In [1]:
import warnings
warnings.filterwarnings('ignore')
from IPython.display import display, clear_output
from __future__ import print_function
from ipywidgets import interact, interactive, fixed, interact_manual, Layout
import ipywidgets as widgets
from IPython.display import display
import matplotlib.pyplot as plt
%matplotlib inline
import pandas as pd
from numpy import median
from openpyxl import Workbook
import plotly
import numpy as np
import statistics
import plotly.express as px
%matplotlib widget
import plotly.graph_objects as go
import plotly.io as pio
pio.renderers.default='notebook'
In [2]:
Data = pd.read_csv('/Users/codywang/Library/Containers/com.microsoft.Excel/Data/Downloads/Classof2022CareerOutcomes1.csv')
Data.head()
Out[2]:
Program Graduation Year Undergraduate Major Active Include in Reporting Industry With what company will you be employed after graduation? Job Title US State / Canada Province City Base Salary Base Salary Pay Period Estimated Total Compensation Estimated Total Compensation Pay Period Reported Date
0 Undergrad Business 2022 Accounting Yes Yes Financial Services Deloitte Audit Associate Georgia Atlanta - GA $60,000.00 per year $60,000.00 per year 05/19/2022
1 Undergrad Business 2022 Finance Yes Yes Consulting Deloitte Analyst Massachusetts Boston - MA $80,000.00 per year $80,000.00 per year 06/28/2022
2 Undergrad Business 2022 Financial Management Yes Yes NaN Vandley Industries NaN NaN NaN NaN NaN NaN NaN 04/25/2022
3 Undergrad Business 2022 Financial Management Yes Yes NaN Key Bank Banking Teller Connecticut West Hartford - CT $42,850.00 per year $42,850.00 per year 06/13/2022
4 Undergrad Business 2022 Digital Marketing and Analytics Yes Yes Consulting AlphaSights Client Service Associate New York New York - NY $70,000.00 per year $70,000.00 per year 04/22/2022
In [6]:
major = Data['Undergraduate Major'].value_counts()
major.to_excel('Majors_ALL.xlsx',
               sheet_name='1')
df1 = pd.read_excel('Majors_ALL.xlsx')
df1.columns = ['Majors', 'Number of People']
values1 = df1['Number of People']
names1 = df1['Majors']
fig1 = px.pie(df1,
              values=values1,
              names=names1,
              title="Students' major distribution"
              )
fig1.update_traces(
    textposition='outside',
    textinfo='percent+label'
)
fig1.update_layout(showlegend=False)

fig1.show()
In [18]:
plotly.offline.plot(fig1,filename='majors.html',config={'displayModeBar': False})
Out[18]:
'majors.html'
In [12]:
where = Data['With what company will you be employed after graduation?'].value_counts()[:15].sort_values(ascending=False)
where.to_excel('Companies_ALL.xlsx',
               sheet_name='1')  # after companies use _ to distinguish each department. eg. companies_BUSN
df2 = pd.read_excel('Companies_ALL.xlsx')
df2.columns = ['companies', 'numbers']
values2 = df2['numbers']
names2 = df2['companies']

fig2 = px.pie(df2,
              values=values2,
              names=names2,
              title='Companies that hired our students'
              )
fig2.update_traces(
    textposition='outside',
    textinfo='percent+label'
)
fig2.show()
In [17]:
plotly.offline.plot(fig2,filename='companies.html',config={'displayModeBar': False})
Out[17]:
'companies.html'
In [14]:
industry = Data['Industry'].value_counts()
industry.to_excel('Industry_ALL.xlsx', sheet_name='1')
df3 = pd.read_excel('Industry_ALL.xlsx')
df3.columns = ['Industries', 'numbers']
values3 = df3['numbers']
names3 = df3['Industries']
fig3 = px.pie(df3,
              values=values3,
              names=names3,
              title='Industries that students work for'
              )
fig3.update_traces(
    textposition='outside',
    textinfo='percent+label'
)
fig3.show()
In [16]:
plotly.offline.plot(fig3,filename='industry.html',config={'displayModeBar': False})
Out[16]:
'industry.html'