使用索引为pandas DataFrame中的特定单元格设置值

#1 楼

df.xs('C')['x']=10

df['x']['C'] = 10

df.at['C', 'x'] = 10

In [18]: %timeit df.set_value('C', 'x', 10)
100000 loops, best of 3: 2.9 µs per loop

In [20]: %timeit df['x']['C'] = 10
100000 loops, best of 3: 6.31 µs per loop

In [81]: %timeit df.at['C', 'x'] = 10
100000 loops, best of 3: 9.2 µs per loop

#2 楼

#3 楼

df.loc[df[<some_column_name>] == <condition>, [<another_column_name>]] = <value_to_add>

#4 楼

df.ix['x','C']=10

#5 楼

#6 楼

df.loc['C', 'x'] = 10

#7 楼

   A   B   C
0  1   8   4 
1  3   9   6
2  22 33  52

def prepossessing(df):
  for index in range(0,len(df)): 
      df.iat[index,0] = df.iat[index,0] * 2
  return df

    0
0   54
1   15
2   15
3   8
4   31
5   63
6   11

     0
0   108
1   30
2   30
3   16
4   62
5   126
6   22

#8 楼

df.at[0, 'clm1'] = 0

#9 楼

 df.iloc[[2], [0]] = 10
 

#10 楼

    for index, row in result.iterrows():
        if np.isnan(row['weight']):
            result.at[index, 'weight'] = 0.0

#11 楼

>>> df
                   Cars  Prices (U$)
0               Audi TT        120.0
1 Lamborghini Aventador        245.0
2      Chevrolet Malibu        190.0
>>> df.set_value(2, 'Prices (U$)', 240.0)
__main__:1: FutureWarning: set_value is deprecated and will be removed in a future release.
Please use .at[] or .iat[] accessors instead

                   Cars  Prices (U$)
0               Audi TT        120.0
1 Lamborghini Aventador        245.0
2      Chevrolet Malibu        240.0

>>> df.iat[1, 1] = 260.0
>>> df
                   Cars  Prices (U$)
0               Audi TT        120.0
1 Lamborghini Aventador        260.0
2      Chevrolet Malibu        240.0

>>> df.at[2, "Cars"] = "Chevrolet Corvette"
>>> df
                  Cars  Prices (U$)
0               Audi TT        120.0
1 Lamborghini Aventador        260.0
2    Chevrolet Corvette        240.0

#12 楼

import numpy as np
import pandas as pd

df = pd.DataFrame(np.random.rand(100, 100))

%timeit df.iat[50,50]=50 # ✓
%timeit df.at[50,50]=50 #  ✔
%timeit df.set_value(50,50,50) # will deprecate
%timeit df.iloc[50,50]=50
%timeit df.loc[50,50]=50

7.06 µs ± 118 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)
5.52 µs ± 64.2 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)
3.68 µs ± 80.8 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)
98.7 µs ± 1.07 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)
109 µs ± 1.42 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)

#13 楼

import numpy as np, pandas as pd

df1 = pd.DataFrame(index=np.arange(3), columns=['x','y','z'])
df1['x'] = ['A','B','C']
df1.at[2,'y'] = 400

# rows/columns specified does not exist, appends new rows/columns to existing data frame
df1.at['D','w'] = 9000
df1.loc['E','q'] = 499

# using df[<some_column_name>] == <condition> to retrieve target rows
df1.at[df1['x']=='B', 'y'] = 10000
df1.loc[df1['x']=='B', ['z','w']] = 10000

# using a list of index to setup values
df1.iloc[[1,2,4], 2] = 9999
df1.loc[[0,'D','E'],'w'] = 7500
df1.at[[0,2,"D"],'x'] = 10
df1.at[:, ['y', 'w']] = 8000

df1
>>> df1
     x     y     z     w      q
0   10  8000   NaN  8000    NaN
1    B  8000  9999  8000    NaN
2   10  8000  9999  8000    NaN
D   10  8000   NaN  8000    NaN
E  NaN  8000  9999  8000  499.0

#14 楼

conditional_index = df.loc[ df['col name'] <condition> ].index

==5, >10 , =="Any string", >= DateTime

df.loc[conditional_index , [col name]]= <new value>

df.loc[conditional_index, [col1,col2]]= <new value>

df.loc[conditional_index, [col1,col2]]= df.loc[conditional_index,'col name']

#15 楼

#16 楼

df.loc[index_position, "column_name"] = some_value

#17 楼

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed Nov 21 16:38:46 2018

@author: gebbissimo
"""

import pandas as pd
import numpy as np
import time

NUM_ROWS = 100000
NUM_COLS = 1000
data = np.random.rand(NUM_ROWS,NUM_COLS)
df = pd.DataFrame(data)

NUM_ROWS_NEW = 100
data_tot = np.random.rand(NUM_ROWS + NUM_ROWS_NEW,NUM_COLS)
df_tot = pd.DataFrame(data_tot)

DATA_NEW = np.random.rand(1,NUM_COLS)


#%% FUNCTIONS

# create and append
def create_and_append(df):
    for i in range(NUM_ROWS_NEW):
        df_new = pd.DataFrame(DATA_NEW)
        df = df.append(df_new)
    return df

# create and concatenate
def create_and_concat(df):
    for i in range(NUM_ROWS_NEW):
        df_new = pd.DataFrame(DATA_NEW)
        df = pd.concat((df, df_new))
    return df


# store as dict and 
def store_as_list(df):
    lst = [[] for i in range(NUM_ROWS_NEW)]
    for i in range(NUM_ROWS_NEW):
        for j in range(NUM_COLS):
            lst[i].append(DATA_NEW[0,j])
    df_new = pd.DataFrame(lst)
    df_tot = df.append(df_new)
    return df_tot

# store as dict and 
def store_as_dict(df):
    dct = {}
    for j in range(NUM_COLS):
        dct[j] = []
        for i in range(NUM_ROWS_NEW):
            dct[j].append(DATA_NEW[0,j])
    df_new = pd.DataFrame(dct)
    df_tot = df.append(df_new)
    return df_tot




# preallocate and fill using .at
def fill_using_at(df):
    for i in range(NUM_ROWS_NEW):
        for j in range(NUM_COLS):
            #print("i,j={},{}".format(i,j))
            df.at[NUM_ROWS+i,j] = DATA_NEW[0,j]
    return df


# preallocate and fill using .at
def fill_using_set(df):
    for i in range(NUM_ROWS_NEW):
        for j in range(NUM_COLS):
            #print("i,j={},{}".format(i,j))
            df.set_value(NUM_ROWS+i,j,DATA_NEW[0,j])
    return df


#%% TESTS
t0 = time.time()    
create_and_append(df)
t1 = time.time()
print('Needed {} seconds'.format(t1-t0))

t0 = time.time()    
create_and_concat(df)
t1 = time.time()
print('Needed {} seconds'.format(t1-t0))

t0 = time.time()    
store_as_list(df)
t1 = time.time()
print('Needed {} seconds'.format(t1-t0))

t0 = time.time()    
store_as_dict(df)
t1 = time.time()
print('Needed {} seconds'.format(t1-t0))

t0 = time.time()    
fill_using_at(df_tot)
t1 = time.time()
print('Needed {} seconds'.format(t1-t0))

t0 = time.time()    
fill_using_set(df_tot)
t1 = time.time()
print('Needed {} seconds'.format(t1-t0))

#18 楼

#19 楼

x = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})
x.iloc[1] = dict(A=10, B=-10)

#20 楼

#21 楼

src_df = pd.read_sql_query(src_sql,src_connection)
for index1, row1 in src_df.iterrows():
    for index, row in vertical_df.iterrows():
        src_df.set_value(index=index1,col=u'etl_load_key',value=etl_load_key)
        if (row1[u'src_id'] == row['SRC_ID']) is True:
            src_df.set_value(index=index1,col=u'vertical',value=row['VERTICAL'])