#!/usr/bin/env python # -*- encoding: utf-8 -*- """ A random forest model. The doc is here : http://scikit-learn.org/dev/modules/generated/sklearn.ensemble.RandomForestClassifier.html C'est le premier modèle que j'ai utilisé. Pour 5 arbres, Kaggle me donne 75.59% de réussites. -------------------------------------------------------------------------------- Sortie du script ---------------- .. runblock:: console $ python RandomForest.py Résultats --------- La soumission du résultat à Kaggle donne 77.38%. -------------------------------------------------------------------------------- """ __author__ = 'Lilian BESSON (mailto:lilian.besson[AT]normale.fr)' from KaggleModel import * ################################################################################ # Beginning to learn from sklearn.ensemble import RandomForestClassifier from sklearn.utils import shuffle ################################################################################ # ok, let use this 'cross validation' process to find the best # meta parameter : n_estimators n_estimators_quality = {} #: Espace de recherche list_n_estimators = [1,2,4,5,8,10,20] #,30,40,50,60,75,82,100] Number_try = 10 #: Nombre de tests utilisés pour méta-apprendre proportion_train = 0.67 #: Proportion d'individus utilisés pour méta-apprendre. print("Find the best value for the meta parameter n_estimators, with %i run for each..." % Number_try) print("Searching in the range : %s..." % str(list_n_estimators)) print("""Using the first part (%2.2f%%, %i passengers) of the training dataset as training, and the second part (%2.2f%%, %i passengers) as testing !""" % ( 100.0*proportion_train, int(number_passengers*proportion_train), 100.0*(1-proportion_train), number_passengers - int(number_passengers*proportion_train) )) for n_estimators in list_n_estimators: # train_data = shuffle(train_data) Forest = RandomForestClassifier(n_estimators = n_estimators, criterion='entropy') # 'gini' or 'entropy' print("For %i random tree(s), learning from the first part of the dataset..." % n_estimators) quality=[] for nb_essais in xrange(Number_try): # train_data = shuffle(train_data) Forest = Forest.fit(train_data[0:int(number_passengers*proportion_train),1::], train_data[0:int(number_passengers*proportion_train),0]) Output = Forest.predict(train_data[number_passengers - int(number_passengers*proportion_train)::,1::]) quality.append(100.0 * Output[Output == train_data[number_passengers - int(number_passengers*proportion_train)::,0]].size / Output.size) n_estimators_quality[n_estimators] = np.mean(quality) print("... this value of n_estimators seems to have a (mean) quality = %2.2f%%..." % np.mean(quality)) val = n_estimators_quality.values() #: La valeur optimale trouvée pour le paramètre n_estimators best_n_estimators = n_estimators_quality.keys()[val.index(np.max(val))] print("With trying each of the following n_estimators (%s), each %i times, the best one is %.0f. (for a quality = %2.2f%%)" % (str(list_n_estimators), Number_try, best_n_estimators, np.max(val))) ################################################################################ # And then use this 'best' value of n_estimators to predict on the test dataset print("Creating the random forest (of %i estimators)..." % n_estimators) Forest = RandomForestClassifier(n_estimators = best_n_estimators, criterion = 'entropy') # 'gini' or 'entropy' print("Learning...") Forest = Forest.fit(train_data[0::,1::],train_data[0::,0]) #: The score for this classifier. score = (100.0*Forest.score(train_data[0::,1::], train_data[0::,0]) ) print(" Proportion of perfect fitting for the training dataset = %2.2f%%" % score ) # ~ must be < 95% # Predict on the testing set test_file_object = csv.reader(open('test.csv', 'rb')) header = test_file_object.next() print("Predicting for the testing dataset") Output = Forest.predict(test_data) # Write the output open_file_object = csv.writer(open("csv/RandomForest_best.csv", "wb")) z = 0 for row in test_file_object: row.insert(0, int(Output[z])) # Insert the prediction at the start of the row open_file_object.writerow(row) # Write the row to the file z += 1 print("Prediction: wrote in the file csv/RandomForest_best.csv.")