Rolled back changes.

app.py

@@ -12,11 +12,11 @@ from sklearn.feature_extraction.text import TfidfVectorizer
 from flair.data import Sentence
 from flair.models import SequenceTagger
 
-# Load pickled model and vectorizer
-model = 'lr_021823.pkl'
-model_loaded = pickle.load(open(model, 'rb'))
-vectorizer = 'vectorizer_021823.pkl'
-vectorizer_loaded = pickle.load(open(vectorizer, 'rb'))
+# file name
+#lr_filename = 'lr_021223.pkl'
+
+# Load model from pickle file
+# model = pickle.load(open(lr_filename, 'rb'))
 
 
 # Process input text, including removing stopwords, converting to lowercase, and removing punctuation
@@ -30,19 +30,33 @@ def process_text(text):
     text = " ".join(text.split())
     return text
 
-# Vectorize text
+# Vectorize input text
+vec = CountVectorizer()
+'''
 def vectorize_text(text):
-    text = process_text(text)
-    text = vectorizer_loaded.transform([text])
-    return text
+    #text = process_text(text)
+    #text = vectorizer.fit_transform([text])
+    #return text
+'''
 
 # Valid input for the model so number of features match
-def class_predict(text):
+def predict(text):
+    # Load the pickled model
+    filename = 'lr_021223.pkl'
+    loaded_model = pickle.load(open(filename, 'rb'))
+    text = vec.transform([text])
     text = process_text(text)
-    vec = vectorizer_loaded.transform([text])
-    prediction = model_loaded.predict(vec)
+    prediction = loaded_model.predict(text)
     return prediction
 
+'''
+Prediction function
+#def predict(text):
+    #text = vectorize_text(text)
+    #prediction = model.predict(text)
+    #return prediction
+'''
+
 # Specify NER model
 tagger = SequenceTagger.load('best-model.pt') # SequenceTagger.load('best-model.pt')
 
@@ -57,7 +71,7 @@ def run_ner(input_text):
 
 # Run both models, and return a tuple of their results
 def run_models(input_text):
-    prediction = class_predict(input_text)
+    prediction = 0 # This "0" is a placeholder to avoid errors; once the LR model is working, use this instead: prediction = predict(input_text)
     entities = run_ner(input_text)
     return prediction, entities