Upload 3 files

knn_model.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69d9b5be2223b9acb49fe7cf16a6df47daa312ed35b21e2a9341b9ae97575c60
-size 4223478
+oid sha256:6ceaeb3f040b36abf9aadbd303aeb88f4745d1a41c620b803d6a56c3229e0dd1
+size 5725078

nca_model.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fd5ab8d8adb40ead5421e8d90e36c99004f2af426be6659e7add2f0c58893e7
-size 43294492
+oid sha256:c5053da7e87086d6ec242c2ae73df5e0a299ab0cb2dc395c81f8cc625f84987a
+size 57724892

train_classifier.py

@@ -55,7 +55,7 @@ word_vectorizer.fit(requiredText)
 joblib.dump(word_vectorizer, 'tfidf_vectorizer.joblib')
 WordFeatures = word_vectorizer.transform(requiredText)
 
-nca = NeighborhoodComponentsAnalysis(n_components=300, random_state=42)
+nca = NeighborhoodComponentsAnalysis(n_components=400, random_state=42)
 WordFeatures = nca.fit_transform(WordFeatures.toarray(), requiredTarget)
 nca_filename = f'nca_model.joblib'
 joblib.dump(nca, nca_filename)
@@ -72,6 +72,11 @@ print(X_test.shape)
 # knn = KNeighborsClassifier()
 # gs = GridSearchCV(estimator=knn, param_grid=param_grid, scoring="accuracy", verbose=1, cv=10, n_jobs=3)
 # grid_search = gs.fit(X_train, y_train)
+# results_df = pd.DataFrame(grid_search.cv_results_)
+# # results_df.to_excel('grid_search_results_with_nca_500.xlsx', index=False)
+# # results_df.to_excel('grid_search_results_with_nca_400.xlsx', index=False)
+# # results_df.to_excel('grid_search_results_with_nca_300.xlsx', index=False)
+# # results_df.to_excel('grid_search_results_no_nca.xlsx', index=False)
 # best_score = grid_search.best_score_
 # best_parameters = grid_search.best_params_
 # print("Best Score:", best_score)
@@ -80,7 +85,7 @@ print(X_test.shape)
 knn = KNeighborsClassifier(n_neighbors=1, 
                            metric='manhattan',
                            weights='uniform',
-                           algorithm='ball_tree',
+                           algorithm='kd_tree',
                            )
 knn.fit(X_train, y_train)