pands学习day2

pandas数据结构基础知识学习

 

# !/usr/bin/env python
# -*-encoding:utf-8-*-
# @Time:21:10
# @File:day2.py
# @Author:秦时明月
# pandas 数据结构学习
'''
1、预备知识
    a、容器
    b、使用函数
    c、取子集和建索引
2、加载人工数据
3、Series
    a、创建series
        dict
        ndarray
        scalar
        lists
    b、切片
4、dataframe
'''
import pandas as pd
s=pd.Series(['banana',42])
# print(s)

# 手动指定索引
a=pd.Series(['Wes Mckinney','Creator of Pandas'],index=['Person','Who'])
# print(a)

sec=pd.DataFrame({
    'name':['coco','william'],
    'sex':['nan','nv'],
    'age':[32,89],
    'born':['1991-08-10','1992-07-24'],
    'school':['daxue','dada']
},index=['one','two'])
# print(sec)

# 使用有序字典，需要导入collections模块中ordereddict
from collections import OrderedDict

se=pd.DataFrame(OrderedDict({
    'name':['coco','william'],
    'sex':['nan','nv'],
    'age':[32,89],
    'born':['1991-08-10','1992-07-24'],
    'school':['daxue','dada']
}))
# print(se)
qw=pd.DataFrame({
    'name':['coco','william'],
    'sex':['nan','nv'],
    'age':[32,89],
    'born':['1991-08-10','1992-07-24'],
    'school':['daxue','dada']
},index=['one','two'],
columns=['name','sex','age','school'])
# print(qw)
'''
first_row=qw.loc['two']
print(first_row)
print(first_row.index)
print(first_row.values)
print(first_row.keys)
'''
# 获取第一个索引
# print(first_row.index[0])     # 属性
# print(first_row.keys()[0])    # 方法

# 获取age列
# ages=qw['age']
# print(ages)
#
# print(ages.mean())
#
# print(ages.min())
#
# print(ages.max())

# print(ages.std())

# 布尔子集：series
ser_file=pd.read_csv(r'E:\ython\demo\data_anysis\pandas\data\scientists.csv')
ages=ser_file['Age']
# print(ages)

# 获取基本统计量
# print(ages.describe())
# 所有年龄平均值
print(ages.mean())

print(ages[ages>ages.mean()])

print(ages>ages.mean())
manual=[True,True,False]
print(ages[manual])