first commit

.gitattributes

@@ -0,0 +1 @@
+*.pkl filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+.venv

app.py

@@ -0,0 +1,70 @@
+import streamlit as st
+import pickle
+import PyPDF2
+import docx
+from io import BytesIO
+import re
+import string
+import nltk
+import sklearn
+from nltk.corpus import stopwords
+from nltk.stem import WordNetLemmatizer
+from nltk.tokenize import word_tokenize
+from contractions import fix
+
+st.title('Spam Email Dection System')
+st.markdown(
+    """
+    <style>
+    .stApp {
+        background-color: #0066cc;
+    }
+    </style>
+    """,
+    unsafe_allow_html=True
+)
+
+model = pickle.load(open('model.pkl','rb'))
+count_vectorizer = pickle.load(open('count_vectorizer.pkl','rb'))
+
+stop_words = set(stopwords.words('english'))
+lemmatizer = WordNetLemmatizer()
+
+def clean_text_advance(text):
+   text = text.lower()
+   test =fix(text)
+   text = re.sub(r'http\\S+','', text)
+   text = re.sub(r'<.*?>', '', text)
+   text = text.translate(str.maketrans('','', string.punctuation)) 
+   tokens = word_tokenize(text)
+   clean_tokens = [lemmatizer.lemmatize(word) for word in tokens if word not in stop_words]
+   return  ''.join(clean_tokens)
+
+
+
+
+def detection_email(text):
+    cleaned_text = clean_text_advance(text)
+    features = count_vectorizer.transform([cleaned_text])
+    results = model.predict(features)
+    if results == 0:
+        return 'Not Spam'
+    else:
+        return 'Spam'
+        
+
+
+search_query = st.text_input('Enter your email text')
+
+
+
+
+
+if st.button('Detect Spam'):
+    if  search_query:
+        results = detection_email(search_query)
+        if results == 0:
+            st.write('Not spam')
+        else:
+            st.write('Spam')
+

count_vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f1c227783fe9f6612b8d94fd12baa223853ed728ea4bf9ba3a5af730121f050
+size 4762473

model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c383d63f60b322f9768a19791612f8768c09bc55cd05b4020e7b074988167b3
+size 48572084

requirements.txt

@@ -0,0 +1,52 @@
+altair==6.0.0
+anyascii==0.3.3
+attrs==25.4.0
+blinker==1.9.0
+cachetools==7.0.5
+certifi==2026.2.25
+charset-normalizer==3.4.5
+click==8.3.1
+colorama==0.4.6
+contractions==0.1.73
+gitdb==4.0.12
+GitPython==3.1.46
+idna==3.11
+Jinja2==3.1.6
+joblib==1.5.3
+jsonschema==4.26.0
+jsonschema-specifications==2025.9.1
+lxml==6.0.2
+MarkupSafe==3.0.3
+narwhals==2.18.0
+nltk==3.9.3
+numpy==2.4.3
+packaging==26.0
+pandas==2.3.3
+pillow==12.1.1
+protobuf==6.33.5
+pyahocorasick==2.3.0
+pyarrow==23.0.1
+pydeck==0.9.1
+PyPDF2==3.0.1
+python-dateutil==2.9.0.post0
+python-docx==1.2.0
+pytz==2026.1.post1
+referencing==0.37.0
+regex==2026.2.28
+requests==2.32.5
+rpds-py==0.30.0
+scikit-learn==1.8.0
+scipy==1.17.1
+six==1.17.0
+smmap==5.0.3
+streamlit==1.55.0
+tenacity==9.1.4
+textsearch==0.0.24
+threadpoolctl==3.6.0
+toml==0.10.2
+tornado==6.5.5
+tqdm==4.67.3
+typing_extensions==4.15.0
+tzdata==2025.3
+urllib3==2.6.3
+watchdog==6.0.0