I'm building a resume parser that can extract 'skills' from a resume.
I'm extracting the resume skills by comparing the resume text with a dataset (a CSV file that contains about 38k technical skills). If there's a match, the matched words should be returned as a list.
What I have tried:
#Loading the dataset & viewing it's contents
import pandas as pd
skills_data=pd.read_csv('/content/drive/My Drive/skills.csv')
df=skills_data.copy()
df.head()
Output-->
Skill
0 supply chain engineering\n
1 bullet\n
2 commutations\n
3 pay equity\n
4 student retention\n
#Converting CSV values to list & checking the values
skill_list=[df.values.tolist()]
skill_list
Output-->
[[['supply chain engineering\n'],
['bullet\n'],
['commutations\n'],
['pay equity\n'],
['student retention\n'],
['pulsar'],
['hevacomp\n'],
['travel insurance\n'],
['payback\n'],
['soaps\n'],
['erdf\n'],
['3d simulation\n'],
['中級\n'],
['server side\n'],
['filemaker server\n']]]
#Matching the Skills
y=text.split()
for sk in skill_list:
for txt in y:
if sk==txt:
print (txt)
Output-->
Nothing
There are no errors in my code, but no output either. How do I match the words & how do I ensure that they are not case sensitive?