Create app.py

app.py

@@ -0,0 +1,107 @@
+import re
+import string
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import accuracy_score, confusion_matrix
+from sklearn import feature_extraction, linear_model, model_selection, preprocessing
+from sklearn.metrics import accuracy_score,precision_score
+from sklearn.model_selection import train_test_split
+from sklearn.pipeline import Pipeline
+import matplotlib.pyplot as plt
+import seaborn as sns
+import nltk
+from nltk.corpus import stopwords
+from nltk.stem import PorterStemmer
+from nltk.tokenize import sent_tokenize, word_tokenize
+from wordcloud import WordCloud, STOPWORDS
+from tokenizers import (
+    decoders,
+    models,
+    normalizers,
+    pre_tokenizers,
+    processors,
+    trainers,
+    Tokenizer,
+)
+import gc
+import warnings
+warnings.filterwarnings("ignore")
+nltk.download('punkt')
+nltk.download('stopwords')
+import pickle
+model = pickle.load(open("/content/fakenews.sav", 'rb'))
+import gradio as gr
+def predict(text):
+    text=pd.DataFrame([text], columns=["text"])
+    text=text["text"]
+    text=text.apply(wordpre)
+    text=lower_and_tokenize(text)
+    text = text.apply(lambda x: [lemmatizer.lemmatize(word) for word in x])
+    text = text.apply(lambda x: ' '.join(x))
+    # tokenize and encode sequences in the test set
+    tokens_text = tokenizer.batch_encode_plus(
+        text.tolist(),
+        max_length = max_seq_len,
+        padding="max_length",
+        truncation=True,
+        return_token_type_ids=True,
+        add_special_tokens = True,
+    )
+    # for text set
+    text_seq = torch.tensor(tokens_text['input_ids'])
+    text_mask = torch.tensor(tokens_text['attention_mask'])
+    text_y=torch.tensor([0])
+    # wrap tensors
+    text_data = TensorDataset(text_seq, text_mask,text_y)
+
+    # sampler for sampling the data during testing
+    text_sampler = SequentialSampler(text_data)
+
+    # dataLoader for test set
+    text_dataloader = DataLoader(text_data, sampler = text_sampler, batch_size=batch_size)
+    random.seed(seed_val)
+    torch.manual_seed(seed_val)
+    torch.cuda.manual_seed_all(seed_val)
+    total_eval_accuracy = 0
+    total_eval_loss = 0
+    y_true = []
+    y_pred = []
+    total_t0 = time.time()
+    use=listmodel[bestidx]
+    use.eval()
+    total_eval_accuracy = 0
+    total_eval_loss = 0
+    y_true = []
+    y_pred = []
+    t0=time.time()
+
+    for batch in text_dataloader:
+        input_ids = batch[0].to(device)
+        input_mask = batch[1].to(device)
+        labels = batch[2].to(device)
+        with torch.no_grad():
+            out = model(input_ids, input_mask,labels=labels)
+            del input_ids,input_mask
+            gc.collect()
+            loss = out[0]
+            logi = out.logits
+            logits_tensor = torch.tensor(logi)
+        loss = criterion(logits_tensor, labels)
+        total_eval_loss += loss.item()
+        pred = torch.argmax(logits_tensor, dim = 1)
+        y_pred.append(pred.flatten())
+        del pred,logi,out,logits_tensor
+        gc.collect()  
+
+    predict=str()
+    if y_pred==[1]:
+       predict="This may be a fake news."
+    else:
+       predict="This may be a real news."
+    return predict
+demo = gr.Interface(
+    fn=predict,
+    inputs=["text"],
+    outputs=["predict"],
+)
+demo.launch(share=True)