Upload utils.py

utils.py

@@ -0,0 +1,77 @@
+import re
+import pickle
+import numpy as np
+import pandas as pd
+
+
+tfidf = pickle.load(open('models/tfidf.sav', 'rb'))
+svc_sentiment = pickle.load(open('models/sentiment_model.sav', 'rb'))
+tfidf_sentiment = pickle.load(open('models/tfidf_sentiment.sav', 'rb'))
+svc = pickle.load(open('models/svc_model.sav', 'rb'))
+
+labels = [
+       'Product quality', 'Knowledge',
+       'Appointment', 'Service etiquette', 'Waiting time',
+       'Repair speed', 'Repair cost', 'Repair quality', 'Warranty',
+       'Product replacement', 'Loan sets']
+
+sample_file = pd.read_csv('sample.csv').to_csv(index=False).encode('utf-8')
+
+print('utils imported!')
+
+def get_single_prediction(text):
+    
+    # manipulate data into a format that we pass to our model
+    text = text.lower().strip() #lower case
+
+    # Vectorise text and store in new dataframe. Sentence vector = average of word vectors
+    text_vectors = tfidf.transform(list(text))
+
+    # Make topic predictions
+    results = svc.predict_proba(text_vectors).squeeze().round(2)
+    pred_prob = pd.DataFrame({'topic': labels, 'probability': results}).sort_values('probability', ascending=True)
+    
+    # Make sentiment predictions
+    text_vectors_sentiment = tfidf_sentiment.transform(list(text))
+    
+    results_sentiment = svc_sentiment.predict_proba(text_vectors).squeeze().round(2)
+    pred_prob_sentiment = pd.DataFrame({'sentiment': ['Negative', 'Positive'], 'probability': results_sentiment}).sort_values('probability', ascending=True)
+    
+
+    return (pred_prob, pred_prob_sentiment)
+
+def get_multiple_predictions(csv):
+    
+    df = pd.read_csv(csv)
+    df.columns = ['sequence']
+
+    df['sequence_clean'] = df['sequence'].str.lower().str.strip()
+
+    # Remove rows with blank string
+    invalid = df[(pd.isna(df['sequence_clean'])) | (df['sequence_clean'] == '')]
+    invalid.drop(columns=['sequence_clean'], inplace=True)
+    
+    # Drop rows with blank string
+    df.dropna(inplace=True)
+    df = df[df['sequence_clean'] != ''].reset_index(drop=True)
+    
+    # Vectorise text and get topic predictions 
+    text_vectors = tfidf.transform(df['sequence_clean'])
+    pred_results = pd.DataFrame(svc.predict(text_vectors), columns = labels)
+
+    # Vectorise text and get sentiment predictions 
+    text_vectors_sentiment = tfidf_sentiment.transform(df['sequence_clean'])
+    pred_results_sentiment = pd.DataFrame(svc_sentiment.predict(text_vectors_sentiment), columns = ['sentiment'])    
+    
+    # Join back to original sequence
+    final_results = df.join(pred_results).join(pred_results_sentiment)
+    final_results['others'] = final_results[labels].max(axis=1)
+    final_results['others'] = final_results['others'].apply(lambda x: 1 if x == 0 else 0)
+    
+    final_results.drop(columns=['sequence_clean'], inplace=True)
+    
+    # Append invalid rows
+    if len(invalid) == 0:
+        return final_results.to_csv(index=False).encode('utf-8')
+    else:
+        return pd.concat([final_results, invalid]).reset_index(drop=True).to_csv(index=False).encode('utf-8')