Adding new logic to filtering connections ipynb

Author: martech-engineer

src/backend/services/filering_url_connections.ipynb

@@ -349,6 +349,108 @@
     "else:\n",
     "    print(\"No best PageRank URLs found based on the provided criteria.\")"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "c0huYdotnVlL"
+   },
+   "source": [
+    "# FINDING BEST PERFORMERS ON FOLDER DEPTH INTERVAL"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "xn5xIY1QnVWz"
+   },
+   "outputs": [],
+   "source": [
+    "from google.colab import drive\n",
+    "import pandas as pd\n",
+    "import os\n",
+    "\n",
+    "# Mount Google Drive\n",
+    "drive.mount(\"/content/drive\")\n",
+    "\n",
+    "# Define path to CSV file\n",
+    "base_path = \"/content/drive/My Drive/WebKnoGraph/data\"\n",
+    "file_path = os.path.join(base_path, \"url_analysis_results.csv\")\n",
+    "\n",
+    "\n",
+    "def get_overall_top_performers_in_range(file_path, min_depth, max_depth, n_total_top):\n",
+    "    \"\"\"\n",
+    "    Retrieves the overall top N performing URLs (based on PageRank) within a defined range of folder depth levels.\n",
+    "\n",
+    "    Args:\n",
+    "        file_path (str): The path to the CSV file containing URL analysis results.\n",
+    "        min_depth (int): The minimum folder depth level in the range (inclusive).\n",
+    "        max_depth (int): The maximum folder depth level in the range (inclusive).\n",
+    "        n_total_top (int): The total number of top performing URLs to retrieve across the entire range.\n",
+    "\n",
+    "    Returns:\n",
+    "        pandas.DataFrame: A DataFrame containing the 'URL' column of the overall top performers.\n",
+    "                          Returns an empty DataFrame if no matching data or missing columns.\n",
+    "    \"\"\"\n",
+    "    try:\n",
+    "        df = pd.read_csv(file_path)\n",
+    "    except FileNotFoundError:\n",
+    "        print(f\"Error: File not found at {file_path}\")\n",
+    "        return pd.DataFrame()  # Return empty DataFrame on error\n",
+    "\n",
+    "    required_cols = {\"URL\", \"Folder_Depth\", \"PageRank\"}\n",
+    "    if not required_cols.issubset(df.columns):\n",
+    "        raise ValueError(\n",
+    "            f\"Missing one or more required columns: {required_cols - set(df.columns)}\"\n",
+    "        )\n",
+    "\n",
+    "    # Filter by the defined folder depth range\n",
+    "    filtered_df = df[\n",
+    "        (df[\"Folder_Depth\"] >= min_depth) & (df[\"Folder_Depth\"] <= max_depth)\n",
+    "    ]\n",
+    "\n",
+    "    if filtered_df.empty:\n",
+    "        print(f\"No data found for folder depths between {min_depth} and {max_depth}.\")\n",
+    "        return pd.DataFrame()\n",
+    "\n",
+    "    # Sort the entire filtered DataFrame by 'PageRank' in descending order\n",
+    "    sorted_df = filtered_df.sort_values(by=\"PageRank\", ascending=False)\n",
+    "\n",
+    "    # Get the overall top N performers\n",
+    "    overall_top_performers = sorted_df.head(n_total_top)\n",
+    "\n",
+    "    return overall_top_performers[[\"URL\"]]\n",
+    "\n",
+    "\n",
+    "# --- User Inputs ---\n",
+    "try:\n",
+    "    min_depth_input = int(input(\"Enter minimum folder depth level (integer): \"))\n",
+    "    max_depth_input = int(input(\"Enter maximum folder depth level (integer): \"))\n",
+    "    n_total_top_input = int(input(\"Enter total number of top performers to retrieve: \"))\n",
+    "\n",
+    "    if min_depth_input > max_depth_input:\n",
+    "        print(\"Error: Minimum depth cannot be greater than maximum depth.\")\n",
+    "        exit()\n",
+    "\n",
+    "except ValueError:\n",
+    "    print(\"Invalid input. Please enter integers for depth range and count.\")\n",
+    "    exit()  # Exit if inputs are not valid integers\n",
+    "\n",
+    "# --- Run Analysis ---\n",
+    "print(\n",
+    "    f\"\\nRetrieving the overall top {n_total_top_input} performers from folder depths {min_depth_input} to {max_depth_input}:\"\n",
+    ")\n",
+    "overall_top_pages = get_overall_top_performers_in_range(\n",
+    "    file_path, min_depth_input, max_depth_input, n_total_top_input\n",
+    ")\n",
+    "\n",
+    "if not overall_top_pages.empty:\n",
+    "    for url in overall_top_pages[\"URL\"]:\n",
+    "        print(url)\n",
+    "else:\n",
+    "    print(\"No overall top performers found based on the provided criteria.\")"
+   ]
   }
  ],
  "metadata": {