In [1]:

    

URL = 'https://data.seattle.gov/api/views/65db-xm6k/rows.csv?accessType=DOWNLOAD'


    

In [2]:

    

from urllib.request import urlretrieve
urlretrieve(URL, 'Fremont.csv')


    

    
Out[2]:





('Fremont.csv', <http.client.HTTPMessage at 0x10fe9d3c8>)

In [3]:

    

!head Fremont.csv


    

    




Date,Fremont Bridge West Sidewalk,Fremont Bridge East Sidewalk
10/03/2012 12:00:00 AM,4,9
10/03/2012 01:00:00 AM,4,6
10/03/2012 02:00:00 AM,1,1
10/03/2012 03:00:00 AM,2,3
10/03/2012 04:00:00 AM,6,1
10/03/2012 05:00:00 AM,21,10
10/03/2012 06:00:00 AM,105,50
10/03/2012 07:00:00 AM,257,95
10/03/2012 08:00:00 AM,291,146

In [4]:

    

import pandas as pd
df = pd.read_csv('Fremont.csv', index_col='Date', parse_dates=True)
df.head()


    

    
Out[4]:






  

    

      

      
Fremont Bridge West Sidewalk
      
Fremont Bridge East Sidewalk
    
    

      
Date
      

      

    
  
  

    

      
2012-10-03 00:00:00
      
4.0
      
9.0
    
    

      
2012-10-03 01:00:00
      
4.0
      
6.0
    
    

      
2012-10-03 02:00:00
      
1.0
      
1.0
    
    

      
2012-10-03 03:00:00
      
2.0
      
3.0
    
    

      
2012-10-03 04:00:00
      
6.0
      
1.0
    
  

In [5]:

    

%matplotlib inline


    

In [6]:

    

df.info()


    

    




<class 'pandas.core.frame.DataFrame'>
DatetimeIndex: 38640 entries, 2012-10-03 00:00:00 to 2017-02-28 23:00:00
Data columns (total 2 columns):
Fremont Bridge West Sidewalk    38633 non-null float64
Fremont Bridge East Sidewalk    38633 non-null float64
dtypes: float64(2)
memory usage: 905.6 KB

In [7]:

    

df.plot()


    

    
Out[7]:





<matplotlib.axes._subplots.AxesSubplot at 0x118e50e80>






    

In [8]:

    

import matplotlib.pyplot as plt
plt.style.use('fivethirtyeight')

df.columns = ['West', 'East']

df.resample('W').sum().plot();


    

In [9]:

    

df['Total'] = df['West'] + df['East']

ax = df.resample('D').sum().rolling(365).sum().plot();
ax.set_ylim(0, None);


    

In [10]:

    

#trend in individual days
df.groupby(df.index.time).mean().plot();


    

In [11]:

    

pivoted = df.pivot_table('Total', index=df.index.time, columns=df.index.date)
pivoted.iloc[:5, :5]


    

    
Out[11]:






  

    

      

      
2012-10-03
      
2012-10-04
      
2012-10-05
      
2012-10-06
      
2012-10-07
    
  
  

    

      
00:00:00
      
13.0
      
18.0
      
11.0
      
15.0
      
11.0
    
    

      
01:00:00
      
10.0
      
3.0
      
8.0
      
15.0
      
17.0
    
    

      
02:00:00
      
2.0
      
9.0
      
7.0
      
9.0
      
3.0
    
    

      
03:00:00
      
5.0
      
3.0
      
4.0
      
3.0
      
6.0
    
    

      
04:00:00
      
7.0
      
8.0
      
9.0
      
5.0
      
3.0
    
  

In [12]:

    

#line for each days of the year
pivoted.plot(legend=False, alpha=0.01);


    

In [ ]: