recommendation_helpers.py

import numpy as np
import pandas as pd
from sklearn.metrics import mean_squared_error

# calculating mean squere error
def get_mse(pred, actual):
    # Ignore nonzero terms.
    pred = pred[actual.nonzero()].flatten()
    actual = actual[actual.nonzero()].flatten()
    return mean_squared_error(pred, actual)

# cross validation
def train_test_split(ratings):
    test = np.zeros(ratings.shape)
    train = ratings.copy()
    for user in xrange(ratings.shape[0]):
        test_ratings = np.random.choice(ratings[user, :].nonzero()[0], 
                                        size=10, 
                                        replace=False)
        train[user, test_ratings] = 0.
        test[user, test_ratings] = ratings[user, test_ratings]
        
    # Test and training are truly disjoint
    assert(np.all((train * test) == 0)) 
    return train, test

# measure distance L2
def calc_similarity(ratings, kind='user', epsilon=1e-9):
    # epsilon -> small number for handling dived-by-zero errors
    if kind == 'user':
        sim = ratings.dot(ratings.T) + epsilon
    elif kind == 'item':
        sim = ratings.T.dot(ratings) + epsilon
    norms = np.array([np.sqrt(np.diagonal(sim))])
    return (sim / norms / norms.T)



def predict_simple(ratings, similarity, kind='user'):
    if kind == 'user':
        return similarity.dot(ratings) / np.array([np.abs(similarity).sum(axis=1)]).T
    elif kind == 'item':
        return ratings.dot(similarity) / np.array([np.abs(similarity).sum(axis=1)])

def predict_topk(ratings, similarity, kind='user', k=40):
    pred = np.zeros(ratings.shape)
    if kind == 'user':
        for i in xrange(ratings.shape[0]):
            top_k_users = [np.argsort(similarity[:,i])[:-k-1:-1]]
            for j in xrange(ratings.shape[1]):
                pred[i, j] = similarity[i, :][top_k_users].dot(ratings[:, j][top_k_users]) 
                pred[i, j] /= np.sum(np.abs(similarity[i, :][top_k_users]))
    if kind == 'item':
        for j in xrange(ratings.shape[1]):
            top_k_items = [np.argsort(similarity[:,j])[:-k-1:-1]]
            for i in xrange(ratings.shape[0]):
                pred[i, j] = similarity[j, :][top_k_items].dot(ratings[i, :][top_k_items].T) 
                pred[i, j] /= np.sum(np.abs(similarity[j, :][top_k_items]))        
    
    return pred