movie_data_read.py

import pandas as pd

# read_csv using pandas. 
# Column names available in the readme file

#Reading users file(943*5):
u_cols = ['user_id', 'age', 'sex', 'occupation', 'zip_code']
users = pd.read_csv('ml-100k/u.user', sep='|', names=u_cols,
 encoding='latin-1')
#print users
print users.shape       #i.e. dimensions: 943*5
print users.head()

#Reading ratings file(100000,4):
r_cols = ['user_id', 'movie_id', 'rating', 'unix_timestamp']
ratings = pd.read_csv('ml-100k/u.data', sep='\t', names=r_cols,
 encoding='latin-1')
#print ratings
print ratings.shape
print ratings.head()

#Reading items file(1682*24):
i_cols = ['movie id', 'movie title' ,'release date','video release date', 'IMDb URL', 'unknown', 'Action', 'Adventure',
 'Animation', 'Children\'s', 'Comedy', 'Crime', 'Documentary', 'Drama', 'Fantasy',
 'Film-Noir', 'Horror', 'Musical', 'Mystery', 'Romance', 'Sci-Fi', 'Thriller', 'War', 'Western']
items = pd.read_csv('ml-100k/u.item', sep='|', names=i_cols,
 encoding='latin-1')
#print items
print items.shape
print items.head()