{"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":"2025-01-08T12:50:09.758551Z","iopub.execute_input":"2025-01-08T12:50:09.758954Z","iopub.status.idle":"2025-01-08T12:50:12.305268Z","shell.execute_reply.started":"2025-01-08T12:50:09.758917Z","shell.execute_reply":"2025-01-08T12:50:12.304079Z"}},"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":"2025-01-08T12:50:21.521899Z","iopub.execute_input":"2025-01-08T12:50:21.522242Z","iopub.status.idle":"2025-01-08T12:50:21.527094Z","shell.execute_reply.started":"2025-01-08T12:50:21.522216Z","shell.execute_reply":"2025-01-08T12:50:21.525807Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df = pd.read_csv(train_csv_path)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-08T12:50:26.649902Z","iopub.execute_input":"2025-01-08T12:50:26.650266Z","iopub.status.idle":"2025-01-08T12:50:26.672778Z","shell.execute_reply.started":"2025-01-08T12:50:26.650241Z","shell.execute_reply":"2025-01-08T12:50:26.671669Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\ndf.head()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-08T12:50:31.256217Z","iopub.execute_input":"2025-01-08T12:50:31.256555Z","iopub.status.idle":"2025-01-08T12:50:31.276094Z","shell.execute_reply.started":"2025-01-08T12:50:31.256518Z","shell.execute_reply":"2025-01-08T12:50:31.274767Z"}},"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":"2025-01-08T13:00:01.692592Z","iopub.execute_input":"2025-01-08T13:00:01.693041Z","iopub.status.idle":"2025-01-08T13:00:01.699568Z","shell.execute_reply.started":"2025-01-08T13:00:01.693011Z","shell.execute_reply":"2025-01-08T13:00:01.698133Z"}},"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":"2025-01-08T12:52:54.380273Z","iopub.execute_input":"2025-01-08T12:52:54.380631Z","iopub.status.idle":"2025-01-08T12:52:57.562763Z","shell.execute_reply.started":"2025-01-08T12:52:54.380602Z","shell.execute_reply":"2025-01-08T12:52:57.56127Z"}},"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":"2025-01-08T12:53:42.500837Z","iopub.execute_input":"2025-01-08T12:53:42.501219Z","iopub.status.idle":"2025-01-08T12:53:42.689271Z","shell.execute_reply.started":"2025-01-08T12:53:42.501175Z","shell.execute_reply":"2025-01-08T12:53:42.687947Z"}},"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":"2025-01-08T12:53:52.847618Z","iopub.execute_input":"2025-01-08T12:53:52.848189Z","iopub.status.idle":"2025-01-08T12:53:53.02635Z","shell.execute_reply.started":"2025-01-08T12:53:52.848133Z","shell.execute_reply":"2025-01-08T12:53:53.024415Z"}},"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":"2025-01-08T12:54:17.384022Z","iopub.execute_input":"2025-01-08T12:54:17.384355Z","iopub.status.idle":"2025-01-08T12:54:17.661849Z","shell.execute_reply.started":"2025-01-08T12:54:17.384328Z","shell.execute_reply":"2025-01-08T12:54:17.660505Z"}},"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":"2025-01-08T12:55:29.379571Z","iopub.execute_input":"2025-01-08T12:55:29.379986Z","iopub.status.idle":"2025-01-08T12:55:29.680483Z","shell.execute_reply.started":"2025-01-08T12:55:29.379956Z","shell.execute_reply":"2025-01-08T12:55:29.679264Z"}},"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\"","metadata":{"nbgrader":{"grade":true,"grade_id":"scatter_plot","locked":true,"points":3,"solution":false},"trusted":true,"execution":{"iopub.status.busy":"2025-01-08T12:55:50.139429Z","iopub.execute_input":"2025-01-08T12:55:50.139841Z","iopub.status.idle":"2025-01-08T12:55:50.555066Z","shell.execute_reply.started":"2025-01-08T12:55:50.139811Z","shell.execute_reply":"2025-01-08T12:55:50.553768Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Pair Plot","metadata":{}},{"cell_type":"code","source":"sns.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\"","metadata":{"nbgrader":{"grade":true,"grade_id":"pair_plot","locked":true,"points":3,"solution":false},"trusted":true,"execution":{"iopub.status.busy":"2025-01-08T12:56:13.060834Z","iopub.execute_input":"2025-01-08T12:56:13.061237Z","iopub.status.idle":"2025-01-08T12:56:19.234698Z","shell.execute_reply.started":"2025-01-08T12:56:13.061199Z","shell.execute_reply":"2025-01-08T12:56:19.233476Z"}},"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":"2025-01-08T12:56:52.868145Z","iopub.execute_input":"2025-01-08T12:56:52.868478Z","iopub.status.idle":"2025-01-08T12:56:53.075669Z","shell.execute_reply.started":"2025-01-08T12:56:52.868443Z","shell.execute_reply":"2025-01-08T12:56:53.074584Z"}},"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":"2025-01-08T12:57:09.288582Z","iopub.execute_input":"2025-01-08T12:57:09.288989Z","iopub.status.idle":"2025-01-08T12:57:09.459033Z","shell.execute_reply.started":"2025-01-08T12:57:09.28896Z","shell.execute_reply":"2025-01-08T12:57:09.457958Z"}},"outputs":[],"execution_count":null}]}