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

# ## Pandas basics

# In[1]:


import pandas as pd


# <h3>Pandas series</h3>
# <p>
# pandas series is similar to numpy array, But it suppport lots of extra functionality like <b> Pandaseries.describe()</b>
# </p>
# <p>
# Basic acces is samilar to numpy arrary, it support access by index( s[5] ) or slicing ( s[5:10] ).<br/>
# It also support vectorise operation and looping like numpy array.<br />
# Implemented in C so it works very fast.
# </p>

# ### Benfits of Pandas series

# In[8]:


s=pd.Series([2,3,4,5,6])
print s.describe()


# <h3> Pandas Index </h3>
# <p>
# Hybrid of list and python Dictionary. It map key value pair.
# </p>

# In[11]:


sal=pd.Series([40,12,43,56],
             index=['Ram',
                  'Syam',
                  "Rahul",
                  "Ganesh"])
print sal


# In[20]:


print sal[0]


# <h4>lookUp by index</h4>

# In[21]:


print sal.loc["Syam"]


# <p>Using <b>sal[position]</b> is not prefered instead prefer to use <b>sal.iloc[position]</b>
# becouse Index has different meaning in series so it avoid confusion</p>

# In[19]:


print sal.iloc[3]


# <p><b>argmax()</b> function return index of max value element </p>

# In[24]:


print sal.argmax()


# In[25]:


print sal.loc["Ganesh"]
print sal.max()


# ### Adding series with Differen index

# In[27]:


a=pd.Series([1,2,3,4],
            index=["a","b","c","d"])
b=pd.Series([9,8,7,6],
           index=["c","d","e","f"])
print a


# In[28]:


print b


# In[29]:


print a+b


# <p><b>C,D</b> are common in both so added correctly rest are just assign a volue <b>NaN (Not a number)</b> </p>
# <h4>we can modify it such that in case of mismatch original data will assign instead of NaN or drop All NaN </h4>

# In[35]:


res = (a+b)
print res.dropna()


# #### Treat missing values as 0

# In[37]:


res=a.add(b,fill_value=0)
print res


# <b>s.apply(function_name)</b> used to apply some operation on each element.
# <h3>Example:</h3>
# <p>
# adding 5 to each element , we can do this by simply series+5 becouse it is a vector, But lets do using this new techniqe <b>s.apply(function)</b>
# </p>

# In[39]:


print res


# In[40]:


print res+5


# In[41]:


def add_5(x):
    return x+5


# In[44]:


print res.apply(add_5)


# <h3> Plotting </h3>
# <p>
# automaticaly plot index vs data plot
# </p>

# In[47]:


get_ipython().run_line_magic('pylab', 'inline')
res.plot()