import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
recent_grads = pd.read_csv('recent-grads.csv')
recent_grads.iloc[0]
recent_grads.head()
recent_grads.tail()
recent_grads.describe()
raw_data_count = len(recent_grads)
raw_data_count
# Dropped any rows with missing values
recent_grads = recent_grads.dropna(axis = 0 , how = 'any')
cleaned_data_count = len(recent_grads)
cleaned_data_count
recent_grads.plot(x='Sample_size' , y = 'Median' , kind = 'scatter')
ax = 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')