notebook.community

Edit and run



In [1]:

    
import numpy as np
import pandas as pd
from pandas import Series, DataFrame



In [2]:

    
arr = np.array([[1,2,np.nan], [np.nan,3,4]])



In [3]:

    
dframe1 = DataFrame(arr, index=['A', 'B'], columns=['One', 'Two', 'Three'])
dframe1



In [4]:

    
dframe1.sum()









    Out[4]:





One      1.0
Two      5.0
Three    4.0
dtype: float64



In [5]:

    
dframe1.sum(axis=1)









    Out[5]:





A    3.0
B    7.0
dtype: float64



In [6]:

    
dframe1.idxmin()









    Out[6]:





One      A
Two      A
Three    B
dtype: object



In [7]:

    
dframe1.cumsum()



In [8]:

    
dframe1.describe()









    



/Users/andymeyers/anaconda/lib/python2.7/site-packages/numpy/lib/function_base.py:3834: RuntimeWarning: Invalid value encountered in percentile
  RuntimeWarning)






    Out[8]:






  
    
      
      One
      Two
      Three
    
  
  
    
      count
      1.0
      2.000000
      1.0
    
    
      mean
      1.0
      2.500000
      4.0
    
    
      std
      NaN
      0.707107
      NaN
    
    
      min
      1.0
      2.000000
      4.0
    
    
      25%
      NaN
      2.250000
      NaN
    
    
      50%
      NaN
      2.500000
      NaN
    
    
      75%
      NaN
      2.750000
      NaN
    
    
      max
      1.0
      3.000000
      4.0



In [9]:

    
from IPython.display import YouTubeVideo



In [10]:

    
YouTubeVideo('xGbpuFNR1ME')









    Out[10]:



In [13]:

    
YouTubeVideo('4EXNedimDMs')









    Out[13]:



In [15]:

    
import pandas.io.data as pdweb

import datetime



In [16]:

    
prices = pdweb.get_data_yahoo(['CVX', 'XOM', 'BP'], start=datetime.datetime(2010, 1,1), end = datetime.datetime(2013, 1,1))['Adj Close']

prices.head()



In [17]:

    
volume = pdweb.get_data_yahoo(['CVX', 'XOM', 'BP'], start=datetime.datetime(2010, 1,1), end = datetime.datetime(2013, 1,1))['Volume']



In [18]:

    
volume.head()



In [19]:

    
rets = prices.pct_change()



In [20]:

    
corr = rets.corr



In [22]:

    
%matplotlib inline
prices.plot()









    Out[22]:





<matplotlib.axes._subplots.AxesSubplot at 0x118664550>



In [27]:

    
import seaborn as sns
import matplotlib.pyplot as plt



In [33]:

    
sns.heatmap(corr(), annot=True)









    Out[33]:





<matplotlib.axes._subplots.AxesSubplot at 0x11eab98d0>



In [38]:

    
ser1 = Series(['w',  'w', 'x', 'y', 'z', 'w', 'x', 'y', 'x', 'a'])

ser1









    Out[38]:





0    w
1    w
2    x
3    y
4    z
5    w
6    x
7    y
8    x
9    a
dtype: object



In [40]:

    
ser1.unique()









    Out[40]:





array(['w', 'x', 'y', 'z', 'a'], dtype=object)



In [41]:

    
ser1.value_counts()









    Out[41]:





w    3
x    3
y    2
a    1
z    1
dtype: int64



In [ ]:

	BP	CVX	XOM
Date
2010-01-04	42.257896	61.192517	56.700952
2010-01-05	42.557951	61.625962	56.922342
2010-01-06	42.779422	61.633698	57.414323
2010-01-07	42.765133	61.401501	57.233934
2010-01-08	42.865151	61.509861	57.004337

	BP	CVX	XOM
Date
2010-01-04	3956100.0	10173800.0	27809100.0
2010-01-05	4109600.0	10593700.0	30174700.0
2010-01-06	6227900.0	11014600.0	35044700.0
2010-01-07	4431300.0	9626900.0	27192100.0
2010-01-08	3786100.0	5624300.0	24891800.0

	One	Two	Three
count	1.0	2.000000	1.0
mean	1.0	2.500000	4.0
std	NaN	0.707107	NaN
min	1.0	2.000000	4.0
25%	NaN	2.250000	NaN
50%	NaN	2.500000	NaN
75%	NaN	2.750000	NaN
max	1.0	3.000000	4.0