{"cells":[{"metadata":{"_uuid":"fe76d1d1ded592430e7548feacfa38dc42f085d9"},"cell_type":"markdown","source":"# Import Library"},{"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 in \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 \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nfrom keras.preprocessing.image import ImageDataGenerator, load_img\nfrom keras.utils import to_categorical\nfrom sklearn.model_selection import train_test_split\nimport matplotlib.pyplot as plt\nimport random\n\nimport os\nprint(os.listdir(\"../input\"))\n\nFAST_RUN = True\nIMAGE_WIDTH=128\nIMAGE_HEIGHT=128\nIMAGE_SIZE=(IMAGE_WIDTH, IMAGE_HEIGHT)\nIMAGE_CHANNELS=3 # RGB color\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"7335a579cc0268fba5d34d6f7558f33c187eedb3"},"cell_type":"markdown","source":"# Prepare Traning Data"},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"filenames = os.listdir(\"../input/train/train\")\ncategories = []\nfor filename in filenames:\n    category = filename.split('.')[0]\n    if category == 'dog':\n        categories.append(1)\n    else:\n        categories.append(0)\ncategories = [str(i) for i in categories]\ndf = pd.DataFrame({\n    'filename': filenames,\n    'category': categories\n})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"type(df['category'][0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"915bb9ba7063ab4d5c07c542419ae119003a5f98"},"cell_type":"code","source":"df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"72bf69e817f67f5a2eaff8561217e22077248553"},"cell_type":"code","source":"df.tail()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"fa26f0bc7a6d835a24989790b20f3c6f32946f45"},"cell_type":"code","source":"df['category'].value_counts().plot.bar()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"3a08da58107777a1dd05c4a4bf5c484484923cac"},"cell_type":"markdown","source":"From our data we have 12000 cats and 12000 dogs"},{"metadata":{"_uuid":"400a293df3c8499059d9175f3915187074efd971"},"cell_type":"markdown","source":"# See sample image"},{"metadata":{"trusted":true,"_uuid":"602b40f7353871cb161c60b5237f0da0096b2f47"},"cell_type":"code","source":"sample = random.choice(filenames)\nimage = load_img(\"../input/train/train/\"+sample)\nplt.imshow(image)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"b244e6b7715a04fc6df92dd6dfa3d35c473ca600"},"cell_type":"markdown","source":"# Build Model\n\n<img src=\"https://i.imgur.com/ebkMGGu.jpg\" width=\"100%\"/>"},{"metadata":{"trusted":true,"_uuid":"8c9f833c1441b657c779844912d0b8028218d454"},"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Conv2D, MaxPooling2D, Dropout, Flatten, Dense, Activation, BatchNormalization\n\nmodel = Sequential()\n\nmodel.add(Conv2D(32, (3, 3), activation='relu', input_shape=(IMAGE_WIDTH, IMAGE_HEIGHT, IMAGE_CHANNELS)))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(64, (3, 3), activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(128, (3, 3), activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Flatten())\nmodel.add(Dense(512, activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.5))\nmodel.add(Dense(1, activation='sigmoid'))\n\nmodel.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])\n\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"bd496f6c65888a969be3703135b0b03a8a1190c8"},"cell_type":"markdown","source":"# Callbacks"},{"metadata":{"trusted":true,"_uuid":"9aa032f0f6da539d23918890d2d131cc3aac8c7a"},"cell_type":"code","source":"from keras.callbacks import EarlyStopping, ReduceLROnPlateau","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"76c9ba4fb7f930c96b2c3e0d6b68ed9fa6a4227b"},"cell_type":"markdown","source":"**Early Stop**\n\nTo prevent over fitting we will stop the learning after 10 epochs and val_loss value not decreased"},{"metadata":{"trusted":true,"_uuid":"3421c5ec428da6c0d8cc1184179a9caff1e01d1c"},"cell_type":"code","source":"earlystop = EarlyStopping(patience=10)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"51d3fe52e911286433cedf6e47332948a253361e"},"cell_type":"markdown","source":"**Learning Rate Reduction**\n\nWe will reduce the learning rate when then accuracy not increase for 2 steps"},{"metadata":{"trusted":true,"_uuid":"8010a5661ad8924d2db24af0f3c00b1593b38901"},"cell_type":"code","source":"learning_rate_reduction = ReduceLROnPlateau(monitor='val_acc', \n                                            patience=2, \n                                            verbose=1, \n                                            factor=0.5, \n                                            min_lr=0.00001)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a79cc604199469789f183096d863f7248e5f6aab"},"cell_type":"code","source":"callbacks = [earlystop, learning_rate_reduction]","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"a29ebfd697dd7183a1a1345ea41ec138874340b7"},"cell_type":"markdown","source":"### Prepare Test and Train Data"},{"metadata":{"trusted":true,"_uuid":"4eeb7af8dcf02c4ef5ca744c8305c51a2f5cedef"},"cell_type":"code","source":"train_df, validate_df = train_test_split(df, test_size=0.20, random_state=42)\ntrain_df = train_df.reset_index(drop=True)\nvalidate_df = validate_df.reset_index(drop=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.head()\nvalidate_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b84836337441705eda9d2e655665ffa14d9feead"},"cell_type":"code","source":"train_df['category'].value_counts().plot.bar()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"19cf03f9a3c39532d6e2d06bd30be49a5afd9d57"},"cell_type":"code","source":"validate_df['category'].value_counts().plot.bar()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ae3dec0361f0443132d0309d3b883ee80070cf9f"},"cell_type":"code","source":"total_train = train_df.shape[0]\ntotal_validate = validate_df.shape[0]\nbatch_size=15\nprint(total_train , total_validate)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"ff760be9104f7d9492467b8d9d3405011aa77d11"},"cell_type":"markdown","source":"# Traning Generator"},{"metadata":{"trusted":true,"_uuid":"4d1c7818703a8a4bac5c036fdea45972aa9e5e9e"},"cell_type":"code","source":"train_datagen = ImageDataGenerator(\n    rotation_range=15,\n    rescale=1./255,\n    shear_range=0.1,\n    zoom_range=0.2,\n    horizontal_flip=True,\n    width_shift_range=0.1,\n    height_shift_range=0.1\n)\n\ntrain_generator = train_datagen.flow_from_dataframe(\n    train_df, \n    \"../input/train/train/\", \n    x_col='filename',\n    y_col='category',\n    target_size=IMAGE_SIZE,\n    class_mode='binary',\n    batch_size=batch_size\n)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"859c7b2857939c19fd2e3bb32839c9f7deb5aa3f"},"cell_type":"markdown","source":"### Validation Generator"},{"metadata":{"trusted":true,"_uuid":"7925e16bcacc89f4484fb6fe47e54d6420af732e"},"cell_type":"code","source":"validation_datagen = ImageDataGenerator(rescale=1./255)\nvalidation_generator = validation_datagen.flow_from_dataframe(\n    validate_df, \n    \"../input/train/train/\", \n    x_col='filename',\n    y_col='category',\n    target_size=IMAGE_SIZE,\n    class_mode='binary',\n    batch_size=batch_size\n)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"6e17fc1f002fedd60febb78fee5e81770640b909"},"cell_type":"markdown","source":"# See how our generator work"},{"metadata":{"trusted":true,"_uuid":"4252cce168ab65f88e44a8ebc2672607bc852af4"},"cell_type":"code","source":"example_df = train_df.sample(n=20).reset_index(drop=True)\nexample_generator = train_datagen.flow_from_dataframe(\n    example_df, \n    \"../input/train/train/\", \n    x_col='filename',\n    y_col='category',\n    target_size=IMAGE_SIZE,\n    class_mode='binary'\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"example_generator","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"23d923dba747f8b47dc75569244cecc6f70df321"},"cell_type":"code","source":"plt.figure(figsize=(12, 12))\nfor i in range(0, 18):\n    plt.subplot(6, 3, i+1)\n    for X_batch, Y_batch in example_generator:\n        image = X_batch[0]\n        plt.imshow(image)\n        break\n        \nplt.tight_layout()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"810ddf1373d9db470ed48da4f30ca5a6c1274435"},"cell_type":"markdown","source":"Seem to be nice "},{"metadata":{"_uuid":"5cd8df64e794ed17de326b613a9819e7da977a0e"},"cell_type":"markdown","source":"# Fit Model"},{"metadata":{"trusted":true,"_uuid":"0836a4cc8aa0abf603e0f96573c0c4ff383ad56b"},"cell_type":"code","source":"epochs=3 if FAST_RUN else 50\nhistory = model.fit_generator(\n    train_generator, \n    epochs=epochs,\n    validation_data=validation_generator,\n    validation_steps=total_validate//batch_size,\n    steps_per_epoch=total_train//batch_size,\n    callbacks=callbacks\n)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"aa1fbc4081ae0de2993188b2bf658a0be5bc0687"},"cell_type":"markdown","source":"# Save Model"},{"metadata":{"trusted":true,"_uuid":"67575a4decdaf79a915d23151626b784ffa82642"},"cell_type":"code","source":"model.save_weights(\"model.h5\")","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"1b76c0a9040bc0babf0a453e567e41e22f8a1e0e"},"cell_type":"markdown","source":"# Virtualize Training"},{"metadata":{"trusted":true,"_uuid":"79055f2dc3e2abb47bea758e0464c86ca42ab431"},"cell_type":"code","source":"fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(12, 12))\nax1.plot(history.history['loss'], color='b', label=\"Training loss\")\nax1.plot(history.history['val_loss'], color='r', label=\"validation loss\")\nax1.set_xticks(np.arange(1, epochs, 1))\nax1.set_yticks(np.arange(0, 1, 0.1))\n\nax2.plot(history.history['acc'], color='b', label=\"Training accuracy\")\nax2.plot(history.history['val_acc'], color='r',label=\"Validation accuracy\")\nax2.set_xticks(np.arange(1, epochs, 1))\n\nlegend = plt.legend(loc='best', shadow=True)\nplt.tight_layout()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"764dc66e4b2bc558f3a0f90b80bb802f5b3d45a8"},"cell_type":"markdown","source":"# Prepare Testing Data"},{"metadata":{"trusted":true,"_uuid":"c35e70d3e1e4834dbbf840fa0ea08c049bfcd915"},"cell_type":"code","source":"test_filenames = os.listdir(\"../input/test1/test1\")\ntest_df = pd.DataFrame({\n    'filename': test_filenames\n})\nnb_samples = test_df.shape[0]","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"291bc3996dce8d05e174b27d64f03996d3e8038e"},"cell_type":"markdown","source":"# Create Testing Generator"},{"metadata":{"trusted":true,"_uuid":"52249ec1c35fb1be3adef386be245de3794e55aa"},"cell_type":"code","source":"test_gen = ImageDataGenerator(rescale=1./255)\ntest_generator = test_gen.flow_from_dataframe(\n    test_df, \n    \"../input/test1/test1/\", \n    x_col='filename',\n    y_col=None,\n    class_mode=None,\n    target_size=IMAGE_SIZE,\n    batch_size=batch_size,\n    shuffle=False\n)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"2fa580afca2931ec5ce374e732d8c1789d03f2ed"},"cell_type":"markdown","source":"# Predict"},{"metadata":{"trusted":true,"_uuid":"4782eb23fa7d003f0e2415d995894017edb2d896"},"cell_type":"code","source":"predict = model.predict_generator(test_generator, steps=np.ceil(nb_samples/batch_size))","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"be7631dc8048d39b38588ce7e31a7273be41449d"},"cell_type":"markdown","source":"As predicted of binary classification result return probability that image likely to be a dog. So we will have threshold 0.5 which mean if predicted value more than 50% it is a dog and under 50% will be a cat."},{"metadata":{"trusted":true},"cell_type":"code","source":"predict","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"341457298e1d0b54f61906fdb12c4e609aef8019"},"cell_type":"code","source":"threshold = 0.5\ntest_df['probability'] = predict\ntest_df['category'] = np.where(test_df['probability'] > threshold, 1,0)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"b00add65fe765529e637c3a9904d710bb7eff1d8"},"cell_type":"markdown","source":"### Virtaulize Result"},{"metadata":{"trusted":true,"_uuid":"d0bf6dd5ff344092fa0121f70bdd60fa5a40e29c"},"cell_type":"code","source":"test_df['category'].value_counts().plot.bar()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"ce72a83f80d6e012b12b82c8ee3365d671a3b307"},"cell_type":"markdown","source":"### See predicted result with images"},{"metadata":{"trusted":true,"_uuid":"98b41dc83075e6297137fb45bf703c313dd4ae28"},"cell_type":"code","source":"sample_test = test_df.head(18)\nsample_test.head()\nplt.figure(figsize=(12, 24))\nfor index, row in sample_test.iterrows():\n    filename = row['filename']\n    category = row['category']\n    probability = row['probability']\n    img = load_img(\"../input/test1/test1/\"+filename, target_size=IMAGE_SIZE)\n    plt.subplot(6, 3, index+1)\n    plt.imshow(img)\n    plt.xlabel(filename + '(' + \"{}\".format(category) + ')' '(' + \"{}\".format(round(probability, 2)) + ')')\nplt.tight_layout()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d1ca25943e73aa20a37f9fb8670ee430caeaaf1f"},"cell_type":"markdown","source":"# Submission"},{"metadata":{"trusted":true,"_uuid":"cce9f3e2ffff0693d79d84590ed71fbbca7c3c7c"},"cell_type":"code","source":"submission_df = test_df.copy()\nsubmission_df['id'] = submission_df['filename'].str.split('.').str[0]\nsubmission_df['label'] = submission_df['category']\nsubmission_df.drop(['filename', 'category'], axis=1, inplace=True)\nsubmission_df.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pd.read_csv('submission1.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df1 = submission_df[['id' ,'label']]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df1.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df1.to_csv('submission1.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pd.re","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}