{"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","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":30822,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"#  Exploratory Data Analysis (EDA) Notebook \nThis notebook provides a basic framework for evaluating Exploratory Data Analysis (EDA) skills using Python. Students must execute each cell and pass the associated tests to proceed.","metadata":{}},{"cell_type":"code","source":"\n\nimport os\nimport random\nimport numpy as np\nimport pandas as pd\nfrom PIL import Image\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport plotly.express as px\nimport plotly.offline as pyo\nfrom IPython.display import HTML\n\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-07T13:41:09.477106Z","iopub.execute_input":"2025-01-07T13:41:09.47744Z","iopub.status.idle":"2025-01-07T13:41:09.482247Z","shell.execute_reply.started":"2025-01-07T13:41:09.47742Z","shell.execute_reply":"2025-01-07T13:41:09.481093Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_csv_path = \"/kaggle/input/UBC-OCEAN/train.csv\"\ntrain_images_path = \"/kaggle/input/UBC-OCEAN/train_images\"\ntrain_thumbnails_path = \"/kaggle/input/UBC-OCEAN/train_thumbnails\"\ntest_csv_path = \"/kaggle/input/UBC-OCEAN/test.csv\"\ntest_images_path = \"/kaggle/input/UBC-OCEAN/test_images\"\ntest_thumbnails_path = \"/kaggle/input/UBC-OCEAN/test_images\"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-07T13:41:21.516523Z","iopub.execute_input":"2025-01-07T13:41:21.516789Z","iopub.status.idle":"2025-01-07T13:41:21.520858Z","shell.execute_reply.started":"2025-01-07T13:41:21.516773Z","shell.execute_reply":"2025-01-07T13:41:21.519637Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df = pd.read_csv(train_csv_path)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-07T13:41:24.256778Z","iopub.execute_input":"2025-01-07T13:41:24.257117Z","iopub.status.idle":"2025-01-07T13:41:24.265063Z","shell.execute_reply.started":"2025-01-07T13:41:24.257088Z","shell.execute_reply":"2025-01-07T13:41:24.264239Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\ndf.head()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-07T13:41:29.530322Z","iopub.execute_input":"2025-01-07T13:41:29.53066Z","iopub.status.idle":"2025-01-07T13:41:29.538137Z","shell.execute_reply.started":"2025-01-07T13:41:29.530638Z","shell.execute_reply":"2025-01-07T13:41:29.537398Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Verify dataset size\nprint(\"Size of the dataset: \", df.shape[0])\nassert df.shape[0] > 0, \"Dataset size must be greater than 0\"","metadata":{"nbgrader":{"grade":true,"grade_id":"dataset_size","locked":true,"points":1,"solution":false},"trusted":true,"execution":{"iopub.status.busy":"2025-01-07T13:41:32.755322Z","iopub.execute_input":"2025-01-07T13:41:32.755652Z","iopub.status.idle":"2025-01-07T13:41:32.760774Z","shell.execute_reply.started":"2025-01-07T13:41:32.755632Z","shell.execute_reply":"2025-01-07T13:41:32.759553Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Visual Exploration\n### Random Image Plotting","metadata":{}},{"cell_type":"code","source":"def plot_images(folder_path: str, resize: bool = False):\n    # Get a list of image file names in the folder\n    image_files = [f for f in os.listdir(folder_path) if f.endswith(('.jpg', '.jpeg', '.png', '.gif'))]\n    num_images_to_plot = 6\n    selected_images = random.sample(image_files, num_images_to_plot)\n    fig, axes = plt.subplots(2, 3, figsize=(12, 8))\n    for i, ax in enumerate(axes.flat):\n        if i < num_images_to_plot:\n            image_path = os.path.join(folder_path, selected_images[i])\n            img = Image.open(image_path)\n            if resize:\n                img = img.resize((512,512))\n            img = np.array(img)\n            ax.imshow(img)\n            ax.set_title(selected_images[i])\n            ax.axis('off')\n    plt.tight_layout()\n    plt.show()\n\n# Test the function\nplot_images('/kaggle/input/UBC-OCEAN/train_thumbnails', resize=True)","metadata":{"nbgrader":{"grade":true,"grade_id":"plot_images","locked":true,"points":2,"solution":false},"trusted":true,"execution":{"iopub.status.busy":"2025-01-07T13:43:02.591662Z","iopub.execute_input":"2025-01-07T13:43:02.591969Z","iopub.status.idle":"2025-01-07T13:43:05.282767Z","shell.execute_reply.started":"2025-01-07T13:43:02.591945Z","shell.execute_reply":"2025-01-07T13:43:05.282047Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Label Distribution","metadata":{}},{"cell_type":"code","source":"label_df = pd.DataFrame(df['label'].value_counts())\nlabel_df.reset_index(inplace=True)\nplt.bar(label_df['label'], label_df['count'], color='skyblue')\nplt.xlabel('Labels')\nplt.ylabel('Count')\nplt.title('Label Distribution')\nplt.show()\nassert len(label_df) > 0, \"Label distribution must be displayed correctly\"","metadata":{"nbgrader":{"grade":true,"grade_id":"label_distribution","locked":true,"points":3,"solution":false},"trusted":true,"execution":{"iopub.status.busy":"2025-01-07T13:42:20.375724Z","iopub.execute_input":"2025-01-07T13:42:20.376003Z","iopub.status.idle":"2025-01-07T13:42:20.536742Z","shell.execute_reply.started":"2025-01-07T13:42:20.375985Z","shell.execute_reply":"2025-01-07T13:42:20.535457Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Class-wise Analysis","metadata":{}},{"cell_type":"code","source":"HGSC = df[df['label']==\"HGSC\"]\nEC = df[df['label']==\"EC\"]\nCC = df[df['label']==\"CC\"]\nLGSC = df[df['label']==\"LGSC\"]\nMC = df[df['label']==\"MC\"]\n\nplt.figure(figsize=(20, 6))\nplt.rcParams['font.size'] = 14\ncolors = ['red', 'lightblue', 'green','magenta', 'yellow']\nplt.pie([len(HGSC), len(EC), len(CC), len(LGSC), len(MC)], \n        labels=['HGSC', 'EC', 'CC', 'LGSC', 'MC'], autopct='%1.1f%%', colors=colors)\nplt.title('Training Set')\nplt.show()\nassert sum([len(HGSC), len(EC), len(CC), len(LGSC), len(MC)]) == len(df), \"Pie chart proportions must match dataset size\"","metadata":{"nbgrader":{"grade":true,"grade_id":"class_analysis","locked":true,"points":4,"solution":false},"trusted":true,"execution":{"iopub.status.busy":"2025-01-07T13:43:59.714092Z","iopub.execute_input":"2025-01-07T13:43:59.714422Z","iopub.status.idle":"2025-01-07T13:43:59.815739Z","shell.execute_reply.started":"2025-01-07T13:43:59.714396Z","shell.execute_reply":"2025-01-07T13:43:59.814871Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Seaborn Visualization\n### Distribution Plot","metadata":{}},{"cell_type":"code","source":"import seaborn as sns\nsns.histplot(data=df, x='label', kde=True, color='blue')\nplt.title('Label Distribution with Seaborn')\nplt.show()\nassert not df['label'].isnull().any(), \"Ensure there are no missing values in the label column\"","metadata":{"nbgrader":{"grade":true,"grade_id":"seaborn_distplot","locked":true,"points":3,"solution":false},"trusted":true,"execution":{"iopub.status.busy":"2025-01-07T13:44:21.322497Z","iopub.execute_input":"2025-01-07T13:44:21.322797Z","iopub.status.idle":"2025-01-07T13:44:21.544306Z","shell.execute_reply.started":"2025-01-07T13:44:21.322776Z","shell.execute_reply":"2025-01-07T13:44:21.543156Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Correlation Matrix","metadata":{}},{"cell_type":"code","source":"numeric_df = df.select_dtypes(include=['number'])\ncorrelation_matrix = numeric_df.corr()\nsns.heatmap(correlation_matrix, annot=True, cmap='RdYlBu')\nplt.title('Correlation Matrix')\nplt.show()\nassert correlation_matrix.shape[0] > 0, \"Correlation matrix must be generated\"","metadata":{"nbgrader":{"grade":true,"grade_id":"correlation_matrix","locked":true,"points":3,"solution":false},"trusted":true,"execution":{"iopub.status.busy":"2025-01-07T13:44:45.109699Z","iopub.execute_input":"2025-01-07T13:44:45.109993Z","iopub.status.idle":"2025-01-07T13:44:45.295191Z","shell.execute_reply.started":"2025-01-07T13:44:45.109973Z","shell.execute_reply":"2025-01-07T13:44:45.293551Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Scatter Plot","metadata":{}},{"cell_type":"code","source":"sns.scatterplot(data=df, x='image_id', y='is_tma', hue='label', palette='RdYlBu')\nplt.title('Scatter Plot of image_id vs is_tma')\nplt.show()\nassert 'image_id' in df.columns and 'is_tma' in df.columns, \"Ensure 'image_id' and 'is_tma' columns exist in the dataset\"","metadata":{"nbgrader":{"grade":true,"grade_id":"scatter_plot","locked":true,"points":3,"solution":false},"trusted":true,"execution":{"iopub.status.busy":"2025-01-07T13:45:08.030983Z","iopub.execute_input":"2025-01-07T13:45:08.031267Z","iopub.status.idle":"2025-01-07T13:45:08.275232Z","shell.execute_reply.started":"2025-01-07T13:45:08.031244Z","shell.execute_reply":"2025-01-07T13:45:08.274536Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Pair Plot","metadata":{}},{"cell_type":"code","source":"sns.pairplot(data=df, hue='label', palette='hsv')\nplt.suptitle('Pair Plot of Dataset Features', y=1.02)\nplt.show()\nassert 'label' in df.columns, \"Ensure the 'label' column is included for the pair plot\"","metadata":{"nbgrader":{"grade":true,"grade_id":"pair_plot","locked":true,"points":3,"solution":false},"trusted":true,"execution":{"iopub.status.busy":"2025-01-07T13:45:38.421825Z","iopub.execute_input":"2025-01-07T13:45:38.422113Z","iopub.status.idle":"2025-01-07T13:45:42.759703Z","shell.execute_reply.started":"2025-01-07T13:45:38.422094Z","shell.execute_reply":"2025-01-07T13:45:42.75887Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Box Plot","metadata":{}},{"cell_type":"code","source":"sns.boxplot(data=df, x='label', y='image_height', palette='rainbow')\nplt.title('Box Plot of Image Height by Subtype')\nplt.show()\nassert 'image_height' in df.columns, \"Ensure 'image_height' exists in the dataset\"","metadata":{"nbgrader":{"grade":true,"grade_id":"box_plot","locked":true,"points":3,"solution":false},"trusted":true,"execution":{"iopub.status.busy":"2025-01-07T13:46:16.942937Z","iopub.execute_input":"2025-01-07T13:46:16.943246Z","iopub.status.idle":"2025-01-07T13:46:17.126694Z","shell.execute_reply.started":"2025-01-07T13:46:16.943221Z","shell.execute_reply":"2025-01-07T13:46:17.125569Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Count Plot","metadata":{}},{"cell_type":"code","source":"sns.countplot(data=df, x='label', palette='twilight')\nplt.title('Count Plot of label')\nplt.show()\nassert 'label' in df.columns, \"Ensure 'label' exists in the dataset\"","metadata":{"nbgrader":{"grade":true,"grade_id":"count_plot","locked":true,"points":2,"solution":false},"trusted":true,"execution":{"iopub.status.busy":"2025-01-07T13:46:44.174133Z","iopub.execute_input":"2025-01-07T13:46:44.174524Z","iopub.status.idle":"2025-01-07T13:46:44.302896Z","shell.execute_reply.started":"2025-01-07T13:46:44.174497Z","shell.execute_reply":"2025-01-07T13:46:44.302219Z"}},"outputs":[],"execution_count":null}]}