def __init__(self): train_data, train_label, test_data, test_label = read_data(2) train_data.astype('float16') train_data = train_data / 255 test_data.astype('float16') test_data = test_data / 255 self.train_data = dataset(train_data) self.train_label = dataset(self.modify_label(train_label)) self.test_data = dataset(test_data) self.test_label = dataset(self.modify_label(test_label))
def main(): train_data, train_label, test_data, test_label = read_data("HOG") #load_predict("mlp3", test_data, test_label) print("Fitting...") clf = SVM(train_data, train_label) save_model(clf, "svm7") print("Predicting...") #pca = PCA(n_components=100) #test_data = pca.fit_transform(test_data) #test_data = test_data[:300] #test_label = test_label[:300] predict_label = clf.predict(test_data) #predict_label = m3(test_data) acc = accuracy(test_label, predict_label) print("Accuracy: ", acc)
import numpy as np import sys import chainer from chainer import Variable, serializers from prepare import get_typemap, read_data from model import create_model2 inputdata_file = sys.argv[1] model_file_name = sys.argv[2] state_file_name = sys.argv[3] typemap = get_typemap(inputdata_file) x, t = read_data(inputdata_file, typemap) dim = [x.shape[1], 120, 50, 1] model, optimizer = create_model2(dim) serializers.load_npz(model_file_name, model) serializers.load_npz(state_file_name, optimizer) y = model.fwd(Variable(x)).data print("expect actual diff acc") for r in np.hstack([t, y, y - t, 1 - abs((y - t) / t)]): print("%6d %6d %5d %.2f" % (r[0], r[1], r[2], r[3])) ac = (1 - abs(y - t) / t).mean() print("total acc = %.3f" % ac) d = 1 - abs(y - t) / t d.sort(axis=0) ac = d[:50].mean() print("total acc = %.3f" % ac)
# -*- coding: utf-8 -*- from prepare import read_data, save_data, prepare_email from prepare import validate_email, validate_password if __name__ == "__main__": start = 35 data = read_data('data_%s00000_%s00000.txt' % (start, start + 2), sep=" ") counter = 0 good_counter = 0 # http://technet.microsoft.com/en-us/library/gg524800.aspx with open('cleansed.txt', 'w') as cleansed, \ open('dirty.txt', 'w') as dirty: for d in data: counter += 1 if len(d) == 1: pass # ('*****@*****.**', '50537580') elif len(d) == 2: email, password = d if validate_password(password): email = prepare_email(email) if validate_email(email): cleansed.write("%s\t%s\n" % (email, password)) good_counter += 1 # ('597305222', '*****@*****.**', '13945560329') elif len(d) == 3 and d[0] in d[1]: email, password = d[1], d[2]
markers = ["^", "o", "*", ".", ",", "v", ">", "<", "+", "1", "2"] colors = ["b", "g", "r", "c", "m", "y", "k", "w", "teal", "darkred", "indigo"] for i in range(num_of_hidden_layers): index = np.where(y == i) plt.scatter(lo[index], la[index], marker=markers[i], color=colors[i]) # parameters mode = sys.argv[1] datafile = sys.argv[2] background_image = None if len(sys.argv) > 3: background_image = sys.argv[3] outputfile = None if len(sys.argv) > 4: outputfile = sys.argv[4] # read csv data lo, la, data = read_data(datafile) # plot min_x = math.floor(min(lo) * 10) / 10 max_x = math.ceil(max(lo) * 10) / 10 min_y = math.floor(min(la) * 10) / 10 max_y = math.ceil(max(la) * 10) / 10 x_ticks = np.arange(min_x, max_x, 0.2) # x label y_ticks = np.arange(min_y, max_y, 0.2) # y label extent = [min_x, max_x, min_y, max_y] # image size plt.figure(figsize=(18,10)) # plot area size subplot_rows = 2 subplot_cols = 4 num_of_hidden_layers_list = [2, 3, 4, 5, 6, 7, 8, 9]