feat: add features.yaml. #3

configs/features.yaml

@@ -0,0 +1,22 @@
+preprocessing:
+  lowercase: true
+  remove_urls: true
+  remove_mentions: true
+  remove_emojis: true
+  remove_special_chars: true
+  remove_stopwords: true
+  lemmatize: true
+  min_token_length: 2
+  language: en
+
+vectorization:
+  method: tfidf  # tfidf | bow | both
+  tfidf:
+    max_features: 10000
+    ngram_range: [1, 2]
+    sublinear_tf: true
+    min_df: 2
+  bow:
+    max_features: 10000
+    ngram_range: [1, 1]
+    min_df: 2