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

# # Guided Project: Visualizing Earnings Based on College Majors

# ### Installing the necessary libaries

# In[1]:


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


# In[2]:


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


# First we want to find out how the Table "recent grads" looks like and try to better understand it

# In[3]:


recent_grads.iloc[[0]]


# In[4]:


recent_grads.head()


# In[5]:


recent_grads.tail()


# We can see between the lowest and highest ranked majors, that the discrepancy between them is up to 80k$.

# In[6]:


recent_grads.describe()


# Some of the rows how more counts then the others (173 / 172)

# In[7]:


raw_data_count = recent_grads.count()
raw_data_count


# e 

# In[8]:


recent_grads_drop = recent_grads.dropna(0)
recent_grads_drop


# In[9]:


recent_grads_drop_desc = recent_grads_drop.describe()
recent_grads_drop_desc


# In[10]:


recent_grads_drop_count = recent_grads_drop.count()
recent_grads_drop_count


# We dropped all empty fields. They all have now the same number (172).

# In[11]:


recent_grads_drop_count_desc = recent_grads_drop_count.describe()
recent_grads_drop_count_desc


# In[12]:


recent_grads = recent_grads_drop
recent_grads


# In[13]:


cleaned_data_count = recent_grads.count()
cleaned_data_count


# In[14]:


recent_grads.plot(x='Sample_size', y='Median', kind='scatter')


# In[15]:


recent_grads.plot(x='Sample_size', y='Unemployment_rate', kind='scatter')


# In[16]:


recent_grads.plot(x='Full_time', y='Median', kind='scatter')


# In[17]:


recent_grads.plot(x='ShareWomen', y='Unemployment_rate', kind='scatter')


# In[18]:


recent_grads.plot(x='Men', y='Median', kind='scatter')


# In[19]:


recent_grads.plot(x='Women', y='Median', kind='scatter')


# INFOS

# In[20]:


recent_grads.plot(x='ShareWomen', y='Median', kind='scatter')


# In[21]:


recent_grads.plot(x='Total', y='Median', kind='scatter')


# Questions: 
# 
# 1) Do students in more popular majors make more money?
# -> No! Not neceserrally 
# 2) Do students that majored in subjects that were majority female make more money?
# -> No! Majors were the majority are women earn i nthe median less.
# 3) Is there any link between the number of full-time employees and median salary?
# -> Not if we just look at the number of full-time employees - but if we are looking at the share between full-time and part-time we could find out, whether full-time gives higher salaries.
# 

# We will generate histograms in separate jupyter notebook cells to explore the distributions of the following columns:
#     Sample_size
#     Median
#     Employed
#     Full_time
#     ShareWomen
#     Unemployment_rate
#     Men
#     Women
# 

# In[22]:


recent_grads['Sample_size'].hist(bins=25, range=(0,5000))


# In[30]:


recent_grads['Median'].hist(bins=25, range=(0,5000))


# In[31]:


recent_grads['Employed'].hist(bins=25, range=(0,5000))


# In[32]:


recent_grads['Full_time'].hist(bins=25, range=(0,5000))


# In[34]:


recent_grads['ShareWomen'].hist(bins=5, range=(0,5000))


# In[36]:


recent_grads['Unemployment_rate'].hist(bins=25, range=(0,5000))


# In[37]:


recent_grads['Men'].hist(bins=25, range=(0,5000))


# In[38]:


recent_grads['Women'].hist(bins=25, range=(0,5000))


# In[47]:


cols = ["Sample_size", "Median", "Employed", "Full_time", "ShareWomen", "Unemployment_rate", "Men", "Women"]

fig = plt.figure(figsize=(5,12))
for r in range(0,4):
    ax = fig.add_subplot(4,1,r+1)
    ax = recent_grads[cols[r]].plot(kind='hist', rot=30)



# In[ ]: