{"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 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","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nfrom keras import layers\nfrom keras import models\nfrom keras import optimizers\nimport matplotlib.pyplot as plt\nfrom keras.preprocessing import image\nfrom sklearn.preprocessing import StandardScaler, OneHotEncoder\nfrom sklearn.model_selection import train_test_split\nfrom tensorflow.keras import regularizers\nimport tensorflow as tf","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def model_olustur(params):\n    model = models.Sequential()\n\n    model.add(layers.Conv2D(filters = 16, kernel_size = (3, 3),input_shape = (28, 28, 1),kernel_initializer=params[\"weight_init\"]))\n    model.add(layers.BatchNormalization())\n    model.add(layers.Activation(params[\"activation\"]))\n    \n    model.add(layers.Conv2D(filters = 32, kernel_size = (3, 3),kernel_initializer=params[\"weight_init\"]))\n    model.add(layers.BatchNormalization())\n    model.add(layers.Activation(params[\"activation\"]))\n    \n\n    model.add(layers.Conv2D(filters = 32, kernel_size = (3, 3),kernel_initializer=params[\"weight_init\"]))\n    model.add(layers.BatchNormalization())\n    model.add(layers.Activation(params[\"activation\"]))\n    model.add(layers.MaxPool2D())\n    \n    model.add(layers.Conv2D(filters = 64, kernel_size = (3, 3),kernel_initializer=params[\"weight_init\"]))\n    model.add(layers.BatchNormalization())\n    model.add(layers.Activation(params[\"activation\"]))\n    \n    model.add(layers.Conv2D(filters = 64, kernel_size = (3, 3),kernel_initializer=params[\"weight_init\"]))\n    model.add(layers.BatchNormalization())\n    model.add(layers.Activation(params[\"activation\"]))\n    \n    model.add(layers.Conv2D(filters = 64, kernel_size = (5, 5),kernel_initializer=params[\"weight_init\"]))\n    model.add(layers.BatchNormalization())\n    model.add(layers.Activation(params[\"activation\"]))\n    \n    model.add(layers.Flatten())\n    model.add(layers.Dropout(0.35))\n    model.add(layers.Dense(256,kernel_initializer=params[\"weight_init\"]))\n    model.add(layers.BatchNormalization())\n    model.add(layers.Activation(params[\"activation\"]))\n    model.add(layers.Dropout(0.3))\n              \n    model.add(layers.Dense(128,kernel_initializer=params[\"weight_init\"]))\n    model.add(layers.BatchNormalization())\n    model.add(layers.Activation(params[\"activation\"]))\n              \n    model.add(layers.Dense(10, activation='softmax',kernel_initializer=params[\"weight_init\"]))\n\n    \n    model.compile(optimizer=optimizers.Adam(lr=0.0001),\n                  loss=\"categorical_crossentropy\",metrics=[\"acc\"])\n    model.summary()\n    \n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\ndata.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_x = data.drop(\"label\",axis=1)\ndata_x = data_x.values.reshape(-1,28,28,1) / 255.\ndata_y = data[[\"label\"]]\ndata_y = tf.keras.utils.to_categorical(data_y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"modeller = list()\nfor i in range(12):\n    modeller.append(model_olustur({\"weight_init\":tf.keras.initializers.RandomNormal(mean=0.0,stddev=0.01),\"activation\":\"swish\"}))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.callbacks import LearningRateScheduler\nannealer = LearningRateScheduler(lambda x: 1e-3 * 0.95 ** x)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"histories = []\ndatagen = image.ImageDataGenerator(\n        rotation_range=0.1,  # randomly rotate images in the range 10 degrees\n        zoom_range = 0.1, # Randomly zoom image 10%\n        width_shift_range=0.1,  # randomly shift images horizontally 1%\n        height_shift_range=0.1)\n\nfor i,model in enumerate(modeller):\n    x_train,x_val,y_train,y_val = train_test_split(data_x,data_y,test_size=0.10)\n    print(f\"{i+1}. model eğitiliyor\")\n    temp = model.fit_generator(datagen.flow(x_train,y_train, batch_size=128),\n                              epochs = 40,steps_per_epoch=x_train.shape[0] // 128, callbacks=[annealer],validation_data=(x_val,y_val))\n    histories.append(temp)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.metrics import accuracy_score","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"accuracies = list()\nfor model in modeller:\n    loss,acc = model.evaluate(x=x_val,y=y_val)\n    accuracies.append(acc)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")\nx_test = test_data.values.reshape(-1,28,28,1)\nx_test = x_test / 255.","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Soft Voting"},{"metadata":{"trusted":true},"cell_type":"code","source":"tahmin = np.zeros((x_test.shape[0],10))\nfor i,model in enumerate(modeller):\n    for a,j in enumerate(modeller[i].predict(x_test).argmax(axis=1)):\n        tahmin[a,j] += 1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"output = pd.DataFrame({'ImageId': list(range(1,x_test.shape[0]+1)),\n                       'Label': tahmin.argmax(axis=1)})\noutput.to_csv('submission_soft.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Hard Voting"},{"metadata":{"trusted":true},"cell_type":"code","source":"tahmin_hard = np.zeros((x_test.shape[0],10))\nfor model in modeller:\n    tahmin_hard += model.predict(x_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"output = pd.DataFrame({'ImageId': list(range(1,x_test.shape[0]+1)),\n                       'Label': tahmin_hard.argmax(axis=1)})\noutput.to_csv('submission_hard.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}