{"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":"2025-12-22T16:27:07.735812Z","iopub.execute_input":"2025-12-22T16:27:07.736232Z","iopub.status.idle":"2025-12-22T16:27:07.747128Z","shell.execute_reply.started":"2025-12-22T16:27:07.736201Z","shell.execute_reply":"2025-12-22T16:27:07.746122Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Digit Recognizer – Basic Machine Learning (ML)\n\nThis notebook uses a basic Machine Learning model (Logistic Regression)\nto classify handwritten digits from the MNIST dataset.\n","metadata":{}},{"cell_type":"code","source":"import pandas as pd\n\n# Load dataset\ntrain = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\ntest = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")\n\nprint(train.shape)\nprint(test.shape)\n\ntrain.head()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-22T16:27:07.748608Z","iopub.execute_input":"2025-12-22T16:27:07.749017Z","iopub.status.idle":"2025-12-22T16:27:11.927705Z","shell.execute_reply.started":"2025-12-22T16:27:07.748884Z","shell.execute_reply":"2025-12-22T16:27:11.926280Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nfrom sklearn.linear_model import SGDClassifier\nfrom sklearn.metrics import accuracy_score\nfrom sklearn.preprocessing import StandardScaler\n\nX = train.drop(\"label\", axis=1)\ny = train[\"label\"]\n\n# Scale\nscaler = StandardScaler()\nX_scaled = scaler.fit_transform(X)\n\n# Use only 8000 samples (FAST + acceptable)\nX_small = X_scaled[:8000]\ny_small = y[:8000]\n\nX_train, X_val, y_train, y_val = train_test_split(\n    X_small, y_small, test_size=0.2, random_state=42\n)\n\nmodel = SGDClassifier(\n    loss=\"log_loss\",\n    max_iter=20,\n    n_jobs=-1,\n    random_state=42\n)\n\nmodel.fit(X_train, y_train)\n\npreds = model.predict(X_val)\nprint(\"Validation Accuracy:\", accuracy_score(y_val, preds))\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-22T16:27:11.929271Z","iopub.execute_input":"2025-12-22T16:27:11.929616Z","iopub.status.idle":"2025-12-22T16:27:14.279075Z","shell.execute_reply.started":"2025-12-22T16:27:11.929586Z","shell.execute_reply":"2025-12-22T16:27:14.277173Z"}},"outputs":[],"execution_count":null}]}