Update app.py

app.py

@@ -1,23 +1,31 @@
-import requests
 import os
+import streamlit as st
 import spacy
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 
-# URL for the legal cases data
-cases_url = '/kaggle/input/legalai/'  # Replace with the actual URL of your legal cases data
+# Load legal data - Cases
+cases_directory = '/kaggle/input/legalai/Object_casedocs/'
+cases_texts = []
 
-# Fetch legal cases data from URL
-response = requests.get(cases_url)
-if response.status_code == 200:
-    cases_content = response.text.splitlines()
-else:
-    print("Failed to fetch legal cases data. Status code:", response.status_code)
-    cases_content = []
+for file_name in os.listdir(cases_directory):
+    file_path = os.path.join(cases_directory, file_name)
+    with open(file_path, 'r') as file:
+        content = file.read()
+        cases_texts.append(content)
+
+# Load legal data - Statutes
+statutes_directory = '/kaggle/input/legalai/Object_statutes/'
+statutes_texts = {}
+for file_name in os.listdir(statutes_directory):
+    file_path = os.path.join(statutes_directory, file_name)
+    with open(file_path, 'r') as file:
+        statute_content = file.read()
+        statutes_texts[file_name] = statute_content
 
 # Preprocess and vectorize text for cases
 nlp = spacy.load("en_core_web_sm")
-processed_cases_texts = [" ".join([token.lemma_ for token in nlp(text) if not token.is_stop]) for text in cases_content]
+processed_cases_texts = [" ".join([token.lemma_ for token in nlp(text) if not token.is_stop]) for text in cases_texts]
 vectorizer_cases = TfidfVectorizer()
 tfidf_matrix_cases = vectorizer_cases.fit_transform(processed_cases_texts)