import file_save_load as fsl
import csv
import unicodedata
from unidecode import unidecode
import io
movies = fsl.read_from_file(
"imdb_dataset_v7.1_6_actors_complete_wrong_genre.tsv", 6)
movies_and_genres = {}
with open("IMDB_files_link/_filtered_data/genres.filtered") as data_file:
reader = csv.reader(data_file, delimiter='\r')
for line in reader:
# line variable here is a list of strings, so we join it into one string
full_line = " ".join(line)
# partition returns 3-tuple: (part_before_delimiter, delimiter, part_after_delimiter)
parted = full_line.partition("\t")
title = parted[0]
# in the part_after_delimiter we delete all \t characters
genre = parted[2].replace("\t", "")
if title not in movies_and_genres:
movies_and_genres[title] = [genre]
else:
movies_and_genres[title].append(genre)
# print movies_and_genres["Den skaldede frisor (2012)"]
# for title in movies_and_genres:
# if "skaldede" in title:
import csv, wikipedia, unicodedata, wptools
import time
import file_save_load as fsl
fileName = 'datasetV_20161118-080950'
actors_amount = 6
movies = fsl.read_from_file(fileName, 6)
def compute_jaccard_index(list_1, list_2):
list_1 = list_1.replace("(", "").replace(")", "")
list_2 = list_2.replace("(", "").replace(")", "")
set_1 = set(list_1.split())
set_2 = set(list_2.split())
return len(set_1.intersection(set_2)) / float(len(set_1.union(set_2)))
movies_with_no_budget = []
wiki_no_budget = []
wiki_budget_ok = []
different_budget_keys = set()
for title in movies:
if movies[title]["budget"] == "no_info":
full_title = title
title_no_year = title.partition("(")[0]
movies_with_no_budget.append([title_no_year, full_title])
counter = 0
for title in movies_with_no_budget:
import csv
import time
import ast
import file_save_load as fsl
######################################################
# adding new budgets
######################################################
fileNameDataset = 'datasetV_20161118-080950'
fileNameBudgets = '_wiki_budg_for_' + fileNameDataset
actors_amount = 3
movies = fsl.read_from_file(fileNameDataset, actors_amount)
# with open('files/datasetV_20161116-203716') as csvfile:
# reader = csv.DictReader(csvfile, delimiter = "\t")
# for entry in reader:
# movies[
# entry["title"]
# ] = {
# "director": entry["director"],
# "rating": entry["rating"],
# "votes": entry["votes"],
# "year": entry["year"],
# "genre": entry["genre"],
# "gross": entry["gross"],
# "budget": entry["budget"],
# "run-time": entry["run-time"] ,
# "actor1": entry["actor1"],
# "actor1_rank": entry["actor1_rank"],
import wikipedia, unicodedata
import file_save_load as fsl
import time
fileName = 'imdb_dataset_v7_no_plots'
actors_amount = 6
movies = fsl.read_from_file(fileName, actors_amount)
# with open('files/datasetV_20161116-203716') as csvfile:
# reader = csv.DictReader(csvfile, delimiter = "\t")
# for entry in reader:
# movies[
# entry["title"]
# ] = {
# "director": entry["director"],
# "rating": entry["rating"],
# "votes": entry["votes"],
# "year": entry["year"],
# "genre": entry["genre"],
# "gross": entry["gross"],
# "budget": entry["budget"],
# "run-time": entry["run-time"] ,
# "actor1": entry["actor1"],
# "actor1_rank": entry["actor1_rank"],
# "actor1_sex": entry["actor1_sex"],
# "actor2": entry["actor2"],
# "actor2_rank": entry["actor2_rank"],
# "actor2_sex": entry["actor2_sex"],
# "actor3": entry["actor3"],
# "actor3_rank": entry["actor3_rank"],
# "actor3_sex": entry["actor3_sex"],