Duplicate from nlphuji/whoops-explorer

Co-authored-by: Yonatan <yonatanbitton@users.noreply.huggingface.co>

.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

.gitignore

@@ -0,0 +1,171 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+.idea
+.idea/
+*.idea
+
+inspectionProfiles
+inspectionProfiles/
+
+debug_dataset.py
+app2.py
+app_tabs.py
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

README.md

@@ -0,0 +1,13 @@
+---
+title: Wmtis Explorer
+emoji: 🔥
+colorFrom: purple
+colorTo: blue
+sdk: gradio
+sdk_version: 3.16.2
+app_file: app.py
+pinned: false
+duplicated_from: nlphuji/whoops-explorer
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,85 @@
+import random
+
+import gradio as gr
+from datasets import load_dataset
+
+whoops = load_dataset("nlphuji/whoops")['test']
+print(f"Loaded WMTIS, first example:")
+print(whoops[0])
+dataset_size = len(whoops)
+print(f"all dataset size: {dataset_size}")
+
+IMAGE = 'image'
+IMAGE_DESIGNER = 'image_designer'
+DESIGNER_EXPLANATION = 'designer_explanation'
+CROWD_CAPTIONS = 'crowd_captions'
+CROWD_EXPLANATIONS = 'crowd_explanations'
+CROWD_UNDERSPECIFIED_CAPTIONS = 'crowd_underspecified_captions'
+SELECTED_CAPTION = 'selected_caption'
+COMMONSENSE_CATEGORY = 'commonsense_category'
+QA = 'question_answering_pairs'
+IMAGE_ID = 'image_id'
+left_side_columns = [IMAGE]
+# right_side_columns = [x for x in whoops.features.keys() if x not in left_side_columns and x not in [QA]]
+right_side_columns = [x for x in whoops.features.keys() if x not in left_side_columns]
+enumerate_cols = [CROWD_CAPTIONS, CROWD_EXPLANATIONS, CROWD_UNDERSPECIFIED_CAPTIONS]
+emoji_to_label = {IMAGE_DESIGNER: '🎨, 🧑‍🎨, 💻', DESIGNER_EXPLANATION: '💡, 🤔, 🧑‍🎨',
+                  CROWD_CAPTIONS: '👥, 💬, 📝', CROWD_EXPLANATIONS: '👥, 💡, 🤔', CROWD_UNDERSPECIFIED_CAPTIONS: '👥, 💬, 👎',
+                  QA: '❓, 🤔, 💡', IMAGE_ID: '🔍, 📄, 💾', COMMONSENSE_CATEGORY: '🤔, 📚, 💡', SELECTED_CAPTION: '📝, 👌, 💬'}
+target_size = (1024, 1024)
+MAX_LINES = 30
+
+def get_instance_values(example):
+    values = []
+    for k in left_side_columns + right_side_columns:
+        if k in enumerate_cols:
+            value = list_to_string(example[k])
+        elif k == QA:
+            qa_list = [f"Q: {x[0]} A: {x[1]}" for x in example[k]]
+            value = list_to_string(qa_list)
+        else:
+            value = example[k]
+        values.append(value)
+    return values
+
+
+def list_to_string(lst):
+    return '\n'.join(['{}. {}'.format(i + 1, item) for i, item in enumerate(lst)])
+
+def plot_image(index):
+    example = whoops_sample[index]
+    instance_values = get_instance_values(example)
+    assert len(left_side_columns) == len(
+        instance_values[:len(left_side_columns)])  # excluding the image & designer
+    for key, value in zip(left_side_columns, instance_values[:len(left_side_columns)]):
+        if key == IMAGE:
+            img = whoops_sample[index]["image"]
+            img_resized = img.resize(target_size)
+            gr.Image(value=img_resized, label=whoops_sample[index]['commonsense_category'])
+        else:
+            label = key.capitalize().replace("_", " ")
+            gr.Textbox(value=value, label=f"{label} {emoji_to_label[key]}")
+    with gr.Accordion("Click for details", open=False):
+        assert len(right_side_columns) == len(
+            instance_values[len(left_side_columns):])  # excluding the image & designer
+        for key, value in zip(right_side_columns, instance_values[len(left_side_columns):]):
+            label = key.capitalize().replace("_", " ")
+            gr.Textbox(value=value, label=f"{label} {emoji_to_label[key]}", max_lines=MAX_LINES)
+
+
+columns_number = 4
+# rows_number = int(dataset_size / columns_number)
+# rows_number = 25
+rows_number = 20
+whoops_sample = whoops.shuffle().select(range(0, columns_number * rows_number))
+index = 0
+
+with gr.Blocks() as demo:
+    gr.Markdown(f"# WHOOPS! Dataset Explorer")
+    for row_num in range(0, rows_number):
+        with gr.Row():
+            for col_num in range(0, columns_number):
+                with gr.Column():
+                    plot_image(index)
+                    index += 1
+demo.launch()

app2.py

@@ -0,0 +1,116 @@
+import random
+
+import gradio as gr
+from datasets import load_dataset
+
+whoops = load_dataset("nlphuji/whoops")['test']
+print(f"Loaded WMTIS, first example:")
+print(whoops[0])
+dataset_size = len(whoops)
+print(f"all dataset size: {dataset_size}")
+
+IMAGE = 'image'
+IMAGE_DESIGNER = 'image_designer'
+DESIGNER_EXPLANATION = 'designer_explanation'
+CROWD_CAPTIONS = 'crowd_captions'
+CROWD_EXPLANATIONS = 'crowd_explanations'
+CROWD_UNDERSPECIFIED_CAPTIONS = 'crowd_underspecified_captions'
+SELECTED_CAPTION = 'selected_caption'
+COMMONSENSE_CATEGORY = 'commonsense_category'
+QA = 'question_answering_pairs'
+IMAGE_ID = 'image_id'
+left_side_columns = [IMAGE]
+# right_side_columns = [x for x in whoops.features.keys() if x not in left_side_columns and x not in [QA]]
+right_side_columns = [x for x in whoops.features.keys() if x not in left_side_columns]
+enumerate_cols = [CROWD_CAPTIONS, CROWD_EXPLANATIONS, CROWD_UNDERSPECIFIED_CAPTIONS]
+emoji_to_label = {IMAGE_DESIGNER: '🎨, 🧑‍🎨, 💻', DESIGNER_EXPLANATION: '💡, 🤔, 🧑‍🎨',
+                  CROWD_CAPTIONS: '👥, 💬, 📝', CROWD_EXPLANATIONS: '👥, 💡, 🤔', CROWD_UNDERSPECIFIED_CAPTIONS: '👥, 💬, 👎',
+                  QA: '❓, 🤔, 💡', IMAGE_ID: '🔍, 📄, 💾', COMMONSENSE_CATEGORY: '🤔, 📚, 💡', SELECTED_CAPTION: '📝, 👌, 💬'}
+target_size = (1024, 1024)
+MAX_LINES = 30
+
+def get_instance_values(example):
+    values = []
+    for k in left_side_columns + right_side_columns:
+        if k in enumerate_cols:
+            value = list_to_string(example[k])
+        elif k == QA:
+            qa_list = [f"Q: {x[0]} A: {x[1]}" for x in example[k]]
+            value = list_to_string(qa_list)
+        else:
+            value = example[k]
+        values.append(value)
+    return values
+
+
+def list_to_string(lst):
+    return '\n'.join(['{}. {}'.format(i + 1, item) for i, item in enumerate(lst)])
+
+def plot_image(index):
+    example = whoops_sample[index]
+    instance_values = get_instance_values(example)
+    assert len(left_side_columns) == len(
+        instance_values[:len(left_side_columns)])  # excluding the image & designer
+    for key, value in zip(left_side_columns, instance_values[:len(left_side_columns)]):
+        if key == IMAGE:
+            img = whoops_sample[index]["image"]
+            img_resized = img.resize(target_size)
+            gr.Image(value=img_resized, label=whoops_sample[index]['commonsense_category'])
+        else:
+            label = key.capitalize().replace("_", " ")
+            gr.Textbox(value=value, label=f"{label} {emoji_to_label[key]}")
+    with gr.Accordion("Click for details", open=False):
+        assert len(right_side_columns) == len(
+            instance_values[len(left_side_columns):])  # excluding the image & designer
+        for key, value in zip(right_side_columns, instance_values[len(left_side_columns):]):
+            label = key.capitalize().replace("_", " ")
+            gr.Textbox(value=value, label=f"{label} {emoji_to_label[key]}", max_lines=MAX_LINES)
+
+
+columns_number = 4
+# rows_number = int(dataset_size / columns_number)
+# rows_number = 25
+rows_number = 20
+whoops_sample = whoops.shuffle().select(range(0, columns_number * rows_number))
+index = 0
+LINES_NUMBER = 20
+
+def display_df():
+    df_images = df.head(LINES_NUMBER)
+    return df_images
+
+def display_next(dataframe, end):
+    start = int(end or len(dataframe))
+    end = int(start) + int(LINES_NUMBER)
+    global df
+    if end >= len(df) - 1:
+        start = 0
+        end = LINES_NUMBER
+        df = df.sample(frac=1)
+        print(f"Shuffle")
+    # print(f"end: {end},start: {start}")
+    df_images = df.iloc[start:end]
+    assert len(df_images) == LINES_NUMBER
+    return df_images, end
+
+
+with gr.Blocks() as demo:
+    gr.Markdown(f"# WHOOPS! Dataset Explorer")
+
+    with gr.Row():
+        num_end = gr.Number(visible=False)
+        b1 = gr.Button("Get Initial dataframe")
+        b2 = gr.Button("Next Rows")
+
+    for row_num in range(0, int(LINES_NUMBER / columns_number)):
+        with gr.Row():
+            for col_num in range(0, columns_number):
+                with gr.Column():
+                    plot_image(index)
+                    index += 1
+
+    b1.click(fn=display_df, outputs=out_dataframe, api_name="initial_dataframe")
+    b2.click(fn=display_next, inputs=[out_dataframe, num_end], outputs=[out_dataframe, num_end],
+             api_name="next_rows")
+
+demo.launch()

app_tabs.py

@@ -0,0 +1,90 @@
+import random
+
+import gradio as gr
+from datasets import load_dataset
+
+wmtis = load_dataset("nlphuji/whoops")['test']
+print(f"Loaded WMTIS, first example:")
+print(wmtis[0])
+dataset_size = len(wmtis)
+print(f"dataset_size: {dataset_size}")
+
+IMAGE = 'image'
+IMAGE_DESIGNER = 'image_designer'
+DESIGNER_EXPLANATION = 'designer_explanation'
+CROWD_CAPTIONS = 'crowd_captions'
+CROWD_EXPLANATIONS = 'crowd_explanations'
+CROWD_UNDERSPECIFIED_CAPTIONS = 'crowd_underspecified_captions'
+SELECTED_CAPTION = 'selected_caption'
+COMMONSENSE_CATEGORY = 'commonsense_category'
+QA = 'question_answering_pairs'
+IMAGE_ID = 'image_id'
+left_side_columns = [IMAGE]
+right_side_columns = [x for x in wmtis.features.keys() if x not in left_side_columns and x not in [QA]]
+enumerate_cols = [CROWD_CAPTIONS, CROWD_EXPLANATIONS, CROWD_UNDERSPECIFIED_CAPTIONS]
+emoji_to_label = {IMAGE_DESIGNER: '🎨, 🧑‍🎨, 💻', DESIGNER_EXPLANATION: '💡, 🤔, 🧑‍🎨',
+                  CROWD_CAPTIONS: '👥, 💬, 📝', CROWD_EXPLANATIONS: '👥, 💡, 🤔', CROWD_UNDERSPECIFIED_CAPTIONS: '👥, 💬, 👎',
+                  QA: '❓, 🤔, 💡', IMAGE_ID: '🔍, 📄, 💾', COMMONSENSE_CATEGORY: '🤔, 📚, 💡', SELECTED_CAPTION: '📝, 👌, 💬'}
+target_size = (1024, 1024)
+
+
+def func(index):
+    example = wmtis[index]
+    values = get_instance_values(example)
+    return values
+
+
+def get_instance_values(example):
+    values = []
+    for k in left_side_columns + right_side_columns:
+        if k in enumerate_cols:
+            value = list_to_string(example[k])
+        elif k == QA:
+            qa_list = [f"Q: {x[0]} A: {x[1]}" for x in example[k]]
+            value = list_to_string(qa_list)
+        else:
+            value = example[k]
+        values.append(value)
+    return values
+
+
+def list_to_string(lst):
+    return '\n'.join(['{}. {}'.format(i + 1, item) for i, item in enumerate(lst)])
+
+def create_image_accordion_block(index):
+    example = wmtis[index]
+    instance_values = get_instance_values(example)
+    assert len(left_side_columns) == len(
+        instance_values[:len(left_side_columns)])  # excluding the image & designer
+    for key, value in zip(left_side_columns, instance_values[:len(left_side_columns)]):
+        if key == IMAGE:
+            img = wmtis[index]["image"]
+            img_resized = img.resize(target_size)
+            gr.Image(value=img_resized, label=f"Image {emoji_to_label[key]}")
+        else:
+            label = key.capitalize().replace("_", " ")
+            gr.Textbox(value=value, label=f"{label} {emoji_to_label[key]}")
+    with gr.Accordion("Open for More!", open=False):
+        assert len(right_side_columns) == len(
+            instance_values[len(left_side_columns):])  # excluding the image & designer
+        for key, value in zip(right_side_columns, instance_values[len(left_side_columns):]):
+            label = key.capitalize().replace("_", " ")
+            gr.Textbox(value=value, label=f"{label} {emoji_to_label[key]}")
+
+
+columns_number = 2
+rows_number = 2
+tabs_number = 27
+
+with gr.Blocks() as demo:
+    gr.Markdown(f"# Whoops! images by category")
+    for tub_num in range(0, tabs_number):
+        print(f"create tab:{tub_num}")
+        with gr.Tab(f"Tab {tub_num}"):
+            for row_num in range(0, rows_number):
+                with gr.Row():
+                    for col_num in range(0, columns_number):
+                        with gr.Column():
+                            index = random.choice(range(0, dataset_size))
+                            create_image_accordion_block(index)
+demo.launch()

requirements.txt

@@ -0,0 +1,2 @@
+datasets
+gradio==3.0.5