Jupyter Data Science Workflow

From exploratory analysis to reproducible science



In [1]:

    
%matplotlib inline
import matplotlib.pyplot as plt

plt.style.use("seaborn")



In [2]:

    
from jupyterworkflow.data import get_fremont_data



In [3]:

    
data = get_fremont_data()



In [4]:

    
data.head()









    Out[4]:






  
    
      
      West
      East
      Total
    
    
      Date
      
      
      
    
  
  
    
      2012-10-03 12:00:00
      4.0
      9.0
      13.0
    
    
      2012-10-03 01:00:00
      4.0
      6.0
      10.0
    
    
      2012-10-03 02:00:00
      1.0
      1.0
      2.0
    
    
      2012-10-03 03:00:00
      2.0
      3.0
      5.0
    
    
      2012-10-03 04:00:00
      6.0
      1.0
      7.0



In [5]:

    
data.resample("W").sum().plot()









    Out[5]:





<matplotlib.axes._subplots.AxesSubplot at 0x7f39abf476d8>



In [6]:

    
data.resample("W").sum().plot()









    Out[6]:





<matplotlib.axes._subplots.AxesSubplot at 0x7f39ac8e0a20>



In [7]:

    
ax = data.resample("D").sum().rolling(365).sum().plot()
ax.set_ylim(0, None)









    Out[7]:





(0, 1058559.2)



In [8]:

    
data.groupby(data.index.time).mean().plot()









    Out[8]:





<matplotlib.axes._subplots.AxesSubplot at 0x7f39a91eb828>



In [9]:

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



In [10]:

    
pivoted.plot(legend=False, alpha=0.01)









    Out[10]:





<matplotlib.axes._subplots.AxesSubplot at 0x7f39a8bd4cc0>



In [11]:

    
get_fremont_data??

	2012-10-03	2012-10-04	2012-10-05	2012-10-06	2012-10-07
01:00:00	50.0	64.5	60.0	96.0	122.5
02:00:00	65.0	64.0	66.0	106.0	122.0
03:00:00	84.5	75.0	84.0	107.0	118.5
04:00:00	161.0	141.5	159.5	94.0	114.0
05:00:00	307.0	266.5	229.5	92.5	100.0

	West	East	Total
Date
2012-10-03 12:00:00	4.0	9.0	13.0
2012-10-03 01:00:00	4.0	6.0	10.0
2012-10-03 02:00:00	1.0	1.0	2.0
2012-10-03 03:00:00	2.0	3.0	5.0
2012-10-03 04:00:00	6.0	1.0	7.0