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

# This notebook is created as a guided project in "Exploratory Data Visualization" course on DataQuest.io to visualize earnings based on college majors.
# <br>
# Data set can be downloaded from [here](https://github.com/fivethirtyeight/data/tree/master/college-majors)

# In[1]:


import pandas as pd
import matplotlib.pyplot as plt
from pandas.plotting import scatter_matrix 
get_ipython().run_line_magic('matplotlib', 'inline')


# In[2]:


recent_grads = pd.read_csv('recent-grads.csv')
recent_grads.head()


# In[3]:


recent_grads.describe()


# In[4]:


recent_grads.shape


# In[5]:


recent_grads.info()


# We see that some of the columns have 172 values, we drop missing values so that all columns have equal number of values.

# ### Dropping missing values

# In[6]:


recent_grads.dropna(inplace=True)
recent_grads.shape


# In[7]:


len(recent_grads['Major_category'].unique())


# #### There are 16 unique major categories in data set. For each category, we will compare:
#  - the number of male and female
#  - the number of employed and unemployed
#  - the number of collge jobs, non college jobs and low wage jobs
#  - the median earning 
#  

# In[8]:


recent_grads.groupby('Major_category')['Men', 'Women'].sum().plot(kind='bar')



# We see that there is a significant gender gap in Education, Engineering, Health and Psychology & Social Work.

# In[9]:


recent_grads.groupby('Major_category')['Employed', 'Unemployed'].sum().plot(kind='bar')


# 0 unemployment in Agriculture & Natural Resources.

# In[10]:


recent_grads.groupby('Major_category')['College_jobs','Non_college_jobs',
       'Low_wage_jobs'].sum().plot(kind='bar')


# In[12]:


recent_grads.groupby('Major_category')['Median'].sum().plot(kind='bar')


# Engineering has highest Median salary while Business has second highest.

# In[17]:


recent_grads[recent_grads['Major_category']=='Engineering']['Median']


# In[11]:


recent_grads['Median'].hist(bins=20, range=(recent_grads['Median'].min(),recent_grads['Median'].max()))


# 30k - 35k is most common salary figure for Engineering students.

# In[29]:


scatter_matrix(recent_grads[['Sample_size', 'Median']], figsize=(10,10))


# In[ ]: