forked from PlayingNumbers/ds_salary_proj
-
Notifications
You must be signed in to change notification settings - Fork 0
/
data_cleaning.py
65 lines (43 loc) · 1.96 KB
/
data_cleaning.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
# -*- coding: utf-8 -*-
"""
Created on Sat Apr 4 17:27:06 2020
@author: Ken
"""
import pandas as pd
df = pd.read_csv('glassdoor_jobs.csv')
#salary parsing
df['hourly'] = df['Salary Estimate'].apply(lambda x: 1 if 'per hour' in x.lower() else 0)
df['employer_provided'] = df['Salary Estimate'].apply(lambda x: 1 if 'employer provided salary:' in x.lower() else 0)
df = df[df['Salary Estimate'] != '-1']
salary = df['Salary Estimate'].apply(lambda x: x.split('(')[0])
minus_Kd = salary.apply(lambda x: x.replace('K','').replace('$',''))
min_hr = minus_Kd.apply(lambda x: x.lower().replace('per hour','').replace('employer provided salary:',''))
df['min_salary'] = min_hr.apply(lambda x: int(x.split('-')[0]))
df['max_salary'] = min_hr.apply(lambda x: int(x.split('-')[1]))
df['avg_salary'] = (df.min_salary+df.max_salary)/2
#Company name text only
df['company_txt'] = df.apply(lambda x: x['Company Name'] if x['Rating'] <0 else x['Company Name'][:-3], axis = 1)
#state field
df['job_state'] = df['Location'].apply(lambda x: x.split(',')[1])
df.job_state.value_counts()
df['same_state'] = df.apply(lambda x: 1 if x.Location == x.Headquarters else 0, axis = 1)
#age of company
df['age'] = df.Founded.apply(lambda x: x if x <1 else 2020 - x)
#parsing of job description (python, etc.)
#python
df['python_yn'] = df['Job Description'].apply(lambda x: 1 if 'python' in x.lower() else 0)
#r studio
df['R_yn'] = df['Job Description'].apply(lambda x: 1 if 'r studio' in x.lower() or 'r-studio' in x.lower() else 0)
df.R_yn.value_counts()
#spark
df['spark'] = df['Job Description'].apply(lambda x: 1 if 'spark' in x.lower() else 0)
df.spark.value_counts()
#aws
df['aws'] = df['Job Description'].apply(lambda x: 1 if 'aws' in x.lower() else 0)
df.aws.value_counts()
#excel
df['excel'] = df['Job Description'].apply(lambda x: 1 if 'excel' in x.lower() else 0)
df.excel.value_counts()
df.columns
df_out = df.drop(['Unnamed: 0'], axis =1)
df_out.to_csv('salary_data_cleaned.csv',index = False)