Merge pull request #104 from Daethyra/v1.5.2

V1.5.2

.github/dependabot-misc.yml

@@ -0,0 +1,24 @@
+  # Enable version updates for npm
+  - package-ecosystem: "npm"
+    # Look for `package.json` and `lock` files in the `root` directory
+    directory: "/project/modules/web-ui" # MUST BE UPDATED UPON TYPESCRIPT PROGRAMMING
+    # Check the npm registry for updates every day (weekdays)
+    schedule:
+      interval: "daily"
+      # Check for npm updates at 9am UTC
+      time: "09:00"
+      timezone: "America/Los_Angeles"
+    target-branch: "master"
+    versioning-strategy: auto
+
+  # Enable version updates for Docker
+  - package-ecosystem: "docker"
+    # Look for a `Dockerfile` in the `root` directory
+    directory: "/project/modules/orchestration"
+    # Check for updates once a week
+    schedule:
+      interval: "daily"
+      # Check for npm updates at 9am UTC
+      time: "09:00"
+      timezone: "America/Los_Angeles"
+    target-branch: "master"

.github/dependabot-python.yml

@@ -0,0 +1,24 @@
+# Please see the documentation for all configuration options:
+# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
+version: 2
+updates:
+  # Enable version updates for multiple branches
+  - package-ecosystem: "pip" 
+    directory: "project/modules/orchestration"
+    schedule:
+      interval: "daily"
+      # Check for pip updates at 9am UTC
+      time: "09:00"
+      timezone: "America/Los_Angeles"
+    target-branch: "master"
+    versioning-strategy: auto
+
+  - package-ecosystem: "pip" 
+    directory: "project/modules/orchestration"
+    schedule:
+      interval: "daily"
+      # Check for pip updates at 9am UTC
+      time: "09:00"
+      timezone: "America/Los_Angeles"
+    target-branch: "v1.5*"
+    versioning-strategy: auto

.github/workflows/greetings.yml

@@ -12,5 +12,5 @@ jobs:
     - uses: actions/first-interaction@v1
       with:
         repo-token: ${{ secrets.GITHUB_TOKEN }}
-        issue-message: "Message that will be displayed on users' first issue"
-        pr-message: "Message that will be displayed on users' first pull request"
+        issue-message: "Thanks for chippin' in, choom. We'll have this looked at right away."
+        pr-message: "OK! Big legend! Nice job, can't wait to see your work."

project/documents/supplementary-information/explanation.txt

@@ -0,0 +1,2 @@
+These subdirectories contain contextual information for the project.
+- The AI may make use of everything inside 'supplementary-information/'

project/modules/CyberSentinel/.env.template

@@ -1,5 +1,19 @@
-TRAINING_DATA_PATH=
+# Create a copy of this file and name it '.env'
+
+# Model Training Configuration
+TRAINING_DATA_PATH=project/modules/CyberSentinel/training-data/
 LEARNING_RATE=0.001
 BATCH_SIZE=32
 EPOCHS=10
 L2_REG=0.01
+
+# Preprocessor Configuration (Use '.' for current working directory)
+INPUT_FILE_PATH=
+PREPROCESSED_DATA_FILE_PATH=project/modules/CyberSentinel/training-data/Processed-Data/
+
+# Temporary file paths for DataLabeler
+TEMP_PDF_FILE_PATH=temp_pdf_data.csv
+TEMP_TXT_FILE_PATH=temp_txt_data.csv
+
+# Path to save labeled data
+LABELED_DATA_FILE_PATH=project/modules/CyberSentinel/preprocess/

project/modules/CyberSentinel/preprocess/data_labeler.py

@@ -1,11 +1,20 @@
+from dotenv import load_dotenv
 import os
 import csv
 from typing import List, Tuple
 
+# Point to the location of the .env file relative to the script's location
+env_path = os.path.join(os.path.dirname(__file__), '../../../.env')
+
+# Load the .env file
+load_dotenv(dotenv_path=env_path)
+
 class DataLabeler:
-    def __init__(self, temp_pdf_file_path: str = "temp_pdf_data.csv", temp_txt_file_path: str = "temp_txt_data.csv"):
-        self.temp_pdf_file_path = temp_pdf_file_path
-        self.temp_txt_file_path = temp_txt_file_path
+    def __init__(self):
+        default_temp_path = os.path.dirname(__file__)
+        self.temp_pdf_file_path = os.getenv('TEMP_PDF_FILE_PATH', os.path.join(default_temp_path, 'temp_pdf_data.csv'))
+        self.temp_txt_file_path = os.getenv('TEMP_TXT_FILE_PATH', os.path.join(default_temp_path, 'temp_txt_data.csv'))
+        self.output_file_path = os.getenv('LABELED_DATA_FILE_PATH')
         self.labeled_pdf_data = self.load_temp_data(self.temp_pdf_file_path)
         self.labeled_txt_data = self.load_temp_data(self.temp_txt_file_path)
 
@@ -36,13 +45,13 @@ def load_temp_data(self, file_path: str) -> List[Tuple[str, bool]]:
     def label_data(self, data: List[str]) -> List[Tuple[str, bool]]:
         labeled_data = []
         for text in data:
-            print("\nSample:")
-            print(text)
+            print(f"\\nSample:{text}")
             label = self.get_user_input("Does this text indicate the intention to commit acts of hate-based violence? (True/False): ")
             labeled_data.append((text, label))
         return labeled_data
 
-    def save_labeled_data_to_csv(self, labeled_data: List[Tuple[str, bool]], file_path: str):
+    def save_labeled_data_to_csv(self, labeled_data: List[Tuple[str, bool]]):
+        file_path = self.output_file_path or input("Enter the path to save the labeled data: ")
         with open(file_path, 'w', newline='', encoding='utf-8') as file:
             writer = csv.writer(file)
             writer.writerow(['text', 'label'])
@@ -52,12 +61,11 @@ def save_labeled_data_to_csv(self, labeled_data: List[Tuple[str, bool]], file_pa
 if __name__ == "__main__":
     data_labeler = DataLabeler()
     # Load the preprocessed data from the file saved by the Preprocessor
-    file_path = input("Enter the path to the preprocessed data file: ")
+    file_path = os.getenv('PREPROCESSED_DATA_FILE_PATH') or input("Enter the path to the preprocessed data file: ")
     with open(file_path, 'r', encoding='utf-8') as file:
         reader = csv.reader(file)
         next(reader)  # Skip the header
         data = [row[0] for row in reader]
 
     labeled_data = data_labeler.label_data(data)
-    output_file_path = input("Enter the path to save the labeled data: ")
-    data_labeler.save_labeled_data_to_csv(labeled_data, output_file_path)
+    data_labeler.save_labeled_data_to_csv(labeled_data)