{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"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)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nfrom subprocess import check_output\nprint(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n\n# Any results you write to the current directory are saved as output."},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"from sklearn.ensemble import RandomForestClassifier\nimport matplotlib.pyplot as plt\nimport sklearn.cross_validation as cross_validation"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"%matplotlib inline"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"dataset = pd.read_csv('../input/train.csv')\ndataset.shape\ntrain_x = dataset.iloc[:,1:]\ntrain_y= dataset.iloc[:,0]\ntest_x = pd.read_csv('../input/test.csv')"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"plt.imshow(train_x.iloc[48,:].reshape((28,28)),cmap='binary')"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"scores = list()\nstd_dev_scores = list()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"ntrees = [100,200,400,500,700,1000]\nfor ntree in ntrees:\n    rf = RandomForestClassifier(n_estimators= ntree, n_jobs=2,oob_score=True)\n    cv_scores = cross_validation.cross_val_score(rf,train_x,train_y,cv=5,n_jobs=2)\n    scores.append(np.mean(cv_scores))\n    std_dev_scores.append(np.std(cv_scores))"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":""}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"}},"nbformat":4,"nbformat_minor":0}