{"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":31089,"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},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import accuracy_score\n\n# Load data\ntrain = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\ntest = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")\n\n# Features and target\nX = train.drop(\"label\", axis=1)\ny = train[\"label\"]\n\n# Split for validation\nX_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)\n\n# Train model\nmodel = RandomForestClassifier(n_estimators=100, random_state=42)\nmodel.fit(X_train, y_train)\n\n# Validate\ny_pred = model.predict(X_val)\nprint(\"Validation Accuracy:\", accuracy_score(y_val, y_pred))\n\n# Predict on test set\ntest_preds = model.predict(test)\n\n# Create submission file\nsubmission = pd.DataFrame({\n    \"ImageId\": list(range(1, len(test_preds)+1)),\n    \"Label\": test_preds\n})\nsubmission.to_csv(\"submission_output.csv\", index=False)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-16T06:52:33.932763Z","iopub.execute_input":"2025-09-16T06:52:33.933125Z","iopub.status.idle":"2025-09-16T06:53:02.839527Z","shell.execute_reply.started":"2025-09-16T06:52:33.933100Z","shell.execute_reply":"2025-09-16T06:53:02.838775Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"submission.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-16T07:00:55.563052Z","iopub.execute_input":"2025-09-16T07:00:55.564135Z","iopub.status.idle":"2025-09-16T07:00:55.587591Z","shell.execute_reply.started":"2025-09-16T07:00:55.564102Z","shell.execute_reply":"2025-09-16T07:00:55.586587Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}