#!/usr/bin/env python
# coding: utf-8

# # Essential Introduction to pandas 

# ## 1. First we will set up our environment in Jupyter
# ### If you don't have pandas_datareader, at the command line enter
# ### conda install -c pandas-datareader or pip install if you don't have Anaconda
# 

# In[71]:


import numpy as np
import pandas as pd
get_ipython().run_line_magic('matplotlib', 'inline')
import matplotlib.pyplot as plt
import pandas_datareader as pdr


# ## 2. Get data (5 years, GOOG AMZN)

# In[73]:


amzn = pdr.get_data_yahoo('AMZN', '20121101')
goog = pdr.get_data_yahoo('GOOG', '2012-11-01')


# ## 3. View head, tail, info

# In[76]:


amzn.head()


# In[77]:


amzn.tail()


# In[79]:


print(amzn.info(), goog.info())


# ## 4. Filtering  using .loc,  .iloc, index

# In[83]:


amzn.loc['20121101','Open']


# In[85]:


amzn.iloc[0,0]


# In[86]:


amzn[amzn.index > '2017-11-01']


# In[ ]:





# ## 5. Filtering with criteria

# In[87]:


print('Mean: %.3f  Std: %.3f'% (amzn['Volume'].mean(), amzn['Volume'].std()) )


# In[88]:


high = amzn['Volume'].mean() + 2* amzn['Volume'].std()


# In[91]:


len(amzn[amzn.Volume >high]) / len(amzn)


# In[ ]:





# ## 6. Adding Columns

# In[92]:


amzn['pct_chng'] = amzn.Close.pct_change()


# In[93]:


amzn.head()


# ## 7. Appending data

# In[97]:


goog_11 = goog.loc['2017-11']
amzn_11 = amzn.loc['2017-11']


# In[100]:


goog_11.append(amzn_11).tail()


# ## 8. Merging Columns from Different DataFrames

# In[101]:


close = pd.DataFrame({'AZMN' : amzn.Close, 'GOOG' : goog.Close})
close.head()


# In[ ]:





# In[ ]:





# ## 9. Grouping  and sorting data 

# In[105]:


goog['Volume'][goog.index > '2017'].resample('M').mean().plot()


# In[ ]:





# In[ ]:





# ## 10. Cumulative Sum and Rolling Calculations

# In[106]:


amzn_change = np.log(amzn.Close /amzn.Close.shift(1))
goog_change = np.log(goog.Close / goog.Close.shift(1))


# In[108]:


amzn_change.cumsum().plot()
goog_change.cumsum().plot()


# ## 11. Create new dataFrame and save to csv

# In[111]:


new = pd.DataFrame({'AMZN': amzn_change[1:], 'GOOG' : goog_change[1:]})
new.to_csv('stocks.csv')


# In[112]:


pd.read_csv('stocks.csv').head()


# In[ ]:





# ## 12. Change the index and remove columns
#  

# In[113]:


new_stocks = pd.read_csv('stocks.csv')
new_stocks.index = new_stocks.Date
new_stocks.head()


# In[114]:


new_stocks.drop(['Date'], axis=1, inplace=True)
new_stocks.head()


# ## 13. Rename Columns

# In[120]:


new_stocks.rename(columns={'AMZN': 'AMZN_chng'}, inplace=True)
new_stocks.head()


# In[ ]:





# In[ ]: