In [19]:

    

import numpy as np 
import pandas as pd

# plots
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline

stat= pd.read_csv('stat80.csv')
wed= pd.read_csv('weather.csv')


    

In [4]:

    

stat.sample(3)


    

    
Out[4]:






  

    

      

      
station_id
      
bikes_available
      
docks_available
      
time
    
  
  

    

      
1950398
      
9
      
8
      
7
      
2013/11/28 01:39:02
    
    

      
2784362
      
12
      
10
      
9
      
2014/01/03 12:49:02
    
    

      
268817
      
3
      
10
      
5
      
2013/09/04 23:09:01
    
  

In [5]:

    

len(stat)


    

    
Out[5]:





2978660

In [6]:

    

stat.dtypes


    

    
Out[6]:





station_id          int64
bikes_available     int64
docks_available     int64
time               object
dtype: object

In [11]:

    

# Histogram of ratings*
stat[['bikes_available','station_id']].groupby('bikes_available').agg([np.size]).plot(kind='bar',figsize=(16,8));


    

In [13]:

    

stat[['station_id','bikes_available']].groupby('station_id').agg([np.size]).hist(bins=100,figsize=(16,8));


    

In [16]:

    

# Number of crashes per year
stat.groupby('time').count()['bikes_available'].plot(figsize=(14,4));


    

In [ ]:

    




    

In [ ]: