cleaning_data.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Sat Aug 14 12:05:53 2021

@author: gintriag
"""

import pandas as pd

df = pd.read_csv("glassdoor_jobs.csv")

# Parsing the salary


# A column for per-hour, and a column for employer provided salary
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'] # Remove rows with -1 in the Salary Estimate column
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

# Only the company name text
df['company_txt'] = df.apply(lambda x: x['Company Name'] if x['Rating'] <0 else x['Company Name'][:-3], axis = 1)

# Field corresponding to the state
df['job_state'] = df['Location'].apply(lambda x: x.split(',')[1])
df['job_headquarters'] = df['Headquarters'].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)

# Company's age
df['age'] = df.Founded.apply(lambda x: x if x <1 else 2021 - x)

# Job description's parsing

# python
df['python_yn'] = df['Job Description'].apply(lambda x: 1 if 'python' in x.lower() else 0)
print(df.python_yn.value_counts())
# 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)
print(df.R_yn.value_counts())

# spark
df['spark_yn'] = df['Job Description'].apply(lambda x: 1 if 'spark' in x.lower() else 0)
print(df.spark_yn.value_counts())

# aws
df['aws_yn'] = df['Job Description'].apply(lambda x: 1 if 'aws' in x.lower() else 0)
print(df.aws_yn.value_counts())

# excel
df['excel_yn'] = df['Job Description'].apply(lambda x: 1 if 'excel' in x.lower() else 0)
print(df.excel_yn.value_counts())

df.columns
df_out = df.drop(['Unnamed: 0'],axis=1)
df_out.to_csv('salary_data_cleaning.csv',index = False)