try again

README.md

@@ -15,5 +15,6 @@ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-
 
 ```
 pip install -r requirements.txt
+python3 -m spacy download en_core_web_sm
 
 ```

app.py

@@ -11,11 +11,14 @@ import re
 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)
+df = pd.read_csv(dataset_path)
+df= df.reindex(np.random.permutation(df.index))
+data = df.copy().iloc[0:200,]
 
 # Load the spaCy English language model with large vocabulary and pre-trained word vectors
 nlp = spacy.load("en_core_web_lg")
@@ -58,6 +61,8 @@ 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)
 
+print(data)
+
 Job_cat = data["Category"].unique()
 Job_cat = np.append(Job_cat, "ALL")
 Job_Category = "INFORMATION-TECHNOLOGY"