In [27]:

    

# SEE EXAMPLES: https://bitbucket.org/hrojas/learn-pandas


    

In [28]:

    

# Import all libraries needed for the tutorial

# General syntax to import specific functions in a library: 
##from (library) import (specific library function)
from pandas import DataFrame, read_csv

# General syntax to import a library but no functions: 
##import (library) as (give the library a nickname/alias)
import matplotlib.pyplot as plt
import pandas as pd #this is how I usually import pandas
import sys #only needed to determine Python version number
import matplotlib #only needed to determine Matplotlib version number

# Enable inline plotting
%matplotlib inline


    

In [29]:

    

print('Python version ' + sys.version)
print('Pandas version ' + pd.__version__)
print('Matplotlib version ' + matplotlib.__version__)


    

    




Python version 3.5.2 |Continuum Analytics, Inc.| (default, Jul  2 2016, 17:53:06) 
[GCC 4.4.7 20120313 (Red Hat 4.4.7-1)]
Pandas version 0.19.2
Matplotlib version 1.5.3

In [30]:

    

# The inital set of baby names and bith rates
names = ['Bob','Jessica','Mary','John','Mel']
births = [968, 155, 77, 578, 973]


    

In [31]:

    

zip?


    

In [32]:

    

BabyDataSet = list(zip(names,births))
BabyDataSet


    

    
Out[32]:





[('Bob', 968), ('Jessica', 155), ('Mary', 77), ('John', 578), ('Mel', 973)]

In [33]:

    

df = pd.DataFrame(data = BabyDataSet, columns=['Names', 'Births'])
df


    

    
Out[33]:






  

    

      

      
Names
      
Births
    
  
  

    

      
0
      
Bob
      
968
    
    

      
1
      
Jessica
      
155
    
    

      
2
      
Mary
      
77
    
    

      
3
      
John
      
578
    
    

      
4
      
Mel
      
973
    
  

In [34]:

    

df.to_csv?


    

In [35]:

    

df.to_csv('births1880.csv',index=False,header=False)


    

In [36]:

    

read_csv?


    

In [37]:

    

Location = 'births1880.csv'
df = pd.read_csv(Location)


    

In [38]:

    

df


    

    
Out[38]:






  

    

      

      
Bob
      
968
    
  
  

    

      
0
      
Jessica
      
155
    
    

      
1
      
Mary
      
77
    
    

      
2
      
John
      
578
    
    

      
3
      
Mel
      
973
    
  

In [39]:

    

df = pd.read_csv(Location, header=None)
df


    

    
Out[39]:






  

    

      

      
0
      
1
    
  
  

    

      
0
      
Bob
      
968
    
    

      
1
      
Jessica
      
155
    
    

      
2
      
Mary
      
77
    
    

      
3
      
John
      
578
    
    

      
4
      
Mel
      
973
    
  

In [40]:

    

df = pd.read_csv(Location, names=['Names','Births'])
df


    

    
Out[40]:






  

    

      

      
Names
      
Births
    
  
  

    

      
0
      
Bob
      
968
    
    

      
1
      
Jessica
      
155
    
    

      
2
      
Mary
      
77
    
    

      
3
      
John
      
578
    
    

      
4
      
Mel
      
973
    
  

In [23]:

    

# Check data type of the columns
df.dtypes


    

    
Out[23]:





Names     object
Births     int64
dtype: object

In [22]:

    

# Check data type of Births column
df.Births.dtype


    

    
Out[22]:





dtype('int64')

In [24]:

    

# Method 1:
Sorted = df.sort_values(['Births'], ascending=False)
Sorted.head(1)


    

    
Out[24]:






  

    

      

      
Names
      
Births
    
  
  

    

      
4
      
Mel
      
973
    
  

In [25]:

    

# Method 2:
df['Births'].max()


    

    
Out[25]:





973

In [26]:

    

# Create graph
df['Births'].plot()

# Maximum value in the data set
MaxValue = df['Births'].max()

# Name associated with the maximum value
MaxName = df['Names'][df['Births'] == df['Births'].max()].values

# Text to display on graph
Text = str(MaxValue) + " - " + MaxName

# Add text to graph
plt.annotate(Text, xy=(1, MaxValue), xytext=(8, 0), 
                 xycoords=('axes fraction', 'data'), textcoords='offset points')

print("The most popular name")
df[df['Births'] == df['Births'].max()]
#Sorted.head(1) can also be used


    

    




The most popular name






    
Out[26]:






  

    

      

      
Names
      
Births
    
  
  

    

      
4
      
Mel
      
973
    
  








    

In [ ]: