library(reshape2)

#długość wektora (sqrt(x1^2 + x2^2 + ...))
norm_vec <- function(x) sqrt(sum(x^2, na.rm=TRUE))

#podobieństwo kosinusowe
cosine <- function(user1, user2) {
  top = sum(user2 * user1, na.rm=TRUE)
  bot = norm_vec(user1) * norm_vec(user2)
  return (top/bot)
}

# user_n szukany użytkownik
# film_n szukany film
# nr = ilość najlepszych podobieństw do analizy
recommend <- function(user, film, nr, mx) {
  userrow = mx[rownames(mx) == user, ]
  has_film = mx[!is.na(mx[,film]), ]
  has_film = has_film[rownames(has_film) != user, ]

  t = apply(has_film, 1, cosine, userrow)
  ord = sort(t, decreasing=TRUE, index.return = TRUE) $ix
  sorted = has_film[ord, ][1:min(nr, nrow(has_film)), ]
  return (sorted)
}

pred_avg <- function(mx, user, film) {
  user = toString(user)
  film = toString(film)
  tmp = recommend(user, film, 20, mx)
  row_means = rowMeans(tmp, na.rm = TRUE)
  user_mean = data.frame(mean(mx[row.names(mx) == user, ], na.rm = TRUE))
  colnames(user_mean) = list("avg")
  regression_table = data.frame(row_means, tmp[, colnames(tmp) == film])
  colnames(regression_table) = list("avg", "rating")
  regression = lm(rating ~ avg, data=regression_table)

  return (predict(regression, user_mean))
}

pred_2 <- function(mx, user, film) {
  user = toString(user)
  film = toString(film)
  tmp = recommend(user, film, 20, mx)
  row_means = rowMeans(tmp, na.rm = TRUE)
  user_mean = data.frame(mean(mx[row.names(mx) == user, ], na.rm = TRUE))
  colnames(user_mean) = list("avg")
  regression_table = data.frame(row_means, tmp[, colnames(tmp) == film])
  colnames(regression_table) = list("avg", "rating")
  regression = lm(rating ~ avg, data=regression_table)

  return (predict(regression, user_mean))
}

prog <- function() {
  set.seed(123)
  MyData <- read.csv(file="~/Desktop/mow-dane/ratings.csv", header=TRUE, sep=",")
  MyData <- MyData[1:3]

  test_indexes = sample(nrow(MyData), size = nrow(MyData)/20)
  TestData <- MyData[test_indexes, ]
  MyData <- MyData[-test_indexes,]

  MyMatrix = acast(MyData, userId ~ movieId , value.var="rating")
  TestMatrix = acast(TestData, userId ~ movieId , value.var="rating")

  #uf1 = list(MyMatrix, 14, 15)
  #uf2 = list(MyMatrix, 14, 15)
  #l1 = list(MyMatrix, MyMatrix)
  #l2 = list(14, 14)
  #l3 = list(15, 15)
  #return lapply(pred_avg, c(l1, l2, l3))
  #pred_avg(MyMatrix, 14, 15)2.759451
  matrixTestData = matrix(TestData)
  for(i in 1:nrow(TestData)) {
    row <- matrix(TestData[i,])
    # do stuff with
    a = row[1,1]
    print(a)
    #predicted_val = pred_2(MyMatrix, row[1], row[2])
  }
}

prog()