Python学习笔记--机器学习-数据科学库--Pandas时间序列

1.Pandas时间序列序列

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
df=pd.read_csv('./911.csv')
#print(df.head(10))
#print(df.info())
##获取分类情况
temp_list=df['title'].str.split(':').to_list()
cate_list=list(set([i[0] for i in temp_list ]))
print(cate_list)

##构造全为0的数组
zeros_df=pd.DataFrame(np.zeros((df.shape[0],len(cate_list))),columns=cate_list)

##赋值 快

for cate in cate_list:
    zeros_df[cate][df['title'].str.contains(cate)]=1
    # print(zeros_df)
    # break

# ##赋值方法2__慢
# for i in range(df.shape[0]):
#     zeros_df.loc[i,temp_list[i][0]]=1
# print(zeros_df)

sum_ret=zeros_df.sum(axis=0)
print(sum_ret)

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
df=pd.read_csv('./911.csv')
#print(df.head(10))
#print(df.info())
##获取分类情况
temp_list=df['title'].str.split(':').to_list()
cate_list=[i[0] for i in temp_list ]
cate_df=pd.DataFrame(np.array(cate_list).reshape((df.shape[0],1)),columns=['cate'])
print(cate_df)
df['cate']=cate_df  ##添加一列
##或者
##df['cate']=pd.DataFrame(np.array(cate_list).reshape((df.shape[0],1)),columns=['cate'])
print(df.head(5))
print(df.groupby(by='cate').count()['title'])
##不同月份紧急电话的次数

解决上述问题可以用Pandas时间序列完成
参数见笔记

import pandas as pd
t1=pd.date_range(start="20171230",end='20180131',freq='D')
print(t1)

DatetimeIndex([‘2017-12-30’, ‘2017-12-31’, ‘2018-01-01’, ‘2018-01-02’,
‘2018-01-03’, ‘2018-01-04’, ‘2018-01-05’, ‘2018-01-06’,
‘2018-01-07’, ‘2018-01-08’, ‘2018-01-09’, ‘2018-01-10’,
‘2018-01-11’, ‘2018-01-12’, ‘2018-01-13’, ‘2018-01-14’,
‘2018-01-15’, ‘2018-01-16’, ‘2018-01-17’, ‘2018-01-18’,
‘2018-01-19’, ‘2018-01-20’, ‘2018-01-21’, ‘2018-01-22’,
‘2018-01-23’, ‘2018-01-24’, ‘2018-01-25’, ‘2018-01-26’,
‘2018-01-27’, ‘2018-01-28’, ‘2018-01-29’, ‘2018-01-30’,
‘2018-01-31’],
dtype=‘datetime64[ns]’, freq=‘D’)

Process finished with exit code 0
D为天，10D 10 天 M 月
在DataFrame中使用时间序列

import time

import pandas as pd
from matplotlib import pyplot as plt
df=pd.read_csv('./911.csv')
df['timeStamp']=pd.to_datetime(df['timeStamp'])
df.set_index('timeStamp',inplace=True)
print(df.head())
count_by_month=df.resample("M").count()['title']
print(count_by_month.head)

##
_x=count_by_month.index
_y=count_by_month.values

##查看可用方法
# for i in _x:
#     print(dir(i))
#     break
_x=[time.strftime('%y%m%d')for i in _x]
plt.figure(figsize=(20,8),dpi=80)
plt.plot(range(len(_x)),_y)
plt.xticks(range(len(_x)),_x,rotation=45)
plt.show()

import pandas as pd
from matplotlib import pyplot as plt
import numpy as np
print('*.* '*50)
##911数据中不同月份不同类型的电话的次数的变化情况
def plot_img(df):
    count_by_month=df.resample('M').count()['title']
##把时间字符串转为时间类型设置为索引
df=pd.read_csv('./911.csv')
df['timeStamp']=pd.to_datetime(df['timeStamp'])
#df.set_index('timeStamp',inplace=True)

##添加列，表示分类
temp_list=df['title'].str.split(':').tolist()
cate_list=[i[0] for i in temp_list]
df['cate']=pd.DataFrame(np.array(cate_list).reshape((df.shape[0],1)))

df.set_index('timeStamp',inplace=True)

print(df.head(1))
plt.figure(figsize=(20,8),dpi=80)

##分组
for group_name,group_data in df.groupby(by='cate'):
    ##对不同分类都进行汇总
    count_by_month=group_data.resample('M').count()['title']

    ##画图
    _x=count_by_month.index
    print(_x)
    _y=count_by_month.values
    _x=[i.strftime('%Y%m%d') for i in _x]
    plt.plot(range(len(_x)),_y,label=group_name)



plt.xticks(range(len(_x)),_x,rotation=45)
plt.legend(loc='best')
plt.show()

Pandas时间序列之PeriodIndex
之前所学习的DatetimeIndex可以理解为时间戳，那么现在我们要学习的PeriodIndex可以理解为时间段
periods=pd.PeriodIndex(year=data[‘year’],month=data[‘month’] , day=data[‘day’] ,hour=data[‘hour’],freq=‘H’)
data=df.set_index(periods).resample(‘10D’).mean()

import time      
                 
import matplotlib
import pandas as 
                 
file_path='./PM2.
df=pd.read_csv(fi
# print(df.head()
# print(df.info()
##把分开的时间字符串通过peri
period=pd.PeriodI
df['datatime']=pe
                 
df['datetime']=pe
                 
                 
##把datetime 设置为索引
df.set_index('dat
print(df.head()) 
##进行降采样          
df=df.resample('7
print(df.head()) 
                 
##处理缺失数据，删除缺失数据  
                 
print(df['PM_US P
data=df['PM_US Po
data_china=df['PM
print(data_china.
##h画图            
_x=data.index    
_x_china=[i.strft
print(len(_x_chin
                 
_y=data.values   
_y_china=data_chi
plt.figure(figsiz
plt.plot(range(le
plt.plot(range(le
plt.xticks(range(
plt.legend(loc='b
plt.show()