pandas统计重复值次数

pandas统计数据项重复值次数和删除

from pandas import DataFrame



df = DataFrame({'key1':['a','a','b','b','a','a'],
                'key2':['one','two','one','two','one','one'],
                'data1':[1,2,3,2,1,1],
                # 'data2':np.random.randn(5)
                })
# 打印数据框
print(df)
#   data1 key1 key2
# 0      1    a  one
# 1      2    a  two
# 2      3    b  one
# 3      2    b  two
# 4      1    a  one
# 5      1    a  one

# 重复项
print(df[df.duplicated()])
#    data1 key1 key2
# 4      1    a  one
# 5      1    a  one

# 统计重复值
dup=df[df.duplicated()].count()
print(dup)	# 最后两项重复
# data1    2
# key1     2
# key2     2

# 去除重复项
nodup=df[-df.duplicated()]
print(nodup)
#    data1 key1 key2
# 0      1    a  one
# 1      2    a  two
# 2      3    b  one
# 3      2    b  two