data anonymization

project2 data anonymization/encryption.ipynb

@@ -0,0 +1,147 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from dotenv import load_dotenv\n",
+    "import os\n",
+    "import requests\n",
+    "import pandas as pd\n",
+    "from cryptography.hazmat.primitives.ciphers import Cipher, algorithms, modes\n",
+    "from cryptography.hazmat.backends import default_backend\n",
+    "import base64\n",
+    "\n",
+    "# Load the .env file\n",
+    "load_dotenv(dotenv_path='api.env')\n",
+    "\n",
+    "# Fetch environment variables\n",
+    "channel1_api_key = os.getenv('CHANNEL1_API_KEY')\n",
+    "channel2_api_key = os.getenv('CHANNEL2_API_KEY')\n",
+    "\n",
+    "# Define API details\n",
+    "channels = {\n",
+    "    \"Channel1\": {\n",
+    "        \"url\": f\"https://api.thingspeak.com/channels/2561136/feeds.json?api_key={channel1_api_key}\",\n",
+    "        \"fields\": [\"created_at\", \"field2\"],\n",
+    "        \"rename\": {\n",
+    "            \"created_at\": \"timestamp\",\n",
+    "            \"field2\": \"Body_temp\"\n",
+    "        }\n",
+    "    },\n",
+    "    \"Channel2\": {\n",
+    "        \"url\": f\"https://api.thingspeak.com/channels/2561145/feeds.json?api_key={channel2_api_key}\",\n",
+    "        \"fields\": [\"created_at\", \"field2\", \"field3\"],\n",
+    "        \"rename\": {\n",
+    "            \"created_at\": \"timestamp\",\n",
+    "            \"field2\": \"heartRate\",\n",
+    "            \"field3\": \"SP02\"\n",
+    "        }\n",
+    "    }\n",
+    "}\n",
+    "\n",
+    "# Function to fetch and transform data\n",
+    "def fetch_and_transform_data(channel_url, fields, rename_columns):\n",
+    "    try:\n",
+    "        response = requests.get(channel_url)\n",
+    "        response.raise_for_status()\n",
+    "        data = response.json()\n",
+    "\n",
+    "        if 'feeds' not in data:\n",
+    "            print(\"Error: 'feeds' key not found in the API response.\")\n",
+    "            return pd.DataFrame()\n",
+    "\n",
+    "        df = pd.DataFrame(data['feeds'])\n",
+    "        df = df[fields]\n",
+    "        df.rename(columns=rename_columns, inplace=True)\n",
+    "        df['timestamp'] = pd.to_datetime(df['timestamp'])\n",
+    "        for column in df.columns:\n",
+    "            if column != 'timestamp':\n",
+    "                df[column] = pd.to_numeric(df[column], errors='coerce').round(2)\n",
+    "\n",
+    "        return df\n",
+    "\n",
+    "    except requests.exceptions.RequestException as e:\n",
+    "        print(f\"Error fetching data from {channel_url}: {e}\")\n",
+    "        return pd.DataFrame()\n",
+    "    except Exception as e:\n",
+    "        print(f\"An error occurred: {e}\")\n",
+    "        return pd.DataFrame()\n",
+    "\n",
+    "# Function to generate a new AES key\n",
+    "def generate_aes_key():\n",
+    "    return os.urandom(32)  \n",
+    "\n",
+    "# Function to encrypt a message using AES\n",
+    "def encrypt_message(key, plaintext):\n",
+    "    iv = os.urandom(16)  # 128-bit IV\n",
+    "    cipher = Cipher(algorithms.AES(key), modes.CFB(iv), backend=default_backend())\n",
+    "    encryptor = cipher.encryptor()\n",
+    "    ciphertext = encryptor.update(plaintext.encode()) + encryptor.finalize()\n",
+    "    return base64.b64encode(iv + ciphertext).decode()\n",
+    "\n",
+    "# Fetch and transform data for both channels\n",
+    "df_channel_1 = fetch_and_transform_data(channels['Channel1']['url'], channels['Channel1']['fields'], channels['Channel1']['rename'])\n",
+    "df_channel_2 = fetch_and_transform_data(channels['Channel2']['url'], channels['Channel2']['fields'], channels['Channel2']['rename'])\n",
+    "\n",
+    "# Display data before encryption\n",
+    "print(\"Channel 1 Data Before Encryption:\")\n",
+    "print(df_channel_1.head())\n",
+    "\n",
+    "print(\"\\nChannel 2 Data Before Encryption:\")\n",
+    "print(df_channel_2.head())\n",
+    "\n",
+    "# Encrypt the data\n",
+    "key = generate_aes_key()\n",
+    "df_channel_1['Body_temp'] = df_channel_1['Body_temp'].apply(lambda x: encrypt_message(key, str(x)))\n",
+    "df_channel_2['heartRate'] = df_channel_2['heartRate'].apply(lambda x: encrypt_message(key, str(x)))\n",
+    "df_channel_2['SP02'] = df_channel_2['SP02'].apply(lambda x: encrypt_message(key, str(x)))\n",
+    "\n",
+    "# Display data after encryption \n",
+    "print(\"\\nChannel 1 Data After Encryption:\")\n",
+    "print(df_channel_1[['timestamp', 'Body_temp']].head())\n",
+    "\n",
+    "print(\"\\nChannel 2 Data After Encryption:\")\n",
+    "print(df_channel_2[['timestamp', 'heartRate', 'SP02']].head())\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Function to decrypt an encrypted message using AES\n",
+    "def decrypt_message(key, ciphertext):\n",
+    "    ciphertext = base64.b64decode(ciphertext)\n",
+    "    iv = ciphertext[:16]  # Extract the IV from the first 16 bytes\n",
+    "    actual_ciphertext = ciphertext[16:]  # The rest is the encrypted message\n",
+    "    cipher = Cipher(algorithms.AES(key), modes.CFB(iv), backend=default_backend())\n",
+    "    decryptor = cipher.decryptor()\n",
+    "    plaintext = decryptor.update(actual_ciphertext) + decryptor.finalize()\n",
+    "    return plaintext.decode()\n",
+    "\n",
+    "# Decrypt the data\n",
+    "df_channel_1['Decrypted_Body_temp'] = df_channel_1['Body_temp'].apply(lambda x: decrypt_message(key, x))\n",
+    "df_channel_2['Decrypted_heartRate'] = df_channel_2['heartRate'].apply(lambda x: decrypt_message(key, x))\n",
+    "df_channel_2['Decrypted_SP02'] = df_channel_2['SP02'].apply(lambda x: decrypt_message(key, x))\n",
+    "\n",
+    "# Display the decrypted data\n",
+    "print(\"\\nChannel 1 Data After Decryption:\")\n",
+    "print(df_channel_1[['timestamp', 'Decrypted_Body_temp']].head())\n",
+    "\n",
+    "print(\"\\nChannel 2 Data After Decryption:\")\n",
+    "print(df_channel_2[['timestamp', 'Decrypted_heartRate', 'Decrypted_SP02']].head())\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}