Duplicate from bigcode/clean-issues-visualization

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Clean Issues Visualization
+emoji: 🐨
+colorFrom: red
+colorTo: purple
+sdk: streamlit
+sdk_version: 1.17.0
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: bigcode/clean-issues-visualization
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,26 @@
+import streamlit as st
+import json
+from datasets import load_dataset
+
+st.set_page_config(page_title="Clean GitHub Issues", layout="wide")
+st.title("GitHub Issues visualization after filtering")
+
+@st.cache()
+def load_data():
+    ds = load_dataset("loubnabnl/preprocessed-issues", split="train")
+    return ds
+
+def print_issue(events):
+    for event in events:
+        st.markdown("""---""")
+        masked_author = f"masked as {event['masked_author']}" if "masked_author" in event else ""
+        st.markdown(f"**Author:** {event['author']} {masked_author}, {event['action']} {event['type']} with title: {event['title']}")
+        st.code(f"{event['text']}", language="html")
+
+samples = load_data()
+col1, _ = st.columns([2, 4])
+with col1:
+    index_example = st.number_input(f"Index of the chosen conversation from the existing {len(samples)}", min_value=0, max_value=len(samples)-1, value=0, step=1)
+
+st.write(f"Issue size: {samples[index_example]['text_size_no_bots']}\n\n")
+print_issue(samples[index_example]["events"])