_reply.started":"2021-10-24T23:32:25.456749Z","shell.execute_reply":"2021-10-24T23:32:25.663020Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Y[10]","metadata":{"execution":{"iopub.status.busy":"2021-10-24T23:32:25.666085Z","iopub.execute_input":"2021-10-24T23:32:25.666528Z","iopub.status.idle":"2021-10-24T23:32:25.674073Z","shell.execute_reply.started":"2021-10-24T23:32:25.666478Z","shell.execute_reply":"2021-10-24T23:32:25.673026Z"},"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((1,784))))\nprint(model.predict_classes(x_train[10].reshape((1,784))))","metadata":{"ExecuteTime":{"end_time":"2019-01-08T21:06:04.363715Z","start_time":"2019-01-08T21:06:04.27849Z"},"execution":{"iopub.status.busy":"2021-10-24T23:32:25.675713Z","iopub.execute_input":"2021-10-24T23:32:25.676075Z","iopub.status.idle":"2021-10-24T23:32:25.807975Z","shell.execute_reply.started":"2021-10-24T23:32:25.676043Z","shell.execute_reply":"2021-10-24T23:32:25.806188Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Avaliando o Modelo","metadata":{}},{"cell_type":"code","source":"import itertools\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":"2021-10-24T23:32:25.809588Z","iopub.execute_input":"2021-10-24T23:32:25.809958Z","iopub.status.idle":"2021-10-24T23:32:25.825091Z","shell.execute_reply.started":"2021-10-24T23:32:25.809909Z","shell.execute_reply":"2021-10-24T23:32:25.823830Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 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":"2021-10-24T23:32:25.826482Z","iopub.execute_input":"2021-10-24T23:32:25.827438Z","iopub.status.idle":"2021-10-24T23:32:26.704967Z","shell.execute_reply.started":"2021-10-24T23:32:25.827392Z","shell.execute_reply":"2021-10-24T23:32:26.703540Z"},"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),784)\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(\"mlp_mnist_v1.csv\",index=False)","metadata":{"execution":{"iopub.status.busy":"2021-10-24T23:32:26.706949Z","iopub.execute_input":"2021-10-24T23:32:26.707447Z","iopub.status.idle":"2021-10-24T23:32:29.875352Z","shell.execute_reply.started":"2021-10-24T23:32:26.707394Z","shell.execute_reply":"2021-10-24T23:32:29.873836Z"},"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, 784))\n\nx_te = x_val + noise\nx_te = np.clip(x_te, 0., 1.)\n\nplt.imshow(x_te.reshape(4200, 28,28)[1], 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":"2021-10-24T23:32:29.877026Z","iopub.execute_input":"2021-10-24T23:32:29.877349Z","iopub.status.idle":"2021-10-24T23:32:30.540744Z","shell.execute_reply.started":"2021-10-24T23:32:29.877317Z","shell.execute_reply":"2021-10-24T23:32:30.539494Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Com ruído, percebemos que a acurácia dos exemplos de validação caiu muito. \nUma MLP aprende a partir de pixels individuais.\nUm modelo Convolucional (CNN) captura melhor regiões, ou padrões espaciais de pixels.\nVeja o exemplo com CNN.","metadata":{}}]}