Reshape data; restyle table

andylolz · May 1, 2024 · 3c0ed61 · 3c0ed61
1 parent b5d9fcb
commit 3c0ed61
Show file tree

Hide file tree

Showing 2 changed files with 65 additions and 18 deletions.
diff --git a/output/index.html b/output/index.html
@@ -7,26 +7,42 @@
   <meta charset="utf-8">
   <meta name="viewport" content="width=device-width, initial-scale=1">
   <title>Community notes</title>
+  <link href="//cdn.jsdelivr.net/npm/[email protected]/dist/css/bootstrap.min.css" rel="stylesheet" integrity="sha384-QWTKZyjpPEjISv5WaRU9OFeRpok6YctnYmDr5pNlyT2bRjXh0JMhjY6hW+ALEwIH" crossorigin="anonymous">
+  <link rel="stylesheet" href="//cdn.datatables.net/v/bs5/jq-3.7.0/dt-2.0.5/datatables.min.css">
 </head>
 <body>
 
-<table>
+<table class="table table-striped">
   {% for row in site.data.notes %}
-    {% if forloop.first %}
+  {% if forloop.first %}
+  <thead>
     <tr>
-      {% for pair in row %}
-        <th>{{ pair[0] }}</th>
-      {% endfor %}
+      <th>Tweet</th>
+      <th>Classification</th>
+      <th>Reasons</th>
+      <th>Summary</th>
     </tr>
-    {% endif %}
+  </thead>
+  <tbody>
+  {% endif %}
 
-    {% tablerow pair in row %}
-      {{ pair[1] }}
-    {% endtablerow %}
+    <tr>
+      <td><a target="_blank" href="https://twitter.com/_/status/{{ row['tweet_id'] }}">{{ row['created_at'] }}</a></td>
+      <td>{{ row['classification'] }}</td>
+      <td>{{ row['reasons'] }}</td>
+      <td>{{ row['summary'] }}</td>
+    </tr>
   {% endfor %}
+  </tbody>
 </table>
 
-<script src="https://cdnjs.cloudflare.com/ajax/libs/Sortable/1.15.2/Sortable.min.js" integrity="sha512-TelkP3PCMJv+viMWynjKcvLsQzx6dJHvIGhfqzFtZKgAjKM1YPqcwzzDEoTc/BHjf43PcPzTQOjuTr4YdE8lNQ==" crossorigin="anonymous" referrerpolicy="no-referrer"></script>
+<!-- <script src="//code.jquery.com/jquery-3.7.1.slim.min.js" integrity="sha256-kmHvs0B+OpCW5GVHUNjv9rOmY0IvSIRcf7zGUDTDQM8=" crossorigin="anonymous"></script> -->
+<script src="//cdn.datatables.net/v/bs5/jq-3.7.0/dt-2.0.5/datatables.min.js"></script>
+<script>
+  let table = new DataTable('table', {
+    // options
+  });
+</script>
 </body>
 </html>
 <html>
diff --git a/script.py b/script.py
@@ -5,7 +5,28 @@
 
 
 def to_isoformat(ms_since_epoch):
-    return str(datetime.utcfromtimestamp(int(ms_since_epoch) / 1000))
+    return str(datetime.utcfromtimestamp(int(ms_since_epoch[:-3])))
+
+
+reasons = {
+    "misleadingOther": "Other",
+    "misleadingFactualError": "Factual error",
+    "misleadingManipulatedMedia": "Manipulated media",
+    "misleadingOutdatedInformation": "Outdated information",
+    "misleadingMissingImportantContext": "Missing important context",
+    "misleadingUnverifiedClaimAsFact": "Unverified claim as fact",
+    "misleadingSatire": "Satire",
+    "notMisleadingOther": "Other",
+    "notMisleadingFactuallyCorrect": "Factually correct",
+    "notMisleadingOutdatedButNotWhenWritten": "Outdated (but not when written)",
+    "notMisleadingClearlySatire": "Clearly satire",
+    "notMisleadingPersonalOpinion": "Personal opinion",
+}
+def get_reasons(row):
+    return ", ".join([
+        v for k, v in reasons.items()
+        if bool(int(row[k]))
+    ])
 
 
 def get_data(date):
@@ -39,10 +60,20 @@ def get_generator():
 with open("output/_data/notes.csv", "w") as fh:
     writer = None
     for row in get_generator():
-        if "fullfact" in row["summary"].lower():
-            row["createdAt"] = to_isoformat(row["createdAtMillis"])
-            del row["createdAtMillis"]
-            if not writer:
-                writer = csv.DictWriter(fh, fieldnames=row.keys())
-                writer.writeheader()
-            _ = writer.writerow(row)
+        if "fullfact" not in row["summary"].lower():
+            # filter out non-fullfact stuff
+            continue
+        output = {
+            "tweet_id": row["tweetId"],
+            "note_id": row["noteId"],
+            "note_author_id": row["noteAuthorParticipantId"],
+            "classification": row["classification"].replace("_", " ").lower().capitalize(),
+            "reasons": get_reasons(row),
+            "summary": row["summary"],
+            "trustworthy_source": bool(row["trustworthySources"]),
+            "created_at": to_isoformat(row["createdAtMillis"]),
+        }
+        if not writer:
+            writer = csv.DictWriter(fh, fieldnames=output.keys())
+            writer.writeheader()
+        _ = writer.writerow(output)