Spaces:
Runtime error
Runtime error
Michelangiolo
commited on
Commit
•
5f36b0b
1
Parent(s):
b24850f
Upload app.py
Browse files
app.py
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
os.system('pip install openpyxl')
|
3 |
+
os.system('pip install sentence-transformers')
|
4 |
+
import pandas as pd
|
5 |
+
from sentence_transformers import SentenceTransformer
|
6 |
+
|
7 |
+
model = SentenceTransformer('all-mpnet-base-v2') #all-MiniLM-L6-v2 #all-mpnet-base-v2
|
8 |
+
|
9 |
+
df = pd.read_parquet('df_encoded.parquet')
|
10 |
+
df
|
11 |
+
|
12 |
+
from sklearn.neighbors import NearestNeighbors
|
13 |
+
import numpy as np
|
14 |
+
import pandas as pd
|
15 |
+
|
16 |
+
from sentence_transformers import SentenceTransformer
|
17 |
+
|
18 |
+
model = SentenceTransformer('all-mpnet-base-v2') #all-MiniLM-L6-v2 #all-mpnet-base-v2
|
19 |
+
|
20 |
+
#prepare model
|
21 |
+
# nbrs = NearestNeighbors(n_neighbors=8, algorithm='ball_tree').fit(df['text_vector_'].values.tolist())
|
22 |
+
|
23 |
+
def filter_df(df, column_name, filter_type, filter_value):
|
24 |
+
if filter_type == '==':
|
25 |
+
df_filtered = df[df[column_name]==filter_value]
|
26 |
+
elif filter_type == '<=':
|
27 |
+
df_filtered = df[df[column_name]<=filter_value]
|
28 |
+
return df_filtered
|
29 |
+
|
30 |
+
def search(df, query):
|
31 |
+
product = model.encode(query).tolist()
|
32 |
+
# product = df.iloc[0]['text_vector_'] #use one of the products as sample
|
33 |
+
|
34 |
+
nbrs = NearestNeighbors(n_neighbors=8, algorithm='ball_tree').fit(df['text_vector_'].values.tolist())
|
35 |
+
distances, indices = nbrs.kneighbors([product]) #input the vector of the reference object
|
36 |
+
|
37 |
+
#print out the description of every recommended product
|
38 |
+
df_search = df.iloc[list(indices)[0]].drop(['skills', 'text_vector_'], axis=1).sort_values('avgFeedbackScore', ascending=False)
|
39 |
+
|
40 |
+
return df_search[['shortName', 'location', 'title', 'hourlyRate', 'avgFeedbackScore', 'description']]
|
41 |
+
|
42 |
+
# search('I want to hire a person who does both backend and')
|
43 |
+
|
44 |
+
df_location = filter_df(df, 'location', '==', 'New York')
|
45 |
+
df_price = filter_df(df_location, 'hourlyRate', '<=', 80)
|
46 |
+
search(df_price, 'I want to hire a person who does both backend and')
|
47 |
+
|
48 |
+
import gradio as gr
|
49 |
+
import os
|
50 |
+
|
51 |
+
#the first module becomes text1, the second module file1
|
52 |
+
def greet(price, location, query):
|
53 |
+
# df1 =
|
54 |
+
df_location = filter_df(df, 'location', '==', location)
|
55 |
+
df_price = filter_df(df_location, 'hourlyRate', '<=', price)
|
56 |
+
df_search = search(df_price, query)
|
57 |
+
return df_search
|
58 |
+
|
59 |
+
with gr.Blocks(theme=gr.themes.Soft(primary_hue='amber', secondary_hue='gray', neutral_hue='amber')) as demo:
|
60 |
+
gr.Markdown(
|
61 |
+
"""
|
62 |
+
# Freelancer Upwork Search
|
63 |
+
"""
|
64 |
+
)
|
65 |
+
input1 = gr.Slider(20, 120, value=90, step_size=5, label="Max Hourly Rate")
|
66 |
+
input2 = gr.Radio(['New York', 'Chicago', 'Washington'], multiselect=False, label='State', value='New York')
|
67 |
+
input3 = gr.Textbox(label='Query', value='I want to develop a mobile app')
|
68 |
+
|
69 |
+
btn = gr.Button(value="Search for Product")
|
70 |
+
output = gr.Dataframe()
|
71 |
+
# btn.click(greet, inputs='text', outputs=['dataframe'])
|
72 |
+
btn.click(greet, [input1, input2, input3], [output])
|
73 |
+
demo.launch(share=True)
|