另一种方法(可能不是很有效):

# add a row
def add_row(df, row):
    colnames = list(df.columns)
    ncol = len(colnames)
    assert ncol == len(row), "Length of row must be the same as width of DataFrame: %s" % row
    return df.append(pd.DataFrame([row], columns=colnames))

你也可以像这样增强DataFrame类:

import pandas as pd
def add_row(self, row):
    self.loc[len(self.index)] = row
pd.DataFrame.add_row = add_row

你只需要loc[df]。形状[0]]或loc[len(df)]

# Assuming your df has 4 columns (str, int, str, bool)
df.loc[df.shape[0]] = ['col1Value', 100, 'col3Value', False] 

or

df.loc[len(df)] = ['col1Value', 100, 'col3Value', False] 

在向dataframe添加大量行的情况下，我对性能感兴趣。所以我尝试了四种最流行的方法，并检查了它们的速度。

性能

使用.append (NPE的答案) 使用。loc (fred的回答) 使用.loc预分配(FooBar的答案) 使用dict并最终创建DataFrame (ShikharDua的回答)

运行时结果(秒):

所以我自己用了加法法。

代码:

import pandas as pd
import numpy as np
import time

del df1, df2, df3, df4
numOfRows = 1000
# append
startTime = time.perf_counter()
df1 = pd.DataFrame(np.random.randint(100, size=(5,5)), columns=['A', 'B', 'C', 'D', 'E'])
for i in range( 1,numOfRows-4):
    df1 = df1.append( dict( (a,np.random.randint(100)) for a in ['A','B','C','D','E']), ignore_index=True)
print('Elapsed time: {:6.3f} seconds for {:d} rows'.format(time.perf_counter() - startTime, numOfRows))
print(df1.shape)

# .loc w/o prealloc
startTime = time.perf_counter()
df2 = pd.DataFrame(np.random.randint(100, size=(5,5)), columns=['A', 'B', 'C', 'D', 'E'])
for i in range( 1,numOfRows):
    df2.loc[i]  = np.random.randint(100, size=(1,5))[0]
print('Elapsed time: {:6.3f} seconds for {:d} rows'.format(time.perf_counter() - startTime, numOfRows))
print(df2.shape)

# .loc with prealloc
df3 = pd.DataFrame(index=np.arange(0, numOfRows), columns=['A', 'B', 'C', 'D', 'E'] )
startTime = time.perf_counter()
for i in range( 1,numOfRows):
    df3.loc[i]  = np.random.randint(100, size=(1,5))[0]
print('Elapsed time: {:6.3f} seconds for {:d} rows'.format(time.perf_counter() - startTime, numOfRows))
print(df3.shape)

# dict
startTime = time.perf_counter()
row_list = []
for i in range (0,5):
    row_list.append(dict( (a,np.random.randint(100)) for a in ['A','B','C','D','E']))
for i in range( 1,numOfRows-4):
    dict1 = dict( (a,np.random.randint(100)) for a in ['A','B','C','D','E'])
    row_list.append(dict1)

df4 = pd.DataFrame(row_list, columns=['A','B','C','D','E'])
print('Elapsed time: {:6.3f} seconds for {:d} rows'.format(time.perf_counter() - startTime, numOfRows))
print(df4.shape)

附注:我相信我的实现并不完美，也许还有一些优化可以做。

有关有效附加，请参见如何向pandas数据框架添加额外行和使用放大设置。

通过loc/ix在不存在的键索引数据上添加行。例如:

In [1]: se = pd.Series([1,2,3])

In [2]: se
Out[2]:
0    1
1    2
2    3
dtype: int64

In [3]: se[5] = 5.

In [4]: se
Out[4]:
0    1.0
1    2.0
2    3.0
5    5.0
dtype: float64

Or:

In [1]: dfi = pd.DataFrame(np.arange(6).reshape(3,2),
   .....:                 columns=['A','B'])
   .....:

In [2]: dfi
Out[2]:
   A  B
0  0  1
1  2  3
2  4  5

In [3]: dfi.loc[:,'C'] = dfi.loc[:,'A']

In [4]: dfi
Out[4]:
   A  B  C
0  0  1  0
1  2  3  2
2  4  5  4
In [5]: dfi.loc[3] = 5

In [6]: dfi
Out[6]:
   A  B  C
0  0  1  0
1  2  3  2
2  4  5  4
3  5  5  5

您还可以建立一个列表的列表，并将其转换为数据框架-

import pandas as pd

columns = ['i','double','square']
rows = []

for i in range(6):
    row = [i, i*2, i*i]
    rows.append(row)

df = pd.DataFrame(rows, columns=columns)

给

    i   double  square
0   0   0   0
1   1   2   1
2   2   4   4
3   3   6   9
4   4   8   16
5   5   10  25

我想出了一个简单而美好的方法:

>>> df
     A  B  C
one  1  2  3
>>> df.loc["two"] = [4,5,6]
>>> df
     A  B  C
one  1  2  3
two  4  5  6

请注意评论中提到的性能警告。