2. 访问DataFrame的组件

  1. in[4]: #  提取列索引
  2.        columns = movie.columns
  3.        #  提取行索引
  4.        index = movie.index
  5.        #  提取数据
  6.        data = movie.values
  1.  in[5]: columns
  2. out[5]: Index(['color', 'director_name', 'num_critic_for_reviews', 'duration',
  3.        'director_facebook_likes', 'actor_3_facebook_likes', 'actor_2_name',
  4.        'actor_1_facebook_likes', 'gross', 'genres', 'actor_1_name',
  5.        'movie_title', 'num_voted_users', 'cast_total_facebook_likes',
  6.        'actor_3_name', 'facenumber_in_poster', 'plot_keywords',
  7.        'movie_imdb_link', 'num_user_for_reviews', 'language', 'country',
  8.        'content_rating', 'budget', 'title_year', 'actor_2_facebook_likes',
  9.        'imdb_score', 'aspect_ratio', 'movie_facebook_likes'],
  10.       dtype='object')
  1.  in[6]: index
  2. out[6]: RangeIndex(start=0, stop=4916, step=1)
  1.  in[7]: data
  2. out[7]: array([['Color', 'James Cameron', 723.0, ..., 7.9, 1.78, 33000],
  3.        ['Color', 'Gore Verbinski', 302.0, ..., 7.1, 2.35, 0],
  4.        ['Color', 'Sam Mendes', 602.0, ..., 6.8, 2.35, 85000],
  5.        ..., 
  6.        ['Color', 'Benjamin Roberds', 13.0, ..., 6.3, nan, 16],
  7.        ['Color', 'Daniel Hsia', 14.0, ..., 6.3, 2.35, 660],
  8.        ['Color', 'Jon Gunn', 43.0, ..., 6.6, 1.85, 456]], dtype=object)
  1.  in[8]: #  index的类型
  2.         type(index) #  pandas.core.indexes.range.RangeIndex
  3. out[8]: pandas.core.indexes.range.RangeIndex
  1.  in[9]: #  columns的类型
  2.         type(columns) #  pandas.core.indexes.base.Index
  3. out[9]: pandas.core.indexes.base.Index
  1.  in[10]: #  data的类型
  2.          type(data) #  numpy.ndarray
  3. out[10]: numpy.ndarray
  1.  in[11]: #  判断是不是子类型
  2.          issubclass(pd.RangeIndex, pd.Index) #  True
  3. out[11]: True

更多

  1.  in[12]: #  访问index的值
  2.          index.values
  3.          #  index的值是个列表，所以可以索引或切片
  4.          index.values[0]
  5. out[12]: array([   0,    1,    2, ..., 4913, 4914, 4915])
  1.  in[13]: #  访问columns的值
  2.          columns.values
  3. out[13]: array(['color', 'director_name', 'num_critic_for_reviews', 'duration',
  4.        'director_facebook_likes', 'actor_3_facebook_likes', 'actor_2_name',
  5.        'actor_1_facebook_likes', 'gross', 'genres', 'actor_1_name',
  6.        'movie_title', 'num_voted_users', 'cast_total_facebook_likes',
  7.        'actor_3_name', 'facenumber_in_poster', 'plot_keywords',
  8.        'movie_imdb_link', 'num_user_for_reviews', 'language', 'country',
  9.        'content_rating', 'budget', 'title_year', 'actor_2_facebook_likes',
  10.        'imdb_score', 'aspect_ratio', 'movie_facebook_likes'], dtype=object)