mycolumns = ['A', 'B']
df = pd.DataFrame(columns=mycolumns)
rows = [[1,2],[3,4],[5,6]]
for row in rows:
    df.loc[len(df)] = row

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。

您可以为此连接两个数据框架。我基本上遇到了这个问题，用字符索引(不是数字)向现有的DataFrame添加新行。

因此，我在一个管道()中输入新行数据，并在一个列表中索引。

new_dict = {put input for new row here}
new_list = [put your index here]

new_df = pd.DataFrame(data=new_dict, index=new_list)

df = pd.concat([existing_df, new_df])

如果你想在末尾添加一行，将其作为列表追加:

valuestoappend = [va1, val2, val3]
res = res.append(pd.Series(valuestoappend, index = ['lib', 'qty1', 'qty2']), ignore_index = True)

在添加一行之前，我们必须将数据帧转换为字典。在这里，你可以看到键作为数据帧中的列，列的值再次存储在字典中，但是每个列的键都是数据帧中的索引号。

这个想法促使我编写下面的代码。

df2 = df.to_dict()
values = ["s_101", "hyderabad", 10, 20, 16, 13, 15, 12, 12, 13, 25, 26, 25, 27, "good", "bad"] # This is the total row that we are going to add
i = 0
for x in df.columns:   # Here df.columns gives us the main dictionary key
    df2[x][101] = values[i]   # Here the 101 is our index number. It is also the key of the sub dictionary
    i += 1

如果你的Dataframe中的所有数据都有相同的dtype，你可以使用NumPy数组。您可以直接将行写入预定义数组，并在最后将其转换为数据框架。 它似乎比转换字典列表还要快。

import pandas as pd
import numpy as np
from string import ascii_uppercase

startTime = time.perf_counter()
numcols, numrows = 5, 10000
npdf = np.ones((numrows, numcols))
for row in range(numrows):
    npdf[row, 0:] = np.random.randint(0, 100, (1, numcols))
df5 = pd.DataFrame(npdf, columns=list(ascii_uppercase[:numcols]))
print('Elapsed time: {:6.3f} seconds for {:d} rows'.format(time.perf_counter() - startTime, numOfRows))
print(df5.shape)