In [21]:

    

import numpy as np 
import pandas as pd

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

trip= pd.read_csv('trip.csv')


    

In [16]:

    

# Duracion de viajes por bicicleta.
plt = trip.groupby('bike_id').sum()['duration'].plot(figsize=(14,4));
plt.set_xlabel('bike_id')
plt.set_ylabel('duration')
plt.set_title('Cantidad de viajes por bicicleta');


    

In [7]:

    

# Top five bikes durations 
trip.sort_values('duration',ascending=False).head(10)


    

    
Out[7]:






  

    

      

      
id
      
duration
      
start_date
      
start_station_name
      
start_station_id
      
end_date
      
end_station_name
      
end_station_id
      
bike_id
      
subscription_type
      
zip_code
    
  
  

    

      
573566
      
568474
      
17270400
      
12/6/2014 21:59
      
South Van Ness at Market
      
66
      
6/24/2015 20:18
      
2nd at Folsom
      
62
      
535
      
Customer
      
95531
    
    

      
382718
      
825850
      
2137000
      
6/28/2015 21:50
      
Market at Sansome
      
77
      
7/23/2015 15:27
      
Yerba Buena Center of the Arts (3rd @ Howard)
      
68
      
466
      
Customer
      
97213
    
    

      
440339
      
750192
      
1852590
      
5/2/2015 6:17
      
San Antonio Shopping Center
      
31
      
5/23/2015 16:53
      
Castro Street and El Camino Real
      
32
      
680
      
Subscriber
      
94024
    
    

      
371066
      
841176
      
1133540
      
7/10/2015 10:35
      
University and Emerson
      
35
      
7/23/2015 13:27
      
University and Emerson
      
35
      
262
      
Customer
      
94306
    
    

      
80510
      
111309
      
722236
      
11/30/2013 13:29
      
University and Emerson
      
35
      
12/8/2013 22:06
      
University and Emerson
      
35
      
247
      
Customer
      
94301
    
    

      
606063
      
522337
      
720454
      
10/30/2014 8:29
      
Redwood City Caltrain Station
      
22
      
11/7/2014 15:36
      
Stanford in Redwood City
      
25
      
692
      
Customer
      
94010
    
    

      
223016
      
323594
      
716480
      
6/13/2014 16:57
      
Harry Bridges Plaza (Ferry Building)
      
50
      
6/21/2014 23:59
      
Civic Center BART (7th at Market)
      
72
      
633
      
Subscriber
      
94131
    
    

      
195379
      
361321
      
715339
      
7/13/2014 5:50
      
Arena Green / SAP Center
      
14
      
7/21/2014 12:32
      
Adobe on Almaden
      
5
      
251
      
Customer
      
nil
    
    

      
421839
      
774999
      
688899
      
5/20/2015 15:27
      
Palo Alto Caltrain Station
      
34
      
5/28/2015 14:49
      
California Ave Caltrain Station
      
36
      
230
      
Customer
      
nil
    
    

      
524521
      
635260
      
655939
      
2/8/2015 3:05
      
San Jose Civic Center
      
3
      
2/15/2015 17:17
      
SJSU 4th at San Carlos
      
12
      
132
      
Customer
      
89451
    
  

In [17]:

    

#Las Mayores cantidad de duraciones por bike_id
plt = trip['duration'].value_counts()[:5].plot('bar');
plt.set_xlabel('bike_id')
plt.set_ylabel('duration')
plt.set_title('Bicicletas con Mayor viajes en Duracion');


    

In [18]:

    

duration_station = trip['duration'].value_counts()
%matplotlib notebook
# top 20
duration_station[:10].plot('bar');


    

In [23]:

    

#Que estacion de Origen tiene las mayor cantidad,las 10
plt = trip['start_station_name'].value_counts()[:10].plot('bar');
plt.set_xlabel('Estaciones')
plt.set_ylabel('Partidas')
plt.set_title('Las 10 estaciones con la mayor cantidad de salidas');


    

In [24]:

    

#Que estacion de Origen tiene las mayor cantidad,las 20
plt = trip['start_station_name'].value_counts()[:20].plot('bar');
plt.set_xlabel('Estaciones')
plt.set_ylabel('Partidas')
plt.set_title('Las 20 estaciones con la mayor cantidad de salidas');


    

In [25]:

    

#Que estacion de destino que tiene las mayor cantidad de llegadas,las 20
plt = trip['end_station_name'].value_counts()[:20].plot('bar');
plt.set_xlabel('Estaciones')
plt.set_ylabel('Llegadas')
plt.set_title('Las 20 estaciones con la mayor cantidad de llegadas');


    

In [9]:

    

status= pd.read_csv('stat80.csv')


    

In [10]:

    

status.sort_values('bikes_available',ascending=False).head(10)


    

    
Out[10]:






  

    

      

      
station_id
      
bikes_available
      
docks_available
      
time
    
  
  

    

      
185339
      
2
      
24
      
3
      
2014/01/07 17:46:03
    
    

      
185338
      
2
      
24
      
3
      
2014/01/07 17:45:02
    
    

      
185337
      
2
      
24
      
3
      
2014/01/07 17:44:02
    
    

      
185336
      
2
      
24
      
3
      
2014/01/07 17:43:03
    
    

      
63706
      
2
      
23
      
4
      
2013/10/14 18:38:01
    
    

      
67035
      
2
      
23
      
4
      
2013/10/17 06:25:01
    
    

      
84226
      
2
      
23
      
4
      
2013/10/29 07:35:02
    
    

      
84225
      
2
      
23
      
4
      
2013/10/29 07:34:01
    
    

      
67027
      
2
      
23
      
4
      
2013/10/17 06:16:01
    
    

      
67028
      
2
      
23
      
4
      
2013/10/17 06:17:01
    
  

In [ ]:

    




    

In [ ]: