Python ensemble.RandomForestClassifier类代码示例

def rand_forest(train_bow,train_labels,test_bow,test_labels,bow_indexes):
    print("Training rndForest")
    rf_classifier=RandomForestClassifier()

    rf_classifier.fit(train_bow,train_labels)
    print("Testing rndForest")
    test(rf_classifier,"rf",test_bow,test_labels,bow_indexes)

def fit_rf(path, index_filter=None, class_filter=None, feature_filter=None, folds=10,
           inverse=False, lc_filter=None):
    """

    path: Dirección del dataset a ocupar para entrenar
    index_filter: Pandas index para filtrar las filas del dataset que se quieren utilizar
    class_filter: Lista de clases que se quiere utilizar
    feature_filter: Lista de features que se quiere utilizar

    """
    data = pd.read_csv(path, index_col=0)
    data, y = utils.filter_data(data, index_filter, class_filter, feature_filter, lc_filter)

    skf = cross_validation.StratifiedKFold(y, n_folds=folds)
    
    results = []
    for train_index, test_index in skf:
        if inverse:
            aux = train_index
            train_index = test_index
            test_index = aux
            
        train_X, test_X = data.iloc[train_index], data.iloc[test_index]
        train_y, test_y = y.iloc[train_index], y.iloc[test_index]

        clf = None
        clf = RandomForestClassifier(n_estimators=100, criterion='entropy', max_depth=14,
                                     min_samples_split=5)

        clf.fit(train_X, train_y)
        results.append(metrics.predict_table(clf, test_X, test_y))

    return pd.concat(results)

 def __init__(self, data, classes, tree_features, n_trees=100):
     self.n_features = np.shape(data)[1]
     n_rows = np.shape(data)[0]
     n_nans = np.sum(np.isnan(data), 0)
     data = data[:, n_nans < n_rows]
     self.n_features = np.shape(data)[1]
     
     n_nans = np.sum(np.isnan(data), 1)
     data = data[n_nans < self.n_features, :]
     self.n_rows = np.shape(data)[0]
     
     if (tree_features > self.n_features):
         tree_features = self.n_features
     
     self.col_list = np.zeros((n_trees, tree_features), dtype='int')
     self.n_trees = n_trees
     self.bags = []
     for i in range(n_trees):
         cols = sample(range(self.n_features), tree_features)
         cols.sort()
         self.col_list[i, :] = cols
         data_temp = data[:, cols]
         n_nans = np.sum(np.isnan(data_temp), 1)
         data_temp = data_temp[n_nans == 0, :]
         classes_temp = classes[n_nans == 0]
         #bag = BaggingClassifier(n_estimators=1, max_features=tree_features)
         bag = RandomForestClassifier(n_estimators=1, max_features=tree_features)
         bag.fit(data_temp, classes_temp)
         self.bags.append(bag)
         print(np.shape(data_temp))

def random_forest_classify(train_data,train_label,test_data):
    rf = RandomForestClassifier(n_estimators=100)
    rf.fit(train_data, ravel(train_label))
    test_label=rf.predict(test_data)
    
    save_result(test_label,'sklearn_random_forest_classify_Result.csv')  
    return test_label 

def get_randomforest_classifier(X_train, y_train, params=None):
    param_grid = {"max_depth": [4, 5, 6, 7],
                  "max_features": [3, 5],
                  "criterion": ["gini", "entropy"]}
                  
    if params is None:
                  
        log = RandomForestClassifier()
        t = start("training random forest ")
        cv = cross_validation.ShuffleSplit(X_train.shape[0], n_iter=10,test_size=0.2, random_state=123)
        clf = grid_search.GridSearchCV(log, param_grid, cv=cv, n_jobs=4, scoring='roc_auc')
        clf = clf.fit(X_train,y_train)
        report(t, nitems=10*len(param_grid))
        
        print("Best score:{} with scorer {}".format(clf.best_score_, clf.scorer_))
        print "With parameters:"
    
        best_parameters = clf.best_estimator_.get_params()
        for param_name in sorted(param_grid.keys()):
            print '\t%s: %r' % (param_name, best_parameters[param_name]) 
    else:
        clf = RandomForestClassifier(**params)
        clf = clf.fit(X_train,y_train)
        
    return clf

 def cls_create(xs, ys):
     
     if algo == "SVM":
         classifier = svm.SVC(C = self.parm, probability=True)
         
     elif algo == "RF":
         classifier = RandomForestClassifier(n_estimators = int(self.parm), criterion='entropy',  n_jobs = 1)
     #
     #classifier = LDA()
     
     new_xs = xs
     
     """
     positive_count = len([y for y in ys if y > 0])
     if positive_count >= 20:
     
         #self.selector = svm.LinearSVC(C = 1, dual = False, penalty="l1")
         self.selector = LDA()
         new_xs = self.selector.fit_transform(xs, ys)
     else:
         self.selector = None
     """
     
     classifier.fit(new_xs, ys)
     probs = classifier.predict_proba(new_xs)            
     
     #self.pclassifier = svm.SVC(parm_val = 1.0)
     #self.pclassifier.fit(probs, ys)
     
     self.threshold, self.positive, self.negative = best_threshold_for_f1(probs, 20, ys)
     return classifier

def train_model_on_gestures(wav_list):

    gestures = {'vattene':0, 'vieniqui':1, 'perfetto':2, 'furbo':3, 'cheduepalle':4,
                    'chevuoi':5, 'daccordo':6, 'seipazzo':7, 'combinato':8, 'freganiente':9, 
                    'ok':10, 'cosatifarei':11, 'basta':12, 'prendere':13, 'noncenepiu':14,
                    'fame':15, 'tantotempo':16, 'buonissimo':17, 'messidaccordo':18, 'sonostufo':19}

    dataX = []
    i = 0
    for wav in wav_list:
        path = re.sub('\_audio.wav$', '', wav)
        print '\n', '##############'
        print path[-25:]
        sample = VideoMat(path, True)
        sk = Skelet(sample)
        rate, data = get_data(wav)
        data_frame = np.asarray(create_features(data, sample.labels, sample.numFrames, sk))
        #print 'data_frame !', data_frame.shape
        #data_frame2 = np.asarray(Head_inter(path, sample.labels).data_frame)
        #data_frame = np.hstack((data_frame, data_frame2))
        dataX += copy.copy(data_frame)
        
        
    # 1 target / 19 * 6 joints infos / 8 Head/Hand distances / 5 Head box = 128 features
    #Train model: Don't use the Head box features, don't really improve the model  
    data_frame = np.asarray(dataX)
    Y = data_frame[:, 0]
    Y = np.asarray([gestures[i] for i in Y])
    X = data_frame[:, 1:]
    X = X.astype(np.float32, copy=False)
    X = X[:, :122] 
    clf = RandomForestClassifier(n_estimators=300, criterion='entropy', min_samples_split=10, 
            min_samples_leaf=1, verbose=2, random_state=1) #n_jobs=2
    clf = clf.fit(X, Y)
    pickle.dump(clf, open('gradient_boosting_model_gestures.pkl','wb'))

def cross_validate():
    print("Reading the data")
    data = cu.get_dataframe(train_file)

    print("Cross-Validating")
    rf = RandomForestClassifier(n_estimators=10,
                                verbose=1,
                                compute_importances=True,
                                n_jobs=2)
    cv = cross_validation.KFold(len(data),
                                k=10,
                                indices=False)
    results = []
    for traincv, testcv in cv:
        print "\t-- cv [%d]"%len(results)
        print "\t","extracting features"
        #...
        feacv = features.extract_features(feature_names,
                                          traincv)
        print "\t","learning"
        rf.fit(feacv, data["OpenStatus"])
        print "\t","predicting"
        probs = rf.predict_proba(testcv)
        print "\t","evaluating"
        results.append( llfun(target[testcv],
                              [x["OpenStatus"] for x in probas]) )
    print "LogLoss: " + str( np.array(results).mean() )

def crossValIteration(dat,classes,cutoff,prop=0.9,reshuffle=False):
	if reshuffle:
		dat.samples = sampleReshuffle(dat)
	saved_samples = [i for i in dat.samples]
	dat.samples = ["{0}_$$_{1}".format(i,v) for i,v in enumerate(dat.samples)]
	train,test=dat.splitTraining(prop, classes)
	print test.samples
	selectedSampleIndicies = [int(i.split("_$$_")[0]) for i in test.samples]
	dat.samples = saved_samples
	print test.samples
	test.samples = [i.split("_$$_")[1] for i in test.samples]
	train.samples = [i.split("_$$_")[1] for i in train.samples]
	print "Training set has {0} samples from classes: {1}".format(len(train.samples),",".join(set(train.samples)))
	print "Test set has {0} samples from classes: {1}".format(len(test.samples),",".join(set(test.samples)))
	print "Selecting data..."
	# select features for each disease
	print "Number of selections made for each class:"

	print "Setting up SVM..."
	Xtrain = train.values.transpose()
	Ytrain = train.samples

	clf=RandomForestClassifier(n_estimators=1000)
	clf.fit(Xtrain,Ytrain)

	Xtest = test.values.transpose()
	Ytest = test.samples
	print "Predicting R-forest..."
	#classification results versus actual
	acc = zip(Ytest,clf.predict(Xtest)) # (actual,predicted)... for each sample
	print acc # this is the elemental form of the "result" lists processed below
	print sum([i[0] == i[1] for i in acc])*1.0/len(acc)
	return acc

def get_preds(features, trees=3000, depth=19):  # features is the number of latents features that I want the nmf to run on
    # Create dataframes
    df = get_nmf(k=features)
    df_full = add_yahoo_to_df(df)
    df_train = add_dummies(df_full)   # Why aren't you using df_full?

    df_test = get_nmf('data_wednesday', k=features) # put in folder name where the json data is
    df_test_full = add_yahoo_to_df(df_test)
    df_test_full = add_dummies(df_test_full)

    # Create models
    X_model_class, y_model_class = get_classifier_data(df_full)
    rf_class = RandomForestClassifier(n_estimators=trees, max_depth=depth)
    rf_class.fit(X_model_class, y_model_class)
    #
    X_model_regress, y_model_regress = get_regressor_data(df_full)
    rf_regress = RandomForestRegressor(n_estimators=trees, max_depth=depth)
    rf_regress.fit(X_model_regress, y_model_regress)

    # Get X and y values
    X_classify, y_classify  = get_classifier_data(pd.DataFrame(df_test_full.ix['2016-04-11']))
    X_regress, y_regress = get_regressor_data(pd.DataFrame(df_test_full.ix['2016-04-11']))

    # Run models

    classifier_preds = rf_class.predict(X_classify)
    classifier_accuracy = accuracy_score(classifier_preds, y_classify)

    regressor_preds = rf_regress.predict(X_regress)
    regressor_mse = mean_squared_error(regressor_preds, y_regress)

    # I want to return the number of features, k, along with the accuracy of the classifier
    # and the MSE of the regressor.  This will give me an idea of how well things are doing
    # based on the number of features.
    return [features, classifier_accuracy, regressor_mse]

def myforest(train, test, trees=250):
    #Training data prep-------------------------------------------------------------------------------------------
    csv_file_object = csv.reader(open(train, 'rb')) #Load in the training csv file
    header = csv_file_object.next() #Skip the fist line as it is a header
    output_header = header[0:2]
    train_data=[]
    for row in csv_file_object: #Skip through each row in the csv file
        train_data.append(row[1:]) #adding each row to the data variable
    train_data = np.array(train_data) #Then convert from a list to an array

    #Test data prep-----------------------------------------------------------------------------------------------
    test_file_object = csv.reader(open(test, 'rb')) #Load in the test csv file
    header = test_file_object.next() #Skip the fist line as it is a header
    test_data=[] #Create a variable called 'test_data'
    ids = []
    for row in test_file_object: #Skip through each row in the csv file
        ids.append(row[0])
        test_data.append(row[1:]) #adding each row to the data variable
    test_data = np.array(test_data) #Then convert from a list to an array

    #Train the forest
    print 'Training'
    forest = RandomForestClassifier(n_estimators=trees)
    forest = forest.fit(train_data[0::,1::], train_data[0::,0])

    print 'Predicting'
    output = forest.predict(test_data)

    open_file_object = csv.writer(open("result.csv", "wb"))
    open_file_object.writerow([output_header[0],output_header[1]])
    open_file_object.writerows(zip(ids, output))

def Random_Forest_classifier(train_input_data,train_output_data,test_input_data,test_output_data):
    tree_list = []
    accuracy_percent = []
    for trees in range(10,200,10):
        clf = RandomForestClassifier(trees)
        clf.fit(train_input_data,train_output_data)
        predicted_output = clf.predict(test_input_data)
        error_list = []
        if isinstance(predicted_output,list) ==False:
            predicted_output = predicted_output.tolist()
        if isinstance(test_output_data,list) ==False:
            test_output_data = test_output_data.tolist()
        for i in range(len(test_output_data)):
            cur_univ_similarities =  similar_univs[similar_univs['univName'] == predicted_output[i]]
            cur_univ_similarity_list = cur_univ_similarities.values.tolist()
            cur_univ_similarity_list = [item for sublist in cur_univ_similarity_list for item in sublist]
            if test_output_data[i] in cur_univ_similarity_list[1:]:
                error_list.append(0)
            else:
                error_list.append(1)
        tree_list.append(trees)
        accuracy_percent.append(100 -((sum(error_list)/float(len(error_list))) * 100))
    tree_list = np.array(tree_list)
    accuracy_percent = np.array(accuracy_percent)
    plt.plot(tree_list,accuracy_percent)
    plt.xlabel('Number of trees')
    plt.ylabel('Percent of accuracy')
    plt.title('Varation of accuracy with trees')
    plt.grid(True)
    plt.savefig("rf1.png")
    plt.show()
    return predicted_output

def main():

    S, col_names_S = load_data(config.paths.training_data,
                               config.paths.cache_folder)
    Xs, Ys, col_names_S = extract_xy(S, col_names_S)

    a = RandomForestClassifier(n_estimators=1)
    a.fit(Xs.toarray(), Ys.toarray().ravel())
    best_features = a.feature_importances_
    max_ind, max_val = max(enumerate(best_features), key=operator.itemgetter(1))
    print best_features
    print max_ind, max_val

    print Xs.shape
    print Ys.shape
    param_range = [1, 3, 5, 7, 10, 15, 20, 30, 60, 80]
    train_scores, test_scores = validation_curve(RandomForestClassifier(criterion='entropy'), Xs, Ys.toarray().ravel(),
                                                 'n_estimators', param_range)

    print train_scores
    print test_scores
    train_mean = np.mean(train_scores, axis=1)
    train_std = np.std(train_scores, axis=1)
    test_mean = np.mean(test_scores, axis=1)
    test_std = np.std(test_scores, axis=1)

    plt.title("Validation Curve for Random Forest")
    plt.xlabel("Number of Trees")
    plt.ylabel("Score")
    plt.plot(param_range, train_mean, label="Training Score", color='r')
    plt.fill_between(param_range, train_mean - train_std, train_mean + train_std, alpha=0.2, color='r')
    plt.plot(param_range, test_mean, label="Test Score", color='b')
    plt.fill_between(param_range, test_mean - test_std, test_mean + test_std, alpha=0.2, color='b')
    plt.legend(loc="best")
    plt.show()

 def randomForest_eval_func(self, chromosome):
     n_estimators, max_features, window_size = self.decode_chromosome(chromosome)
     if self.check_log(n_estimators, max_features, window_size):
         return self.get_means_from_log(n_estimators, max_features, window_size)[0]
     folded_dataset = self.create_folded_dataset(window_size)
     indim = 21 * (2 * window_size + 1)
     mean_AUC = 0
     mean_decision_value = 0
     mean_mcc = 0
     sample_size_over_thousand_flag = False
     for test_fold in xrange(self.fold):
         test_labels, test_dataset, train_labels, train_dataset = folded_dataset.get_test_and_training_dataset(test_fold)
         if len(test_labels) + len(train_labels) > 1000:
             sample_size_over_thousand_flag = True
         clf = RandomForestClassifier(n_estimators=n_estimators, max_features=max_features)
         clf.fit(train_dataset, train_labels)
         probas = clf.predict_proba(test_dataset)
         decision_values = map(lambda x: x[1], probas) # Probability of being binding residue
         AUC, decision_value_and_max_mcc = validate_performance.calculate_AUC(decision_values, test_labels)
         mean_AUC += AUC
         mean_decision_value += decision_value_and_max_mcc[0]
         mean_mcc += decision_value_and_max_mcc[1]
         if sample_size_over_thousand_flag:
             break
     if not sample_size_over_thousand_flag:
         mean_AUC /= self.fold
         mean_decision_value /= self.fold
         mean_mcc /= self.fold
     self.write_log(n_estimators, max_features, window_size, mean_AUC, mean_decision_value, mean_mcc)
     self.add_log(n_estimators, max_features, window_size, mean_AUC, mean_decision_value, mean_mcc)
     return mean_AUC

    def model_and_predict(self, X_train, y_train, X_test):
        district_idx = self.columns.index('PdDistrict')
        districts = set(X_train[:,district_idx])
        district_ys = {}
        # Grow forest and predict separately for each district's records
        for d in districts:
            district_X_train = X_train[X_train[:, district_idx] == d]
            district_X_train = np.delete(district_X_train, district_idx, 1)
            district_y_train = y_train[X_train[:, district_idx] == d]
            district_X_test = X_test[X_test[:, district_idx] == d]
            district_X_test = np.delete(district_X_test, district_idx, 1)
            print "Growing forest for", d

            # Not saving output in Git so make this deterministic 
            # with random_state
            rf = RandomForestClassifier(n_estimators=self.n_trees, n_jobs=-1,
                                        random_state=782629)
            rf.fit(district_X_train, district_y_train)

            district_ys[d] = list(rf.predict(district_X_test))
            print "Finished", d

        print "All predictions made"

        y_hat = []
        for row in X_test:
            d_ys = district_ys[row[district_idx]]
            y_hat.append(d_ys.pop(0))

        return y_hat