Update app.py

app.py

@@ -2,48 +2,24 @@ import numpy as np
 import os
 import gradio as gr
 
-os.environ["WANDB_DISABLED"] = "true"
-
-from datasets import load_dataset, load_metric
-from transformers import (
-    AutoConfig,
-    # AutoModelForSequenceClassification,
-    AutoTokenizer,
-    TrainingArguments,
-    logging,
-pipeline
-)
-
-
-
-
-# model_name = 
-
 
-# tokenizer = AutoTokenizer.from_pretrained(model_name)
+import xgboost as xgb
+from sklearn.feature_extraction.text import TfidfVectorizer
 
-# config = AutoConfig.from_pretrained(model_name)
-
-# pipe = pipeline("text-classification")
-
-# pipe("This restaurant is awesome")
-
-
-
-
-label2id =  {
-    "LABEL_0": "negative",
-    "LABEL_1": "neutral",
-    "LABEL_2": "positive"
-  }
+os.environ["WANDB_DISABLED"] = "true"
 
-analyzer = pipeline(
+model_file_name = "xgb_reg.pkl"
+vectorizer_file_name = 'vectorizer.pk'
 
-    "sentiment-analysis", model="thak123/Cro-Frida", tokenizer="EMBEDDIA/crosloengual-bert"
+# load
+xgb_model_loaded = pickle.load(open(model_file_name, "rb"))
+vectorizer_loaded = pickle.load(open(vectorizer_file_name, "rb"))
 
-)
-def predict_sentiment(x):
-    return label2id[analyzer(x)[0]["label"]]
+# predict
+def predict_sentiment(predict_texts):
+    predictions_loaded = xgb_model_loaded.predict(vectorizer_loaded.transform(predict_texts))
+    return predictions_loaded
+    #le.inverse_transform(predictions_loaded)
 
 
 interface = gr.Interface(