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()

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()

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()

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
Name: sum_pct_change, dtype: float64

谷歌

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

	Open	High	Low	Close	Adj Close	Volume
Date
2017-12-22	1061.109985	1064.199951	1059.439941	1060.119995	1060.119995	755100
2017-12-26	1058.069946	1060.119995	1050.199951	1056.739990	1056.739990	760600
2017-12-27	1057.390015	1058.369995	1048.050049	1049.369995	1049.369995	1271900
2017-12-28	1051.599976	1054.750000	1044.770020	1048.140015	1048.140015	837100
2017-12-29	1046.719971	1049.699951	1044.900024	1046.400024	1046.400024	887500

# 计算涨跌幅
GoogleChange=change(GoogleDf['Close'])

股票累计上涨= 33.11 %

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

Date
2017-12-22    0.348513
2017-12-26    0.344213
2017-12-27    0.334839
2017-12-28    0.333274
2017-12-29    0.331061
Name: sum_pct_change, dtype: float64

苹果

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

	Open	High	Low	Close	Adj Close	Volume
Date
2017-12-22	174.679993	175.419998	174.500000	175.009995	174.299362	16349400
2017-12-26	170.800003	171.470001	169.679993	170.570007	169.877396	33185500
2017-12-27	170.100006	170.779999	169.710007	170.600006	169.907272	21498200
2017-12-28	171.000000	171.850006	170.479996	171.080002	170.385315	16480200
2017-12-29	170.520004	170.589996	169.220001	169.229996	168.542831	25999900

# 计算涨跌幅
AppleChange=change(AppleDf['Close'])

股票累计上涨= 45.7 %

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

Date
2017-12-22    0.506758
2017-12-26    0.468532
2017-12-27    0.468790
2017-12-28    0.472923
2017-12-29    0.456995
Name: sum_pct_change, dtype: float64

腾讯

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

	Open	High	Low	Close	Adj Close	Volume
Date
2017-12-22	403.799988	405.799988	400.799988	405.799988	405.799988	16146080
2017-12-27	405.799988	407.799988	401.000000	401.200012	401.200012	16680601
2017-12-28	404.000000	408.200012	402.200012	408.200012	408.200012	11662053
2017-12-29	408.000000	408.000000	403.399994	406.000000	406.000000	16601658
2018-01-02	406.000000	406.000000	406.000000	406.000000	406.000000	0

# 腾讯是港股，转换为美元,汇率：0.1277
TencentDf[['Open','High','Low','Close','Adj Close']]=TencentDf[['Open','High','Low','Close','Adj Close']]*0.1277
TencentDf.tail()

	Open	High	Low	Close	Adj Close	Volume
Date
2017-12-22	51.565258	51.820658	51.182158	51.820658	51.820658	16146080
2017-12-27	51.820658	52.076058	51.207700	51.233242	51.233242	16680601
2017-12-28	51.590800	52.127142	51.360942	52.127142	52.127142	11662053
2017-12-29	52.101600	52.101600	51.514179	51.846200	51.846200	16601658
2018-01-02	51.846200	51.846200	51.846200	51.846200	51.846200	0

# 计算涨跌幅
TencentChange=change(TencentDf['Close'])

股票累计上涨= 114.36 %

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

Date
2017-12-22    1.142555
2017-12-27    1.118268
2017-12-28    1.155227
2017-12-29    1.143611
2018-01-02    1.143611
Name: sum_pct_change, dtype: float64

亚马逊

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

	Open	High	Low	Close	Adj Close	Volume
Date
2017-12-22	1172.079956	1174.619995	1167.829956	1168.359985	1168.359985	1585100
2017-12-26	1168.359985	1178.319946	1160.550049	1176.760010	1176.760010	2005200
2017-12-27	1179.910034	1187.290039	1175.609985	1182.260010	1182.260010	1867200
2017-12-28	1189.000000	1190.099976	1184.380005	1186.099976	1186.099976	1841700
2017-12-29	1182.349976	1184.000000	1167.500000	1169.469971	1169.469971	2688400

# 计算涨跌幅
AmazonChange=change(AmazonDf['Close'])

股票累计上涨= 55.17 %

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

Date
2017-12-22    0.550228
2017-12-26    0.561373
2017-12-27    0.568671
2017-12-28    0.573766
2017-12-29    0.551700
Name: sum_pct_change, dtype: float64

Facebook

# 读取数据
FacebookDf=pd.read_excel(r'C:\Users\EDY\Desktop\吧哩吧啦\学习\Untitled Folder\Facebook2017年股票数据.xlsx',index_col='Date')
FacebookDf.tail()

	Open	High	Low	Close	Adj Close	Volume
Date
2017-12-22	177.139999	177.529999	176.229996	177.199997	177.199997	8509500
2017-12-26	176.630005	177.000000	174.669998	175.990005	175.990005	8897300
2017-12-27	176.550003	178.440002	176.259995	177.619995	177.619995	9496100
2017-12-28	177.949997	178.940002	177.679993	177.919998	177.919998	12220800
2017-12-29	178.000000	178.850006	176.460007	176.460007	176.460007	10261500

# 计算涨跌幅
FacebookChange=change(FacebookDf['Close'])

股票累计上涨= 51.0 %

'''增加一列每日增长百分比'''
# .pct_change()返回变化百分比，第一行因没有可对比的，返回Nan，填充为0
FacebookDf['pct_change']=FacebookDf['Close'].pct_change(1).fillna(0)
FacebookDf['pct_change'].head()

Date
2017-01-03    0.000000
2017-01-04    0.015660
2017-01-05    0.016682
2017-01-06    0.022707
2017-01-09    0.012074
Name: pct_change, dtype: float64

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

Date
2017-12-22    0.516344
2017-12-26    0.505990
2017-12-27    0.519938
2017-12-28    0.522506
2017-12-29    0.510012
Name: sum_pct_change, dtype: float64

数据可视化

import matplotlib.pyplot as plt

# 查看成交量与股价之间的关系
fig=plt.figure(figsize=(10,5))
AliDf.plot(x='Volume',y='Close',kind='scatter')
plt.xlabel('成交量')
plt.ylabel('股价')
plt.title('成交量与股价之间的关系')
plt.show()

# 查看各个参数之间的相关性，与股价与成交量之间呈中度相关
AliDf.corr()

	Open	High	Low	Close	Adj Close	Volume	sum_pct_change
Open	1.000000	0.999281	0.998798	0.998226	0.998226	0.424686	0.998226
High	0.999281	1.000000	0.998782	0.999077	0.999077	0.432467	0.999077
Low	0.998798	0.998782	1.000000	0.999249	0.999249	0.401456	0.999249
Close	0.998226	0.999077	0.999249	1.000000	1.000000	0.415801	1.000000
Adj Close	0.998226	0.999077	0.999249	1.000000	1.000000	0.415801	1.000000
Volume	0.424686	0.432467	0.401456	0.415801	0.415801	1.000000	0.415801
sum_pct_change	0.998226	0.999077	0.999249	1.000000	1.000000	0.415801	1.000000

查看各个公司的股价平均值

AliDf['Close'].mean()

141.79179260159364

'''数据准备'''
# 计算每家公司的收盘价平均值
Close_mean={'Alibaba':AliDf['Close'].mean(),
            'Google':GoogleDf['Close'].mean(),
            'Apple':AppleDf['Close'].mean(),
            'Tencent':TencentDf['Close'].mean(),
            'Amazon':AmazonDf['Close'].mean(),
            'Facebook':FacebookDf['Close'].mean()}
CloseMeanSer=pd.Series(Close_mean)
CloseMeanSer.sort_values(ascending=False,inplace=True) 

'''绘制柱状图'''
# 创建画板
fig=plt.figure(figsize=(10,5))
# 绘图
CloseMeanSer.plot(kind='bar')
# 设置x、y轴标签及标题
plt.xlabel('公司')
plt.ylabel('股价平均值（美元）')
plt.title('2017年各公司股价平均值')
# 设置y周标签刻度
plt.yticks(np.arange(0,1100,100))
# 显示y轴网格
plt.grid(True,axis='y')
# 显示图像
plt.show()

亚马逊和谷歌的平均股价很高，远远超过其他4家，但是仅看平均值并不能代表什么，下面从分布和走势方面查看

查看各公司股价分布情况

'''数据准备'''
# 将6家公司的收盘价整合到一起
CloseCollectDf=pd.concat([AliDf['Close'],
                          GoogleDf['Close'],
                          AppleDf['Close'],
                          TencentDf['Close'],
                          AmazonDf['Close'],
                          FacebookDf['Close']],axis=1)
CloseCollectDf.columns=['Alibaba','Google','Apple','Tencent','Amazon','Facebook']

'''绘制箱型图'''
# 创建画板
fig=plt.figure(figsize=(20,10))
fig.suptitle('2017年各公司股价分布',fontsize=18)
# 子图1
ax1=plt.subplot(121)
CloseCollectDf.plot(ax=ax1,kind='box')
plt.xlabel('公司')
plt.ylabel('股价（美元）')
plt.title('2017年各公司股价分布')
plt.grid(True,axis='y')

# 因谷歌和亚马逊和两外四家的差别较大，分开查看，
# 子图2
ax2=plt.subplot(222)
CloseCollectDf[['Google','Amazon']].plot(ax=ax2,kind='box')
# 设置x、y轴标签及标题
plt.ylabel('股价（美元）')
plt.title('2017年谷歌和亚马逊股价分布')
# 设置y周标签刻度
# plt.yticks(np.arange(0,1300,100))
# 显示y轴网格
plt.grid(True,axis='y')

# 子图3
ax3=plt.subplot(224)
CloseCollectDf[['Alibaba','Apple','Tencent','Facebook']].plot(ax=ax3,kind='box')
# 设置x、y轴标签及标题
plt.xlabel('公司')
plt.ylabel('股价（美元）')
plt.title('2017年阿里、苹果、腾讯、Facebook股价分布')
# 设置y周标签刻度
# plt.yticks(np.arange(0,1300,100))
# 显示y轴网格
plt.grid(True,axis='y')

plt.subplot

# 显示图像
plt.show()

从箱型图看，谷歌和亚马逊的股价分布较广，且中位数偏上，腾讯股价最为集中，波动最小，相对稳定。

股价走势对比

# 创建画板并设置大小,constrained_layout=True设置自动调整子图之间间距
fig=plt.figure(figsize=(15,10),constrained_layout=True)
# ax=plt.subplots(2,1,sharex=True)
fig.suptitle('股价走势对比',fontsize=18)

'''绘制图像1 '''
ax1=plt.subplot(211)
plt.plot(AliDf.index,AliDf['Close'],label='Alibaba')
plt.plot(GoogleDf.index,GoogleDf['Close'],label='Google')
plt.plot(AppleDf.index,AppleDf['Close'],label='Apple')
plt.plot(TencentDf.index,TencentDf['Close'],label='Tencent')
plt.plot(AmazonDf.index,AmazonDf['Close'],label='Amazon')
plt.plot(FacebookDf.index,FacebookDf['Close'],label='Facebook')
# # 设置xy轴标签
plt.xlabel('时间')
plt.ylabel('股价')
# 设置标题
# plt.title('股价走势对比')
# 图例显示位置、大小
plt.legend(loc='upper left',fontsize=12)
# 设置x,y轴间隔,设置旋转角度，以免重叠
plt.xticks(AliDf.index[::10],rotation=45)
plt.yticks(np.arange(0, 1300, step=100))
# 显示网格
plt.grid(True)

'''绘制图像2'''
ax2=plt.subplot(212)
plt.plot(AliDf.index,AliDf['sum_pct_change'],label='Alibaba')
plt.plot(GoogleDf.index,GoogleDf['sum_pct_change'],label='Google')
plt.plot(AppleDf.index,AppleDf['sum_pct_change'],label='Apple')
plt.plot(TencentDf.index,TencentDf['sum_pct_change'],label='Tencent')
plt.plot(AmazonDf.index,AmazonDf['sum_pct_change'],label='Amazon')
plt.plot(FacebookDf.index,FacebookDf['sum_pct_change'],label='Facebook')

# 设置xy轴标签
plt.xlabel('时间')
plt.ylabel('累计增长率')
# 设置标题
# plt.title('股价走势对比')
# 图例显示位置、大小
plt.legend(loc='upper left',fontsize=12)
# 设置x,y轴间隔,设置旋转角度，以免重叠
plt.xticks(AliDf.index[::10],rotation=45)
plt.yticks(np.arange(0, 1.2, step=0.1))
# 显示网格
plt.grid(True)

# 调整子图间距，subplots_adjust(left=None, bottom=None, right=None, top=None,wspace=None, hspace=None)

# 显示图像
plt.show()

可以看出，在2017年间，亚马逊和谷歌的股价虽然偏高，涨幅却不如阿里巴巴和腾讯。

总结

观察以上图形，可以得出一下结果：
1、2017年谷歌和亚马逊股价偏高，波动较大，但其涨幅并不高；
2、2017年阿里巴巴和腾讯的股价平均值相对较小，股价波动比较小，其涨幅却很高，分别达到了94.62%和114.36%。