first commit

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,16 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="3">
+            <item index="0" class="java.lang.String" itemvalue="matplotlib" />
+            <item index="1" class="java.lang.String" itemvalue="CLIP" />
+            <item index="2" class="java.lang.String" itemvalue="transformers" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9 (venv) (2)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/whoops-dataset-viewer.iml" filepath="$PROJECT_DIR$/.idea/whoops-dataset-viewer.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

.idea/whoops-dataset-viewer.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="Python 3.9 (venv) (2)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

app.py

@@ -0,0 +1,61 @@
+import json
+import gradio as gr
+from datasets import load_dataset
+
+whoops = load_dataset("nlphuji/whoops")['test']
+BUCKET_PATH = 'https://wmtis.s3.eu-west-1.amazonaws.com/wmtis_images'
+
+df = whoops.to_pandas()
+def get_image_url(img_id):
+    return f"{BUCKET_PATH}/{img_id}.png"
+
+df['image_url'] = df['image_id'].apply(lambda x: get_image_url(x))
+df['image_url'] = df['image_url'].apply(lambda x: '<a href= "' + str(x) + '" target="_blank"> <img src= "' + str(
+    x) + '"/> </a>')
+
+def dumps(x, c):
+    if c in ['crowd_captions', 'crowd_underspecified_captions']:
+        return json.dumps(list(x))
+    elif c == 'question_answering_pairs':
+        return json.dumps([list(xi) for xi in x])
+    return json.dumps(x)
+
+for c in ['designer_explanation', 'selected_caption', 'crowd_captions', 'crowd_underspecified_captions',
+          'question_answering_pairs', 'commonsense_category', 'image_id', 'image_designer']:
+    print(c)
+    df[c] = df[c].apply(lambda x: dumps(x, c))
+
+df = df[['image_url', 'designer_explanation', 'selected_caption', 'crowd_captions', 'crowd_underspecified_captions',
+         'question_answering_pairs', 'commonsense_category', 'image_id', 'image_designer']]
+
+LINES_NUMBER = 20
+
+def display_df():
+    df_images = df.head(LINES_NUMBER)
+    return df_images
+
+def display_next(dataframe, end):
+    start = (end or dataframe.index[-1]) + 1
+    end = start + (LINES_NUMBER-1)
+    df_images = df.loc[start:end]
+    return df_images, end
+
+# Gradio Blocks
+with gr.Blocks() as demo:
+    gr.Markdown("<h1><center>WHOOPS! Dataset Viewer</center></h1>")
+
+    with gr.Row():
+        num_end = gr.Number(visible=False)
+        b1 = gr.Button("Get Initial dataframe")
+        b2 = gr.Button("Next Rows")
+
+    with gr.Row():
+        out_dataframe = gr.Dataframe(wrap=True, max_rows=LINES_NUMBER, overflow_row_behaviour="paginate",
+                                     datatype=["markdown", "markdown", "str", "str", "str", "str", "str", "str","str","str"],
+                                     interactive=False)
+
+    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(debug=True, show_error=True)

app2.py

@@ -0,0 +1,143 @@
+# import gradio as gr
+# import ast
+# import requests
+#
+# # Using Gradio Demos as API - This is Hot!
+# API_URL_INITIAL = "https://ysharma-playground-ai-exploration.hf.space/run/initial_dataframe"
+# API_URL_NEXT10 = "https://ysharma-playground-ai-exploration.hf.space/run/next_10_rows"
+#
+#
+# # define inference function
+# # First: Get initial images for the grid display
+# def get_initial_images():
+#     response = requests.post(API_URL_INITIAL, json={
+#         "data": []
+#     }).json()
+#     # data = response["data"][0]['data'][0][0][:-1]
+#     response_dict = response['data'][0]
+#     return response_dict  # , [resp[0][:-1] for resp in response["data"][0]["data"]]
+#
+#
+# # Second: Process response dictionary to get imges as hyperlinked image tags
+# def process_response(response_dict):
+#     return [resp[0][:-1] for resp in response_dict["data"]]
+#
+#
+# response_dict = get_initial_images()
+# initial = process_response(response_dict)
+# initial_imgs = '<div style="display: grid; grid-template-columns: repeat(3, 1fr); grid-template-rows: repeat(3, 1fr); grid-gap: 0; background-color: #fff; padding: 20px; box-shadow: 0 5px 10px rgba(0, 0, 0, 0.2);">\n' + "\n".join(
+#     initial[:-1])
+#
+#
+# # Third: Load more images for the grid
+# def get_next10_images(response_dict, row_count):
+#     row_count = int(row_count)
+#     # print("(1)",type(response_dict))
+#     # Convert the string to a dictionary
+#     if isinstance(response_dict, dict) == False:
+#         response_dict = ast.literal_eval(response_dict)
+#     response = requests.post(API_URL_NEXT10, json={
+#         "data": [response_dict, row_count]  # len(initial)-1
+#     }).json()
+#     row_count += 10
+#     response_dict = response['data'][0]
+#     # print("(2)",type(response))
+#     # print("(3)",type(response['data'][0]))
+#     next_set = [resp[0][:-1] for resp in response_dict["data"]]
+#     next_set_images = '<div style="display: grid; grid-template-columns: repeat(3, 1fr); grid-template-rows: repeat(3, 1fr); grid-gap: 0; background-color: #fff; padding: 20px; box-shadow: 0 5px 10px rgba(0, 0, 0, 0.2); ">\n' + "\n".join(
+#         next_set[:-1])
+#     return response_dict, row_count, next_set_images  # response['data'][0]
+#
+#
+# # get_next10_images(response_dict=response_dict, row_count=9)
+# # position: fixed; top: 0; left: 0; width: 100%; background-color: #fff; padding: 20px; box-shadow: 0 5px 10px rgba(0, 0, 0, 0.2);
+#
+# # Defining the Blocks layout
+# with gr.Blocks(css="""#img_search img {width: 100%; height: 100%; object-fit: cover;}""") as demo:
+#     gr.HTML(value="top of page", elem_id="top", visible=False)
+#     gr.HTML("""<div style="text-align: center; max-width: 700px; margin: 0 auto;">
+#         <div
+#         style="
+#             display: inline-flex;
+#             align-items: center;
+#             gap: 0.8rem;
+#             font-size: 1.75rem;
+#         "
+#         >
+#         <h1 style="font-weight: 900; margin-bottom: 7px; margin-top: 5px;">
+#             Using Gradio Demos as API - 2 </h1><br></div>
+#         <div><h4 style="font-weight: 500; margin-bottom: 7px; margin-top: 5px;">
+#             Stream <a href="https://github.com/playgroundai/liked_images" target="_blank">PlaygroundAI Images</a> ina beautiful grid</h4><br>
+#         </div>""")
+#     # with gr.Accordion(label="Details about the working:", open=False, elem_id='accordion'):
+#     #     gr.HTML("""
+#     #     <p style="margin-bottom: 10px; font-size: 90%"><br>
+#     #     ▶️Do you see the "view api" link located in the footer of this application?
+#     #     By clicking on this link, a page will open which provides documentation on the REST API that developers can use to query the Interface function / Block events.<br>
+#     #     ▶️In this demo, I am making such an API request to the <a href="https://huggingface.co/spaces/ysharma/Playground_AI_Exploration" target="_blank">Playground_AI_Exploration</a> Space.<br>
+#     #     ▶️I am exposing an API endpoint of this Gradio app as well. This can easily be done by one line of code, just set the api_name parameter of the event listener.
+#     #     </p></div>""")
+#
+#     with gr.Column():  # (elem_id = "col-container"):
+#         b1 = gr.Button("Load More Images").style(full_width=False)
+#         df = gr.Textbox(visible=False, elem_id='dataframe', value=response_dict)
+#         row_count = gr.Number(visible=False, value=19)
+#         img_search = gr.HTML(label='Images from PlaygroundAI dataset', elem_id="img_search",
+#                              value=initial_imgs)  # initial[:-1] )
+#
+#     gr.HTML('''<center><a href="https://huggingface.co/spaces/ysharma/Stream_PlaygroundAI_Images?duplicate=true"><img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a></center>
+#     #     </p></div>''')
+#     b1.click(get_next10_images, [df, row_count], [df, row_count, img_search], api_name="load_playgroundai_images")
+#
+# demo.launch(debug=True)
+
+import pandas as pd
+import gradio as gr
+
+df = pd.read_csv("/Users/yonatanbitton/Downloads/whoops_dataset.csv")
+df['image_url'] = df['image_url'].apply(lambda x: '<a href= "' + str(x) + '" target="_blank"> <img src= "' + str(
+    x) + '"/> </a>')
+df['designer_explanation'] = df['designer_explanation'].apply(lambda x: str(x))
+df['selected_caption'] = df['selected_caption'].apply(lambda x: str(x))
+df['crowd_captions'] = df['crowd_captions'].apply(lambda x: str(x))
+df['crowd_underspecified_captions'] = df['crowd_underspecified_captions'].apply(lambda x: str(x))
+df['question_answering_pairs'] = df['question_answering_pairs'].apply(lambda x: str(x))
+df['commonsense_category'] = df['commonsense_category'].apply(lambda x: str(x))
+df['image_id'] = df['image_id'].apply(lambda x: str(x))
+df['image_designer'] = df['image_designer'].apply(lambda x: str(x))
+df = df[['image_url', 'designer_explanation', 'selected_caption', 'crowd_captions', 'crowd_underspecified_captions',
+         'question_answering_pairs', 'commonsense_category', 'image_id', 'image_designer']]
+
+LINES_NUMBER = 20
+
+def display_df():
+    df_images = df.head(LINES_NUMBER)
+    return df_images
+
+
+def display_next10(dataframe, end):
+    start = (end or dataframe.index[-1]) + 1
+    end = start + (LINES_NUMBER-1)
+    df_images = df.loc[start:end]
+    return df_images, end
+
+
+# Gradio Blocks
+with gr.Blocks() as demo:
+    gr.Markdown("<h1><center>WHOOPS! Dataset Viewer</center></h1>")
+
+    with gr.Row():
+        num_end = gr.Number(visible=False)
+        b1 = gr.Button("Get Initial dataframe")
+        b2 = gr.Button("Next 10 Rows")
+
+    with gr.Row():
+        out_dataframe = gr.Dataframe(wrap=True, max_rows=LINES_NUMBER, overflow_row_behaviour="paginate",
+                                     datatype=["markdown", "markdown", "str", "str", "str", "str", "str", "str","str","str"],
+                                     interactive=False)
+
+    b1.click(fn=display_df, outputs=out_dataframe, api_name="initial_dataframe")
+    b2.click(fn=display_next10, inputs=[out_dataframe, num_end], outputs=[out_dataframe, num_end],
+             api_name="next_10_rows")
+
+demo.launch(debug=True, show_error=True)

requirements.txt

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