Final_Assignment_Template

Sleeping

App Files Files Community

Romain Fayoux commited on about 1 month ago

Commit

279f51f

1 Parent(s): 58f5703

Corrected eval to discard exact match as it is not the eval used by the

Browse files

Files changed (1) hide show

eval/eval_notebook.ipynb +33 -12

eval/eval_notebook.ipynb CHANGED Viewed

@@ -2,21 +2,30 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 29,
    "metadata": {},
-   "outputs": [],
    "source": [
     "import pandas as pd\n",
     "import json\n",
     "from phoenix.client import Client\n",
     "\n",
     "# Load the existing spans\n",
-    "spans_df = Client().spans.get_spans_dataframe(project_name=\"default\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -26,7 +35,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -36,14 +45,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/var/folders/pj/v1zrqj1d10x9_1rd2njh_r_r0000gn/T/ipykernel_36696/3107371246.py:2: SettingWithCopyWarning: \n",
       "A value is trying to be set on a copy of a slice from a DataFrame.\n",
       "Try using .loc[row_indexer,col_indexer] = value instead\n",
       "\n",
@@ -60,9 +69,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
    "metadata": {},
-   "outputs": [],
    "source": [
     "from phoenix.evals.evaluators import bind_evaluator, async_evaluate_dataframe\n",
     "from evaluators import conciseness_evaluator\n",
@@ -71,12 +92,12 @@
     "# Define the evaluator\n",
     "conciseness_evaluator = bind_evaluator(evaluator=conciseness_evaluator, input_mapping={ \"output\": \"attributes.output.value\", \"expected\": \"Final answer\"})\n",
     "question_scorer_eval = bind_evaluator(evaluator=question_scorer, input_mapping={ \"output\": \"attributes.output.value\", \"expected\": \"Final answer\"})\n",
-    "results_df = await async_evaluate_dataframe(agents_merged_df, evaluators=[exact_match_eval, conciseness_evaluator, question_scorer_eval])\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -88,7 +109,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
    "metadata": {},
    "outputs": [
     {

  "cells": [
   {
    "cell_type": "code",
+   "execution_count": 1,
    "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/romainfayoux/Documents/Programmation/Final_Assignment_Template/.venv/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    }
+   ],
    "source": [
     "import pandas as pd\n",
     "import json\n",
     "from phoenix.client import Client\n",
     "\n",
     "# Load the existing spans\n",
+    "spans_df = Client().spans.get_spans_dataframe(project_name=\"default\", start_time=\"2025-10-23\")"
    ]
   },
   {
    "cell_type": "code",
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
   },
   {
    "cell_type": "code",
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
   },
   {
    "cell_type": "code",
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
+      "/var/folders/pj/v1zrqj1d10x9_1rd2njh_r_r0000gn/T/ipykernel_35129/3107371246.py:2: SettingWithCopyWarning: \n",
       "A value is trying to be set on a copy of a slice from a DataFrame.\n",
       "Try using .loc[row_indexer,col_indexer] = value instead\n",
       "\n",
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {},
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'exact_match_eval' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
+      "\u001b[31mNameError\u001b[39m                                 Traceback (most recent call last)",
+      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[5]\u001b[39m\u001b[32m, line 8\u001b[39m\n\u001b[32m      6\u001b[39m conciseness_evaluator = bind_evaluator(evaluator=conciseness_evaluator, input_mapping={ \u001b[33m\"\u001b[39m\u001b[33moutput\u001b[39m\u001b[33m\"\u001b[39m: \u001b[33m\"\u001b[39m\u001b[33mattributes.output.value\u001b[39m\u001b[33m\"\u001b[39m, \u001b[33m\"\u001b[39m\u001b[33mexpected\u001b[39m\u001b[33m\"\u001b[39m: \u001b[33m\"\u001b[39m\u001b[33mFinal answer\u001b[39m\u001b[33m\"\u001b[39m})\n\u001b[32m      7\u001b[39m question_scorer_eval = bind_evaluator(evaluator=question_scorer, input_mapping={ \u001b[33m\"\u001b[39m\u001b[33moutput\u001b[39m\u001b[33m\"\u001b[39m: \u001b[33m\"\u001b[39m\u001b[33mattributes.output.value\u001b[39m\u001b[33m\"\u001b[39m, \u001b[33m\"\u001b[39m\u001b[33mexpected\u001b[39m\u001b[33m\"\u001b[39m: \u001b[33m\"\u001b[39m\u001b[33mFinal answer\u001b[39m\u001b[33m\"\u001b[39m})\n\u001b[32m----> \u001b[39m\u001b[32m8\u001b[39m results_df = \u001b[38;5;28;01mawait\u001b[39;00m async_evaluate_dataframe(agents_merged_df, evaluators=[\u001b[43mexact_match_eval\u001b[49m, conciseness_evaluator, question_scorer_eval])\n",
+      "\u001b[31mNameError\u001b[39m: name 'exact_match_eval' is not defined"
+     ]
+    }
+   ],
    "source": [
     "from phoenix.evals.evaluators import bind_evaluator, async_evaluate_dataframe\n",
     "from evaluators import conciseness_evaluator\n",
     "# Define the evaluator\n",
     "conciseness_evaluator = bind_evaluator(evaluator=conciseness_evaluator, input_mapping={ \"output\": \"attributes.output.value\", \"expected\": \"Final answer\"})\n",
     "question_scorer_eval = bind_evaluator(evaluator=question_scorer, input_mapping={ \"output\": \"attributes.output.value\", \"expected\": \"Final answer\"})\n",
+    "results_df = await async_evaluate_dataframe(agents_merged_df, evaluators=[conciseness_evaluator, question_scorer_eval])\n"
    ]
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {