Update bot detection model and features

BotDetectionEDA.ipynb

@@ -13,19 +13,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {
     "id": "pLAYgHzBCh3U"
    },
    "outputs": [],
    "source": [
-    "# Import necessary libraries for data manipulation, visualization, and machine learning\n",
+    "\n",
     "import pandas as pd\n",
     "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
     "import seaborn as sns\n",
     "\n",
-    "# Machine Learning Libraries\n",
     "from sklearn.model_selection import train_test_split\n",
     "from sklearn.preprocessing import StandardScaler\n",
     "from sklearn.ensemble import RandomForestClassifier\n",
@@ -35,7 +34,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -258,11 +257,11 @@
     }
    ],
    "source": [
-    "# Load the dataset\n",
-    "file_path = \"../Dataset/training_data.csv\"  # Update with your actual file path\n",
+    "\n",
+    "file_path = \"../Dataset/training_data.csv\"  \n",
     "df = pd.read_csv(file_path)\n",
     "\n",
-    "# Display first few rows\n",
+    "\n",
     "df.head()\n"
    ]
   },
@@ -317,7 +316,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
@@ -338,11 +337,11 @@
     }
    ],
    "source": [
-    "# Convert boolean columns to integer (0 or 1)\n",
+    "\n",
     "bool_cols = [\"verified\", \"default_profile\", \"default_profile_image\"]\n",
     "df[bool_cols] = df[bool_cols].astype(int)\n",
     "\n",
-    "# Verify changes\n",
+    "\n",
     "print(df.dtypes[bool_cols])\n"
    ]
   },
@@ -352,14 +351,14 @@
     "id": "UWtBhVBX8Hy2"
    },
    "source": [
-    "#Data Visualization\n",
+    "# Data Visualization\n",
     "Visualizing the distribution of numerical features to understand data patterns.\n",
     "This helps in identifying skewness, outliers, and differences between bot and non-bot accounts.\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -381,26 +380,22 @@
     }
    ],
    "source": [
-    "# ---------------- Feature Distributions (Histograms & KDE) ---------------- #\n",
     "\n",
-    "# Define numeric columns for visualization\n",
     "num_cols = [\n",
     "    \"followers_count\", \"friends_count\", \"listedcount\", \"favourites_count\",\n",
     "    \"statuses_count\", \"verified\", \"default_profile\", \"default_profile_image\", \"bot\"\n",
     "]\n",
     "\n",
-    "# Reduce figure size while maintaining clarity\n",
     "plt.figure(figsize=(12, 8))\n",
     "\n",
-    "# Loop through numeric columns and plot\n",
     "for i, col in enumerate(num_cols):\n",
     "    plt.subplot(3, 3, i + 1)\n",
     "    sns.histplot(df[col], bins=20, kde=True)\n",
-    "    plt.title(f\"{col} Distribution\", fontsize=10)  # Reduce title font size\n",
-    "    plt.xlabel(\"\")  # Remove x-labels for cleaner visuals\n",
+    "    plt.title(f\"{col} Distribution\", fontsize=10) \n",
+    "    plt.xlabel(\"\")  \n",
     "    plt.ylabel(\"\")\n",
     "\n",
-    "plt.tight_layout(pad=1)  # Adjust padding for compact layout\n",
+    "plt.tight_layout(pad=1) \n",
     "plt.show()\n",
     "\n"
    ]
@@ -414,7 +409,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -436,26 +431,24 @@
     }
    ],
    "source": [
-    "# ---------------- Boxplots vs. Bot Label ---------------- #\n",
+    "# Boxplots vs. Bot Label\n",
     "\n",
-    "# Reduce figure size while maintaining readability\n",
     "plt.figure(figsize=(12, 9))\n",
     "\n",
-    "# Loop through numeric columns and plot boxplots\n",
     "for i, col in enumerate(num_cols):\n",
     "    plt.subplot(3, 3, i + 1)\n",
     "    sns.boxplot(x=df[\"bot\"], y=df[col])\n",
-    "    plt.title(f\"{col} vs. Bot\", fontsize=10)  # Smaller font size for compact view\n",
-    "    plt.xlabel(\"\")  # Remove x-labels for cleaner visualization\n",
+    "    plt.title(f\"{col} vs. Bot\", fontsize=10) \n",
+    "    plt.xlabel(\"\")  \n",
     "    plt.ylabel(\"\")\n",
     "\n",
-    "plt.tight_layout(pad=1)  # Adjust padding for compact layout\n",
+    "plt.tight_layout(pad=1) \n",
     "plt.show()\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -477,19 +470,18 @@
     }
    ],
    "source": [
-    "# ---------------- Violin Plots vs. Bot Label ---------------- #\n",
+    "# Violin Plots vs. Bot Label \n",
     "\n",
     "plt.figure(figsize=(12, 9))\n",
     "\n",
-    "# Loop through numeric columns and plot violin plots\n",
     "for i, col in enumerate(num_cols):\n",
     "    plt.subplot(3, 3, i + 1)\n",
     "    sns.violinplot(x=df[\"bot\"], y=df[col])\n",
     "    plt.title(f\"{col} vs. Bot\", fontsize=10)\n",
-    "    plt.xlabel(\"\")  # Remove x-labels for cleaner visualization\n",
+    "    plt.xlabel(\"\") \n",
     "    plt.ylabel(\"\")\n",
     "\n",
-    "plt.tight_layout(pad=1)  # Adjust padding for compact layout\n",
+    "plt.tight_layout(pad=1)  \n",
     "plt.show()\n"
    ]
   },
@@ -511,7 +503,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": null,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -533,8 +525,8 @@
     }
    ],
    "source": [
-    "# Pair Plot with Reduced Size\n",
-    "sns.pairplot(df[num_cols], diag_kind=\"kde\", corner=True, height=1.5)  # Reduce height\n",
+    "# SNS Pairplot\n",
+    "sns.pairplot(df[num_cols], diag_kind=\"kde\", corner=True, height=1.5)  \n",
     "plt.show()\n"
    ]
   },
@@ -559,7 +551,7 @@
     "id": "PIGWwIhF9HT_"
    },
    "source": [
-    "#Correlation Heatmap\n",
+    "# Correlation Heatmap\n",
     "\n",
     "This heatmap visualizes the correlation between numerical features.\n",
     "Strong correlations indicate possible redundancy, while weak correlations may suggest independent variables.\n",
@@ -568,7 +560,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": null,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -590,7 +582,7 @@
     }
    ],
    "source": [
-    "# ---------------- Correlation Heatmap ---------------- #\n",
+    "\n",
     "plt.figure(figsize=(12, 8))\n",
     "corr_matrix = df[num_cols].corr()\n",
     "\n",
@@ -643,7 +635,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.0"
+   "version": "3.10.11"
   }
  },
  "nbformat": 4,