写入到CSV
import pandas as pd
class PanCsv():
def Csv_01(self):
df = pd.read_csv('nba.csv')
print(df)
# 三个字段 name, site, age
nme = ["Google", "Runoob", "Taobao", "Wiki"]
st = ["www.google.com", "www.runoob.com", "www.taobao.com", "www.wikipedia.org"]
ag = [90, 40, 80, 98]
# 字典
dict = {'name': nme, 'site': st, 'age': ag}
df = pd.DataFrame(dict)
# 保存 dataframe
df.to_csv('site.csv')
if __name__ == '__main__':
PanCsv().Csv_01()
pandas基础应用
import pandas as pd
class panddf():
def panddf01(self):
data =[['cool',10],['ruin',12],['pyh',13]]
df = pd.DataFrame(data,columns=['sitr','age'],dtype= int)
print(df)
# ndarrays创建,ndarray的长度必须相同, 如果传递了 index,则索引的长度应等于数组的长度。如果没有传递索引,则默认情况下,索引将是range(n),其中n是数组长度
data1 = {'Site': ['Google', 'Runoob', 'Wiki'], 'Age': [10, 12, 13]}
df1 = pd.DataFrame(data1)
print(df1)
# 使用字典创建 没有对应的部分数据为 NaN。
data3 = [{'a': 1, 'b': 2}, {'a': 5, 'b': 10, 'c': 20}]
df3 = pd.DataFrame(data3)
print(df3)
date4 = {"calories":[420,380,112],"duration":[50,40,45]}
df4 =pd.DataFrame(date4)
print(df4.loc[[0,1]]) #返回第一行和第二行
df5=pd.DataFrame(date4,index=["day01","day02","day03"])
print(df5)
print(df5.loc["day01"])# 返回指定索引
if __name__ == '__main__':
panddf().panddf01()
Series
import pandas as pd
class Pandser():
def ser_o1(self):
# Pandas Series 类似表格中的一个列(column),类似于一维数组,可以保存任何数据类型。
# Series 由索引(index)和列组成,函数如下
a = [1, 2, 3]
mychar=pd.Series(a)
print(mychar)
print(mychar[1])#索引值从0开始
#指定索引的值
a1 = ["Googlr","Runoob","Wiki"]
mychar2 = pd.Series(a,index=["x","y","z"])
print(mychar2)
#通过Key/Value 创建字典
sites={1:"GG",2:"CC",3:"py"}
mychar3=pd.Series(sites)
mycharT3 = pd.Series(sites,index=[1,2])#根据索引读取部分值
mycharT4 = pd.Series(sites, index=[1, 2],name="SeriesName")#设置 Series 名称参数:
print(mychar3)
print(mycharT3)
print(mycharT4)
if __name__ == '__main__':
# unittest.main()
Pandser().ser_o1()