Python | 股票数据可视化

import numpy as np
import pandas as pd
from pandas_datareader import data
import datetime as dt

数据准备

'''
获取国内股票数据的方式是：“股票代码”+“对应股市”（港股为.hk，A股为.ss）
例如腾讯是港股是：0700.hk
'''
#字典：6家公司的股票
# gafataDict={'谷歌':'GOOG','亚马逊':'AMZN','Facebook':'FB', '苹果':'AAPL','阿里巴巴':'BABA','腾讯':'0700.hk'}

'''
定义函数
函数功能：计算股票涨跌幅=（现在股价-买入价格）/买入价格
输入参数：column是收盘价这一列的数据
返回数据：涨跌幅
'''
def change(column):
    # 买入价格
    buyPrice=column[0]
    # 现在股价
    curPrice=column[column.size-1]
    priceChange=(curPrice-buyPrice)/buyPrice
    # 判断股票是上涨还是下跌
    if priceChange>0:
        print('股票累计上涨=',round(priceChange*100,2),'%')
    elif priceChange==0:
        print('股票无变化=',round(priceChange*100,2)*100,'%')
    else:
        print('股票累计下跌=',round(priceChange*100,2)*100,'%')
    
    # 返回数据
    return priceChange

'''
三星电子

每日股票价位信息
Open:开盘价
High:最高加
Low：最低价
Close：收盘价
Volume：成交量

因雅虎连接不到，仅以三星作为获取数据示例
'''
sxDf = data.DataReader('005930', 'naver', start='2021-01-01', end='2022-01-01')
sxDf.head()

	Open	High	Low	Close	Volume
Date
2021-01-04	81000	84400	80200	83000	38655276
2021-01-05	81600	83900	81600	83900	35335669
2021-01-06	83300	84500	82100	82200	42089013
2021-01-07	82800	84200	82700	82900	32644642
2021-01-08	83300	90000	83000	88800	59013307

sxDf.info()

<class 'pandas.core.frame.DataFrame'>
DatetimeIndex: 248 entries, 2021-01-04 to 2021-12-30
Data columns (total 5 columns):
 #   Column  Non-Null Count  Dtype 
---  ------  --------------  ----- 
 0   Open    248 non-null    object
 1   High    248 non-null    object
 2   Low     248 non-null    object
 3   Close   248 non-null    object
 4   Volume  248 non-null    object
dtypes: object(5)
memory usage: 11.6+ KB

sxDf.iloc[:,0:4]=sxDf.iloc[:,0:4].astype('float')
sxDf.iloc[:,-1]=sxDf.iloc[:,-1].astype('int')
sxDf.info()

<class 'pandas.core.frame.DataFrame'>
DatetimeIndex: 248 entries, 2021-01-04 to 2021-12-30
Data columns (total 5 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   Open    248 non-null    float64
 1   High    248 non-null    float64
 2   Low     248 non-null    float64
 3   Close   248 non-null    float64
 4   Volume  248 non-null    int32  
dtypes: float64(4), int32(1)
memory usage: 10.7 KB

阿里巴巴

# 读取数据
AliDf=pd.read_excel(r'C:\Users\EDY\Desktop\吧哩吧啦\学习\Untitled Folder\阿里巴巴2017年股票数据.xlsx',index_col='Date')
AliDf.tail()

	Open	High	Low	Close	Adj Close	Volume
Date
2017-12-22	175.839996	176.660004	175.039993	176.289993	176.289993	12524700
2017-12-26	174.550003	175.149994	171.729996	172.330002	172.330002	12913800
2017-12-27	172.289993	173.869995	171.729996	172.970001	172.970001	10152300
2017-12-28	173.039993	173.529999	171.669998	172.300003	172.300003	9508100
2017-12-29	172.279999	173.669998	171.199997	172.429993	172.429993	9704600

# 查看基本信息及数据类型
AliDf.info()

<class 'pandas.core.frame.DataFrame'>
DatetimeIndex: 251 entries, 2017-01-03 to 2017-12-29
Data columns (total 6 columns):
 #   Column     Non-Null Count  Dtype  
---  ------     --------------  -----  
 0   Open       251 non-null    float64
 1   High       251 non-null    float64
 2   Low        251 non-null    float64
 3   Close      251 non-null    float64
 4   Adj Close  251 non-null    float64
 5   Volume     251 non-null    int64  
dtypes: float64(5), int64(1)
memory usage: 13.7 KB

# 计算涨跌幅
AliChange=change(AliDf['Close'])

股票累计上涨= 94.62 %

'''增加一列累计增长百分比'''
#一开始的股价
Close1=AliDf['Close'][0]
# # .apply(lambda x: format(x, '.2%'))
AliDf['sum_pct_change']=AliDf['Close'].apply(lambda x: (x-Close1)/Close1)
AliDf['sum_pct_change'].tail()

Date
2017-12-22    0.989729
2017-12-26    0.945034
2017-12-27    0.952257
2017-12-28    0.944695
2017-12-29    0.946162
N