{"nbformat_minor": 1, "metadata": {"language_info": {"codemirror_mode": {"version": 3, "name": "ipython"}, "name": "python", "pygments_lexer": "ipython3", "nbconvert_exporter": "python", "version": "3.6.1", "file_extension": ".py", "mimetype": "text/x-python"}, "kernelspec": {"display_name": "Python 3", "name": "python3", "language": "python"}}, "cells": [{"outputs": [], "metadata": {"_uuid": "e265494767b1b4b84bb6ca2689be38a523b1bfcc", "_cell_guid": "ed243219-46f7-4c60-afb3-992306726d23", "trusted": true}, "cell_type": "code", "execution_count": null, "source": "#Copied from Python CNN notebook\nfrom sklearn.ensemble import RandomForestClassifier\nimport numpy as np\nimport pandas as pd\n\ndataset = pd.read_csv(\"../input/train.csv\")\ntarget = dataset[[\"label\"]].values.ravel()\ntrain = dataset.iloc[:,1:].values\ntest = pd.read_csv(\"../input/test.csv\")\n\nrf = RandomForestClassifier(n_estimators=100)\nrf.fit(train,target)\npred = rf.predict(test)\nnp.savetxt('submission_rand_forest.csv',np.c_[range(1,len(test)+1),pred],delimiter=',',header='ImageId,Label',comments = '',fmt = '%d')\ntarget = target.astype(np.uint8)\ntrain = np.array(train).reshape((-1,1,28,28)).astype(np.uint8)\ntest = np.array(test).reshape((-1,1,28,28)).astype(np.uint8)\nimport matplotlib.pyplot as plt\nimport matplotlib.cm as cm\nplt.imshow(train[1729][0],cmap = cm.binary)\nimport lasagne\nfrom lasagne import layers\nfrom lasagne.updates import nesterov_momentum\nfrom nolearn.lasagne import NeuralNet\nfrom nolearn.lasagne import visualize\n\nnet1 = NeuralNet(\n    layers = [\n        ('input',layers.InputLayer),\n        ('hidden',layers.DenseLayer),\n        ('output',layers.DenseLayer),\n    ],\n    input_shape = (None,1,28,28),\n    hidden_num_units = 1000,\n    output_nonlinearity = lasagne.nonlinearities.softmax,\n    output_num_units = 10,\n    update = nesterov_momentum,\n    update_learning_rate = 0.0001,\n    update_momentum = 0.9,\n    max_epochs = 15,\n    verbose = 1,\n    )\nnet1.fit(train,target)\nprint(\"Done!\")\n"}], "nbformat": 4}