python的pandas清除负数数据-Pandas 数据处理,数据清洗详解

# -*-coding:utf-8-*-

from pandas import DataFrame

import pandas as pd

import numpy as np

"""

获取行列数据

"""

df = DataFrame(np.random.rand(4, 5), columns=["A", "B", "C", "D", "E"])

print df

print

df["col_sum"] = df.apply(lambda x: x.sum(), axis=1) # 横向求和，axis=1表示横向

df.loc["row_sum"] = df.apply(lambda x: x.sum()) # loc获取一整列的数据，对一列数据进行求和

print df

print

dd = pd.DataFrame(np.arange(0, 60, 2).reshape(10, 3), columns=list("abc"))

# loc获取一整列的数据

print dd

print

print dd.loc[0:len(dd), "a"]

print

print dd.loc[0:3, ["a", "b"]]

print

print dd.loc[[1, 5], ["b", "c"]]

print "--------------------------------------"

# iloc获取某个位置的元素，或者某个区域的元素

print dd.iloc[1, 1]

print dd.iloc[0:3, [0, 1]]

print dd.iloc[[0, 3, 5], 0:2]

print "--------------------------------------"

"""

去重函数 drop_duplicates()

"""

from pandas import Series, DataFrame

data = DataFrame({"k": [1, 1, 2, 2]})

print data

print type(data) #

print

isduplicates = data.duplicated() # duplicated()判断是否是重复的项