{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import io\n",
    "import pandas as pd\n",
    "from dotenv import load_dotenv\n",
    "from azure.identity import DefaultAzureCredential\n",
    "from azure.storage.blob import ContainerClient"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load all environment variables\n",
    "load_dotenv()\n",
    "account_url = os.getenv('AZ_STORAGE_EP')\n",
    "container_name = os.getenv('AZ_STORAGE_CONTAINER')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Authenticate\n",
    "default_credential = DefaultAzureCredential()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For the first time, you might need to authenticate via the Azure CLI\n",
    "\n",
    "Download it from https://learn.microsoft.com/en-us/cli/azure/install-azure-cli-windows?tabs=azure-cli\n",
    "\n",
    "Install then run `az login` in your terminal. Once you have logged in with your browser try the `DefaultAzureCredential()` again!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Connect to container\n",
    "container_client = ContainerClient(account_url, container_name, default_credential)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "newdir/cats.parquet\n",
      "newdir/ronald.jpeg\n"
     ]
    }
   ],
   "source": [
    "# List files in container - should be empty\n",
    "blob_list = container_client.list_blob_names()\n",
    "for blob in blob_list:\n",
    "    if blob.startswith('newdir'):\n",
    "        print(blob)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Upload file to container\n",
    "with open(file='data/cats.csv', mode=\"rb\") as data:\n",
    "    blob_client = container_client.upload_blob(name='newdir/cats.csv', \n",
    "                                               data=data, \n",
    "                                               overwrite=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "newdir/cats.csv\n",
      "newdir/cats.parquet\n",
      "newdir/ronald.jpeg\n"
     ]
    }
   ],
   "source": [
    "# # Check files have uploaded - List files in container again\n",
    "blob_list = container_client.list_blobs()\n",
    "for blob in blob_list:\n",
    "    if blob['name'].startswith('newdir'):\n",
    "        print(blob['name'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Name</th>\n",
       "      <th>Physical_characteristics</th>\n",
       "      <th>Behaviour</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Ronald</td>\n",
       "      <td>White and ginger</td>\n",
       "      <td>Lazy and greedy but undoubtedly cutest and best</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Kaspie</td>\n",
       "      <td>Small calico</td>\n",
       "      <td>Sweet and very shy but adventurous</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Hennimore</td>\n",
       "      <td>Pale orange</td>\n",
       "      <td>Unhinged and always in a state of panic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Thug cat</td>\n",
       "      <td>Black and white - very large</td>\n",
       "      <td>Local bully</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Son of Stripey</td>\n",
       "      <td>Grey tabby</td>\n",
       "      <td>Very vocal</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Name      Physical_characteristics  \\\n",
       "0          Ronald              White and ginger   \n",
       "1          Kaspie                  Small calico   \n",
       "2       Hennimore                   Pale orange   \n",
       "3        Thug cat  Black and white - very large   \n",
       "4  Son of Stripey                    Grey tabby   \n",
       "\n",
       "                                         Behaviour  \n",
       "0  Lazy and greedy but undoubtedly cutest and best  \n",
       "1               Sweet and very shy but adventurous  \n",
       "2          Unhinged and always in a state of panic  \n",
       "3                                      Local bully  \n",
       "4                                       Very vocal  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Download file from Azure container to temporary filepath\n",
    "\n",
    "# Connect to blob\n",
    "blob_client = container_client.get_blob_client('newdir/cats.csv')\n",
    "\n",
    "# Write to local file from blob\n",
    "temp_filepath = os.path.join('temp_data', 'cats.csv')\n",
    "with open(file=temp_filepath, mode=\"wb\") as sample_blob:\n",
    "    download_stream = blob_client.download_blob()\n",
    "    sample_blob.write(download_stream.readall())\n",
    "cat_data = pd.read_csv(temp_filepath)\n",
    "cat_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Name</th>\n",
       "      <th>Physical_characteristics</th>\n",
       "      <th>Behaviour</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Ronald</td>\n",
       "      <td>White and ginger</td>\n",
       "      <td>Lazy and greedy but undoubtedly cutest and best</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Kaspie</td>\n",
       "      <td>Small calico</td>\n",
       "      <td>Sweet and very shy but adventurous</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Hennimore</td>\n",
       "      <td>Pale orange</td>\n",
       "      <td>Unhinged and always in a state of panic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Thug cat</td>\n",
       "      <td>Black and white - very large</td>\n",
       "      <td>Local bully</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Son of Stripey</td>\n",
       "      <td>Grey tabby</td>\n",
       "      <td>Very vocal</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Name      Physical_characteristics  \\\n",
       "0          Ronald              White and ginger   \n",
       "1          Kaspie                  Small calico   \n",
       "2       Hennimore                   Pale orange   \n",
       "3        Thug cat  Black and white - very large   \n",
       "4  Son of Stripey                    Grey tabby   \n",
       "\n",
       "                                         Behaviour  \n",
       "0  Lazy and greedy but undoubtedly cutest and best  \n",
       "1               Sweet and very shy but adventurous  \n",
       "2          Unhinged and always in a state of panic  \n",
       "3                                      Local bully  \n",
       "4                                       Very vocal  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Load directly from Azure - no local copy\n",
    "\n",
    "download_stream = blob_client.download_blob()\n",
    "stream_object = io.BytesIO(download_stream.readall())\n",
    "cat_data = pd.read_csv(stream_object)\n",
    "cat_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "# !!!!!!!!! Delete from Azure container !!!!!!!!!\n",
    "blob_client = container_client.get_blob_client('newdir/cats.csv')\n",
    "blob_client.delete_blob()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "newdir/cats.parquet\n",
      "newdir/ronald.jpeg\n"
     ]
    }
   ],
   "source": [
    "blob_list = container_client.list_blobs()\n",
    "for blob in blob_list:\n",
    "    if blob['name'].startswith('newdir'):\n",
    "        print(blob['name'])"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}