book_top = xlrd.open_workbook('top50Info.xlsx')
table_top = book_top.sheet_by_name('data')
data_top = []
for i in range(1,51):
data_tmp = table_top.row_values(i)
data_top.append(data_tmp[4:56])
book = xlrd.open_workbook('candidatesFeatures.xlsx')
table = book.sheet_by_name('data')
data = []
for i in range(1,2934):
data_tmp = table.row_values(i)
data_top.append(data_tmp[4:56])
book_last = xlrd.open_workbook('last200Info.xlsx')
table_last = book_last.sheet_by_name('data')
for i in range(1,51):
data_tmp = table_last.row_values(i)
data_top.append(data_tmp[4:56])
data_x=data_top
data_y=np.concatenate((np.ones(50),-np.ones(2933),np.zeros(50)))
data=[data_x,data_y]
writeParamsIntoFile(data,'dataset')
valid_set_x_top = np.array(data_top[40:45])
test_set_x_top = np.array(data_top[45:])
book_last = xlrd.open_workbook('last200Info.xlsx')
table_last = book_last.sheet_by_name('data')
data_last = []
for i in range(1,51):
data_tmp = table_last.row_values(i)
data_last.append(data_tmp[4:56])
set_y_last=np.zeros(50)
'''
for i in range(0,50):
set_y_last.append(random.randint(5,9))
'''
train_set_x_last = np.array(data_last[0:40])
valid_set_x_last = np.array(data_last[40:45])
test_set_x_last = np.array(data_last[45:])
train_set_x=np.concatenate((train_set_x_top,train_set_x_last))
train_set_y=np.concatenate((set_y_top[0:40],set_y_last[0:40]))
valid_set_x=np.concatenate((valid_set_x_top,valid_set_x_last))
valid_set_y=np.concatenate((set_y_top[40:45],set_y_last[40:45]))
test_set_x=np.concatenate((test_set_x_top,test_set_x_last))
test_set_y=np.concatenate((set_y_top[45:],set_y_last[45:]))
dataset=[(train_set_x,train_set_y),(valid_set_x,valid_set_y),(test_set_x,test_set_y)]
writeParamsIntoFile(dataset,'dataset_train')
print train_set_y
