In [1]:
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
In [2]:
recent_grads = pd.read_csv('recent-grads.csv')
In [3]:
recent_grads.iloc[0]
Out[3]:
In [4]:
recent_grads.head()
Out[4]:
In [5]:
recent_grads.tail()
Out[5]:
In [6]:
recent_grads.describe(include='all')
Out[6]:
Clean the data by removing rows with missing values
In [7]:
raw_data_count = recent_grads.shape[0]
recent_grads = recent_grads.dropna()
cleaned_data_count = recent_grads.shape[0]
print(raw_data_count, cleaned_data_count)
In [8]:
ax = recent_grads.plot(x='Sample_size', y='Employed', kind='scatter', title='Employed vs. Sample_size', figsize=(5,10))
In [9]:
recent_grads.plot(x='Sample_size', y='Median', kind='scatter')
Out[9]:
In [10]:
recent_grads.plot(x='Sample_size', y='Unemployment_rate', kind='scatter')
Out[10]:
In [11]:
recent_grads.plot(x='Full_time', y='Median', kind='scatter')
Out[11]:
In [12]:
recent_grads.plot(x='ShareWomen', y='Unemployment_rate', kind='scatter')
Out[12]:
In [13]:
recent_grads.plot(x='Men', y='Median', kind='scatter')
Out[13]:
In [14]:
recent_grads.plot(x='Women', y='Median', kind='scatter')
Out[14]:
Do students in more popular majors make more money?
- No Do students that majored in subjects that were majority female make more money?
- No Is there any link between the number of full-time employees and median salary?
- Highest salaries are with small amount of employees
In [15]:
recent_grads['Sample_size'].hist(bins=25, range=(0,5000))
Out[15]:
In [16]:
recent_grads['Median'].hist(bins=25, range=(20000, 50000))
Out[16]:
In [17]:
recent_grads['Employed'].hist(bins=25)
Out[17]:
In [18]:
recent_grads['Full_time'].hist(bins=25)
Out[18]:
In [19]:
recent_grads['ShareWomen'].hist(bins=25)
Out[19]:
In [20]:
recent_grads['Unemployment_rate'].hist(bins=25)
Out[20]:
In [21]:
recent_grads['Men'].hist(bins=25, range=(0,75000))
Out[21]:
In [22]:
recent_grads['Women'].hist(bins=25, range=(0,75000))
Out[22]:
What percent of majors are predominantly male?
- ? Predominantly female?
- ? What's the most common median salary range?
- 20000, 50000
In [23]:
from pandas.plotting import scatter_matrix
scatter_matrix(recent_grads[['Sample_size','Median']], figsize=(10,10))
Out[23]:
In [24]:
scatter_matrix(recent_grads[['Sample_size','Median','Unemployment_rate']], figsize=(10,10))
Out[24]:
In [25]:
recent_grads[:10].plot.bar(x='Major', y='ShareWomen')
Out[25]:
In [26]:
recent_grads[-10:].plot.bar(x='Major', y='ShareWomen')
Out[26]:
In [27]:
recent_grads[:10].plot.bar(x='Major', y='Unemployment_rate')
Out[27]:
In [28]:
recent_grads[-10:].plot.bar(x='Major', y='Unemployment_rate')
Out[28]:
Other visualization explored on my own¶
Grouped bar plot¶
This plot shows quantity of men and women in each category of majors
In [29]:
(recent_grads[['Major_category','Men','Women']]
.groupby(['Major_category'])
.sum()
.plot.bar())
Out[29]:
Box plot¶
Distributions of median salaries and unemployment rate
In [30]:
recent_grads[['Median']].boxplot()
Out[30]:
In [31]:
recent_grads[['Unemployment_rate']].boxplot()
Out[31]:
Hexagonal bin plot¶
In [34]:
recent_grads.plot.hexbin(x='Women', y='Median',gridsize=25)
Out[34]:
In [37]:
recent_grads.plot.hexbin(x='Men', y='Median',gridsize=25)
Out[37]:
In [ ]: