Add Jupyter notebook for loading and analyzing RAG scores from CSV

test_RAG.ipynb

@@ -0,0 +1,295 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "81bb23ad",
+   "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>query</th>\n",
+       "      <th>semantic_similarity</th>\n",
+       "      <th>rougeL_f1</th>\n",
+       "      <th>status</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>What is the Berry Export Summary 2028 and what...</td>\n",
+       "      <td>0.8763</td>\n",
+       "      <td>0.3206</td>\n",
+       "      <td>PASS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>What are some of the benefits reported from ha...</td>\n",
+       "      <td>0.9655</td>\n",
+       "      <td>0.6016</td>\n",
+       "      <td>PASS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>What are the unique features of the Coolands f...</td>\n",
+       "      <td>0.7942</td>\n",
+       "      <td>0.2519</td>\n",
+       "      <td>PASS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>What is the main difference between the Nation...</td>\n",
+       "      <td>0.9024</td>\n",
+       "      <td>0.2597</td>\n",
+       "      <td>PASS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>How did Gunnar Nelson win the fight against Za...</td>\n",
+       "      <td>0.8510</td>\n",
+       "      <td>0.3101</td>\n",
+       "      <td>PASS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>What are some of the features of Fabiana Filip...</td>\n",
+       "      <td>0.9099</td>\n",
+       "      <td>0.2963</td>\n",
+       "      <td>PASS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>How did Dan Foley feel about his portrayal on ...</td>\n",
+       "      <td>0.9170</td>\n",
+       "      <td>0.4444</td>\n",
+       "      <td>PASS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>What is the reason for the closure of the comm...</td>\n",
+       "      <td>0.8298</td>\n",
+       "      <td>0.3636</td>\n",
+       "      <td>PASS</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>What are the five love and relationship podcas...</td>\n",
+       "      <td>0.7104</td>\n",
+       "      <td>0.1860</td>\n",
+       "      <td>FAIL</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>Which two teams dropped out of the Primal Ques...</td>\n",
+       "      <td>0.9701</td>\n",
+       "      <td>0.4258</td>\n",
+       "      <td>PASS</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                               query  semantic_similarity  \\\n",
+       "0  What is the Berry Export Summary 2028 and what...               0.8763   \n",
+       "1  What are some of the benefits reported from ha...               0.9655   \n",
+       "2  What are the unique features of the Coolands f...               0.7942   \n",
+       "3  What is the main difference between the Nation...               0.9024   \n",
+       "4  How did Gunnar Nelson win the fight against Za...               0.8510   \n",
+       "5  What are some of the features of Fabiana Filip...               0.9099   \n",
+       "6  How did Dan Foley feel about his portrayal on ...               0.9170   \n",
+       "7  What is the reason for the closure of the comm...               0.8298   \n",
+       "8  What are the five love and relationship podcas...               0.7104   \n",
+       "9  Which two teams dropped out of the Primal Ques...               0.9701   \n",
+       "\n",
+       "   rougeL_f1 status  \n",
+       "0     0.3206   PASS  \n",
+       "1     0.6016   PASS  \n",
+       "2     0.2519   PASS  \n",
+       "3     0.2597   PASS  \n",
+       "4     0.3101   PASS  \n",
+       "5     0.2963   PASS  \n",
+       "6     0.4444   PASS  \n",
+       "7     0.3636   PASS  \n",
+       "8     0.1860   FAIL  \n",
+       "9     0.4258   PASS  "
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Load scores from CSV\n",
+    "\n",
+    "import pandas as pd\n",
+    "\n",
+    "df = pd.read_csv(\"rag_scores.csv\")\n",
+    "\n",
+    "df.head(10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "58e0482f",
+   "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>semantic_similarity</th>\n",
+       "      <th>rougeL_f1</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>75.000000</td>\n",
+       "      <td>75.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mean</th>\n",
+       "      <td>0.852692</td>\n",
+       "      <td>0.395061</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>std</th>\n",
+       "      <td>0.088759</td>\n",
+       "      <td>0.216511</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>min</th>\n",
+       "      <td>0.591500</td>\n",
+       "      <td>0.098600</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25%</th>\n",
+       "      <td>0.794600</td>\n",
+       "      <td>0.251600</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>50%</th>\n",
+       "      <td>0.873200</td>\n",
+       "      <td>0.325600</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75%</th>\n",
+       "      <td>0.918150</td>\n",
+       "      <td>0.495100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>max</th>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>1.000000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       semantic_similarity  rougeL_f1\n",
+       "count            75.000000  75.000000\n",
+       "mean              0.852692   0.395061\n",
+       "std               0.088759   0.216511\n",
+       "min               0.591500   0.098600\n",
+       "25%               0.794600   0.251600\n",
+       "50%               0.873200   0.325600\n",
+       "75%               0.918150   0.495100\n",
+       "max               1.000000   1.000000"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "a9073d52",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "status\n",
+       "PASS    64\n",
+       "FAIL    11\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['status'].value_counts()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "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": "3.12.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}