{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import os\nprint(os.listdir(\"../input\"))\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom glob import glob\nimport PIL\nfrom PIL import Image\nfrom keras.preprocessing.image import ImageDataGenerator","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"image=\"../input/siim-isic-melanoma-classification/jpeg/train/ISIC_0015719.jpg\"\nPIL.Image.open(image)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Defining data path\nIMAGE_PATH = \"../input/siim-isic-melanoma-classification/\"\n\ntrain_df = pd.read_csv('../input/siim-isic-melanoma-classification/train.csv')\ntest_df = pd.read_csv('../input/siim-isic-melanoma-classification/test.csv')\n\n\n#Training data\nprint('Training data shape: ', train_df.shape)\ntrain_df.head(5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.groupby(['benign_malignant']).count()['sex'].to_frame()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Null values and Data types\nprint('Train Set')\nprint(train_df.info())\nprint('-------------')\nprint('Test Set')\nprint(test_df.info())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Total number of images in the dataset(train+test)\nprint(\"Total images in Train set: \",train_df['image_name'].count())\nprint(\"Total images in Test set: \",test_df['image_name'].count())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"columns = train_df.keys()\ncolumns = list(columns)\nprint(columns)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df['target'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df['sex'].value_counts(normalize=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"images = train_df['image_name'].values\n\n# Extract 9 random images from it\nrandom_images = [np.random.choice(images+'.jpg') for i in range(9)]\n\n# Location of the image dir\nimg_dir = IMAGE_PATH+'/jpeg/train'\n\nprint('Display Random Images')\n\n# Adjust the size of your images\nplt.figure(figsize=(10,8))\n\n# Iterate and plot random images\nfor i in range(9):\n    plt.subplot(3, 3, i + 1)\n    img = plt.imread(os.path.join(img_dir, random_images[i]))\n    plt.imshow(img, cmap='gray')\n    plt.axis('off')\n    \n# Adjust subplot parameters to give specified padding\nplt.tight_layout()   ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"benign = train_df[train_df['benign_malignant']=='benign']\nmalignant = train_df[train_df['benign_malignant']=='malignant']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"images = malignant['image_name'].values\n\n# Extract 9 random images from it\nrandom_images = [np.random.choice(images+'.jpg') for i in range(9)]\n\n# Location of the image dir\nimg_dir = IMAGE_PATH+'/jpeg/train'\n\nprint('Display malignant Images')\n\n# Adjust the size of your images\nplt.figure(figsize=(10,8))\n\n# Iterate and plot random images\nfor i in range(9):\n    plt.subplot(3, 3, i + 1)\n    img = plt.imread(os.path.join(img_dir, random_images[i]))\n    plt.imshow(img, cmap='gray')\n    plt.axis('off')\n    \n# Adjust subplot parameters to give specified padding\nplt.tight_layout()   ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"images = benign['image_name'].values\n\n# Extract 9 random images from it\nrandom_images = [np.random.choice(images+'.jpg') for i in range(9)]\n\n# Location of the image dir\nimg_dir = IMAGE_PATH+'/jpeg/train'\n\nprint('Display benign Images')\n\n# Adjust the size of your images\nplt.figure(figsize=(10,8))\n\n# Iterate and plot random images\nfor i in range(9):\n    plt.subplot(3, 3, i + 1)\n    img = plt.imread(os.path.join(img_dir, random_images[i]))\n    plt.imshow(img, cmap='gray')\n    plt.axis('off')\n    \n# Adjust subplot parameters to give specified padding\nplt.tight_layout()   ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df =pd.read_csv('../input/siim-isic-melanoma-classification/train.csv')\ndf","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = df.drop(columns=['patient_id','sex','age_approx','anatom_site_general_challenge','diagnosis','benign_malignant'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.columns = ['name','label']\ndf","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data = pd.DataFrame(df[df['label']==1])\ndata","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data2 = pd.DataFrame(df[df['label']==0])\ndata2 = data2[:584]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data = data.append(data2)\ndata","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}