micaleel

ratings = pd.read_csv('ratings_small.csv') # loading data from csv
"""
ratings_small.csv has 4 columns - userId, movieId, ratings, and timestammp
it is most generic data format for CF related data
"""

val_indx = get_cv_idxs(len(ratings))  # index for validation set
wd = 2e-4 # weight decay
n_factors = 50 # n_factors - dimension of embedding matrix (D)

micaleel

import time
import datetime


class Stopwatch:
    def __init__(self, message: None, silent=False, callback=None):
        self._start = None
        self._stop = None
        self._silent = silent
        self._message = message

micaleel

from nltk.corpus import stopwords
import string


STOPWORDS = frozenset(stopwords.words('english'))

def is_valid(token):
    return word.isalpha() and w not in STOPWORDS and len(token) > 1

def clean(text):

micaleel

num = int(input('Enter a positive number: '))

# Ensure that the number is positive; otherwise, exit.
if num < 0:
    print('You entered a negative number')
    exit()

for i in range(1, num + 1):
    # Finding the factors of i
    factors = []

micaleel

"""Find duplicate BitTex entries."""

import sys
import os
from collections import Counter
from pprint import pprint


def extract_id(line):
	x = line.index('{')

micaleel

import unittest, os, os.path, sys, urllib
import tornado.database
import tornado.options
from tornado.options import options
from tornado.testing import AsyncHTTPTestCase

# add application root to sys.path
APP_ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))
sys.path.append(os.path.join(APP_ROOT, '..'))

micaleel

Movies Recommendation:

• MovieLens - Movie Recommendation Data Sets http://www.grouplens.org/node/73
• Yahoo! - Movie, Music, and Images Ratings Data Sets http://webscope.sandbox.yahoo.com/catalog.php?datatype=r
• Jester - Movie Ratings Data Sets (Collaborative Filtering Dataset) http://www.ieor.berkeley.edu/~goldberg/jester-data/
• Cornell University - Movie-review data for use in sentiment-analysis experiments http://www.cs.cornell.edu/people/pabo/movie-review-data/

Music Recommendation:

• Last.fm - Music Recommendation Data Sets http://www.dtic.upf.edu/~ocelma/MusicRecommendationDataset/index.html

micaleel

def compute_edit_dist(df_explanations, perturb_scale=0.0, gold_std_col='rank_target_item_average_rating'):
    """Computes the edit distance between the rankings from different approaches.

        Args:
            perturb_scale: noise level; higher values indicate more noise.
            gold_std_col: column with gold standard ranking.
            df_explanations: DataFrame of explanations for a single session.

        Returns:

micaleel

from IPython.core.display import HTML

HTML("""
<style>
 {
    display: table-cell;
    text-align: center;
   .output_png vertical-align: middle;
}
</style>

micaleel

"""Information Retrieval metrics

Useful Resources:
http://www.cs.utexas.edu/~mooney/ir-course/slides/Evaluation.ppt
http://www.nii.ac.jp/TechReports/05-014E.pdf
http://www.stanford.edu/class/cs276/handouts/EvaluationNew-handout-6-per.pdf
http://hal.archives-ouvertes.fr/docs/00/72/67/60/PDF/07-busa-fekete.pdf
Learning to Rank for Information Retrieval (Tie-Yan Liu)
"""
import numpy as np