Speedup an IF check over a numpy array/pandas dataframe

I'm trying to process some data in pandas that looks like this in the CSV (it's much bigger):

2014.01.02,09:00,1.37562,1.37562,1.37545,1.37545,21
2014.01.02,09:01,1.37545,1.37550,1.37542,1.37546,18
2014.01.02,09:02,1.37546,1.37550,1.37546,1.37546,15
2014.01.02,09:03,1.37546,1.37563,1.37546,1.37559,39
2014.01.02,09:04,1.37559,1.37562,1.37555,1.37561,37
2014.01.02,09:05,1.37561,1.37564,1.37558,1.37561,35
2014.01.02,09:06,1.37561,1.37566,1.37558,1.37563,38
2014.01.02,09:07,1.37563,1.37567,1.37561,1.37566,42
2014.01.02,09:08,1.37570,1.37571,1.37564,1.37566,25

I imported it using:

raw_data = pd.read_csv('raw_data.csv', engine='c', header=None, index_col=0, names=['date', 'time', 'open', 'high', 'low', 'close', 'volume'], parse_dates=[[0,1]])

And got this (data):

                        open     high      low    close  volume
date_time                                                      
2014-01-02 09:00:00  1.37562  1.37562  1.37545  1.37545      21
2014-01-02 09:01:00  1.37545  1.37550  1.37542  1.37546      18
2014-01-02 09:02:00  1.37546  1.37550  1.37546  1.37546      15
2014-01-02 09:03:00  1.37546  1.37563  1.37546  1.37559      39
2014-01-02 09:04:00  1.37559  1.37562  1.37555  1.37561      37
2014-01-02 09:05:00  1.37561  1.37564  1.37558  1.37561      35
2014-01-02 09:06:00  1.37561  1.37566  1.37558  1.37563      38
2014-01-02 09:07:00  1.37563  1.37567  1.37561  1.37566      42
2014-01-02 09:08:00  1.37570  1.37571  1.37564  1.37566      25
2014-01-02 09:09:00  1.37566  1.37566  1.37555  1.37560      27
2014-01-02 09:10:00  1.37558  1.37559  1.37527  1.37527      44
2014-01-02 09:11:00  1.37527  1.37537  1.37527  1.37533      28
2014-01-02 09:12:00  1.37532  1.37534  1.37528  1.37528      22
2014-01-02 09:13:00  1.37534  1.37537  1.37521  1.37532      26
2014-01-02 09:14:00  1.37532  1.37536  1.37528  1.37534      16
2014-01-02 09:15:00  1.37534  1.37534  1.37526  1.37532      20
2014-01-02 09:16:00  1.37532  1.37533  1.37526  1.37529      23
2014-01-02 09:17:00  1.37529  1.37536  1.37529  1.37530      19
2014-01-02 09:18:00  1.37530  1.37530  1.37527  1.37527      19
2014-01-02 09:19:00  1.37527  1.37530  1.37527  1.37527      16
2014-01-02 09:20:00  1.37528  1.37542  1.37527  1.37541      22
2014-01-02 09:21:00  1.37542  1.37542  1.37536  1.37536      16
2014-01-02 09:22:00  1.37536  1.37559  1.37536  1.37559      32

Now, I want to construct an y array for the condition where I pick a X_period=10 from my data put it's data on X and then depending on the close of X_period+5 compared with the open of X_period I fill an y array:

X_period = 10
period = X_period + 5
columns = data.shape[1]
X = np.zeros((len(self.data)-period, columns*X_period), dtype=np.float)
y = np.zeros(len(data)-period, dtype=np.int)
for i in range(len(data)-period):
    input_data = data.ix[:, 0:columns].iloc[i:i+X_period]
    X[i] = np.array(input_data, dtype=np.float).ravel()
    if float(data['close'].iloc[i+period-1]) > float(self.data['open'].iloc[i+self.X_period-1]):
        self.y[i] = 1
    elif float(data['close'].iloc[i+period-1]) < float(self.data['open'].iloc[i+self.X_period-1]):
        self.y[i] = 2

Now, this does the job but it's very slow. Any ideia on how to speed this up?