Update app.py

app.py

@@ -1,63 +1,39 @@
-from transformers import AutoModelForSequenceClassification
-from transformers import TFAutoModelForSequenceClassification
-from transformers import AutoTokenizer
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
 import numpy as np
 from scipy.special import softmax
-import csv
 import urllib.request
+import csv
+from huggingface_hub import snapshot_download
 
-# Preprocess text (username and link placeholders)
-def preprocess(text):
-    new_text = []
- 
- 
-    for t in text.split(" "):
-        t = '@user' if t.startswith('@') and len(t) > 1 else t
-        t = 'http' if t.startswith('http') else t
-        new_text.append(t)
-    return " ".join(new_text)
-
-# Tasks:
-# emoji, emotion, hate, irony, offensive, sentiment
-# stance/abortion, stance/atheism, stance/climate, stance/feminist, stance/hillary
-
-task='sentiment'
+# Define model
+task = 'sentiment'
 MODEL = f"cardiffnlp/twitter-roberta-base-{task}"
 
-tokenizer = AutoTokenizer.from_pretrained(MODEL)
+# Download model
+snapshot_download(repo_id=MODEL)
+
+# Load tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained(MODEL, local_files_only=True)
+model = AutoModelForSequenceClassification.from_pretrained(MODEL, local_files_only=True)
+
+# Preprocessing function
+def preprocess(text):
+    return " ".join(['@user' if t.startswith('@') else 'http' if t.startswith('http') else t for t in text.split()])
 
-# download label mapping
-labels=[]
+# Load labels
+labels = []
 mapping_link = f"https://raw.githubusercontent.com/cardiffnlp/tweeteval/main/datasets/{task}/mapping.txt"
 with urllib.request.urlopen(mapping_link) as f:
-    html = f.read().decode('utf-8').split("\n")
-    csvreader = csv.reader(html, delimiter='\t')
-labels = [row[1] for row in csvreader if len(row) > 1]
-
-# PT
-model = AutoModelForSequenceClassification.from_pretrained(MODEL)
-model.save_pretrained(MODEL)
+    labels = [row[1] for row in csv.reader(f.read().decode('utf-8').split("\n"), delimiter='\t') if len(row) > 1]
 
+# Sentiment analysis
 text = "Good night 😊"
-text = preprocess(text)
-encoded_input = tokenizer(text, return_tensors='pt')
+encoded_input = tokenizer(preprocess(text), return_tensors='pt')
 output = model(**encoded_input)
-scores = output[0][0].detach().numpy()
-scores = softmax(scores)
-
-# # TF
-# model = TFAutoModelForSequenceClassification.from_pretrained(MODEL)
-# model.save_pretrained(MODEL)
+scores = softmax(output.logits.detach().numpy()[0])
 
-# text = "Good night 😊"
-# encoded_input = tokenizer(text, return_tensors='tf')
-# output = model(encoded_input)
-# scores = output[0][0].numpy()
-# scores = softmax(scores)
-
-ranking = np.argsort(scores)
-ranking = ranking[::-1]
+# Print results
+ranking = np.argsort(scores)[::-1]
 for i in range(scores.shape[0]):
-    l = labels[ranking[i]]
-    s = scores[ranking[i]]
-    print(f"{i+1}) {l} {np.round(float(s), 4)}")
+    print(f"{i+1}) {labels[ranking[i]]} {np.round(float(scores[ranking[i]]), 4)}")
+