{"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":"code","source":"# How I imported in my environment.\n# import numpy as np\n# import pandas as pd \n# import matplotlib.pyplot as plt\n# import matplotlib.image as mpimg\n\n# from sklearn.model_selection import train_test_split\n# from tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# from tensorflow.keras.models import Sequential\n# from tensorflow.keras.layers import Conv2D, MaxPooling2D\n# from tensorflow.keras.layers import Activation, Flatten, Dropout, Dense\n# from tensorflow.keras.optimizers import Adam","metadata":{"execution":{"iopub.status.busy":"2023-11-11T04:17:23.834834Z","iopub.execute_input":"2023-11-11T04:17:23.835308Z","iopub.status.idle":"2023-11-11T04:17:23.841319Z","shell.execute_reply.started":"2023-11-11T04:17:23.835274Z","shell.execute_reply":"2023-11-11T04:17:23.839596Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd \nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\n\nfrom sklearn.model_selection import train_test_split\nfrom keras.preprocessing.image import ImageDataGenerator\n\nfrom keras.models import Sequential\nfrom keras.layers.convolutional import Conv2D\nfrom keras.layers.convolutional import MaxPooling2D\nfrom keras.layers.core import Activation\nfrom keras.layers.core import Flatten\nfrom keras.layers.core import Dropout\nfrom keras.layers.core import Dense\nfrom keras.optimizers import Adam","metadata":{"execution":{"iopub.status.busy":"2023-11-11T04:17:23.867425Z","iopub.execute_input":"2023-11-11T04:17:23.868643Z","iopub.status.idle":"2023-11-11T04:17:23.874873Z","shell.execute_reply.started":"2023-11-11T04:17:23.868601Z","shell.execute_reply":"2023-11-11T04:17:23.874146Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Load the training data into a DataFrame. \n# Print the shape of the resulting DataFrame.\n\nhcd = pd.read_csv('/kaggle/input/histopathologic-cancer-detection/train_labels.csv')\nprint(hcd.shape)","metadata":{"execution":{"iopub.status.busy":"2023-11-11T04:17:23.876558Z","iopub.execute_input":"2023-11-11T04:17:23.877044Z","iopub.status.idle":"2023-11-11T04:17:24.131639Z","shell.execute_reply.started":"2023-11-11T04:17:23.877018Z","shell.execute_reply":"2023-11-11T04:17:24.130644Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Display the head of the train DataFrame. \nhcd.head()","metadata":{"execution":{"iopub.status.busy":"2023-11-11T04:17:24.132834Z","iopub.execute_input":"2023-11-11T04:17:24.133152Z","iopub.status.idle":"2023-11-11T04:17:24.142599Z","shell.execute_reply.started":"2023-11-11T04:17:24.133124Z","shell.execute_reply":"2023-11-11T04:17:24.141516Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#label distrobution\n(hcd.label.value_counts() / len(hcd)).to_frame()","metadata":{"execution":{"iopub.status.busy":"2023-11-11T04:17:24.144583Z","iopub.execute_input":"2023-11-11T04:17:24.145648Z","iopub.status.idle":"2023-11-11T04:17:24.166774Z","shell.execute_reply.started":"2023-11-11T04:17:24.145613Z","shell.execute_reply":"2023-11-11T04:17:24.164469Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Adding a variable for the image directory\nimg_dir = '/kaggle/input/histopathologic-cancer-detection/train'","metadata":{"execution":{"iopub.status.busy":"2023-11-11T04:17:24.168626Z","iopub.execute_input":"2023-11-11T04:17:24.169077Z","iopub.status.idle":"2023-11-11T04:17:24.179036Z","shell.execute_reply.started":"2023-11-11T04:17:24.169038Z","shell.execute_reply":"2023-11-11T04:17:24.177331Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample = hcd.sample(n=9).reset_index()\n\nplt.figure(figsize=(3,3))\n\nfor i, row in sample.iterrows():\n\n    img = mpimg.imread(f'{img_dir}/{row.id}.tif')    \n    label = row.label\n\n    plt.subplot(3,3,i+1)\n    plt.imshow(img)\n    plt.text(0, -5, f'Class {label}', color='k')\n        \n    plt.axis('off')\n\nplt.tight_layout()\nplt.show()\n    ","metadata":{"execution":{"iopub.status.busy":"2023-11-11T04:17:24.180233Z","iopub.execute_input":"2023-11-11T04:17:24.180602Z","iopub.status.idle":"2023-11-11T04:17:24.575576Z","shell.execute_reply.started":"2023-11-11T04:17:24.18057Z","shell.execute_reply":"2023-11-11T04:17:24.574798Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#using data generators \ntrain_df, valid_df = train_test_split(hcd, test_size=0.2, random_state=39, stratify=hcd.label)\n\nprint(train_df.shape)\nprint(valid_df.shape)","metadata":{"execution":{"iopub.status.busy":"2023-11-11T04:17:24.576841Z","iopub.execute_input":"2023-11-11T04:17:24.577441Z","iopub.status.idle":"2023-11-11T04:17:24.697913Z","shell.execute_reply.started":"2023-11-11T04:17:24.577414Z","shell.execute_reply":"2023-11-11T04:17:24.695734Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#scaling images \ntrain_datagen = ImageDataGenerator(rescale=1/255)\nvalid_datagen = ImageDataGenerator(rescale=1/255)","metadata":{"execution":{"iopub.status.busy":"2023-11-11T04:17:24.699683Z","iopub.execute_input":"2023-11-11T04:17:24.700725Z","iopub.status.idle":"2023-11-11T04:17:24.705487Z","shell.execute_reply.started":"2023-11-11T04:17:24.700689Z","shell.execute_reply":"2023-11-11T04:17:24.704523Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df['id'] = train_df['id'] + '.tif'\nvalid_df['id'] = valid_df['id'] + '.tif'","metadata":{"execution":{"iopub.status.busy":"2023-11-11T04:17:24.708649Z","iopub.execute_input":"2023-11-11T04:17:24.709034Z","iopub.status.idle":"2023-11-11T04:17:24.790525Z","shell.execute_reply.started":"2023-11-11T04:17:24.709002Z","shell.execute_reply":"2023-11-11T04:17:24.789287Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Creating Data Generators for CNN\ntrain_datagen = ImageDataGenerator(\n    rescale=1/255,\n    rotation_range=40,\n    width_shift_range=0.2,\n    height_shift_range=0.2,\n    shear_range=0.2,\n    zoom_range=0.2,\n    horizontal_flip=True,\n    fill_mode='nearest'\n)\n\nvalid_datagen = ImageDataGenerator(rescale=1/255)\n\ntrain_df['label'] = train_df['label'].astype(str)\nvalid_df['label'] = valid_df['label'].astype(str)\n\ntrain_generator = train_datagen.flow_from_dataframe(\n    dataframe=train_df,\n    directory=img_dir,\n    x_col='id',\n    y_col='label',\n    target_size=(96, 96),\n    batch_size=32,\n    class_mode='binary'\n)\n\nvalidation_generator = valid_datagen.flow_from_dataframe(\n    dataframe=valid_df,\n    directory=img_dir,\n    x_col='id',\n    y_col='label',\n    target_size=(96, 96),\n    batch_size=32,\n    class_mode='binary'\n)","metadata":{"execution":{"iopub.status.busy":"2023-11-11T04:17:24.792003Z","iopub.execute_input":"2023-11-11T04:17:24.792615Z","iopub.status.idle":"2023-11-11T04:19:41.21045Z","shell.execute_reply.started":"2023-11-11T04:17:24.792574Z","shell.execute_reply":"2023-11-11T04:19:41.209158Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = Sequential()\n\n# Convolutional layer\nmodel.add(Conv2D(32, (3, 3), activation='relu', input_shape=(96, 96, 3)))\nmodel.add(MaxPooling2D((2, 2)))\n\n# Second layer\nmodel.add(Conv2D(64, (3, 3), activation='relu'))\nmodel.add(MaxPooling2D((2, 2)))\n\n# Third layer\nmodel.add(Conv2D(128, (3, 3), activation='relu'))\nmodel.add(MaxPooling2D((2, 2)))\n\nmodel.add(Flatten())\n\nmodel.add(Dense(128, activation='relu'))\n\n# Dropout layer\nmodel.add(Dropout(0.5))\n\n# Output layer\nmodel.add(Dense(1, activation='sigmoid'))\n\n# Compiling the model\nmodel.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])","metadata":{"execution":{"iopub.status.busy":"2023-11-11T04:19:41.211961Z","iopub.execute_input":"2023-11-11T04:19:41.21225Z","iopub.status.idle":"2023-11-11T04:19:41.664305Z","shell.execute_reply.started":"2023-11-11T04:19:41.212224Z","shell.execute_reply":"2023-11-11T04:19:41.663208Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#test to see if this saves \n","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# I'll save another version","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Evaluate the accuracy\naccuracy = model.evaluate(validation_generator)\nprint(f\"Accuracy on the validation set: {accuracy}\")","metadata":{"execution":{"iopub.status.busy":"2023-11-11T04:19:41.666107Z","iopub.execute_input":"2023-11-11T04:19:41.666479Z","iopub.status.idle":"2023-11-11T04:25:04.316236Z","shell.execute_reply.started":"2023-11-11T04:19:41.666443Z","shell.execute_reply":"2023-11-11T04:25:04.314437Z"},"trusted":true},"execution_count":null,"outputs":[]}]}