import pandas as pd
fpath = './ant-learn-pandas-master/datas/student_excel/student_excel.xlsx'
#skiprows忽略两个空行
rating = pd.read_excel(fpath,skiprows=2)
print(rating)
检测:
#检测所有格是否为空值
print(rating.isnull())
#或者
print(rating.notnull())
删除空值:
#删掉全是空值的列
rating.dropna(axis='columns', how='all', inplace=True)
#删掉全是空值的行
rating.dropna(axis='index', how='all', inplace=True)
填充:
将分数为NaN的填充为0
rating.loc[:, '分数'] = rating.loc[:, '分数'].fillna(0)
将姓名为NaN的用前面的姓名填充
#用前面的填充空值姓名
rating.loc[:, '姓名'] = rating.loc[:, '姓名'].fillna(method='ffill')
将清洗好的excel保存
rating.to_excel('路径',index=False)
sh为条件,用bool值判断是否满足条件
astype作用为将Series类型转为字符串类型
sh = rating['分数'].astype(str).str.startswith('0')
print(rating[sh == True])