Create utils.py

utils.py

@@ -0,0 +1,27 @@
+import re
+import nltk
+from wordcloud import WordCloud
+import matplotlib.pyplot as plt
+import io
+
+nltk.download("stopwords")
+from nltk.corpus import stopwords
+
+stop_words = set(stopwords.words("english"))
+
+def clean_text(text):
+    text = re.sub(r"http\S+", "", text)        # remove URLs
+    text = re.sub(r"[^a-zA-Z\s]", "", text)    # remove special chars
+    text = text.lower()
+    tokens = [w for w in text.split() if w not in stop_words]
+    return " ".join(tokens)
+
+def generate_wordcloud(text):
+    wordcloud = WordCloud(width=800, height=400, background_color="white").generate(text)
+    img = io.BytesIO()
+    plt.figure(figsize=(8, 4))
+    plt.imshow(wordcloud, interpolation="bilinear")
+    plt.axis("off")
+    plt.savefig(img, format="png")
+    plt.close()
+    return img.getvalue()