217 lines
7.1 KiB
Python
217 lines
7.1 KiB
Python
import os
|
||
|
||
def parse_review_line(line):
|
||
parts = line.strip().split("|")
|
||
return {
|
||
"user_id": parts[0],
|
||
"movie_title": parts[1],
|
||
"rating": float(parts[2]),
|
||
"review_text": parts[3],
|
||
"watch_date": parts[4],
|
||
"useful_votes": int(parts[5]),
|
||
"total_votes": int(parts[6])
|
||
}
|
||
|
||
def load_reviews(file_path):
|
||
if not os.path.exists(file_path):
|
||
print("Файл не найден")
|
||
return []
|
||
f = open(file_path, "r", encoding="utf-8")
|
||
reviews = []
|
||
for line in f:
|
||
line = line.strip()
|
||
if line != "":
|
||
reviews.append(parse_review_line(line))
|
||
f.close()
|
||
return reviews
|
||
|
||
def filter_by_min_rating(reviews, min_rating):
|
||
result = []
|
||
for r in reviews:
|
||
if r["rating"] >= min_rating:
|
||
result.append(r)
|
||
return result
|
||
|
||
def calculate_average_rating(reviews):
|
||
if len(reviews) == 0:
|
||
return 0
|
||
total = sum(r["rating"] for r in reviews)
|
||
return round(total / len(reviews), 2)
|
||
|
||
def get_movie_statistics(reviews):
|
||
stats = {}
|
||
for r in reviews:
|
||
title = r["movie_title"]
|
||
if title not in stats:
|
||
stats[title] = {}
|
||
stats[title]["reviews_count"] = 0
|
||
stats[title]["total_rating"] = 0
|
||
stats[title]["total_useful_votes"] = 0
|
||
stats[title]["reviews_count"] = stats[title]["reviews_count"] + 1
|
||
stats[title]["total_rating"] = stats[title]["total_rating"] + r["rating"]
|
||
stats[title]["total_useful_votes"] = stats[title]["total_useful_votes"] + r["useful_votes"]
|
||
|
||
for title in stats:
|
||
stats[title]["average_rating"] = round(stats[title]["total_rating"] / stats[title]["reviews_count"], 2)
|
||
del stats[title]["total_rating"]
|
||
|
||
items = list(stats.items())
|
||
items.sort(key=lambda x: x[1]["reviews_count"], reverse=True)
|
||
|
||
result = {}
|
||
for title, data in items:
|
||
result[title] = data
|
||
return result
|
||
|
||
def find_most_useful_review(reviews):
|
||
if len(reviews) == 0:
|
||
return {}
|
||
|
||
best = min(reviews, key=lambda x: - (x["useful_votes"] / x["total_votes"]) if x["total_votes"] > 0 else -1)
|
||
percent = (best["useful_votes"] / best["total_votes"]) * 100 if best["total_votes"] > 0 else 0
|
||
|
||
return {
|
||
"movie_title": best["movie_title"],
|
||
"review_text": best["review_text"],
|
||
"useful_percentage": round(percent, 2)
|
||
}
|
||
|
||
def group_reviews_by_month(reviews):
|
||
months = {}
|
||
for r in reviews:
|
||
month = r["watch_date"][:7]
|
||
if month in months:
|
||
months[month] = months[month] + 1
|
||
else:
|
||
months[month] = 1
|
||
|
||
result = dict(sorted(months.items()))
|
||
return result
|
||
|
||
def filter_by_keywords(reviews, keywords):
|
||
result = []
|
||
for r in reviews:
|
||
text = r["review_text"].lower()
|
||
if any(k.lower() in text for k in keywords):
|
||
result.append(r)
|
||
return result
|
||
|
||
def get_top_movies_by_rating(reviews, n):
|
||
data = {}
|
||
for r in reviews:
|
||
title = r["movie_title"]
|
||
if title not in data:
|
||
data[title] = {}
|
||
data[title]["total"] = 0
|
||
data[title]["count"] = 0
|
||
data[title]["total"] = data[title]["total"] + r["rating"]
|
||
data[title]["count"] = data[title]["count"] + 1
|
||
|
||
ratings = []
|
||
for title in data:
|
||
if data[title]["count"] >= 2:
|
||
avg = data[title]["total"] / data[title]["count"]
|
||
ratings.append((title, round(avg, 2)))
|
||
|
||
ratings.sort(key=lambda x: x[1], reverse=True)
|
||
return ratings[:n]
|
||
|
||
def generate_review_report(reviews, file_path):
|
||
if len(reviews) == 0:
|
||
return
|
||
|
||
total = len(reviews)
|
||
avg_rating = calculate_average_rating(reviews)
|
||
movie_stats = get_movie_statistics(reviews)
|
||
top_movies = get_top_movies_by_rating(reviews, 3)
|
||
monthly = group_reviews_by_month(reviews)
|
||
|
||
useful_list = []
|
||
for r in reviews:
|
||
if r["total_votes"] > 0:
|
||
percent = (r["useful_votes"] / r["total_votes"]) * 100
|
||
useful_list.append((r, percent))
|
||
|
||
useful_list.sort(key=lambda x: x[1], reverse=True)
|
||
|
||
f = open(file_path, "w", encoding="utf-8")
|
||
f.write("ОТЧЕТ ПО РЕЦЕНЗИЯМ\n")
|
||
f.write("\n")
|
||
f.write("Всего рецензий: " + str(total) + "\n")
|
||
f.write("Средний рейтинг: " + str(avg_rating) + "\n")
|
||
f.write("\n")
|
||
f.write("ТОП 5 ФИЛЬМОВ ПО КОЛИЧЕСТВУ РЕЦЕНЗИЙ\n")
|
||
|
||
items = list(movie_stats.items())
|
||
for i in range(min(5, len(items))):
|
||
title, s = items[i]
|
||
f.write(str(i + 1) + ". " + title + " - рецензий: " + str(s["reviews_count"]) + ", средний рейтинг: " + str(s["average_rating"]) + "\n")
|
||
|
||
f.write("\n")
|
||
f.write("ТОП 3 САМЫХ ПОЛЕЗНЫХ РЕЦЕНЗИЙ ()\n")
|
||
|
||
for i in range(min(3, len(useful_list))):
|
||
r, p = useful_list[i]
|
||
f.write(str(i + 1) + ". " + r["movie_title"] + " - " + str(p) + "%\n")
|
||
f.write(" " + r["review_text"][:100] + "\n")
|
||
|
||
f.write("\n")
|
||
f.write("ДИНАМИКА ПО МЕСЯЦАМ\n")
|
||
|
||
for m in monthly:
|
||
f.write(m + ": " + str(monthly[m]) + " рецензий\n")
|
||
|
||
f.write("\n")
|
||
f.write("ТОП 3 ФИЛЬМА ПО СРЕДНЕМУ РЕЙТИНГУ (мин 2 рецензии)\n")
|
||
|
||
for i in range(len(top_movies)):
|
||
title, rating = top_movies[i]
|
||
f.write(str(i + 1) + ". " + title + " - " + str(rating) + "\n")
|
||
|
||
f.close()
|
||
|
||
if not os.path.exists("data"):
|
||
os.makedirs("data")
|
||
|
||
def main():
|
||
reviews = load_reviews("data/data.txt")
|
||
|
||
if len(reviews) == 0:
|
||
return
|
||
|
||
print("Общее количество рецензий:", len(reviews))
|
||
print()
|
||
|
||
print("Средний рейтинг:", calculate_average_rating(reviews))
|
||
print()
|
||
|
||
print("Топ 5 фильмов по количеству рецензий:")
|
||
stats = get_movie_statistics(reviews)
|
||
count = 0
|
||
for title in stats:
|
||
if count >= 5:
|
||
break
|
||
s = stats[title]
|
||
print(str(count + 1) + ".", title, "-", s["reviews_count"], "рецензий, средний рейтинг:", s["average_rating"])
|
||
count = count + 1
|
||
print()
|
||
|
||
print("Самая полезная рецензия:")
|
||
useful = find_most_useful_review(reviews)
|
||
print("Фильм:", useful["movie_title"])
|
||
print("Полезность:", useful["useful_percentage"], "%")
|
||
print("Текст:", useful["review_text"][:100], "...")
|
||
print()
|
||
|
||
print("Топ 3 фильма по среднему рейтингу (мин 2 рецензии):")
|
||
top = get_top_movies_by_rating(reviews, 3)
|
||
for i in range(len(top)):
|
||
title, rating = top[i]
|
||
print(str(i + 1) + ".", title, "-", rating)
|
||
print()
|
||
|
||
generate_review_report(reviews, "data/report.txt")
|
||
print("Отчет сохранен в файл data/report.txt")
|
||
|
||
if __name__ == "__main__":
|
||
main() |