pa-shk/re_dial_tmdb

---
dataset_info:
- config_name: re_dial
features:
- name: movieMentions
list:
- name: movieId
dtype: string
- name: movieName
dtype: string
- name: respondentQuestions
list:
- name: movieId
dtype: string
- name: suggested
dtype: int32
- name: seen
dtype: int32
- name: liked
dtype: int32
- name: messages
list:
- name: timeOffset
dtype: int32
- name: text
dtype: string
- name: senderWorkerId
dtype: int32
- name: messageId
dtype: int32
- name: conversationId
dtype: int32
- name: respondentWorkerId
dtype: int32
- name: initiatorWorkerId
dtype: int32
- name: initiatorQuestions
list:
- name: movieId
dtype: string
- name: suggested
dtype: int32
- name: seen
dtype: int32
- name: liked
dtype: int32
- name: recommended_movies
sequence:
sequence: string
- name: liked_movies
sequence:
sequence: string
- name: dialogs
list:
list:
- name: messageId
dtype: int64
- name: senderWorkerId
dtype: int64
- name: text
dtype: string
- name: timeOffset
dtype: int64
- name: formatted_dialogs
sequence: string
splits:
- name: train
num_bytes: 70328286.69120033
num_examples: 8554
- name: val
num_bytes: 10770406.308799675
num_examples: 1310
- name: test
num_bytes: 9788058
num_examples: 1310
download_size: 25397794
dataset_size: 90886751.0
- config_name: tmdb
features:
- name: id
dtype: string
- name: name
dtype: string
- name: metadata
struct:
- name: adult
dtype: bool
- name: budget
dtype: int64
- name: genres
dtype: string
- name: imdb_id
dtype: string
- name: original_language
dtype: string
- name: original_title
dtype: string
- name: overview
dtype: string
- name: popularity
dtype: float64
- name: production_companies
dtype: string
- name: production_countries
dtype: string
- name: release_date
dtype: string
- name: revenue
dtype: int64
- name: runtime
dtype: int64
- name: spoken_languages
dtype: string
- name: status
dtype: string
- name: tagline
dtype: string
- name: vote_average
dtype: float64
- name: vote_count
dtype: int64
splits:
- name: train
num_bytes: 3557601
num_examples: 6629
download_size: 2083449
dataset_size: 3557601
configs:
- config_name: re_dial
data_files:
- split: train
path: re_dial/train-*
- split: val
path: re_dial/val-*
- split: test
path: re_dial/test-*
- config_name: tmdb
data_files:
- split: train
path: tmdb/train-*
---

原始信息汇总

数据集概述

数据集名称: re_dial

• 配置名称: re_dial
• 特征:
  • movieMentions:
    • movieId: string
    • movieName: string
  • respondentQuestions:
    • movieId: string
    • suggested: int32
    • seen: int32
    • liked: int32
  • messages:
    • timeOffset: int32
    • text: string
    • senderWorkerId: int32
    • messageId: int32
  • conversationId: int32
  • respondentWorkerId: int32
  • initiatorWorkerId: int32
  • initiatorQuestions:
    • movieId: string
    • suggested: int32
    • seen: int32
    • liked: int32
  • recommended_movies: sequence of string
  • liked_movies: sequence of string
  • dialogs:
    • messageId: int64
    • senderWorkerId: int64
    • text: string
    • timeOffset: int64
  • formatted_dialogs: sequence of string
• 分割:
  • train:
    • num_bytes: 70328286.69120033
    • num_examples: 8554
  • val:
    • num_bytes: 10770406.308799675
    • num_examples: 1310
  • test:
    • num_bytes: 9788058
    • num_examples: 1310
• 下载大小: 25397794
• 数据集大小: 90886751.0

数据集名称: tmdb

• 配置名称: tmdb
• 特征:
  • id: string
  • name: string
  • metadata:
    • adult: bool
    • budget: int64
    • genres: string
    • imdb_id: string
    • original_language: string
    • original_title: string
    • overview: string
    • popularity: float64
    • production_companies: string
    • production_countries: string
    • release_date: string
    • revenue: int64
    • runtime: int64
    • spoken_languages: string
    • status: string
    • tagline: string
    • vote_average: float64
    • vote_count: int64
• 分割:
  • train:
    • num_bytes: 3557601
    • num_examples: 6629
• 下载大小: 2083449
• 数据集大小: 3557601

数据文件路径

• re_dial:
  • train: re_dial/train-*
  • val: re_dial/val-*
  • test: re_dial/test-*
• tmdb:
  • train: tmdb/train-*