fix calculation

app.py

@@ -54,16 +54,19 @@ async def classify(body:JobAndCV):
         "positions": str(positions), 
         "userMajors": str(userMajors), 
         "skills": str(body.cv.skills), 
-        "yoe": yoe
+        "yoe": yoe,
+        "location": str(body.cv.location)
     }
     job = {
         "jobDesc": body.job.jobDesc, 
         "role": body.job.role, 
         "majors": str(body.job.majors), 
         "skills": str(body.job.skills), 
-        "minYoE": body.job.minYoE
+        "minYoE": body.job.minYoE,
+        "location": str(body.job.location)
     }
-    results = classificator.predict(cv, job)
+    weight = body.weight.dict()
+    results = classificator.predict(cv, job, weight)
     return ClassificationResult(**results)
 
 @app.post("/cv", response_model=CVExtracted)

classificator.py

@@ -3,6 +3,10 @@ from sklearn.metrics.pairwise import cosine_similarity
 import numpy as np
 import pandas as pd
 import pickle 
+from geopy.geocoders import Nominatim
+from geopy.distance import geodesic
+
+
 st = SentenceTransformer('all-mpnet-base-v2')
 filename = 'svc.pkl'
 
@@ -29,24 +33,42 @@ with open(filename, 'rb') as file:
 #     "minYoE": body.job.minYoE
 # }
 
-def predict(cv, job):
+
+geolocator = Nominatim(user_agent="geo_distance_calculator")
+
+def get_coordinates(city):
+    location = geolocator.geocode(city)
+    if location:
+        return (location.latitude, location.longitude)
+    else:
+        return None
+
+def predict(cv, job, weight):
   diffYoe = cv['yoe'] - job['minYoE']
   results = {}
   role_req_exp = cosine_similarity(st.encode(cv['experiences']).reshape(1,-1), st.encode(job['role']+'\n'+job['jobDesc']).reshape(1,-1))[0][0] if cv['experiences'] != '[]' else 0
   role_pos = cosine_similarity(st.encode(cv['positions']).reshape(1,-1), st.encode(job['role']).reshape(1,-1))[0][0] if cv['positions'] != '[]' else 0
   major_similarity = cosine_similarity(st.encode(cv['userMajors']).reshape(1,-1), st.encode(job['majors']).reshape(1,-1))[0][0] if cv['userMajors'] != '[]' else 0
   skill_similarity = cosine_similarity(st.encode(cv['skills']).reshape(1,-1), st.encode(job['skills']).reshape(1,-1))[0][0] if cv['skills'] != '[]' else 0
-  score_yoe = 0.5 if diffYoe == -1 else (0 if diffYoe < 0 else 1)
-  score = 0.35 * role_req_exp + 0.1 * role_pos  + 0.15 * major_similarity + 0.3* score_yoe + 0.1 * skill_similarity 
-  data = [{
-    'role_req-exp': role_req_exp,      
-    'role_pos': role_pos,            
-    'major_similarity':  major_similarity,  
-    'skill_similarity':  skill_similarity,
-    'score': score           
-  }]
-  X = pd.DataFrame.from_dict(data)
-  res = model.predict(X)
-  results['score'] = model.predict_proba(X)[:, 1]
-  results['is_accepted'] = res[0]
+  # score_yoe = 0.5 if diffYoe == -1 else (0 if diffYoe < 0 else 1)
+  coords_1 = get_coordinates(cv['location'])
+  coords_2 = get_coordinates(job['location'])
+  distance = 999999
+  if coords_1 and coords_2:
+      distance = geodesic(coords_1, coords_2).kilometers
+  else:
+      raise ValueError("Could not get coordinates for one or both cities.")
+
+  score = weight['exp'] * role_req_exp + weight['position'] * role_pos  + weight['major'] * major_similarity + weight['diffYoe']* diffYoe + weight['skills'] * skill_similarity + weight['location'] * (1 / (1 + distance))
+  # data = [{
+  #   'role_req-exp': role_req_exp,      
+  #   'role_pos': role_pos,            
+  #   'major_similarity':  major_similarity,  
+  #   'skill_similarity':  skill_similarity,
+  #   'score': score           
+  # }]
+  # X = pd.DataFrame.from_dict(data)
+  # res = model.predict(X)
+  results['score'] = score #model.predict_proba(X)[:, 1]
+  # results['is_accepted'] = res[0]
   return results

models.py

@@ -31,6 +31,7 @@ class CVToClassify(BaseModel):
     educations: List[dict[str, Any]]
     skills: List[str]
     experiences: List[dict[str, Any]]
+    location: str
 
 class JobToClassify(BaseModel):
     minYoE: int
@@ -38,14 +39,23 @@ class JobToClassify(BaseModel):
     skills: List[str]
     role: str
     majors: List[str]
+    location: str
 
+class Weight(BaseModel):
+    exp: float
+    position: float
+    major: float
+    skills: float
+    diffYoe: float
+    location: float
 
 class JobAndCV(BaseModel):
     cv: CVToClassify
     job: JobToClassify
+    weight: Weight
 
 class ClassificationResult(BaseModel):
     score: float
-    is_accepted: bool
+
 class InsertedLink(BaseModel):
     link: str

requirements.txt

@@ -7,4 +7,5 @@ sentence_transformers
 scikit-learn
 numpy
 pandas
-openai
+openai
+geopy