I want to analyze MovieLens data set and load on my machine the M1 file. I combine actually two data files (ratings.dat and movies.dat) and sort the table according 'userId' and 'Time' columns. The head of my DataFrame looks like here (all columns values are corresponding to the original data sets):
In [36]: df.head(10)
Out[36]:
userId movieId Rating Time movieName \
40034 1 150 5 978301777 Apollo 13 (1995)
77615 1 1028 5 978301777 Mary Poppins (1964)
550485 1 2018 4 978301777 Bambi (1942)
400889 1 1962 4 978301753 Driving Miss Daisy (1989)
787274 1 1035 5 978301753 Sound of Music, The (1965)
128308 1 938 4 978301752 Gigi (1958)
497972 1 3105 5 978301713 Awakenings (1990)
28417 1 2028 5 978301619 Saving Private Ryan (1998)
6551 1 1961 5 978301590 Rain Man (1988)
35492 1 2692 4 978301570 Run Lola Run (Lola rennt) (1998)
genre
40034 Drama
77615 Children's|Comedy|Musical
550485 Animation|Children's
400889 Drama
787274 Musical
128308 Musical
497972 Drama
28417 Action|Drama|War
6551 Drama
35492 Action|Crime|Romance
[10 rows x 6 columns]
I can not understand that the same user with user Id 1 see or rated the different movies (Apollo13 (Id:150), Mary Poppins (Id:1028) and Bambi (Id:2018) exactly at the same time (up to the milleseconds). If somebody works already with this data set, please, clear this situation.
