{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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 in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.metrics import f1_score, accuracy_score\n# Input data files are available in the \"../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# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"df = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\ndf.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample = df.iloc[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample = df.iloc[4].drop(\"label\")","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":""},{"metadata":{"trusted":true},"cell_type":"code","source":"sample  = sample.values.reshape(28,28)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"The presentation of data "},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.matshow(sample, cmap = \"gray\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = df.drop(\"label\", axis = 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = df[\"label\"].values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_test, y_train, y_test = train_test_split(X,y, test_size = 0.2, random_state = 22)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"rf_model = RandomForestClassifier()\nrf_model.fit(X_train, y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions = rf_model.predict(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(f1_score(y_test, predictions, average=\"weighted\"))\nprint(\"Accuracy:\", accuracy_score(y_test, predictions))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":1}