Your commit message here

main.py

@@ -2,7 +2,6 @@ import threading
 from functions import extract_text_from_pdf, get_most_similar_job
 from fastapi import  UploadFile, HTTPException, FastAPI
 import pandas as pd
-from fastapi import UploadFile, HTTPException
 from sklearn.feature_extraction.text import TfidfVectorizer
 
 
@@ -38,14 +37,13 @@ def fit_threads(text):
 
 
 df = pd.read_csv("all.csv")
-df['concatenated_column'] = pd.concat([df['job_title'] + df['job_description'] + df['job_requirements'], df['city_name']], axis=1).astype(str).agg(''.join, axis=1)
-x = df['concatenated_column']
+concatenated_column = pd.concat([df['job_title'] + df['job_description'] + df['job_requirements'], df['city_name']], axis=1).astype(str).agg(''.join, axis=1)
+x = concatenated_column
 y = df["label"]
 vectorizer = TfidfVectorizer(stop_words='english')
-
+print("df done")
 vectorizer.fit(x)
 df_vect = vectorizer.transform(x)
-print(df.shape, len(df))
 # Initialize the summarizer model
 
 
@@ -58,14 +56,13 @@ def summarization(text):
     part = summarizer(text, max_length=150, min_length=30, do_sample=False)
     summ_data.append(part[0]["summary_text"].replace("\xa0", ""))
 
-
+print("start api code")
 app = FastAPI(project_name="cv")
 
 @app.get("/")
 async def read_root():
     return {"Hello": "World, Project name is : CV Description"}
 
-
 @app.post("/prediction")
 async def detect(cv: UploadFile, number_of_jobs: int):
     
@@ -79,6 +76,8 @@ async def detect(cv: UploadFile, number_of_jobs: int):
             status_code=415, detail="Please inter PDF file "
         )
 
+
+
     cv_data = extract_text_from_pdf(await cv.read())
     index = len(cv_data)//3
     text = [cv_data[:index], cv_data[index:2*index], cv_data[2*index:]]
@@ -89,7 +88,7 @@ async def detect(cv: UploadFile, number_of_jobs: int):
     cv_vect = vectorizer.transform([data])
     indices = get_most_similar_job(data=data, cv_vect=cv_vect, df_vect=df_vect)
     # Check if all threads have finished
-    print("ALL Done")
+    print("ALL Done \n\n")
     
     prediction_data = df.iloc[indices[:number_of_jobs]].applymap(lambda x: str(x)).to_dict(orient='records')