Finding sum of large array based on row values

Hello, I have a big matrix where the 1st column varies for the year (1993 to 2014), 2nd column is month, 3rd column is day, 4th is hour, fifth min, sixth second and the last column is value. The value of 4th column varies from 0 to 23 hr, making a full day.

1993  4  2  0  0  0  2,44
1993  4  2  0  15  0  2,34
1993  4  2  0  30  0  2,21
1993  4  2  0  45  0  2,14
1993  4  2  1  0  0  2,04
1993  4  2  1  15  0  1,98
1993  4  2  1  30  0  1,92
1993  4  2  1  45  0  1,87
1993  4  2  2  0  0  1,79
1993  4  2  2  15  0  1,75
1993  4  2  2  30  0  1,73
1993  4  2  2  45  0  1,73
1993  4  2  3  0  0  1,72
1993  4  2  3  15  0  1,73
1993  4  2  3  30  0  1,78
1993  4  2  3  45  0  1,77
......................................................
......................................................
......................................................

2014  12  31  21  0  0  3,82
2014  12  31  21  15  0  3,89
2014  12  31  21  30  0  3,88
2014  12  31  21  45  0  3,89
2014  12  31  22  0  0  3,90
2014  12  31  22  15  0  3,85
2014  12  31  22  30  0  3,81
2014  12  31  22  45  0  3,74
2014  12  31  23  0  0  3,66
2014  12  31  23  15  0  3,56
2014  12  31  23  30  0  3,45
2014  12  31  23  45  0  3,34

I have to group the similar 4th row element (which varies from 0 to 23) and find out mean of the last column. So, the desired output would be:

1993  4  2  0  0  0  2.28
1993  4  2  1  0  0  1.95
1993  4  2  2  0  0  1.75
1993  4  2  3  0  0  1.75
.....................................................
.....................................................
2014  12  31  21  0  0  3,87
2014  12  31  22  0  0  3.82

Any help on this?

[José-Luis]

I'm gonna go ahead and assume that this is a text file.

Answer 1

[alice]

Calling your matrix data:

[dateAndHour,~,index] = unique(data(:,1:4),'rows');             % find the hours present in the matrix and attribute each element of the matrix to one of these hours 
hourlyMean = accumarray(index,data(:,7),[],@mean);              % compute the hourly mean
output = [dateAndHour,zeros(size(dateAndHour,1),2),hourlyMean]; % build the output

[Jan]

Note that mean will reply the mean over the 2nd dimension, when an index occurs once only. See https://www.mathworks.com/matlabcentral/answers/352429-hourly-mean-for-my-data