date ranges

app.py

@@ -2,7 +2,7 @@ import gradio as gr
 from df.PaperCentral import PaperCentral
 from gradio_calendar import Calendar
 from datetime import datetime, timedelta
-from typing import Union, List
+from typing import Union, List, Optional
 from author_leaderboard_tab import author_leaderboard_tab
 from author_leaderboard_contrib_tab import author_resource_leaderboard_tab
 from zoneinfo import ZoneInfo  # Available in Python 3.9 and later
@@ -18,10 +18,11 @@ with gr.Blocks(css="style.css") as demo:
         with gr.Tab("Paper-central", id="tab-paper-central"):
             with gr.Accordion(label="⭐Release notes", open=False):
                 gr.Markdown("""
-                - 11/10/2024 - Leaderboards added
-                - 8/10/2024 - MICCAI proceedings added        
-                - 7/10/2024 - COLM2024 proceedings added     
-                - 4/10/2024 - You can now filter by Title
+                - **October 16, 2024** – Added functionality to filter papers by date ranges.
+                - **October 11, 2024** – Introduced leaderboards feature.
+                - **October 8, 2024** – MICCAI 2024 proceedings added.
+                - **October 7, 2024** – COLM 2024 proceedings added.
+                - **October 4, 2024** – Added functionality to filter papers by title.
                 """)
 
             # Create a row for navigation buttons and calendar
@@ -39,6 +40,12 @@ with gr.Blocks(css="style.css") as demo:
                         value=datetime.now(ZoneInfo('America/Los_Angeles')).strftime('%Y-%m-%d')
                         # Default to today's date in PST
                     )
+                    # Add Radio buttons for date ranges
+                    date_range_radio = gr.Radio(
+                        label="Date Range",
+                        choices=["This week", "This month", "This year", "All time"],
+                        value=None,
+                    )
 
             # Create a row for Hugging Face options and Conference options
             with gr.Row():
@@ -119,7 +126,6 @@ with gr.Blocks(css="style.css") as demo:
                 author_resource_leaderboard_tab()
 
 
-
     # Define function to move to the next day
     def go_to_next_day(
             date: Union[str, datetime],
@@ -128,19 +134,16 @@ with gr.Blocks(css="style.css") as demo:
             conference_options_list: List[str],
             author_search_input: str,
             title_search_input: str,
+            date_range_option: Optional[str],
     ) -> tuple:
         """
         Moves the selected date to the next day and updates the data.
 
-        Args:
-            date (Union[str, datetime]): The current date selected in the calendar.
-            cat_options_list (List[str]): List of selected Category options.
-            hf_options_list (List[str]): List of selected Hugging Face options.
-            conference_options_list (List[str]): List of selected Conference options.
-
         Returns:
             tuple: The new date as a string and the updated Dataframe component.
         """
+        date_range_update = gr.update(value=None)
+
         # Ensure the date is in string format
         if isinstance(date, datetime):
             date_str = date.strftime('%Y-%m-%d')
@@ -159,10 +162,11 @@ with gr.Blocks(css="style.css") as demo:
             conference_options=conference_options_list,
             author_search_input=author_search_input,
             title_search_input=title_search_input,
+            date_range_option=date_range_option,
         )
 
         # Return the new date and updated Dataframe
-        return new_date_str, updated_data
+        return new_date_str, updated_data, date_range_update
 
 
     # Define function to move to the previous day
@@ -173,19 +177,17 @@ with gr.Blocks(css="style.css") as demo:
             conference_options_list: List[str],
             author_search_input: str,
             title_search_input: str,
+            date_range_option: Optional[str],
     ) -> tuple:
         """
         Moves the selected date to the previous day and updates the data.
 
-        Args:
-            date (Union[str, datetime]): The current date selected in the calendar.
-            cat_options_list (List[str]): List of selected Category options.
-            hf_options_list (List[str]): List of selected Hugging Face options.
-            conference_options_list (List[str]): List of selected Conference options.
-
         Returns:
             tuple: The new date as a string and the updated Dataframe component.
         """
+        # If date_range_option is selected, do nothing
+        date_range_update = gr.update(value=None)
+
         # Ensure the date is in string format
         if isinstance(date, datetime):
             date_str = date.strftime('%Y-%m-%d')
@@ -204,10 +206,11 @@ with gr.Blocks(css="style.css") as demo:
             conference_options=conference_options_list,
             author_search_input=author_search_input,
             title_search_input=title_search_input,
+            date_range_option=date_range_option,
         )
 
         # Return the new date and updated Dataframe
-        return new_date_str, updated_data
+        return new_date_str, updated_data, date_range_update
 
 
     # Define function to update data when date or options change
@@ -218,18 +221,10 @@ with gr.Blocks(css="style.css") as demo:
             conference_options_list: List[str],
             author_search_input: str,
             title_search_input: str,
+            date_range_option: Optional[str],
     ):
         """
         Updates the data displayed in the Dataframe based on the selected date and options.
-
-        Args:
-            date (Union[str, datetime]): The selected date.
-            cat_options_list (List[str]): List of selected Category options.
-            hf_options_list (List[str]): List of selected Hugging Face options.
-            conference_options_list (List[str]): List of selected Conference options.
-
-        Returns:
-            gr.Dataframe.update: An update object for the Dataframe component.
         """
         return paper_central_df.filter(
             selected_date=date,
@@ -238,6 +233,7 @@ with gr.Blocks(css="style.css") as demo:
             conference_options=conference_options_list,
             author_search_input=author_search_input,
             title_search_input=title_search_input,
+            date_range_option=date_range_option,
         )
 
 
@@ -249,8 +245,8 @@ with gr.Blocks(css="style.css") as demo:
             conference_options_list: List[str],
             author_search_input: str,
             title_search_input: str,
+            date_range_option: Optional[str],
     ):
-
         cat_options_update = gr.update()
         paper_central_component_update = gr.update()
         visible = True
@@ -266,6 +262,7 @@ with gr.Blocks(css="style.css") as demo:
                 conference_options_list,
                 author_search_input,
                 title_search_input,
+                date_range_option,
             )
             visible = False
 
@@ -284,6 +281,7 @@ with gr.Blocks(css="style.css") as demo:
             conference_options_list: List[str],
             author_search_input: str,
             title_search_input: str,
+            date_range_option: Optional[str],
     ):
         conference_options_update = gr.update()
         paper_central_component_update = gr.update()
@@ -300,6 +298,7 @@ with gr.Blocks(css="style.css") as demo:
                 [],
                 author_search_input,
                 title_search_input,
+                date_range_option,
             )
             visible = True
 
@@ -310,6 +309,7 @@ with gr.Blocks(css="style.css") as demo:
         return paper_central_component_update, conference_options_update, calendar_update, next_day_btn_update, prev_day_btn_update
 
 
+    # Include date_range_radio in the inputs
     inputs = [
         calendar,
         cat_options,
@@ -317,6 +317,7 @@ with gr.Blocks(css="style.css") as demo:
         conference_options,
         author_search,
         title_search,
+        date_range_radio,
     ]
 
     # Set up the event listener for the author search
@@ -336,14 +337,14 @@ with gr.Blocks(css="style.css") as demo:
     next_day_btn.click(
         fn=go_to_next_day,
         inputs=inputs,
-        outputs=[calendar, paper_central_component],
+        outputs=[calendar, paper_central_component, date_range_radio],
     )
 
     # Set up the event listener for the 'Previous Day' button
     prev_day_btn.click(
         fn=go_to_previous_day,
         inputs=inputs,
-        outputs=[calendar, paper_central_component],
+        outputs=[calendar, paper_central_component, date_range_radio],
     )
 
     # Set up the event listener for the calendar date change
@@ -374,6 +375,13 @@ with gr.Blocks(css="style.css") as demo:
         outputs=[paper_central_component, conference_options, calendar, next_day_btn, prev_day_btn],
     )
 
+    # Set up the event listener for the date range radio button change
+    date_range_radio.change(
+        fn=update_data,
+        inputs=inputs,
+        outputs=paper_central_component,
+    )
+
     # Load the initial data when the app starts
     request = gr.Request()
 

df/PaperCentral.py

@@ -13,6 +13,7 @@ from constants import (
 import gradio as gr
 from utils import load_and_process
 import numpy as np
+from datetime import datetime, timedelta
 
 
 class PaperCentral:
@@ -278,23 +279,17 @@ class PaperCentral:
             conference_options: Optional[List[str]] = None,
             author_search_input: Optional[str] = None,
             title_search_input: Optional[str] = None,
+            date_range_option: Optional[str] = None,
     ) -> gr.update:
         """
         Filter the DataFrame based on selected date and options, and prepare it for display.
-
-        Args:
-            selected_date (Optional[str]): The date to filter the DataFrame.
-            hf_options (Optional[List[str]]): List of options selected by the user.
-            conference_options (Optional[List[str]]): List of conference options selected by the user.
-
-        Returns:
-            gr.Update: An update object for the Gradio Dataframe component.
         """
         filtered_df: pd.DataFrame = self.df_raw.copy()
 
         # Start with the initial columns to display
         columns_to_show: List[str] = PaperCentral.COLUMNS_START_PAPER_PAGE.copy()
 
+        # Handle title search
         if title_search_input:
             if 'title' not in columns_to_show:
                 columns_to_show.append('authors')
@@ -303,14 +298,13 @@ class PaperCentral:
 
             def title_match(title):
                 if isinstance(title, str):
-                    # If authors_list is a single string
                     return search_string in title.lower()
                 else:
-                    # Handle unexpected data types
                     return False
 
             filtered_df = filtered_df[filtered_df['title'].apply(title_match)]
 
+        # Handle author search
         if author_search_input:
             if 'authors' not in columns_to_show:
                 columns_to_show.append('authors')
@@ -318,55 +312,71 @@ class PaperCentral:
             search_string = author_search_input.lower()
 
             def author_matches(authors_list):
-                # Check if authors_list is None or empty
                 if authors_list is None or len(authors_list) == 0:
                     return False
-
-                # Check if authors_list is an iterable (list, tuple, Series, or ndarray)
                 if isinstance(authors_list, (list, tuple, pd.Series, np.ndarray)):
                     return any(
                         isinstance(author, str) and search_string in author.lower()
                         for author in authors_list
                     )
                 elif isinstance(authors_list, str):
-                    # If authors_list is a single string
                     return search_string in authors_list.lower()
                 else:
-                    # Handle unexpected data types
                     return False
 
             filtered_df = filtered_df[filtered_df['authors'].apply(author_matches)]
 
+        # Handle category options
         if cat_options:
             options = [o.replace(".*", "") for o in cat_options]
-            # Initialize filter series
             conference_filter = pd.Series(False, index=filtered_df.index)
             for option in options:
-                # Filter rows where 'conference_name' contains the conference string (case-insensitive)
                 conference_filter |= (
                         filtered_df['primary_category'].notna() &
                         filtered_df['primary_category'].str.contains(option, case=False)
                 )
             filtered_df = filtered_df[conference_filter]
 
-        # Date
-        if selected_date and not conference_options:
-            selected_date = pd.to_datetime(selected_date).strftime('%Y-%m-%d')
-            filtered_df = filtered_df[filtered_df['date'] == selected_date]
+        # Handle date filtering
+        if not conference_options:
+            if date_range_option:
+                today = datetime.now()
+                if date_range_option == "This week":
+                    start_date = (today - timedelta(days=7)).strftime('%Y-%m-%d')
+                    end_date = today.strftime('%Y-%m-%d')
+                elif date_range_option == "This month":
+                    start_date = (today - timedelta(days=30)).strftime('%Y-%m-%d')
+                    end_date = today.strftime('%Y-%m-%d')
+                elif date_range_option == "This year":
+                    start_date = (today - timedelta(days=365)).strftime('%Y-%m-%d')
+                    end_date = today.strftime('%Y-%m-%d')
+                elif date_range_option == "All time":
+                    start_date = None
+                    end_date = None
+                else:
+                    start_date = None
+                    end_date = None
+
+                if start_date and end_date:
+                    filtered_df = filtered_df[
+                        (filtered_df['date'] >= start_date) & (filtered_df['date'] <= end_date)
+                        ]
+                else:
+                    pass  # No date filtering for "All time"
+            elif selected_date:
+                selected_date = pd.to_datetime(selected_date).strftime('%Y-%m-%d')
+                filtered_df = filtered_df[filtered_df['date'] == selected_date]
 
-        # HF options
+        # Handle Hugging Face options
         if hf_options:
             if "🤗 artifacts" in hf_options:
-                # Filter rows where 'paper_page' is not empty or NaN
                 filtered_df = filtered_df[
                     (filtered_df['paper_page'] != "") & (filtered_df['paper_page'].notna())
                     ]
-
-                # Add 'upvotes' column if not already in columns_to_show
                 if 'upvotes' not in columns_to_show:
                     columns_to_show.append('upvotes')
-
-                # Add 'num_models' column if not already in columns_to_show
+                if 'num_comments' not in columns_to_show:
+                    columns_to_show.append('num_comments')
                 if 'num_models' not in columns_to_show:
                     columns_to_show.append('num_models')
                 if 'num_datasets' not in columns_to_show:
@@ -383,6 +393,7 @@ class PaperCentral:
                 if 'num_models' not in columns_to_show:
                     columns_to_show.append('num_models')
                 filtered_df = filtered_df[filtered_df['num_models'] != 0]
+
             if "spaces" in hf_options:
                 if 'num_spaces' not in columns_to_show:
                     columns_to_show.append('num_spaces')
@@ -395,36 +406,26 @@ class PaperCentral:
 
         # Apply conference filtering
         if conference_options:
-
-            columns_to_show.remove("date")
-            columns_to_show.remove("arxiv_id")
+            columns_to_show = [col for col in columns_to_show if col not in ["date", "arxiv_id"]]
 
             if 'conference_name' not in columns_to_show:
                 columns_to_show.append('conference_name')
-
             if 'proceedings' not in columns_to_show:
                 columns_to_show.append('proceedings')
-
             if 'type' not in columns_to_show:
                 columns_to_show.append('type')
-
             if 'id' not in columns_to_show:
                 columns_to_show.append('id')
 
-            # If "In proceedings" is selected
             if "In proceedings" in conference_options:
-                # Filter rows where 'conference_name' is not None, not NaN, and not empty
                 filtered_df = filtered_df[
                     filtered_df['conference_name'].notna() & (filtered_df['conference_name'] != "")
                     ]
 
-            # For other conference options
             other_conferences = [conf for conf in conference_options if conf != "In proceedings"]
             if other_conferences:
-                # Initialize filter series
                 conference_filter = pd.Series(False, index=filtered_df.index)
                 for conference in other_conferences:
-                    # Filter rows where 'conference_name' contains the conference string (case-insensitive)
                     conference_filter |= (
                             filtered_df['conference_name'].notna() &
                             (filtered_df['conference_name'].str.lower() == conference.lower())
@@ -436,8 +437,6 @@ class PaperCentral:
 
         # Ensure columns are ordered according to COLUMNS_ORDER_PAPER_PAGE
         columns_in_order: List[str] = [col for col in PaperCentral.COLUMNS_ORDER_PAPER_PAGE if col in columns_to_show]
-
-        # Select and reorder the columns
         filtered_df = filtered_df[columns_in_order]
 
         # Rename columns for display

requirements.txt

@@ -1,3 +1,3 @@
-gradio
+gradio==4.44.0
 gradio_calendar
 datasets