Upload app.py

app.py

@@ -0,0 +1,73 @@
+import os
+os.system('pip install openpyxl')
+os.system('pip install sentence-transformers')
+import pandas as pd
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer('all-mpnet-base-v2') #all-MiniLM-L6-v2 #all-mpnet-base-v2
+
+df = pd.read_parquet('df_encoded.parquet')
+df
+
+from sklearn.neighbors import NearestNeighbors
+import numpy as np
+import pandas as pd
+
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer('all-mpnet-base-v2') #all-MiniLM-L6-v2 #all-mpnet-base-v2
+
+#prepare model
+# nbrs = NearestNeighbors(n_neighbors=8, algorithm='ball_tree').fit(df['text_vector_'].values.tolist())
+
+def filter_df(df, column_name, filter_type, filter_value):
+    if filter_type == '==':
+        df_filtered = df[df[column_name]==filter_value]
+    elif filter_type == '<=':
+        df_filtered = df[df[column_name]<=filter_value]
+    return df_filtered
+
+def search(df, query):
+    product = model.encode(query).tolist()
+    # product = df.iloc[0]['text_vector_'] #use one of the products as sample
+
+    nbrs = NearestNeighbors(n_neighbors=8, algorithm='ball_tree').fit(df['text_vector_'].values.tolist())
+    distances, indices = nbrs.kneighbors([product]) #input the vector of the reference object
+
+    #print out the description of every recommended product
+    df_search = df.iloc[list(indices)[0]].drop(['skills', 'text_vector_'], axis=1).sort_values('avgFeedbackScore', ascending=False)
+
+    return df_search[['shortName', 'location', 'title', 'hourlyRate', 'avgFeedbackScore', 'description']]
+
+# search('I want to hire a person who does both backend and')
+
+df_location = filter_df(df, 'location', '==', 'New York')
+df_price = filter_df(df_location, 'hourlyRate', '<=', 80)
+search(df_price, 'I want to hire a person who does both backend and')
+
+import gradio as gr
+import os
+
+#the first module becomes text1, the second module file1
+def greet(price, location, query):
+    # df1 = 
+    df_location = filter_df(df, 'location', '==', location)
+    df_price = filter_df(df_location, 'hourlyRate', '<=', price)
+    df_search = search(df_price, query)
+    return df_search
+
+with gr.Blocks(theme=gr.themes.Soft(primary_hue='amber', secondary_hue='gray', neutral_hue='amber')) as demo:
+    gr.Markdown(
+    """
+    # Freelancer Upwork Search
+    """
+    )
+    input1 = gr.Slider(20, 120, value=90, step_size=5, label="Max Hourly Rate")
+    input2 = gr.Radio(['New York', 'Chicago', 'Washington'], multiselect=False, label='State', value='New York')
+    input3 = gr.Textbox(label='Query', value='I want to develop a mobile app')
+
+    btn = gr.Button(value="Search for Product")
+    output = gr.Dataframe()
+    # btn.click(greet, inputs='text', outputs=['dataframe'])
+    btn.click(greet, [input1, input2, input3], [output])
+demo.launch(share=True)