2. 选取DataFrame的行

  1. #  还是读取college数据集
  2.  In[14]: college = pd.read_csv('data/college.csv', index_col='INSTNM')
  3.          college.head()
  4. Out[14]:

2. 选取DataFrame的行 - 图1

  1. #  选取第61行
  2.  In[15]: pd.options.display.max_rows = 6
  3.  In[16]: college.iloc[60]
  4. Out[16]:

2. 选取DataFrame的行 - 图2

  1. #  也可以通过行标签选取
  2.  In[17]: college.loc['University of Alaska Anchorage']
  3. Out[17]: CITY                  Anchorage
  4.          STABBR                       AK
  5.          HBCU                          0
  6.                                      ...    
  7.          UG25ABV                  0.4386
  8.          MD_EARN_WNE_P10           42500
  9.          GRAD_DEBT_MDN_SUPP      19449.5
  10.          Name: University of Alaska Anchorage, Length: 26, dtype: object
  1. #  选取多个不连续的行
  2.  In[18]: college.iloc[[60, 99, 3]]
  3. Out[18]:

2. 选取DataFrame的行 - 图3

  1. #  也可以用loc加列表来选取
  2.  In[19]: labels = ['University of Alaska Anchorage',
  3.                    'International Academy of Hair Design',
  4.                    'University of Alabama in Huntsville']
  5.          college.loc[labels]
  6. Out[19]:

2. 选取DataFrame的行 - 图4

  1. #  iloc可以用切片连续选取
  2.  In[20]: college.iloc[99:102]
  3. Out[20]:

2. 选取DataFrame的行 - 图5

  1. #  loc可以用标签连续选取
  2.  In[21]: start = 'International Academy of Hair Design'
  3.          stop = 'Mesa Community College'
  4.          college.loc[start:stop]
  5. Out[21]:

2. 选取DataFrame的行 - 图6

更多

  1. #  .index.tolist()可以直接提取索引标签，生成一个列表
  2.  In[22]: college.iloc[[60, 99, 3]].index.tolist()
  3. Out[22]: ['University of Alaska Anchorage',
  4.           'International Academy of Hair Design',
  5.           'University of Alabama in Huntsville']