python数据处理

# pandas 的使用
import pandas as pd
#import jieba   没有导入库，会报这样的错误：No module named 'jieba'
s1 = pd.Series(data = ['A','B','C','D'],index = ['a','b','c','d'])
print(s1)
df1 = pd.DataFrame(data = [[1,2,3],[4,5,6]],columns=['a','b','c'],index=[1,2])
print(df1['a'][1])  #第一个中括号是列索引，第二个中括号是行索引
print(df1.head(1))  #DataFrame的头几行
print(df1.tail(1))  #DataFrame的末尾几行
print(df1.shape)     #DataFrame的行数和列数，返回值是元组，分别是行数和列数
print(df1[['a','c']].dtypes)  #查看列的数据类型
print(df1[['a','c']]) #取a列和c列
print(df1.loc[2:2,]) #loc[,]   逗号前面是行，后面是列，冒号前后代表起始行和结束行
print(df1.describe()) # 每列的描述性统计值
print(df1.info()) #每列的基本信息：非空值统计数、数据类型
data = pd.read_csv(r'C:\Users\Administrator\Desktop\food.csv',sep=',',encoding='ANSI')
# 读取csv文件写入DataFrame
print(data['like'].describe())
data.to_csv(r'C:\Users\Administrator\Desktop\food.csv')
# 把DataFrame写入csv

data1 = data[data['like'] > 50]
data2 = data[data['like'] > 60]

data3 = data[(data['like'] > 50) & (data['like'] > 60)]
print(data3)
# select data.food_name
# from data
# where data.like > 60 and data.like > 50;
data1['add']=[1,2,3]  #增加一列
data1['add'] = data1['add']+5 #给字段重新赋值

data1['add'][150] = 99 #修改某字段当中的某行的值
print(data1)


















# https://www.bilibili.com/read/cv17303442/

pandas简介 - 哔哩哔哩