#!/usr/bin/env python # coding: utf-8 # ## Pandas basics # In[1]: import pandas as pd #
# pandas series is similar to numpy array, But it suppport lots of extra functionality like Pandaseries.describe() #
#
# Basic acces is samilar to numpy arrary, it support access by index( s[5] ) or slicing ( s[5:10] ).
# It also support vectorise operation and looping like numpy array.
# Implemented in C so it works very fast.
#
# Hybrid of list and python Dictionary. It map key value pair. #
# In[11]: sal=pd.Series([40,12,43,56], index=['Ram', 'Syam', "Rahul", "Ganesh"]) print sal # In[20]: print sal[0] #Using sal[position] is not prefered instead prefer to use sal.iloc[position] # becouse Index has different meaning in series so it avoid confusion
# In[19]: print sal.iloc[3] #argmax() function return index of max value element
# 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 #C,D are common in both so added correctly rest are just assign a volue NaN (Not a number)
## 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 s.apply(function) #
# 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) ## automaticaly plot index vs data plot #
# In[47]: get_ipython().run_line_magic('pylab', 'inline') res.plot()