__author__ = 'rok'
from collections import defaultdict
import operator
filename = "u.data"

lines = [line.strip() for line in open(filename)]
ocene_filmov = defaultdict(list)
stevilo_ogledanih_filmov = defaultdict(int)
for line in lines:
    tokens = line.split("\t")
    ocene_filmov[tokens[1]].append(int(tokens[2]))
    stevilo_ogledanih_filmov[tokens[0]] += 1

stevilo_filmov_nad_20 = 0

out = "povprecne_ocene.out"
data_out = "data.tab"
povprecne_ocene = {}

for key, value in ocene_filmov.iteritems():
    # print "Film", key, "ima", value, "ocene"
    if len(value) >= 20:
        stevilo_filmov_nad_20 += 1
        avg = sum(value) / float(len(value))
        povprecne_ocene[key] = avg

stolpci = ["user_id", "item_id", "rating", "timestamp"]
tipi = ["d", "d", "c", "d"]

with open(data_out, "w") as f_out:
    for stolpec in stolpci:
        f_out.write(stolpec + "\t")
    f_out.write("\n")
    for tip in tipi:
        f_out.write(tip + "\t")
    f_out.write("\n")
    # special nesto
    f_out.write("\n")

    for line in lines:
        tokens = line.split("\t")
        if tokens[0] in povprecne_ocene.keys():
            f_out.write(line + "\n")



sortirane_povp_ocene = sorted(povprecne_ocene.items(), key=operator.itemgetter(1))

print "10 najslabsih: "

i = 0
while i != 10:
    print sortirane_povp_ocene[i][0]
    i += 1

print "10 najboljsih: "

i = 0
while i != 10:
    print sortirane_povp_ocene[len(sortirane_povp_ocene) - 1 - i][0]
    i += 1

print "Gledanost filmov: "
sortirani_filmi_po_gledanosti = sorted(stevilo_ogledanih_filmov.items(), key=operator.itemgetter(1))

print "10 najmanj gledanih: "

i = 0
while i != 10:
    print sortirani_filmi_po_gledanosti[i][0]
    i += 1

print "10 najbolj gledanih: "

i = 0
while i != 10:
    print sortirani_filmi_po_gledanosti[len(sortirani_filmi_po_gledanosti) - 1 - i][0]
    i += 1