Upload 5 files

knn_model.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ceaeb3f040b36abf9aadbd303aeb88f4745d1a41c620b803d6a56c3229e0dd1
-size 5725078
+oid sha256:63bcb5d47a13120d48d2fda296c68c5f96102f00ec9d6811909b2625228a5cd3
+size 4293046

nca_model.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5053da7e87086d6ec242c2ae73df5e0a299ab0cb2dc395c81f8cc625f84987a
-size 57724892
+oid sha256:6f123db7c979eb889c1943ef83369ba45078628adf30063f4908dd1e039d835a
+size 43294492

tfidf_vectorizer.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:986d302aa10cddb969608ad2afe08fade436d19afd812ba508a0c8b4f1498a2b
+oid sha256:3d3defdb1fda27499f742f2da47e46eb9d10bf33fd0bb8922a3ee465d7e8bef6
 size 794455

train_classifier.py

@@ -11,14 +11,14 @@ from sklearn.model_selection import train_test_split, GridSearchCV
 from sklearn.neighbors import KNeighborsClassifier, NeighborhoodComponentsAnalysis
 from sklearn.preprocessing import LabelEncoder
 
-file_path = '~/Projects/hau/csstudy/resume-screening-and-classification/knn-trial/datasets/dataset_hr_edited.csv'
+file_path = '~/Projects/hau/csstudy/resume-screening-and-classification/knn-trial/datasets/Labeled_LiveCareer_Resumes_1076.xlsx'
 
-resumeDataSet = pd.read_csv(file_path)
+resumeDataSet = pd.read_excel(file_path)
 
 stop_words = set(stopwords.words('english'))
 stemmer = PorterStemmer()
 
-print (resumeDataSet['Category'].value_counts())
+print (resumeDataSet['Actual Category'].value_counts())
 
 def cleanResume(resumeText):
     resumeText = re.sub('http\S+\s*', ' ', resumeText)  # remove URLs
@@ -38,12 +38,12 @@ def cleanResume(resumeText):
 resumeDataSet['cleaned_resume'] = resumeDataSet.Resume.apply(lambda x: cleanResume(x))
 
 le = LabelEncoder()
-resumeDataSet['Category'] = le.fit_transform(resumeDataSet['Category'])
+resumeDataSet['Actual Category'] = le.fit_transform(resumeDataSet['Actual Category'])
 le_filename = f'label_encoder.joblib'
 joblib.dump(le, le_filename)
 
 requiredText = resumeDataSet['cleaned_resume'].values
-requiredTarget = resumeDataSet['Category'].values
+requiredTarget = resumeDataSet['Actual Category'].values
 
 word_vectorizer = TfidfVectorizer(
     stop_words='english',
@@ -55,7 +55,7 @@ word_vectorizer.fit(requiredText)
 joblib.dump(word_vectorizer, 'tfidf_vectorizer.joblib')
 WordFeatures = word_vectorizer.transform(requiredText)
 
-nca = NeighborhoodComponentsAnalysis(n_components=400, random_state=42)
+nca = NeighborhoodComponentsAnalysis(n_components=300, random_state=42)
 WordFeatures = nca.fit_transform(WordFeatures.toarray(), requiredTarget)
 nca_filename = f'nca_model.joblib'
 joblib.dump(nca, nca_filename)