数据统计（python）时间序列：911分类案例、 pandas的时间序列、911的时间统计、 911的复合统计、pm2.5的统计

1.911分类案例_代码示例

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
from matplotlib import font_manager
my_font = font_manager.FontProperties(fname="c:/Windows/Fonts/simkai.ttf")

df = pd.read_csv("./911.csv")
# print(df.info())
'''
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 249737 entries, 0 to 249736
Data columns (total 9 columns):
 #   Column     Non-Null Count   Dtype  
---  ------     --------------   -----  
 0   lat        249737 non-null  float64
 1   lng        249737 non-null  float64
 2   desc       249737 non-null  object 
 3   zip        219391 non-null  float64
 4   title      249737 non-null  object 
 5   timeStamp  249737 non-null  object 
 6   twp        249644 non-null  object 
 7   addr       249737 non-null  object 
 8   e          249737 non-null  int64  
dtypes: float64(3), int64(1), object(5)
memory usage: 17.1+ MB
'''

time_data = pd.DataFrame(df['timeStamp'])
# print(time_data)
'''
                  timeStamp
0       2015-12-10 17:10:52
1       2015-12-10 17:29:21
2       2015-12-10 14:39:21
...                     ...
249735  2017-09-20 19:42:05
249736  2017-09-20 19:42:29
[249737 rows x 1 columns]
'''

#获取分类
# print(type(df["title"])) # <class 'pandas.core.series.Series'>
tempt_list = df["title"].str.split(':').tolist()
# print(tempt_list)
'''
RESCUE - ELEVATOR'], 
[['Traffic', ' DISABLED VEHICLE -'], 
['Fire', ' FIRE ALARM'], 
['Traffic', ' ROAD OBSTRUCTION -'], 
···
['Fire', ' FIRE INVESTIGATION'],
 ['EMS', ' UNKNOWN MEDICAL EMERGENCY'], 
 ['Traffic', ' ROAD OBSTRUCTION -']]
'''

# cate_list = set([i[0] for i in tempt_list]) # set()保证元素不重复
# print(cate_list)
'''{'Traffic', 'EMS', 'Fire'} '''

cate_list = list(set([i[0] for i in tempt_list]))
# print(cate_list)
'''['Traffic', 'EMS', 'Fire']'''

#构造全为0的数组
zero_array = pd.DataFrame(np.zeros((df.shape[0], len(cate_list))), columns=cate_list)
# print(zero_array)
'''
        EMS  Fire  Traffic
0       0.0   0.0      0.0
1       0.0   0.0      0.0
2       0.0   0.0      0.0
...     ...   ...      ...
249735  0.0   0.0      0.0
249736  0.0   0.0      0.0
[249737 rows x 3 columns]
'''

#赋值
# print(df["title"].str.contains('EMS'))
'''
0          True
1          Tru