import pandas as pd
import numpy as np
# 读取训练数据,header=-1第一行非字段名称
csv_data = pd.read_csv('D:/data/abc.csv',encoding='gbk',header=-1)
##校验每行的列数
def by_size(rows):
f_count = True
f_800 = True
if rows.count()!=8:
f_count = False
#logging.error(rows.index())
print(rows.describe().name+1) ##获取行号
##第一个字段为800
if rows[0]=='800':
f_800 = False
if f_count and f_800:
return True
else:
return False
#每行数据处理
li_te=csv_data.apply( func=by_size, axis = 1)
print(li_te)
loc与iloc区别测试
df = pd.DataFrame(np.random.randn(5,2),index=range(0,10,2),columns=list('AB'))
print(df)
print('——————————————')
print(df.loc[2])
print(df.loc[[2]])
print('——————————————')
print(df.iloc[2])
print(df.iloc[[2]])