In [1]:
import pandas as pd
In [2]:
employees = pd.read_excel('employee_data.xlsx')
In [3]:
employees.head(10)
Out[3]:
Employee Gender Age Prior Experience Beta Experience Education Annual Salary
0 1 1 39 5 12 4 57700
1 2 0 44 12 8 6 76400
2 3 0 24 0 2 4 44000
3 4 1 25 2 1 4 41600
4 5 0 56 5 25 8 163900
5 6 1 41 9 10 4 72700
6 7 1 33 6 2 6 60300
7 8 0 37 11 6 4 63500
8 9 1 51 12 16 6 131200
9 10 0 23 0 1 4 39200
In [4]:
emp_sorted = employees.sort_values('Age', ascending=False)
emp_sorted.head()
Out[4]:
Employee Gender Age Prior Experience Beta Experience Education Annual Salary
103 104 1 65 4 9 4 57800
93 94 1 64 5 7 4 55700
21 22 0 63 16 20 4 140400
101 102 0 61 9 15 6 109100
77 78 1 61 0 7 4 40500
In [5]:
emp_sorted = emp_sorted.reset_index(drop=True)
emp_sorted.head()
Out[5]:
Employee Gender Age Prior Experience Beta Experience Education Annual Salary
0 104 1 65 4 9 4 57800
1 94 1 64 5 7 4 55700
2 22 0 63 16 20 4 140400
3 102 0 61 9 15 6 109100
4 78 1 61 0 7 4 40500
In [7]:
emp_female = employees[employees['Gender']==1].reset_index(drop=True)
In [8]:
emp_female.head()
Out[8]:
Employee Gender Age Prior Experience Beta Experience Education Annual Salary
0 1 1 39 5 12 4 57700
1 4 1 25 2 1 4 41600
2 6 1 41 9 10 4 72700
3 7 1 33 6 2 6 60300
4 9 1 51 12 16 6 131200
In [9]:
emp_female.shape
Out[9]:
(119, 7)
In [10]:
emp_female['Age'].dtypes
Out[10]:
dtype('int64')
In [11]:
emp_female['Age'].mean()
Out[11]:
40.319327731092436
In [12]:
fem_mean = emp_female['Age'].mean()
round(fem_mean,2)
Out[12]:
40.32
In [13]:
emp_female['Annual Salary'].min()
Out[13]:
12400
In [14]:
emp_female['Age'].max()
Out[14]:
65
In [15]:
emp_female['Age'].median()
Out[15]:
42.0
In [16]:
emp_female['Total Experience'] = emp_female['Prior Experience']+emp_female['Beta Experience']
In [17]:
emp_female.head()
Out[17]:
Employee Gender Age Prior Experience Beta Experience Education Annual Salary Total Experience
0 1 1 39 5 12 4 57700 17
1 4 1 25 2 1 4 41600 3
2 6 1 41 9 10 4 72700 19
3 7 1 33 6 2 6 60300 8
4 9 1 51 12 16 6 131200 28
In [ ]:
emp_female.to_excel('emp_female.xlsx')
In [ ]: