Last active
March 27, 2019 05:58
-
-
Save pytholabsbot1/c3a3c334d25f27e099acb8d040eda632 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
%matplotlib inline | |
import matplotlib | |
import matplotlib.pyplot as plt | |
import numpy as np | |
# pass in column names for each CSV as the column name is not given in the file and read them using pandas. | |
# You can check the column names from the readme file | |
#Reading users file: | |
u_cols = ['user_id', 'age', 'sex', 'occupation', 'zip_code'] | |
users = pd.read_csv('ml-100k/u.user', sep='|', names=u_cols,encoding='latin-1') | |
#Reading ratings file: | |
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') | |
#Reading items file: | |
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') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment