{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":45867,"databundleVersionId":6924515,"sourceType":"competition"}],"dockerImageVersionId":30558,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"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)\nimport cv2 as cv\nimport matplotlib.pyplot as plt\nfrom matplotlib import gridspec\nimport matplotlib.image as img\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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-12-20T13:32:42.197447Z","iopub.execute_input":"2023-12-20T13:32:42.197838Z","iopub.status.idle":"2023-12-20T13:32:43.646654Z","shell.execute_reply.started":"2023-12-20T13:32:42.197801Z","shell.execute_reply":"2023-12-20T13:32:43.645194Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\nmy_data = pd.read_csv('/kaggle/input/UBC-OCEAN/test.csv')\nprint(my_data.head())\nprint(my_data.shape)","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:32:43.648579Z","iopub.execute_input":"2023-12-20T13:32:43.649025Z","iopub.status.idle":"2023-12-20T13:32:43.686441Z","shell.execute_reply.started":"2023-12-20T13:32:43.648994Z","shell.execute_reply":"2023-12-20T13:32:43.68528Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample_submission = pd.read_csv(\"/kaggle/input/UBC-OCEAN/sample_submission.csv\")\nprint(sample_submission.head())\nsample_submission.shape","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:32:43.68777Z","iopub.execute_input":"2023-12-20T13:32:43.688081Z","iopub.status.idle":"2023-12-20T13:32:43.702825Z","shell.execute_reply.started":"2023-12-20T13:32:43.688054Z","shell.execute_reply":"2023-12-20T13:32:43.701338Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\ntrain = pd.read_csv('/kaggle/input/UBC-OCEAN/train.csv')\nprint(train.head())\nprint(train.shape)","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:32:43.705461Z","iopub.execute_input":"2023-12-20T13:32:43.70582Z","iopub.status.idle":"2023-12-20T13:32:43.721368Z","shell.execute_reply.started":"2023-12-20T13:32:43.705789Z","shell.execute_reply":"2023-12-20T13:32:43.720056Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.info()","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:32:43.722972Z","iopub.execute_input":"2023-12-20T13:32:43.723354Z","iopub.status.idle":"2023-12-20T13:32:43.752313Z","shell.execute_reply.started":"2023-12-20T13:32:43.723321Z","shell.execute_reply":"2023-12-20T13:32:43.751437Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/UBC-OCEAN/train.csv')\nlabels=train['label'].unique()\nprint(labels)\nid_train=train['image_id'].value_counts()\nprint(id_train)\ntrain_is_tma=train[train['is_tma']==False].value_counts()\nprint(train_is_tma)\ntrain_is_tma1=train[train['is_tma']==True].value_counts()\nprint(train_is_tma1)\n","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:32:43.753296Z","iopub.execute_input":"2023-12-20T13:32:43.753717Z","iopub.status.idle":"2023-12-20T13:32:43.78944Z","shell.execute_reply.started":"2023-12-20T13:32:43.753677Z","shell.execute_reply":"2023-12-20T13:32:43.788162Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/UBC-OCEAN/train.csv')\n\n\ntrain_is_tma_false = train[train['is_tma'] == False]\nunique_image_ids = train_is_tma_false['image_id'].unique()\nprint(unique_image_ids)\n\nunique_labels = train_is_tma_false['label'].unique()\n\nprint(unique_labels)\n\n","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:32:43.790897Z","iopub.execute_input":"2023-12-20T13:32:43.791241Z","iopub.status.idle":"2023-12-20T13:32:43.806868Z","shell.execute_reply.started":"2023-12-20T13:32:43.791192Z","shell.execute_reply":"2023-12-20T13:32:43.805475Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#import matplotlib.image as img\n#import matplotlib.pyplot as plt\n#image = img.imread(\"/kaggle/input/UBC-OCEAN/train_images/13387.png\")\n#plt.imshow(image)\n#image.size","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:32:43.808422Z","iopub.execute_input":"2023-12-20T13:32:43.809055Z","iopub.status.idle":"2023-12-20T13:32:43.81442Z","shell.execute_reply.started":"2023-12-20T13:32:43.80901Z","shell.execute_reply":"2023-12-20T13:32:43.813053Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#image2 = img.imread(\"/kaggle/input/UBC-OCEAN/train_thumbnails/13387_thumbnail.png\")\n#plt.imshow(image2)\n#image2.size","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:32:43.815979Z","iopub.execute_input":"2023-12-20T13:32:43.816658Z","iopub.status.idle":"2023-12-20T13:32:43.824646Z","shell.execute_reply.started":"2023-12-20T13:32:43.816412Z","shell.execute_reply":"2023-12-20T13:32:43.822853Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nfrom PIL import Image\n","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:32:43.829213Z","iopub.execute_input":"2023-12-20T13:32:43.829681Z","iopub.status.idle":"2023-12-20T13:32:43.835282Z","shell.execute_reply.started":"2023-12-20T13:32:43.829645Z","shell.execute_reply":"2023-12-20T13:32:43.834101Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"root = \"/kaggle/input/UBC-OCEAN/train_thumbnails\"\nfnames = os.listdir(root)\nlen(fnames)","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:32:43.837007Z","iopub.execute_input":"2023-12-20T13:32:43.837416Z","iopub.status.idle":"2023-12-20T13:32:43.849459Z","shell.execute_reply.started":"2023-12-20T13:32:43.837385Z","shell.execute_reply":"2023-12-20T13:32:43.848458Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"root2 = \"/kaggle/input/UBC-OCEAN/test_thumbnails\"\nfnames2 = os.listdir(root2)\nlen(fnames2)","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:32:43.851186Z","iopub.execute_input":"2023-12-20T13:32:43.851653Z","iopub.status.idle":"2023-12-20T13:32:43.863187Z","shell.execute_reply.started":"2023-12-20T13:32:43.851617Z","shell.execute_reply":"2023-12-20T13:32:43.862155Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"root3 = \"/kaggle/input/UBC-OCEAN/train_images\"\nfnames3 = os.listdir(root3)\nlen(fnames3)","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:32:43.864572Z","iopub.execute_input":"2023-12-20T13:32:43.865287Z","iopub.status.idle":"2023-12-20T13:32:43.872898Z","shell.execute_reply.started":"2023-12-20T13:32:43.865254Z","shell.execute_reply":"2023-12-20T13:32:43.871959Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"root4 = \"/kaggle/input/UBC-OCEAN/test_images\"\nfnames4 = os.listdir(root4)\nlen(fnames4)","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:32:43.874351Z","iopub.execute_input":"2023-12-20T13:32:43.875035Z","iopub.status.idle":"2023-12-20T13:32:43.885152Z","shell.execute_reply.started":"2023-12-20T13:32:43.874999Z","shell.execute_reply":"2023-12-20T13:32:43.883829Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fig, axs = plt.subplots(nrows=2,ncols=5)\naxs = axs.flatten()\nfor i in range(10):\n    filepath = os.path.join(root,fnames[i])\n    img = Image.open(filepath)\n    axs[i].imshow(img)\n    #axs[i].axis(\"off\")\n    axs[i].set_title(fnames[i])\n    \nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:32:43.886799Z","iopub.execute_input":"2023-12-20T13:32:43.887571Z","iopub.status.idle":"2023-12-20T13:32:53.469961Z","shell.execute_reply.started":"2023-12-20T13:32:43.887525Z","shell.execute_reply":"2023-12-20T13:32:53.468656Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from PIL import Image\nimport os\n\nimage_data=[]\nimage_label=[]\npath_thumbnails='/kaggle/input/UBC-OCEAN/train_thumbnails'\nfor img , label in zip(train_is_tma_false['image_id'],train_is_tma_false['label']):\n    image_path=os.path.join('/kaggle/input/UBC-OCEAN/train_thumbnails',str(img))\n    image = Image.open(filepath)\n    image = image.resize((512,512))\n    image = image.convert(\"RGB\")\n    image = np.array(image)\n    image_data.append(image)\n    image_label.append(label)","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:32:53.471717Z","iopub.execute_input":"2023-12-20T13:32:53.472944Z","iopub.status.idle":"2023-12-20T13:33:58.802524Z","shell.execute_reply.started":"2023-12-20T13:32:53.472896Z","shell.execute_reply":"2023-12-20T13:33:58.801637Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(len(image_data))\nprint(len( image_label))","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:33:58.803851Z","iopub.execute_input":"2023-12-20T13:33:58.804334Z","iopub.status.idle":"2023-12-20T13:33:58.811271Z","shell.execute_reply.started":"2023-12-20T13:33:58.804293Z","shell.execute_reply":"2023-12-20T13:33:58.810089Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"image_label_1 = []\nfor i in image_label:\n    if i==\"CC\":\n        image_label_1.append(0)\n    elif i==\"EC\":\n        image_label_1.append(1)\n    elif i==\"HGSC\":\n        image_label_1.append(2)\n    elif i==\"LGSC\":\n        image_label_1.append(3)\n    elif i==\"MC\":\n        image_label_1.append(4)\nprint(image_label_1 )\nprint(len(image_label_1 ))","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:33:58.8131Z","iopub.execute_input":"2023-12-20T13:33:58.813466Z","iopub.status.idle":"2023-12-20T13:33:58.826713Z","shell.execute_reply.started":"2023-12-20T13:33:58.813435Z","shell.execute_reply":"2023-12-20T13:33:58.825451Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x=np.array(image_data)\ny=np.array(image_label_1)\n","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:33:58.828318Z","iopub.execute_input":"2023-12-20T13:33:58.829501Z","iopub.status.idle":"2023-12-20T13:33:58.97236Z","shell.execute_reply.started":"2023-12-20T13:33:58.829462Z","shell.execute_reply":"2023-12-20T13:33:58.971013Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nx_train, x_test, y_train, y_test = train_test_split (x,y ,test_size=0.3, random_state=42)\nprint (len(x_train))\nprint (len(x_test))\nprint (len( y_train))\nprint (len(y_test))","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:33:58.973902Z","iopub.execute_input":"2023-12-20T13:33:58.974309Z","iopub.status.idle":"2023-12-20T13:34:00.515527Z","shell.execute_reply.started":"2023-12-20T13:33:58.974272Z","shell.execute_reply":"2023-12-20T13:34:00.514238Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Normalized\n#x_train_normalize=np.array(x_train)/255\n#x_test_normalize=np.array(x_test)/255","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:34:00.51725Z","iopub.execute_input":"2023-12-20T13:34:00.517804Z","iopub.status.idle":"2023-12-20T13:34:00.526515Z","shell.execute_reply.started":"2023-12-20T13:34:00.517766Z","shell.execute_reply":"2023-12-20T13:34:00.525Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Conv2D, MaxPool2D, Dropout, Flatten, Dense, BatchNormalization\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom sklearn.metrics import accuracy_score\n\n# Assuming x_train, y_train, x_test, y_test are your training and testing data\n\nmodel = Sequential()\n\nmodel.add(Conv2D(filters=100, kernel_size=(3, 3), padding='Same', activation='relu', input_shape=(512, 512, 3)))\nmodel.add(Conv2D(filters=75, kernel_size=(3, 3), padding='Same', activation='relu'))\nmodel.add(MaxPool2D(pool_size=(4, 4)))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(filters=100, kernel_size=(3, 3), padding='Same', activation='relu'))\nmodel.add(Conv2D(filters=75, kernel_size=(3, 3), padding='Same', activation='relu'))\nmodel.add(MaxPool2D(pool_size=(4, 4), strides=(2, 2)))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.25))\n\nmodel.add(Flatten())\nmodel.add(Dense(50, activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.5))\nmodel.add(Dense(5, activation='softmax'))\n\nmodel.compile(optimizer=\"adam\", loss=\"sparse_categorical_crossentropy\", metrics=[\"accuracy\"])\nmodel.summary()","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:34:00.530058Z","iopub.execute_input":"2023-12-20T13:34:00.530605Z","iopub.status.idle":"2023-12-20T13:34:10.31221Z","shell.execute_reply.started":"2023-12-20T13:34:00.530556Z","shell.execute_reply":"2023-12-20T13:34:10.311032Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Data Augmentation\ndatagen = ImageDataGenerator(rotation_range=20, width_shift_range=0.2, height_shift_range=0.2, shear_range=0.2, zoom_range=0.2, horizontal_flip=True)\ndatagen.fit(x_train)\n","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:34:10.314484Z","iopub.execute_input":"2023-12-20T13:34:10.314934Z","iopub.status.idle":"2023-12-20T13:34:11.034746Z","shell.execute_reply.started":"2023-12-20T13:34:10.314894Z","shell.execute_reply":"2023-12-20T13:34:11.033527Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"hist = model.fit(datagen.flow(x_train, y_train, batch_size=64), epochs=15, validation_data=(x_test, y_test))","metadata":{"execution":{"iopub.status.busy":"2023-12-20T13:34:11.036584Z","iopub.execute_input":"2023-12-20T13:34:11.037739Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Evaluate on test set\ntest_loss, test_acc = model.evaluate(x_test, y_test)\nprint(f'Test Accuracy: {test_acc}')\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# You can also plot the training history for better visualization\nimport matplotlib.pyplot as plt\nplt.plot(hist.history['accuracy'], label='Training Accuracy')\nplt.plot(hist.history['val_accuracy'], label='Validation Accuracy')\nplt.xlabel('Epoch')\nplt.ylabel('Accuracy')\nplt.legend()\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.plot(hist.history['loss'],color='red',label='training loss')\nplt.plot(hist.history['val_loss'],color='blue',label='validation loss')\nplt.legend()\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.models import load_model\nimport numpy as np\n\nmodel.save('my_model.h5')\n\n\nloaded_model = load_model('my_model.h5')\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions = loaded_model.predict(x_test)\n\n\npredicted_classes = np.argmax(predictions, axis=1)\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"accuracy = accuracy_score(y_test, predicted_classes)\nprint(f'Test Accuracy (from saved model): {accuracy}')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}