{"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":"2025-01-06T08:59:49.881366Z","iopub.execute_input":"2025-01-06T08:59:49.881747Z","iopub.status.idle":"2025-01-06T08:59:52.76367Z","shell.execute_reply.started":"2025-01-06T08:59:49.881689Z","shell.execute_reply":"2025-01-06T08:59:52.762373Z"}},"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":"2025-01-06T09:01:20.111187Z","iopub.execute_input":"2025-01-06T09:01:20.11155Z","iopub.status.idle":"2025-01-06T09:01:20.116989Z","shell.execute_reply.started":"2025-01-06T09:01:20.111521Z","shell.execute_reply":"2025-01-06T09:01:20.115803Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df = pd.read_csv(train_csv_path)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-06T09:01:23.710485Z","iopub.execute_input":"2025-01-06T09:01:23.710853Z","iopub.status.idle":"2025-01-06T09:01:23.718743Z","shell.execute_reply.started":"2025-01-06T09:01:23.710824Z","shell.execute_reply":"2025-01-06T09:01:23.717797Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\ndf.head()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-06T09:00:09.605344Z","iopub.execute_input":"2025-01-06T09:00:09.605669Z","iopub.status.idle":"2025-01-06T09:00:09.626904Z","shell.execute_reply.started":"2025-01-06T09:00:09.605645Z","shell.execute_reply":"2025-01-06T09:00:09.625854Z"}},"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":"2025-01-06T09:00:13.494512Z","iopub.execute_input":"2025-01-06T09:00:13.494911Z","iopub.status.idle":"2025-01-06T09:00:13.501065Z","shell.execute_reply.started":"2025-01-06T09:00:13.494878Z","shell.execute_reply":"2025-01-06T09:00:13.499907Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-06T09:02:47.637392Z","iopub.execute_input":"2025-01-06T09:02:47.637831Z","iopub.status.idle":"2025-01-06T09:02:50.350908Z","shell.execute_reply.started":"2025-01-06T09:02:47.637795Z","shell.execute_reply":"2025-01-06T09:02:50.349794Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-06T09:02:00.435825Z","iopub.execute_input":"2025-01-06T09:02:00.43624Z","iopub.status.idle":"2025-01-06T09:02:00.667854Z","shell.execute_reply.started":"2025-01-06T09:02:00.436211Z","shell.execute_reply":"2025-01-06T09:02:00.666549Z"}},"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":"2025-01-06T09:03:06.235389Z","iopub.execute_input":"2025-01-06T09:03:06.235738Z","iopub.status.idle":"2025-01-06T09:03:06.409263Z","shell.execute_reply.started":"2025-01-06T09:03:06.235685Z","shell.execute_reply":"2025-01-06T09:03:06.407883Z"}},"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":"2025-01-06T09:03:09.483223Z","iopub.execute_input":"2025-01-06T09:03:09.483579Z","iopub.status.idle":"2025-01-06T09:03:09.739757Z","shell.execute_reply.started":"2025-01-06T09:03:09.483548Z","shell.execute_reply":"2025-01-06T09:03:09.738686Z"}},"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='coolwarm')\nplt.title('Correlation Matrix')\nplt.show()\nassert correlation_matrix.shape[0] > 0, \"Correlation matrix must be generated\"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-06T09:03:43.21909Z","iopub.execute_input":"2025-01-06T09:03:43.219398Z","iopub.status.idle":"2025-01-06T09:03:43.50404Z","shell.execute_reply.started":"2025-01-06T09:03:43.219375Z","shell.execute_reply":"2025-01-06T09:03:43.502914Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Scatter Plot","metadata":{}},{"cell_type":"code","source":"sns.scatterplot(data=df, x='image_width', y='image_height', hue='label', palette='Set2')\nplt.title('Scatter Plot of image_width vs image_height')\nplt.show()\nassert 'image_width' in df.columns and 'image_height' in df.columns, \"Ensure 'image_width' and 'image_height' columns exist in the dataset\"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-06T09:04:11.450686Z","iopub.execute_input":"2025-01-06T09:04:11.451089Z","iopub.status.idle":"2025-01-06T09:04:11.85189Z","shell.execute_reply.started":"2025-01-06T09:04:11.45106Z","shell.execute_reply":"2025-01-06T09:04:11.850753Z"}},"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":"2025-01-06T09:04:19.588238Z","iopub.execute_input":"2025-01-06T09:04:19.58858Z","iopub.status.idle":"2025-01-06T09:04:25.295431Z","shell.execute_reply.started":"2025-01-06T09:04:19.58855Z","shell.execute_reply":"2025-01-06T09:04:25.294326Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### Box Plot","metadata":{}},{"cell_type":"code","source":"sns.boxplot(data=df, x='label', y='image_id', palette='cool')\nplt.title('Box Plot of image_id by Label')\nplt.show()\nassert 'image_id' in df.columns, \"Ensure 'image_id' exists in the dataset\"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-06T09:04:47.574271Z","iopub.execute_input":"2025-01-06T09:04:47.57465Z","iopub.status.idle":"2025-01-06T09:04:47.836241Z","shell.execute_reply.started":"2025-01-06T09:04:47.574623Z","shell.execute_reply":"2025-01-06T09:04:47.835082Z"}},"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 label')\nplt.show()\nassert 'label' in df.columns, \"Ensure 'label' exists in the dataset\"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-01-06T09:05:13.894353Z","iopub.execute_input":"2025-01-06T09:05:13.894749Z","iopub.status.idle":"2025-01-06T09:05:14.114023Z","shell.execute_reply.started":"2025-01-06T09:05:13.894695Z","shell.execute_reply":"2025-01-06T09:05:14.113037Z"}},"outputs":[],"execution_count":null}]}