The dataset is stored in recent-grads.csv file.It contains information on earnings of college majors in US from 2010 to 2012.
It can be download form here：https://github.com/fivethirtyeight/data/tree/master/college-majors
In this project,I will explore the dataset and try to find some patterns in the earning of majors then plot it use matplotlib library.
代码使用jupyter完成：
读取数据：
import pandas as pd
recent_grads=pd.read_csv('./data/recent-grads.csv')
recent_grads.columns
print(recent_grads.info())
print(recent_grads.describe())
print(recent_grads.head(1))
处理缺失值:
raw_data_count=recent_grads.shape[0]
print(raw_data_count)
cleaned_data_count=recent_grads.dropna().shape[0]
print(cleaned_data_count)
==>>173
172
绘制散点图，查看各属性之间的关系：
import matplotlib.pyplot as plt
%matplotlib inline
recent_grads.plot(x='Full_time',y='Median',kind='scatter')
recent_grads.plot(x='Unemployed',y='Median',kind='scatter')
recent_grads.plot(x='Men',y='Median',kind='scatter')
recent_grads.plot(x='Women',y='Median',kind='scatter')
得到
我们继续绘制柱状图，查看各属性的分布情况：
columns=['Median','Employed','Employed','Unemployment_rate','Women','Men']
['Men'].hist()
fig=plt.figure(figsize=(6,18))
for i,col in enumerate(columns):
ax=fig.add_subplot(6,1,i+1)
ax=recent_grads[col].hist(color='orange')
plt.show()
为了更方便的查看就业人数与薪资的关系，使用scatter_matrix函数来构建散点图矩阵：
from pandas.tools.plotting import scatter_matrix
scatter_matrix(recent_grads[['Employed','Median']],figsize=(10,10),c=['red','blue'])
关于该矩阵的说明：
接下来不妨做些有意思的事情，分析一下薪资前10以及后10的专业中女生所占比例：
recent_grads[:10].plot.bar(x='Major',y='ShareWomen')
plt.legend(loc='upper left')
plt.title('The 10 highest paying majors.')
recent_grads[162:].plot(x='Major',y='ShareWomen',kind='bar')
plt.title('The 10 lowest paying majors.')
分析薪资较高的专业中的男女性别比例：
recent_grads[:10].plot.bar(x='Major',y=['Men','Women'])
