pandas中的DataFrame数据遍历解读

data = pd.read_csv('save\LH8888.csv')
print(type(data))
print(data)

for i, line in data.iterrows():
	print(i)
    print(line)
    print(line['date'])  

for line in data.itertuples():
    print(line)

for line in data.itertuples():
    print(line)
    print(getattr(line, 'date'))
    print(line[1])

for i, index in data.iteritems():
    print(index)

print(data.iloc[1, 5])
print(data.loc[1, 'volume'])

data.iloc[1, 5] = 10
print(data.loc[1, 'volume'])
print(data)

for i in range(data.shape[0]):
    for j in range(data.shape[1]):
        print(data.iloc[i, j])

import pandas as pd
import numpy as np

# 生成樣例數據
def gen_sample():
    aaa = np.random.uniform(1,1000,3000)
    bbb = np.random.uniform(1,1000,3000)
    ccc = np.random.uniform(1,1000,3000)
    ddd = np.random.uniform(1,1000,3000)
    return pd.DataFrame({'aaa':aaa,'bbb':bbb, 'ccc': ccc, 'ddd': ddd})

# for + iloc 定位
def method0_sum(DF):
    for i in range(len(DF)):
        a = DF.iloc[i,0] + DF.iloc[i,1]

# for + iat 定位
def method1_sum(DF):
    for i in range(len(DF)):
        a = DF.iat[i,0] + DF.iat[i,1]

# pandas.DataFrame.iterrows() 迭代器
def method2_sum(DF):
    for index, rows in DF.iterrows():
        a = rows['aaa'] + rows['bbb']

# pandas.DataFrame.apply 迭代
def method3_sum(DF):
    a = DF.apply(lambda x: x.aaa + x.bbb, axis=1)

# pandas.DataFrame.apply 迭代 
def method4_sum(DF):
    a = DF[['aaa','bbb']].apply(lambda x: x.aaa + x.bbb, axis=1)
    
# 列表
def method5_sum(DF):
    a = [ a+b for a,b in zip(DF['aaa'],DF['bbb']) ]

# pandas  
def method6_sum(DF):
    a = DF['aaa'] + DF['bbb']

# numpy 
def method7_sum(DF):
    a = DF['aaa'].values + DF['bbb'].values
    
# for + itertuples
def method8_sum(DF):
    for row in DF.itertuples():
        a = getattr(row, 'aaa') + getattr(row, 'bbb')
        

df = gen_sample()
print('for + iloc 定位:')
%timeit method0_sum(df)

df = gen_sample()
print('for + iat 定位:')
%timeit method1_sum(df)

df = gen_sample()
print('apply 迭代:')
%timeit method3_sum(df)

df = gen_sample()
print('apply 迭代 + 兩列:')
%timeit method4_sum(df)

df = gen_sample()
print('列表:')
%timeit method5_sum(df)

df = gen_sample()
print('pandas 数组操作:')
%timeit method6_sum(df)

df = gen_sample()
print('numpy 数组操作：')
%timeit method7_sum(df)

df = gen_sample()
print('for itertuples')
%timeit method8_sum(df)

df = gen_sample()
print('for iteritems')
%timeit method9_sum(df)

df = gen_sample()
print('for iterrows:')
%timeit method2_sum(df)