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

# # Exercise 02
# 
# Estimate a regression using the Income data
# 
# 
# ## Forecast of income
# 
# We'll be working with a dataset from US Census indome ([data dictionary](https://archive.ics.uci.edu/ml/datasets/Adult)).
# 
# Many businesses would like to personalize their offer based on customer’s income. High-income customers could be, for instance, exposed to premium products. As a customer’s income is not always explicitly known, predictive model could estimate income of a person based on other information.
# 
# Our goal is to create a predictive model that will be able to output an estimation of a person income.

# In[5]:


import pandas as pd
import numpy as np

get_ipython().run_line_magic('matplotlib', 'inline')
import matplotlib.pyplot as plt

# read the data and set the datetime as the index
import zipfile
with zipfile.ZipFile('../datasets/income.csv.zip', 'r') as z:
    f = z.open('income.csv')
    income = pd.read_csv(f, index_col=0)

income.head()


# In[6]:


income.shape


# # Exercise 2.1 
# 
# What is the relation between the age and Income?
# 
# For a one percent increase in the Age how much the income increases?
# 
# Using sklearn estimate a linear regression and predict the income when the Age is 30 and 40 years

# In[3]:


income.plot(x='Age', y='Income', kind='scatter')


# In[ ]:





# # Exercise 2.2
# Evaluate the model using the MSE

# In[ ]:





# 
# # Exercise 2.3
# 
# Run a regression model using as features the Age and Age$^2$ using the OLS equations

# In[ ]:





# # Exercise 2.4
# 
# 
# Estimate a regression using more features.
# 
# How is the performance compared to using only the Age?

# In[ ]:





# # Exercise 2.5
# 
# 
# Estimate a logistic regression to predict if a person is in the United States.
# 
# What is the performance of the model

# In[10]:


income['isUS'] = (income['Country'] == 'United-States')*1.0
income['isUS'].value_counts()


# In[ ]: