File size: 2,953 Bytes
8735397 9411e01 8735397 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 |
# app.py
from transformers import (
AutoModelForSequenceClassification,
AutoTokenizer,
AutoModelForTokenClassification,
pipeline
)
import gradio as gr
import torch
# Use a pipeline as a high-level helper
from transformers import pipeline
CLASS_MODEL_NAME = "AmandaCAI/resume-classifier"
NER_MODEL_NAME = "AmandaCAI/ner-keywords-extract"
# 初始化分类模型
class_tokenizer = AutoTokenizer.from_pretrained(CLASS_MODEL_NAME)
class_model = AutoModelForSequenceClassification.from_pretrained(CLASS_MODEL_NAME)
# 初始化NER模型
ner_tokenizer = AutoTokenizer.from_pretrained(NER_MODEL_NAME)
ner_model = AutoModelForTokenClassification.from_pretrained(NER_MODEL_NAME)
ner_pipeline = pipeline("ner", model=ner_model, tokenizer=ner_tokenizer, aggregation_strategy="simple")
# 岗位分类标签（根据你的训练数据调整）
job_categories = [
"Data Science", "Java Developer", "HR",
"Python Developer", "Web Designing", "Testing"
]
def analyze_resume(text):
"""处理简历分析的主函数"""
# 岗位分类
class_inputs = class_tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
with torch.no_grad():
class_logits = class_model(**class_inputs).logits
predicted_class = torch.argmax(class_logits).item()
class_label = job_categories[predicted_class]
# 技能提取
ner_results = ner_pipeline(text)
skills = [entity["word"] for entity in ner_results if entity["entity_group"] == "SKILL"]
# 工作经验提取（示例）
experience = [entity["word"] for entity in ner_results if entity["entity_group"] == "EXPERIENCE"]
return {
"岗位类别": class_label,
"匹配度": f"{torch.softmax(class_logits, dim=1)[0][predicted_class].item()*100:.1f}%",
"核心技能": list(set(skills))[:5], # 取前5个不重复技能
"工作经验": list(set(experience))[:3]
}
# Gradio界面设计
with gr.Blocks(theme=gr.themes.Soft()) as demo:
gr.Markdown("# 🧠 AI Resume Analyzer")
with gr.Row():
with gr.Column():
input_text = gr.Textbox(label="📝 Paste Resume Text Here", lines=10,
placeholder="Enter your resume text here...")
submit_btn = gr.Button("Start the analysis", variant="primary")
with gr.Column():
output_json = gr.JSON(label="Analysis result")
# 示例数据
gr.Examples(
examples=[[
"""John Smith
Senior Python Developer
Skills: Python, Django, AWS, Machine Learning
Experience: 5+ years at Google, 3 years at Amazon
Education: MIT Computer Science"""
]],
inputs=[input_text]
)
submit_btn.click(
fn=analyze_resume,
inputs=[input_text],
outputs=output_json
)
# 启动应用
if __name__ == "__main__":
demo.launch() |