Spaces:
Sleeping
Sleeping
changed emoji and cleaned up the article
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
title: Salary Predictor
|
3 |
-
emoji:
|
4 |
colorFrom: blue
|
5 |
colorTo: yellow
|
6 |
sdk: gradio
|
|
|
1 |
---
|
2 |
title: Salary Predictor
|
3 |
+
emoji: 💰
|
4 |
colorFrom: blue
|
5 |
colorTo: yellow
|
6 |
sdk: gradio
|
app.py
CHANGED
@@ -31,14 +31,24 @@ article = """ This project was built by Marie Pelletier <br/>
|
|
31 |
<a href="https://www.linkedin.com/in/marie-pelletier-14837441/">LinkedIn</a><br/>
|
32 |
<a href="https://github.com/Marie000">Github</a>
|
33 |
</p>
|
34 |
-
<p>This is a work in progress and is not meant to be used as an accurate predictor of
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
|
43 |
demo = gr.Interface(
|
44 |
fn=predict,
|
|
|
31 |
<a href="https://www.linkedin.com/in/marie-pelletier-14837441/">LinkedIn</a><br/>
|
32 |
<a href="https://github.com/Marie000">Github</a>
|
33 |
</p>
|
34 |
+
<p>This is a work in progress and is not meant to be used as an accurate predictor of
|
35 |
+
salary. It is limited by the <a
|
36 |
+
href="https://www.kaggle.com/datasets/arshkon/linkedin-job-postings/data">
|
37 |
+
data that was
|
38 |
+
used</a>,
|
39 |
+
which is US-based, from 2023. It also does not take into account regions or
|
40 |
+
fluctuations in the market over time. The dataset included over 33,000 job postings,
|
41 |
+
but only 13,000 had salary information.</p>
|
42 |
+
<p>For all you statistic nerds, the r-squared score of the model was around 0.6.
|
43 |
+
For the rest of you, that level of accuracy can probably be described as "better than
|
44 |
+
nothing". It might have been better if I had more data to work with. Or maybe there is
|
45 |
+
just so much we can infer from a description alone.</p>
|
46 |
+
|
47 |
+
<p>For this first test, only the description of the job is taken into account.
|
48 |
+
Adding other information, including the date of the posting and the location,
|
49 |
+
could improve the prediction.</p>
|
50 |
+
<p>The google colab notebook used to generate this model can be found
|
51 |
+
<a href="https://github.com/Marie000/Linkedin-predictor-model">here</a>"""
|
52 |
|
53 |
demo = gr.Interface(
|
54 |
fn=predict,
|