{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.12.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceType":"competition","sourceId":3004,"databundleVersionId":861823}],"dockerImageVersionId":31328,"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":"2026-05-16T16:41:54.048300Z","iopub.execute_input":"2026-05-16T16:41:54.049434Z","iopub.status.idle":"2026-05-16T16:41:54.057518Z","shell.execute_reply.started":"2026-05-16T16:41:54.049394Z","shell.execute_reply":"2026-05-16T16:41:54.056443Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import MinMaxScaler  # Normalization\nfrom sklearn.linear_model import LogisticRegression\n\n# 1. Load the dataset (Only 'train.csv' is required for model training)\ndigits = pd.read_csv('/kaggle/input/competitions/digit-recognizer/train.csv')\n\n# 2. Visualize the 11th handwritten digit image\nplt.imshow(digits.iloc[10, 1:].values.reshape(28, 28), cmap=\"Greys\")\nplt.show()\n\n# 3. Split features and labels\nX = digits.drop('label', axis=1)\ny = digits['label']  # Labels\n\n# 4. Split data into training and testing sets\nx_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)\n\n# 5. Feature Scaling (Normalization)\npreprocessor = MinMaxScaler()\nx_train = preprocessor.fit_transform(x_train)\nx_test = preprocessor.transform(x_test)\n\n# 6. Model Training\nmodel = LogisticRegression(max_iter=500)\nmodel.fit(x_train, y_train)\n\n# 7. Model Evaluation\naccuracy = model.score(x_test, y_test)\nprint(f\"Model accuracy on test set: {accuracy:.4f}\")\n\n# 8. Prediction (Extract the 124th sample from x_test to avoid format and dimension errors)\n# Note: x_test is already normalized and has no 'label' column, which is ideal for direct prediction.\nsingle_sample = x_test[123].reshape(28, 28)\nplt.imshow(single_sample, cmap=\"Greys\")\nplt.show()\n\n# Perform prediction\nprediction = model.predict(x_test[123].reshape(1, -1))\nprint(\"The model predicted result is:\", prediction)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-05-16T16:41:54.203648Z","iopub.execute_input":"2026-05-16T16:41:54.205213Z","iopub.status.idle":"2026-05-16T16:42:36.123254Z","shell.execute_reply.started":"2026-05-16T16:41:54.205086Z","shell.execute_reply":"2026-05-16T16:42:36.122242Z"}},"outputs":[],"execution_count":null}]}