Upload 7 files

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Fake.csv filter=lfs diff=lfs merge=lfs -text
+True.csv filter=lfs diff=lfs merge=lfs -text

Fake.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bebf8bcfe95678bf2c732bf413a2ce5f621af0102c82bf08083b2e5d3c693d0c
+size 62789876

True.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba0844414a65dc6ae7402b8eee5306da24b6b56488d6767135af466c7dcb2775
+size 53582940

app.py

@@ -0,0 +1,78 @@
+import streamlit as st 
+import torch
+import re 
+import torch.nn as nn
+import joblib
+import torch.nn.functional as F
+
+st.title("News Classification")
+
+## mopdel 
+
+vocab_size = 37852
+embedding_dim = 45
+hidden_units = 25
+num_classes = 2
+max_len = 55
+
+class LSTMModel(nn.Module):
+    def __init__(self, vocab_size, embedding_dim, hidden_units, num_classes):
+        super(LSTMModel, self).__init__()
+        self.embedding = nn.Embedding(vocab_size, embedding_dim)
+        self.lstm = nn.LSTM(embedding_dim, hidden_units, batch_first=True, dropout=0.2,bidirectional=True)
+        self.fc = nn.Linear(hidden_units* 2, num_classes)
+
+    def forward(self, x):
+        x = self.embedding(x)
+        output, _ = self.lstm(x)
+        x = output[:, -1, :]
+        x = self.fc(x)
+        return F.softmax(x, dim=1)
+
+model = LSTMModel(vocab_size, embedding_dim, hidden_units, num_classes)
+## load the weights
+model.load_state_dict(torch.load( "news_classfication.pth", map_location=torch.device("cpu")))
+model.eval()  
+
+tokenizer=joblib.load("tokenizer.pkl")
+
+def preprocess(words):
+    normalized = []
+    for i in words:
+        i = i.lower()
+        # get rid of urlss
+        i = re.sub('https?://\S+|www\.\S+', '', i)
+        # get rid of non words and extra spaces
+        i = re.sub('\\W', ' ', i)
+        i = re.sub('\n', '', i)
+        i = re.sub(' +', ' ', i)
+        i = re.sub('^ ', '', i)
+        i = re.sub(' $', '', i)
+
+        normalized.append(i)
+        text=[tokenizer.encode(text.lower()).ids for text in normalized]
+        max_length = 20 
+        flattened_text = [token for sublist in text for token in sublist]
+        if len(flattened_text) > max_length:
+            flattened_text = flattened_text[:max_length] 
+        else:
+            flattened_text += [0] * (max_length - len(flattened_text))
+        text_tensor = torch.tensor(flattened_text, dtype=torch.long)
+        text_tensor = text_tensor.unsqueeze(0)       
+    return text_tensor
+  
+
+
+
+text=st.text_input("Enter the news  Tittle ",value="Sheriff David Clarke Becomes An Internet Joke For Threatening To Poke People 'In The Eye'")
+
+if st.button("submit"):
+    words=text.split()
+    v=preprocess(words)
+    output=model(v)
+    if output.argmax()==0:
+        st.write("Its a Fake news")
+    else:
+        st.write("Its not a Fake news")
+
+

news_classfication.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a6a9c12929a5d98deb0e7af30d2c3f39fc2c82a65c32771404cb28e9028daa
+size 6874152

requirements.txt

@@ -0,0 +1,8 @@
+streamlit==1.30.0
+pandas==2.1.4
+torch==2.2.0
+torchvision==0.17.0
+numpy==1.26.3
+scikit-learn==1.3.2
+tokenizers==0.15.1
+joblib==1.2.0

tokenizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd836e1eeb44d11836cbe52a4d10d4b2d5579c6265611dfd16941dfdfb1f9ed2
+size 645410