From 89db1d8673be36e4e02e8acca6704b0888a5096c Mon Sep 17 00:00:00 2001
From: Paul Gauthier <aider@paulg.org>
Date: Mon, 6 May 2024 11:50:10 -0700
Subject: [PATCH] aider: Added a second bar for `row.percent_cases_well_formed`
 to each graph.

# Aider chat conversation:

USER: in each graph, give each model a second bar showing row.percent_cases_well_formed

ASSISTANT: Here are the changes to add a second bar for `row.percent_cases_well_formed` to each graph:

docs/leaderboards/index.md
```markdown
<<<<<<< SEARCH
    var leaderboardData = {
      labels: [],
      datasets: [{
        label: 'Percent correct on code editing tasks',
        data: [],
        backgroundColor: 'rgba(54, 162, 235, 0.2)',
        borderColor: 'rgba(54, 162, 235, 1)',
        borderWidth: 1
      }]
    };

    {% for row in edit_sorted %}
      leaderboardData.labels.push('{{ row.model }}');
      leaderboardData.datasets[0].data.push({{ row.pass_rate_2 }});
    {% endfor %}
=======
    var leaderboardData = {
      labels: [],
      datasets: [{
        label: 'Percent correct on code editing tasks',
        data: [],
        backgroundColor: 'rgba(54, 162, 235, 0.2)',
        borderColor: 'rgba(54, 162, 235, 1)',
        borderWidth: 1
      },
      {
        label: 'Percent cases well formed',
        data: [],
        backgroundColor: 'rgba(255, 99, 132, 0.2)',
        borderColor: 'rgba(255, 99, 132, 1)',
        borderWidth: 1
      }]
    };

    {% for row in edit_sorted %}
      leaderboardData.labels.push('{{ row.model }}');
      leaderboardData.datasets[0].data.push({{ row.pass_rate_2 }});
      leaderboardData.datasets[1].data.push({{ row.percent_cases_well_formed }});
    {% endfor %}
>>>>>>> REPLACE
```

docs/leaderboards/index.md
```markdown
<<<<<<< SEARCH
    var leaderboardData = {
      labels: [],
      datasets: [{
        label: 'Percent correct on code refactoring tasks',
        data: [],
        backgroundColor: 'rgba(54, 162, 235, 0.2)',
        borderColor: 'rgba(54, 162, 235, 1)',
        borderWidth: 1
      }]
    };

    {% for row in refac_sorted %}
      leaderboardData.labels.push('{{ row.model }}');
      leaderboardData.datasets[0].data.push({{ row.pass_rate_1 }});
    {% endfor %}
=======
    var leaderboardData = {
      labels: [],
      datasets: [{
        label: 'Percent correct on code refactoring tasks',
        data: [],
        backgroundColor: 'rgba(54, 162, 235, 0.2)',
        borderColor: 'rgba(54, 162, 235, 1)',
        borderWidth: 1
      },
      {
        label: 'Percent cases well formed',
        data: [],
        backgroundColor: 'rgba(255, 99, 132, 0.2)',
        borderColor: 'rgba(255, 99, 132, 1)',
        borderWidth: 1
      }]
    };

    {% for row in refac_sorted %}
      leaderboardData.labels.push('{{ row.model }}');
      leaderboardData.datasets[0].data.push({{ row.pass_rate_1 }});
      leaderboardData.datasets[1].data.push({{ row.percent_cases_well_formed }});
    {% endfor %}
>>>>>>> REPLACE
```

This adds a second dataset to each chart's `leaderboardData`, with a label of "Percent cases well formed". It sets different colors for the bars and borders.

Then in the loop that populates the data, it pushes the `row.percent_cases_well_formed` value into the second dataset.

With these changes, each model will have two bars - one for the pass rate and one for the percent of cases that were well formed.
---
 docs/leaderboards/index.md | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/docs/leaderboards/index.md b/docs/leaderboards/index.md
index 8340def79..3e64f0226 100644
--- a/docs/leaderboards/index.md
+++ b/docs/leaderboards/index.md
@@ -56,12 +56,20 @@ it will work best with models that score well on the benchmarks.
         backgroundColor: 'rgba(54, 162, 235, 0.2)',
         borderColor: 'rgba(54, 162, 235, 1)',
         borderWidth: 1
+      },
+      {
+        label: 'Percent cases well formed',
+        data: [],
+        backgroundColor: 'rgba(255, 99, 132, 0.2)',
+        borderColor: 'rgba(255, 99, 132, 1)',
+        borderWidth: 1
       }]
     };
 
     {% for row in edit_sorted %}
       leaderboardData.labels.push('{{ row.model }}');
       leaderboardData.datasets[0].data.push({{ row.pass_rate_2 }});
+      leaderboardData.datasets[1].data.push({{ row.percent_cases_well_formed }});
     {% endfor %}
 
     var leaderboardChart = new Chart(ctx, {
@@ -124,12 +132,20 @@ Therefore, results are available for fewer models.
         backgroundColor: 'rgba(54, 162, 235, 0.2)',
         borderColor: 'rgba(54, 162, 235, 1)',
         borderWidth: 1
+      },
+      {
+        label: 'Percent cases well formed',
+        data: [],
+        backgroundColor: 'rgba(255, 99, 132, 0.2)',
+        borderColor: 'rgba(255, 99, 132, 1)',
+        borderWidth: 1
       }]
     };
 
     {% for row in refac_sorted %}
       leaderboardData.labels.push('{{ row.model }}');
       leaderboardData.datasets[0].data.push({{ row.pass_rate_1 }});
+      leaderboardData.datasets[1].data.push({{ row.percent_cases_well_formed }});
     {% endfor %}
 
     var leaderboardChart = new Chart(ctx, {