{"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":"2025-01-06T05:31:07.71904Z","iopub.execute_input":"2025-01-06T05:31:07.719622Z","iopub.status.idle":"2025-01-06T05:31:09.600977Z","shell.execute_reply.started":"2025-01-06T05:31:07.71956Z","shell.execute_reply":"2025-01-06T05:31:09.599811Z"}},"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":"2025-01-06T05:32:28.03922Z","iopub.execute_input":"2025-01-06T05:32:28.039653Z","iopub.status.idle":"2025-01-06T05:32:28.045513Z","shell.execute_reply.started":"2025-01-06T05:32:28.039621Z","shell.execute_reply":"2025-01-06T05:32:28.043974Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df = pd.read_csv(train_csv_path)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-06T05:32:34.793366Z","iopub.execute_input":"2025-01-06T05:32:34.793777Z","iopub.status.idle":"2025-01-06T05:32:34.814045Z","shell.execute_reply.started":"2025-01-06T05:32:34.793744Z","shell.execute_reply":"2025-01-06T05:32:34.81268Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\ndf.head()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-06T05:32:39.417848Z","iopub.execute_input":"2025-01-06T05:32:39.418379Z","iopub.status.idle":"2025-01-06T05:32:39.441479Z","shell.execute_reply.started":"2025-01-06T05:32:39.418338Z","shell.execute_reply":"2025-01-06T05:32:39.440154Z"}},"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":"2025-01-06T05:33:43.482669Z","iopub.execute_input":"2025-01-06T05:33:43.483166Z","iopub.status.idle":"2025-01-06T05:33:43.490655Z","shell.execute_reply.started":"2025-01-06T05:33:43.483095Z","shell.execute_reply":"2025-01-06T05:33:43.489386Z"}},"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":"2025-01-06T05:35:36.418469Z","iopub.execute_input":"2025-01-06T05:35:36.418857Z","iopub.status.idle":"2025-01-06T05:35:39.879931Z","shell.execute_reply.started":"2025-01-06T05:35:36.418826Z","shell.execute_reply":"2025-01-06T05:35:39.878198Z"}},"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":"2025-01-06T05:42:33.763457Z","iopub.execute_input":"2025-01-06T05:42:33.76386Z","iopub.status.idle":"2025-01-06T05:42:33.978094Z","shell.execute_reply.started":"2025-01-06T05:42:33.763827Z","shell.execute_reply":"2025-01-06T05:42:33.977093Z"}},"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":"2025-01-06T05:37:50.699011Z","iopub.execute_input":"2025-01-06T05:37:50.699444Z","iopub.status.idle":"2025-01-06T05:37:50.848962Z","shell.execute_reply.started":"2025-01-06T05:37:50.699412Z","shell.execute_reply":"2025-01-06T05:37:50.847638Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Seaborn Visualization\n### Distribution Plot","metadata":{}},{"cell_type":"code","source":"import warnings\nwarnings.filterwarnings(\"ignore\", category=FutureWarning, module=\"seaborn._oldcore\")\nimport 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\"\ndf.replace([np.inf, -np.inf], np.nan, inplace=True)","metadata":{"nbgrader":{"grade":true,"grade_id":"seaborn_distplot","locked":true,"points":3,"solution":false},"trusted":true,"execution":{"iopub.status.busy":"2025-01-06T05:58:03.723635Z","iopub.execute_input":"2025-01-06T05:58:03.724064Z","iopub.status.idle":"2025-01-06T05:58:03.973149Z","shell.execute_reply.started":"2025-01-06T05:58:03.724024Z","shell.execute_reply":"2025-01-06T05:58:03.971712Z"}},"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='Reds')\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":"2025-01-06T05:40:51.398602Z","iopub.execute_input":"2025-01-06T05:40:51.399006Z","iopub.status.idle":"2025-01-06T05:40:51.750716Z","shell.execute_reply.started":"2025-01-06T05:40:51.398977Z","shell.execute_reply":"2025-01-06T05:40:51.74962Z"}},"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='Blues')\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\"\n","metadata":{"nbgrader":{"grade":true,"grade_id":"scatter_plot","locked":true,"points":3,"solution":false},"trusted":true,"execution":{"iopub.status.busy":"2025-01-06T05:43:24.18069Z","iopub.execute_input":"2025-01-06T05:43:24.181092Z","iopub.status.idle":"2025-01-06T05:43:24.577317Z","shell.execute_reply.started":"2025-01-06T05:43:24.181061Z","shell.execute_reply":"2025-01-06T05:43:24.57597Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Pair Plot","metadata":{}},{"cell_type":"code","source":"import warnings\nwarnings.filterwarnings(\"ignore\", category=FutureWarning, module=\"seaborn._oldcore\")\nsns.pairplot(data=df, hue='label', palette='husl')\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\"\ndf.replace([np.inf, -np.inf], np.nan, inplace=True)","metadata":{"nbgrader":{"grade":true,"grade_id":"pair_plot","locked":true,"points":3,"solution":false},"trusted":true,"execution":{"iopub.status.busy":"2025-01-06T05:51:07.644232Z","iopub.execute_input":"2025-01-06T05:51:07.644674Z","iopub.status.idle":"2025-01-06T05:51:13.874372Z","shell.execute_reply.started":"2025-01-06T05:51:07.644637Z","shell.execute_reply":"2025-01-06T05:51:13.87305Z"}},"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='Blues')\nplt.title('Box Plot of Numerical Feature by Label')\nplt.show()\nassert 'image_height' in df.columns, \"Ensure 'numerical_feature' exists in the dataset\"","metadata":{"nbgrader":{"grade":true,"grade_id":"box_plot","locked":true,"points":3,"solution":false},"trusted":true,"execution":{"iopub.status.busy":"2025-01-06T05:46:29.03953Z","iopub.execute_input":"2025-01-06T05:46:29.040076Z","iopub.status.idle":"2025-01-06T05:46:29.31632Z","shell.execute_reply.started":"2025-01-06T05:46:29.040028Z","shell.execute_reply":"2025-01-06T05:46:29.314991Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Count Plot","metadata":{}},{"cell_type":"code","source":"sns.countplot(data=df, x='label', palette='pastel')\nplt.title('Count Plot of Categorical Feature')\nplt.show()\nassert 'label' in df.columns, \"Ensure 'categorical_feature' exists in the dataset\"","metadata":{"nbgrader":{"grade":true,"grade_id":"count_plot","locked":true,"points":2,"solution":false},"trusted":true,"execution":{"iopub.status.busy":"2025-01-06T05:47:17.464594Z","iopub.execute_input":"2025-01-06T05:47:17.465024Z","iopub.status.idle":"2025-01-06T05:47:17.663157Z","shell.execute_reply.started":"2025-01-06T05:47:17.464986Z","shell.execute_reply":"2025-01-06T05:47:17.661911Z"}},"outputs":[],"execution_count":null}]}