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

# In[22]:


import pandas as pd
import matplotlib.pyplot as plt
print('done')


# In[23]:


get_ipython().run_line_magic('matplotlib', 'inline')


# In[24]:


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


# In[25]:


recent_grads.iloc[0]


# In[52]:


recent_grads['Unemployment_rate']=recent_grads['Unemployment_rate'].astype(int)


# In[56]:


recent_grads['Unemployment_rate'].value_counts()


# In[26]:


recent_grads.describe()


# In[27]:


recent_grads=recent_grads.dropna()
recent_grads.describe().count()


# In[28]:


cleaned_data_count=recent_grads.shape[0]
print('Rows: ',cleaned_data_count)


# In[29]:


recent_grads.plot(x='Sample_size',y='Median', kind='scatter')
recent_grads.plot(x='Sample_size',y='Unemployment_rate', kind='scatter')
recent_grads.plot(x='Full_time',y='Median', kind='scatter')
recent_grads.plot(x='ShareWomen',y='Unemployment_rate', kind='scatter')
recent_grads.plot(x='Men',y='Median', kind='scatter')
recent_grads.plot(x='Women',y='Median', kind='scatter')


# In[30]:


recent_grads['Sample_size'].hist(bins=20, range=(0,1500))


# In[31]:


recent_grads['Sample_size'].hist(bins=15, range=(0,3000))


# In[32]:


recent_grads['Median'].hist()


# In[33]:


recent_grads['Employed'].hist()


# In[34]:


recent_grads['Full_time'].hist(bins=35, range=(0,150000))


# In[35]:


recent_grads['ShareWomen'].hist()


# In[36]:


recent_grads['Unemployment_rate'].hist()


# In[37]:


recent_grads['Men'].hist()


# In[38]:


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


# In[39]:


from pandas.plotting import scatter_matrix


# In[40]:


scatter_matrix(recent_grads[['Sample_size','Median']], figsize=(4,4))


# In[41]:


scatter_matrix(recent_grads[['Sample_size','Median','Unemployment_rate']], figsize=(6,6))


# In[49]:


#recent_grads[:10]["ShareWomen"].plot(kind='bar')
recent_grads[:-10]["ShareWomen"].plot(kind='bar')


# In[58]:


recent_grads[:10].plot.bar(x='Unemployment_rate', y='ShareWomen', legend=False)
recent_grads[163:].plot.bar(x='Unemployment_rate', y='ShareWomen',legend=False)


# In[ ]: