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

# In[1]:


#Importing libraries
import pandas as pd
import os as os
import pycurl
import csv


# In[2]:


#To get the location of current working directory
os.getcwd()


# In[4]:


#To change the working directory
os.chdir('C:\\Anaconda\\abalone')
os.getcwd()


# In[5]:


#Use pycurl to get a datafile from https and write it to a csv file
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/abalone/abalone.data'
c = pycurl.Curl()
c.setopt(c.URL, url)
with open('abalone.csv', 'w+') as s:
    c.setopt(c.WRITEFUNCTION, s.write)
    c.perform()


# In[6]:


abalone = pd.read_csv('abalone.csv')
abalone


# In[8]:


#To add column names
abalone.columns = ['Sex', 'Length','Diameter','Height','Whole weight','Shucked weight','Viscera weight','Shell weight','Rings']


# In[14]:


#To write data to a csv file
abalone.to_csv('abalone.csv')


# In[15]:


#To get 4 top-most observations
abalone.head(4)


# In[16]:


#To get 4 bottom-most observations
abalone.tail(4)


# In[17]:


#To get basic statistics for all numeric variables
abalone.describe()


# In[18]:


#To get covariance 
abalone.cov()


# In[19]:


#To get pairwise-correlation coefficients for all numeric variables
abalone.corr()


# In[20]:


# To get unique values of 'Rings' column
abalone['Rings'].unique() 


# In[21]:


#To subset - have only 'Length','Diameter' and 'Height' in dataset abalone1
abalone1 = abalone[['Length','Diameter','Height']]


# In[22]:


#Inspect abalone1 by checking head and tail
abalone1.head(3)


# In[23]:


abalone1.tail(3)