try again

app.py

@@ -12,8 +12,7 @@ import nltk
 from nltk.corpus import stopwords
 from nltk.stem import WordNetLemmatizer
 nltk.download(['stopwords','wordnet'])
-
-
+nltk.download('omw-1.4')
 # Load the CSV file into a DataFrame
 dataset_path = "Resume.csv" 
 data = pd.read_csv(dataset_path)
@@ -30,7 +29,6 @@ ruler = nlp.add_pipe("entity_ruler")
 # Load skill patterns from disk into the entity ruler
 ruler.from_disk(skill_pattern_path)
 
-
 def get_unique_skills(text):
     doc = nlp(text)
     skills = set()
@@ -54,6 +52,12 @@ def preprocess_resume(resume_str):
     review = " ".join(review)
     return review
 
+# Apply the preprocess_resume function to each resume string and store the result in a new column
+data["Clean_Resume"] = data["Resume_str"].apply(preprocess_resume)
+
+# Extract skills from each preprocessed resume and store them in a new column
+data["skills"] = data["Clean_Resume"].str.lower().apply(get_unique_skills)
+
 Job_cat = data["Category"].unique()
 Job_cat = np.append(Job_cat, "ALL")
 Job_Category = "INFORMATION-TECHNOLOGY"