Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -6,10 +6,24 @@ import networkx as nx
|
|
| 6 |
import matplotlib.pyplot as plt
|
| 7 |
import csv
|
| 8 |
import datetime
|
|
|
|
| 9 |
|
| 10 |
# Sentence-BERT ๋ชจ๋ธ ๋ก๋
|
| 11 |
model = SentenceTransformer('all-MiniLM-L6-v2')
|
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
# ์ถ์ฒ ๊ฒฐ๊ณผ์ ํผ๋๋ฐฑ์ ๊ธฐ๋กํ๋ ํจ์
|
| 14 |
def log_recommendation(employee_name, recommended_programs, feedback=None):
|
| 15 |
with open('recommendation_log.csv', mode='a', newline='') as file:
|
|
@@ -19,34 +33,41 @@ def log_recommendation(employee_name, recommended_programs, feedback=None):
|
|
| 19 |
|
| 20 |
# ์ง์ ๋ฐ์ดํฐ๋ฅผ ๋ถ์ํ์ฌ ๊ต์ก ํ๋ก๊ทธ๋จ์ ์ถ์ฒํ๊ณ ๊ทธ๋ํ๋ฅผ ๊ทธ๋ฆฌ๋ ํจ์
|
| 21 |
def analyze_data(employee_file, program_file, feedback=None):
|
|
|
|
| 22 |
employee_df = pd.read_csv(employee_file.name)
|
| 23 |
program_df = pd.read_csv(program_file.name)
|
| 24 |
|
|
|
|
| 25 |
employee_skills = employee_df['current_skills'].tolist()
|
| 26 |
program_skills = program_df['skills_acquired'].tolist()
|
| 27 |
employee_embeddings = model.encode(employee_skills)
|
| 28 |
program_embeddings = model.encode(program_skills)
|
| 29 |
|
|
|
|
| 30 |
similarities = cosine_similarity(employee_embeddings, program_embeddings)
|
| 31 |
|
|
|
|
| 32 |
recommendations = []
|
|
|
|
| 33 |
for i, employee in employee_df.iterrows():
|
| 34 |
recommended_programs = []
|
| 35 |
for j, program in program_df.iterrows():
|
| 36 |
-
if similarities[i][j] > 0.5:
|
| 37 |
recommended_programs.append(f"{program['program_name']} ({program['duration']})")
|
| 38 |
|
| 39 |
if recommended_programs:
|
| 40 |
recommendation = f"์ง์ {employee['employee_name']}์ ์ถ์ฒ ํ๋ก๊ทธ๋จ: {', '.join(recommended_programs)}"
|
|
|
|
| 41 |
else:
|
| 42 |
recommendation = f"์ง์ {employee['employee_name']}์๊ฒ ์ ํฉํ ํ๋ก๊ทธ๋จ์ด ์์ต๋๋ค."
|
|
|
|
| 43 |
|
|
|
|
| 44 |
log_recommendation(employee['employee_name'], recommended_programs, feedback)
|
| 45 |
|
| 46 |
recommendations.append(recommendation)
|
| 47 |
|
| 48 |
-
|
| 49 |
-
|
| 50 |
G = nx.Graph()
|
| 51 |
for employee in employee_df['employee_name']:
|
| 52 |
G.add_node(employee, type='employee')
|
|
@@ -56,16 +77,20 @@ def analyze_data(employee_file, program_file, feedback=None):
|
|
| 56 |
|
| 57 |
for i, employee in employee_df.iterrows():
|
| 58 |
for j, program in program_df.iterrows():
|
| 59 |
-
if similarities[i][j] > 0.5:
|
| 60 |
G.add_edge(employee['employee_name'], program['program_name'])
|
| 61 |
|
|
|
|
| 62 |
plt.figure(figsize=(10, 8))
|
| 63 |
pos = nx.spring_layout(G)
|
| 64 |
nx.draw(G, pos, with_labels=True, node_color='skyblue', node_size=2000, font_size=10, font_weight='bold')
|
| 65 |
plt.title("์ง์๊ณผ ํ๋ก๊ทธ๋จ ๊ฐ์ ๊ด๊ณ")
|
| 66 |
plt.tight_layout()
|
| 67 |
|
| 68 |
-
|
|
|
|
|
|
|
|
|
|
| 69 |
|
| 70 |
# ์์ ๋ฐ์ดํฐ๋ฅผ ๋ณด์ฌ์ฃผ๋ ํจ์
|
| 71 |
def show_example_data():
|
|
@@ -97,30 +122,17 @@ with gr.Blocks() as demo:
|
|
| 97 |
with gr.Column(scale=1):
|
| 98 |
gr.Markdown("# HybridRAG ์์คํ
")
|
| 99 |
|
| 100 |
-
#
|
| 101 |
-
|
| 102 |
-
|
| 103 |
-
|
| 104 |
-
|
| 105 |
-
|
| 106 |
-
|
| 107 |
-
|
| 108 |
-
|
| 109 |
-
|
| 110 |
-
|
| 111 |
-
output_text = gr.Textbox(label="๋ถ์ ๊ฒฐ๊ณผ")
|
| 112 |
-
|
| 113 |
-
# HR ๊ด๋ฆฌ์๋ง ์ฌ์ฉํ ์ ์๋ ๊ธฐ๋ฅ์ ์ถ๊ฐ
|
| 114 |
-
feedback_input = gr.Radio(choices=["๋ง์กฑ", "๋ถ๋ง์กฑ"], label="์ง์ ํผ๋๋ฐฑ ๊ธฐ๋ก")
|
| 115 |
-
|
| 116 |
-
analyze_button.click(analyze_data, inputs=[employee_file, program_file, feedback_input], outputs=[output_text])
|
| 117 |
-
|
| 118 |
-
with gr.Tab("์ง์"):
|
| 119 |
-
with gr.Box(visible=True) as employee_box:
|
| 120 |
-
gr.Markdown("## ์ง์ ์ธํฐํ์ด์ค")
|
| 121 |
-
gr.Markdown("์ง์์๊ฒ ๋ง์ถคํ ๊ต์ก ํ๋ก๊ทธ๋จ ์ถ์ฒ์ ์ ๊ณตํฉ๋๋ค.")
|
| 122 |
-
employee_data = gr.DataFrame(label="์ง์ ๊ฐ์ธ ๋ฐ์ดํฐ ์์")
|
| 123 |
-
gr.Button("ํ๋ก๊ทธ๋จ ์ถ์ฒ ์์")
|
| 124 |
|
| 125 |
# ์์ ๋ฐ์ดํฐ๋ฅผ ๋ฏธ๋ฆฌ๋ณด๊ธฐ๋ก ์ ๊ณต
|
| 126 |
example_button = gr.Button("์์ ๋ฐ์ดํฐ ๋ณด๊ธฐ")
|
|
@@ -128,5 +140,16 @@ with gr.Blocks() as demo:
|
|
| 128 |
program_example_output = gr.DataFrame(label="๊ต์ก ํ๋ก๊ทธ๋จ ๋ฐ์ดํฐ ์์")
|
| 129 |
example_button.click(show_example_data, outputs=[employee_example_output, program_example_output])
|
| 130 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 131 |
# Gradio ์ธํฐํ์ด์ค ์คํ
|
| 132 |
demo.launch()
|
|
|
|
| 6 |
import matplotlib.pyplot as plt
|
| 7 |
import csv
|
| 8 |
import datetime
|
| 9 |
+
import io
|
| 10 |
|
| 11 |
# Sentence-BERT ๋ชจ๋ธ ๋ก๋
|
| 12 |
model = SentenceTransformer('all-MiniLM-L6-v2')
|
| 13 |
|
| 14 |
+
# ์ถ์ฒ ๊ฒฐ๊ณผ๋ฅผ CSV ํ์ผ๋ก ์ ์ฅํ๋ ํจ์
|
| 15 |
+
def save_recommendations_to_csv(recommendations):
|
| 16 |
+
output = io.StringIO()
|
| 17 |
+
writer = csv.writer(output)
|
| 18 |
+
writer.writerow(["Employee ID", "Employee Name", "Recommended Programs"])
|
| 19 |
+
|
| 20 |
+
# ์ถ์ฒ ๊ฒฐ๊ณผ CSV ํ์ผ์ ๊ธฐ๋ก
|
| 21 |
+
for rec in recommendations:
|
| 22 |
+
writer.writerow(rec)
|
| 23 |
+
|
| 24 |
+
output.seek(0)
|
| 25 |
+
return output
|
| 26 |
+
|
| 27 |
# ์ถ์ฒ ๊ฒฐ๊ณผ์ ํผ๋๋ฐฑ์ ๊ธฐ๋กํ๋ ํจ์
|
| 28 |
def log_recommendation(employee_name, recommended_programs, feedback=None):
|
| 29 |
with open('recommendation_log.csv', mode='a', newline='') as file:
|
|
|
|
| 33 |
|
| 34 |
# ์ง์ ๋ฐ์ดํฐ๋ฅผ ๋ถ์ํ์ฌ ๊ต์ก ํ๋ก๊ทธ๋จ์ ์ถ์ฒํ๊ณ ๊ทธ๋ํ๋ฅผ ๊ทธ๋ฆฌ๋ ํจ์
|
| 35 |
def analyze_data(employee_file, program_file, feedback=None):
|
| 36 |
+
# ์ง์ ๋ฐ์ดํฐ์ ๊ต์ก ํ๋ก๊ทธ๋จ ๋ฐ์ดํฐ ๋ถ๋ฌ์ค๊ธฐ
|
| 37 |
employee_df = pd.read_csv(employee_file.name)
|
| 38 |
program_df = pd.read_csv(program_file.name)
|
| 39 |
|
| 40 |
+
# ์ง์ ์ญ๋๊ณผ ํ๋ก๊ทธ๋จ ํ์ต ๋ชฉํ๋ฅผ ๋ฒกํฐํ
|
| 41 |
employee_skills = employee_df['current_skills'].tolist()
|
| 42 |
program_skills = program_df['skills_acquired'].tolist()
|
| 43 |
employee_embeddings = model.encode(employee_skills)
|
| 44 |
program_embeddings = model.encode(program_skills)
|
| 45 |
|
| 46 |
+
# ์ ์ฌ๋ ๊ณ์ฐ
|
| 47 |
similarities = cosine_similarity(employee_embeddings, program_embeddings)
|
| 48 |
|
| 49 |
+
# ์ง์๋ณ ์ถ์ฒ ํ๋ก๊ทธ๋จ ๋ฆฌ์คํธ
|
| 50 |
recommendations = []
|
| 51 |
+
recommendation_rows = [] # CSV ํ์ผ์ ์ ์ฅํ ๋ฐ์ดํฐ๋ฅผ ์ํ ๋ฆฌ์คํธ
|
| 52 |
for i, employee in employee_df.iterrows():
|
| 53 |
recommended_programs = []
|
| 54 |
for j, program in program_df.iterrows():
|
| 55 |
+
if similarities[i][j] > 0.5: # ์ ์ฌ๋ ์๊ณ๊ฐ ๊ธฐ์ค
|
| 56 |
recommended_programs.append(f"{program['program_name']} ({program['duration']})")
|
| 57 |
|
| 58 |
if recommended_programs:
|
| 59 |
recommendation = f"์ง์ {employee['employee_name']}์ ์ถ์ฒ ํ๋ก๊ทธ๋จ: {', '.join(recommended_programs)}"
|
| 60 |
+
recommendation_rows.append([employee['employee_id'], employee['employee_name'], ", ".join(recommended_programs)])
|
| 61 |
else:
|
| 62 |
recommendation = f"์ง์ {employee['employee_name']}์๊ฒ ์ ํฉํ ํ๋ก๊ทธ๋จ์ด ์์ต๋๋ค."
|
| 63 |
+
recommendation_rows.append([employee['employee_id'], employee['employee_name'], "์ ํฉํ ํ๋ก๊ทธ๋จ ์์"])
|
| 64 |
|
| 65 |
+
# ํผ๋๋ฐฑ ๋ก๊ทธ ๊ธฐ๋ก
|
| 66 |
log_recommendation(employee['employee_name'], recommended_programs, feedback)
|
| 67 |
|
| 68 |
recommendations.append(recommendation)
|
| 69 |
|
| 70 |
+
# ๋คํธ์ํฌ ๊ทธ๋ํ ์์ฑ
|
|
|
|
| 71 |
G = nx.Graph()
|
| 72 |
for employee in employee_df['employee_name']:
|
| 73 |
G.add_node(employee, type='employee')
|
|
|
|
| 77 |
|
| 78 |
for i, employee in employee_df.iterrows():
|
| 79 |
for j, program in program_df.iterrows():
|
| 80 |
+
if similarities[i][j] > 0.5: # ์ ์ฌ๋ ์๊ณ๊ฐ
|
| 81 |
G.add_edge(employee['employee_name'], program['program_name'])
|
| 82 |
|
| 83 |
+
# ๊ทธ๋ํ ์๊ฐํ
|
| 84 |
plt.figure(figsize=(10, 8))
|
| 85 |
pos = nx.spring_layout(G)
|
| 86 |
nx.draw(G, pos, with_labels=True, node_color='skyblue', node_size=2000, font_size=10, font_weight='bold')
|
| 87 |
plt.title("์ง์๊ณผ ํ๋ก๊ทธ๋จ ๊ฐ์ ๊ด๊ณ")
|
| 88 |
plt.tight_layout()
|
| 89 |
|
| 90 |
+
# CSV ํ์ผ๋ก ์ถ์ฒ ๊ฒฐ๊ณผ ๋ฐํ
|
| 91 |
+
csv_output = save_recommendations_to_csv(recommendation_rows)
|
| 92 |
+
|
| 93 |
+
return "\n".join(recommendations), plt.gcf(), csv_output
|
| 94 |
|
| 95 |
# ์์ ๋ฐ์ดํฐ๋ฅผ ๋ณด์ฌ์ฃผ๋ ํจ์
|
| 96 |
def show_example_data():
|
|
|
|
| 122 |
with gr.Column(scale=1):
|
| 123 |
gr.Markdown("# HybridRAG ์์คํ
")
|
| 124 |
|
| 125 |
+
# ์ง์ ๋ฐ์ดํฐ์ ํ๋ก๊ทธ๋จ ๋ฐ์ดํฐ ์
๋ก๋
|
| 126 |
+
employee_file = gr.File(label="์ง์ ๋ฐ์ดํฐ ์
๋ก๋")
|
| 127 |
+
program_file = gr.File(label="๊ต์ก ํ๋ก๊ทธ๋จ ๋ฐ์ดํฐ ์
๋ก๋")
|
| 128 |
+
analyze_button = gr.Button("๋ถ์ ์์")
|
| 129 |
+
output_text = gr.Textbox(label="๋ถ์ ๊ฒฐ๊ณผ")
|
| 130 |
+
|
| 131 |
+
# HR ๊ด๋ฆฌ์๋ ์ง์ ํผ๋๋ฐฑ์ ๊ธฐ๋กํ ์ ์์ต๋๋ค.
|
| 132 |
+
feedback_input = gr.Radio(choices=["๋ง์กฑ", "๋ถ๋ง์กฑ"], label="์ง์ ํผ๋๋ฐฑ ๊ธฐ๋ก")
|
| 133 |
+
|
| 134 |
+
# ๋ถ์ ๋ฒํผ ํด๋ฆญ ์ ์คํ
|
| 135 |
+
analyze_button.click(analyze_data, inputs=[employee_file, program_file, feedback_input], outputs=[output_text])
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 136 |
|
| 137 |
# ์์ ๋ฐ์ดํฐ๋ฅผ ๋ฏธ๋ฆฌ๋ณด๊ธฐ๋ก ์ ๊ณต
|
| 138 |
example_button = gr.Button("์์ ๋ฐ์ดํฐ ๋ณด๊ธฐ")
|
|
|
|
| 140 |
program_example_output = gr.DataFrame(label="๊ต์ก ํ๋ก๊ทธ๋จ ๋ฐ์ดํฐ ์์")
|
| 141 |
example_button.click(show_example_data, outputs=[employee_example_output, program_example_output])
|
| 142 |
|
| 143 |
+
with gr.Column(scale=2):
|
| 144 |
+
gr.Markdown("### ์ ๋ณด ํจ๋")
|
| 145 |
+
gr.Markdown("์
๋ก๋๋ ๋ฐ์ดํฐ์ ๋ํ ๋ถ์ ๋ฐ ๊ฒฐ๊ณผ๋ฅผ ์ฌ๊ธฐ์ ํ์ํฉ๋๋ค.")
|
| 146 |
+
|
| 147 |
+
# ์๊ฐํ ์ฐจํธ ์ถ๋ ฅ
|
| 148 |
+
chart_output = gr.Plot(label="์๊ฐํ ์ฐจํธ")
|
| 149 |
+
|
| 150 |
+
# ๋ถ์ ๋ฒํผ ํด๋ฆญ ์ ์ฐจํธ ์
๋ฐ์ดํธ ๋ฐ ์ถ์ฒ ๊ฒฐ๊ณผ ๋ค์ด๋ก๋ ์ถ๊ฐ
|
| 151 |
+
csv_download = gr.File(label="์ถ์ฒ ๊ฒฐ๊ณผ ๋ค์ด๋ก๋")
|
| 152 |
+
analyze_button.click(analyze_data, inputs=[employee_file, program_file, feedback_input], outputs=[output_text, chart_output, csv_download])
|
| 153 |
+
|
| 154 |
# Gradio ์ธํฐํ์ด์ค ์คํ
|
| 155 |
demo.launch()
|