from IPython.core.display import Image 
Image(filename='./imgs/recsys_arch.png')

import pandas as pd

unames = ['user_id', 'username']
users = pd.read_table('./data/users_set.dat',
                      sep='|', header=None, names=unames)

rnames = ['user_id', 'course_id', 'rating']
ratings = pd.read_table('./data/ratings.dat',
                        sep='|', header=None, names=rnames)

mnames = ['course_id', 'title', 'avg_rating', 'workload', 'university', 'difficulty', 'provider']
courses = pd.read_table('./data/cursos.dat',
                       sep='|', header=None, names=mnames)

# show how one of them looks
ratings.head(10)

# show how one of them looks
users[:5]

courses[:5]

coursetalk = pd.merge(pd.merge(ratings, courses), users)
coursetalk

coursetalk.ix[0]

mean_ratings = coursetalk.pivot_table('rating', rows='provider', aggfunc='mean')
mean_ratings.order(ascending=False)

ratings_by_title = coursetalk.groupby('title').size()
ratings_by_title[:10]

active_titles = ratings_by_title.index[ratings_by_title >= 20]
active_titles[:10]

mean_ratings = coursetalk.pivot_table('rating', rows='title', aggfunc='mean')
mean_ratings

mean_ratings.ix[active_titles].order(ascending=False)

mean_ratings = coursetalk.pivot_table('rating', rows='title',cols='provider', aggfunc='mean')
mean_ratings[:10]

mean_ratings['coursera'][active_titles].order(ascending=False)[:10]

# transform the ratings frame into a ratings matrix
ratings_mtx_df = coursetalk.pivot_table(values='rating',
                                             rows='user_id',
                                             cols='title')
ratings_mtx_df.ix[ratings_mtx_df.index[:15], ratings_mtx_df.columns[:15]]

ratings_gte_4 = ratings_mtx_df[ratings_mtx_df>=4.0]
# with an integer axis index only label-based indexing is possible

ratings_gte_4.ix[ratings_gte_4.index[:15], ratings_gte_4.columns[:15]]

ratings_gte_4_pd = pd.DataFrame({'total': ratings_mtx_df.count(), 'gte_4': ratings_gte_4.count()})
ratings_gte_4_pd.head(10)

ratings_gte_4_pd['gte_4_ratio'] = (ratings_gte_4_pd['gte_4'] * 1.0)/ ratings_gte_4_pd.total
ratings_gte_4_pd.head(10)

ranking = [(title,total,gte_4, score) for title, total, gte_4, score in ratings_gte_4_pd.itertuples()]

for title, total, gte_4, score in sorted(ranking, key=lambda x: (x[3], x[2], x[1])  , reverse=True)[:10]:
    print title, total, gte_4, score

ratings_by_title = coursetalk.groupby('title').size()
ratings_by_title.order(ascending=False)[:10]

for title, total, gte_4, score in sorted(ranking, key=lambda x: (x[2], x[3], x[1])  , reverse=True)[:10]:
    print title, total, gte_4, score

course_users = coursetalk.pivot_table('rating', rows='title', cols='user_id')
course_users.ix[course_users.index[:15], course_users.columns[:15]]

ratings_by_course = coursetalk[coursetalk.title == 'An Introduction to Interactive Programming in Python']
ratings_by_course.set_index('user_id', inplace=True)

their_ids = ratings_by_course.index
their_ratings = course_users[their_ids]
course_users[their_ids].ix[course_users[their_ids].index[:15], course_users[their_ids].columns[:15]]

course_count =  their_ratings.ix['An Introduction to Interactive Programming in Python'].count()
sims = their_ratings.apply(lambda profile: profile.count() / float(course_count) , axis=1)

sims.order(ascending=False)[1:][:10]