Upload 4 files

README.md

@@ -1,20 +1,50 @@
----
-title: Cipher Classifier
-emoji: 🚀
-colorFrom: red
-colorTo: red
-sdk: docker
-app_port: 8501
-tags:
-- streamlit
-pinned: false
-short_description: Streamlit template space
-license: mit
----
-
-# Welcome to Streamlit!
-
-Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
-
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
+# 🔐 Encrypted Text Classifier – 20 Newsgroups Cipher Challenge
+
+This project is built for the [Kaggle Ciphertext Challenge](https://www.kaggle.com/competitions/20-newsgroups-ciphertext-challenge), where the goal is to classify encrypted text documents into 20 different newsgroup categories.
+
+🎯 Even without decrypting the text, we trained a character-level machine learning model that achieves over **63% accuracy**.
+
+---
+
+## 📂 Project Structure
+cipher-classifier/
+├── app.py # Streamlit app
+├── cipher_classifier.pkl # Pickled model + vectorizer
+├── train.csv # Kaggle training data
+├── requirements.txt # Libraries for deployment
+└── README.md
+
+
+---
+
+## 🧠 Model Overview
+
+- **Input:** Ciphertext strings (unreadable encrypted text)
+- **Vectorization:** `CountVectorizer` with char-level n-grams (1 to 3)
+- **Model:** Logistic Regression (sklearn)
+- **Accuracy:** ~63% (without decryption)
+
+---
+
+
+Example Output
+Input (Ciphertext)	Predicted Label
+['W')(7x1zay7Hb3...	15
+Tx4a8M\HNsyp;HM...	8
+
+
+
+📦 Deployment
+This app is designed to run on:
+
+🟢 Hugging Face Spaces
+
+🟢 Streamlit Cloud
+
+🔵 GitHub
+
+
+📌 Kaggle Link
+You can download the dataset from the official competition:
+👉 Kaggle – 20 Newsgroups Ciphertext Challenge
+

app.py

@@ -0,0 +1,20 @@
+import streamlit as st
+import pickle
+
+# Başlık
+st.title("🧠 Encrypted Text Classifier (20 Newsgroups)")
+
+# Modeli yükle
+with open("cipher_classifier.pkl", "rb") as f:
+    vectorizer, model = pickle.load(f)
+
+# Girdi alanı
+text = st.text_area("🔐 Enter encrypted (ciphertext) input:", height=200)
+
+if st.button("🧪 Predict"):
+    if text.strip() == "":
+        st.warning("Lütfen şifreli bir metin girin.")
+    else:
+        X_input = vectorizer.transform([text])
+        prediction = model.predict(X_input)[0]
+        st.success(f"📂 Predicted category: **{prediction}**")

cipher_classifier.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7d71b1fcda5760dbc2df3c4bb7de6ba87832e480b6a0ae337b9bd9bebc8aaf5
+size 185929

requirements.txt

@@ -1,3 +1,3 @@
-altair
-pandas
-streamlit
+streamlit
+scikit-learn
+pandas