{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":3004,"databundleVersionId":861823,"sourceType":"competition"}],"dockerImageVersionId":31239,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-12-22T14:36:07.546374Z","iopub.execute_input":"2025-12-22T14:36:07.547573Z","iopub.status.idle":"2025-12-22T14:36:09.874487Z","shell.execute_reply.started":"2025-12-22T14:36:07.547510Z","shell.execute_reply":"2025-12-22T14:36:09.873747Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\n\n# Load the training data\ntrain = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')\n\n# Show first 5 rows\ntrain.head()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-22T14:36:51.520952Z","iopub.execute_input":"2025-12-22T14:36:51.521819Z","iopub.status.idle":"2025-12-22T14:36:53.807137Z","shell.execute_reply.started":"2025-12-22T14:36:51.521790Z","shell.execute_reply":"2025-12-22T14:36:53.805704Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(\"Shape of dataset:\", train.shape)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-22T14:37:13.362077Z","iopub.execute_input":"2025-12-22T14:37:13.362394Z","iopub.status.idle":"2025-12-22T14:37:13.367696Z","shell.execute_reply.started":"2025-12-22T14:37:13.362370Z","shell.execute_reply":"2025-12-22T14:37:13.366526Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train['label'].value_counts()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-22T14:37:28.760759Z","iopub.execute_input":"2025-12-22T14:37:28.761437Z","iopub.status.idle":"2025-12-22T14:37:28.777376Z","shell.execute_reply.started":"2025-12-22T14:37:28.761407Z","shell.execute_reply":"2025-12-22T14:37:28.775973Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"plt.figure(figsize=(10,4))\n\nfor i in range(10):\n    plt.subplot(2,5,i+1)\n    image = train.iloc[i, 1:].values.reshape(28,28)\n    plt.imshow(image, cmap='gray')\n    plt.title(f\"Label: {train.iloc[i,0]}\")\n    plt.axis('off')\n\nplt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-22T14:37:45.379752Z","iopub.execute_input":"2025-12-22T14:37:45.380063Z","iopub.status.idle":"2025-12-22T14:37:45.941218Z","shell.execute_reply.started":"2025-12-22T14:37:45.380039Z","shell.execute_reply":"2025-12-22T14:37:45.940072Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Exploratory Data Analysis (EDA)\n\nIn this notebook, we explore the Digit Recognizer dataset (MNIST).\n\n- Each image is 28x28 pixels\n- The label column represents digits from 0 to 9\n- Pixel values range from 0 to 255\n- The dataset is well balanced across classes\n\nThis visualization helps us understand the structure of handwritten digits.\n","metadata":{}}]}