adding all files

app.py

@@ -0,0 +1,59 @@
+import gradio as gr
+import joblib
+import pandas as pd
+import re
+import nltk
+from nltk.stem import PorterStemmer
+from nltk.tokenize import word_tokenize
+import numpy as np
+
+
+
+def text_preprocessing(df):
+    """
+    This function does in-place replacement of data so it won't return anything
+    """
+    # Convert to lower cases
+    df['Text'] = df['Text'].str.lower()
+
+    # Remove punctuation
+    df['Text'] = df['Text'].apply(lambda doc: re.sub(r'[^\w\s]+', '', doc))
+
+    # Remove stopwords
+    stop_words = nltk.corpus.stopwords.words('english')
+    df['Text'] = df['Text'].apply(lambda doc: ' '.join([word for word in doc.split() if word not in (stop_words)]))
+
+    # Remove extra spaces
+    df['Text'] = df['Text'].apply(lambda doc: re.sub(' +', ' ', doc))
+
+    # Stemming
+    porter_stemmer = PorterStemmer()
+    df['Text'] = df['Text'].apply(lambda doc: [porter_stemmer.stem(word) for word in word_tokenize(doc)])
+    df['Text'] = df['Text'].apply(lambda words: ' '.join(words))
+
+
+def predict_user_input(paragraph, tfidf, nmf, label_mapping_yp):
+    data = pd.DataFrame({'Text': [paragraph]})
+    text_preprocessing(data)
+    tfidf_transformed = tfidf.transform(data['Text'])
+    nmf_transformed = nmf.transform(tfidf_transformed)
+    y_pred = np.argmax(nmf_transformed, axis=1)
+    y_pred = [label_mapping_yp[y] for y in y_pred]
+    return y_pred[0]
+
+def process_paragraph(paragraph):
+    tfidf = joblib.load('tfidf_vectorizer.pkl')
+    nmf = joblib.load('nmf_model.pkl')
+    label_mapping_yp = joblib.load('label_mapping.pkl')
+    predicted_class = predict_user_input(paragraph, tfidf, nmf, label_mapping_yp)
+    print(f"The predicted class for the input paragraph is: {predicted_class}")
+    return predicted_class
+
+def paragraph_processing_app(paragraph):
+    processed_text = process_paragraph(paragraph)
+    return processed_text
+
+input_text = gr.Textbox(lines=10, label="Enter a article:")
+output_text = gr.Textbox(label="Category(Out of Business, Tech, Sport, Politics and Entertainment.)")
+
+gr.Interface(fn=paragraph_processing_app, inputs=input_text, outputs=output_text).launch()

label_mapping.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21ac6d446fb291df7406c9a01b4253fb4b934d6957491191bd1d88f788c142c5
+size 229

nmf_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e0100525c10de229db44aa9c12bea3b1db4919f88b8d52222312ef290f5764a
+size 788577

tfidf_vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9378646d12b4f73bb1fca002cc27f52429c8a988c3749085f10151f6a70d03e0
+size 560098