wworking date dropdown

app.py

@@ -18,8 +18,11 @@ text_leaderboard[tc.LATENCY] = text_leaderboard[tc.LATENCY].round(1)
 text_leaderboard[tc.CLEMSCORE] = text_leaderboard[tc.CLEMSCORE].round(1)
 
 open_weight_df = text_leaderboard[text_leaderboard[tc.OPEN_WEIGHT] == True]
+print(open_weight_df[tc.PARAMS])
 if not open_weight_df.empty:  # Check if filtered df is non-empty
-    max_parameter_size = open_weight_df[tc.PARAMS].max()
+    # Get max parameter size, ignoring NaN values
+    params = open_weight_df[tc.PARAMS].dropna()
+    max_parameter_size = params.max() if not params.empty else 0
 
 # Short leaderboard containing fixed columns
 short_leaderboard = filter_cols(text_leaderboard)
@@ -92,7 +95,7 @@ with llm_calc_app:
         # First Column
         ####################################
         ## Language Select
-        with gr.Column():
+        with gr.Column(scale=2):
 
             with gr.Row():
                 lang_dropdown = gr.Dropdown(
@@ -102,47 +105,50 @@ with llm_calc_app:
                     label="Languages 🗣️"
                 )
 
+            
+            ## Release Date range selection
+                
             with gr.Row():
-                with gr.Column():
-                    start_year = gr.Dropdown(
-                        choices=YEARS,
-                        value=[YEARS[0]],
-                        allow_custom_value=True
-                    )
-                    start_month = gr.Dropdown(
-                        choices=MONTHS,
-                        value=[MONTHS[0]],
-                        allow_custom_value=True
-                    )
-
-                with gr.Column():
-                    end_year = gr.Dropdown(
-                        choices=YEARS,
-                        value=[YEARS[-1]],
-                        allow_custom_value=True
-                    )
-                    end_month = gr.Dropdown(
-                        choices=MONTHS,
-                        value=[MONTHS[-1]],
-                        allow_custom_value=True
-                    )
-
-
-            # Multiodality Select
-            with gr.Row():
-                multimodal_checkbox = gr.CheckboxGroup(
-                    choices=[tc.SINGLE_IMG, tc.MULT_IMG, tc.AUDIO, tc.VIDEO],
+                start_year_dropdown = gr.Dropdown(
+                    choices = YEARS,
                     value=[],
-                    label="Additional Modalities 📷🎧🎬",
+                    label="Model Release - Year 🗓️"
+                )
+                start_month_dropdown = gr.Dropdown(
+                    choices = MONTHS,
+                    value=[],
+                    label="Month 📜"
                 )
 
-            # Open/Commercial Selection
+                end_year_dropdown = gr.Dropdown(
+                    choices = YEARS,
+                    value=[],
+                    label="End - Year 🗓️"
+                )
+                end_month_dropdown = gr.Dropdown(
+                    choices = MONTHS,
+                    value=[],
+                    label="Month 📜"
+                )
+            
+            ## Price selection
             with gr.Row():
-                open_weight_checkbox = gr.CheckboxGroup(
-                    choices=[tc.OPEN, tc.COMM],
-                    value=[tc.OPEN, tc.COMM],
-                    label="Model Type 🔓 💼",
-                )    
+
+                input_pricing_slider = RangeSlider(
+                    minimum=0, 
+                    maximum=max_input_price, 
+                    value=(0, max_input_price), 
+                    label="💲/1M input tokens",
+                    elem_id="double-slider-3"
+                )
+
+                output_pricing_slider = RangeSlider(
+                    minimum=0, 
+                    maximum=max_output_price, 
+                    value=(0, max_output_price), 
+                    label="💲/1M output tokens",
+                    elem_id="double-slider-4"
+                )
 
             # License selection
             with gr.Row():
@@ -155,9 +161,9 @@ with llm_calc_app:
         #############################################################
         # Second Column
         #############################################################
-        with gr.Column():
+        with gr.Column(scale=1):
 
-            ####### LOG SLIDER 1 ###########
+            ####### parameters ###########
             with gr.Row():
                 parameter_slider = RangeSlider(
                     minimum=0, 
@@ -168,7 +174,7 @@ with llm_calc_app:
                 )
 
                 
-            ########### LOG SLIDER 2 ################
+            ########### Context range ################
 
             with gr.Row():
                 context_slider = RangeSlider(
@@ -179,25 +185,23 @@ with llm_calc_app:
                     step=context_step
                 )
 
-            ############# PRICE SLIDER 1 ###############
+            ############# Modality selection checkbox ###############
             with gr.Row():
-                input_pricing_slider = RangeSlider(
-                    minimum=0, 
-                    maximum=max_input_price, 
-                    value=(0, max_input_price), 
-                    label="💲/1M input tokens",
-                    elem_id="double-slider-3"
+                multimodal_checkbox = gr.CheckboxGroup(
+                    choices=[tc.SINGLE_IMG, tc.MULT_IMG, tc.AUDIO, tc.VIDEO],
+                    value=[],
+                    label="Additional Modalities 📷🎧🎬",
                 )
+                
             
-            ############### PRICE SLIDER 2 ###############
+            # ############### Model Type Checkbox ###############
             with gr.Row():
-                output_pricing_slider = RangeSlider(
-                    minimum=0, 
-                    maximum=max_output_price, 
-                    value=(0, max_output_price), 
-                    label="💲/1M output tokens",
-                    elem_id="double-slider-4"
-                )
+                open_weight_checkbox = gr.CheckboxGroup(
+                    choices=[tc.OPEN, tc.COMM],
+                    value=[tc.OPEN, tc.COMM],
+                    label="Model Type 🔓 💼",
+                )    
+                
        
 
     with gr.Row():
@@ -225,7 +229,7 @@ with llm_calc_app:
             filter,
             [dummy_leaderboard_table, lang_dropdown, parameter_slider,
              input_pricing_slider, output_pricing_slider, multimodal_checkbox,
-             context_slider, open_weight_checkbox, start_year, start_month, end_year, end_month, license_checkbox],
+             context_slider, open_weight_checkbox, start_year_dropdown, start_month_dropdown, end_year_dropdown, end_month_dropdown, license_checkbox],
             [leaderboard_table],   
             queue=True
         )
@@ -234,7 +238,7 @@ with llm_calc_app:
             filter,
             [dummy_leaderboard_table, lang_dropdown, parameter_slider,
              input_pricing_slider, output_pricing_slider, multimodal_checkbox,
-             context_slider, open_weight_checkbox, start_year, start_month, end_year, end_month, license_checkbox],
+             context_slider, open_weight_checkbox, start_year_dropdown, start_month_dropdown, end_year_dropdown, end_month_dropdown, license_checkbox],
             [leaderboard_table],
             queue=True
         )
@@ -243,7 +247,7 @@ with llm_calc_app:
             filter,
             [dummy_leaderboard_table, lang_dropdown, parameter_slider,
              input_pricing_slider, output_pricing_slider, multimodal_checkbox,
-             context_slider, open_weight_checkbox, start_year, start_month, end_year, end_month, license_checkbox],
+             context_slider, open_weight_checkbox, start_year_dropdown, start_month_dropdown, end_year_dropdown, end_month_dropdown, license_checkbox],
             [leaderboard_table],
             queue=True
         )
@@ -252,7 +256,7 @@ with llm_calc_app:
             filter,
             [dummy_leaderboard_table, lang_dropdown, parameter_slider,
              input_pricing_slider, output_pricing_slider, multimodal_checkbox,
-             context_slider, open_weight_checkbox, start_year, start_month, end_year, end_month, license_checkbox],
+             context_slider, open_weight_checkbox, start_year_dropdown, start_month_dropdown, end_year_dropdown, end_month_dropdown, license_checkbox],
             [leaderboard_table],
             queue=True
         )
@@ -261,7 +265,7 @@ with llm_calc_app:
             filter,
             [dummy_leaderboard_table, lang_dropdown, parameter_slider,
              input_pricing_slider, output_pricing_slider, multimodal_checkbox,
-             context_slider, open_weight_checkbox, start_year, start_month, end_year, end_month, license_checkbox],
+             context_slider, open_weight_checkbox, start_year_dropdown, start_month_dropdown, end_year_dropdown, end_month_dropdown, license_checkbox],
             [leaderboard_table],
             queue=True
         )
@@ -270,7 +274,7 @@ with llm_calc_app:
             filter,
             [dummy_leaderboard_table, lang_dropdown, parameter_slider,
              input_pricing_slider, output_pricing_slider, multimodal_checkbox,
-             context_slider, open_weight_checkbox, start_year, start_month, end_year, end_month, license_checkbox],
+             context_slider, open_weight_checkbox, start_year_dropdown, start_month_dropdown, end_year_dropdown, end_month_dropdown, license_checkbox],
             [leaderboard_table],
             queue=True
         )
@@ -279,43 +283,43 @@ with llm_calc_app:
             filter,
             [dummy_leaderboard_table, lang_dropdown, parameter_slider,
              input_pricing_slider, output_pricing_slider, multimodal_checkbox,
-             context_slider, open_weight_checkbox, start_year, start_month, end_year, end_month, license_checkbox],
+             context_slider, open_weight_checkbox, start_year_dropdown, start_month_dropdown, end_year_dropdown, end_month_dropdown, license_checkbox],
             [leaderboard_table],
             queue=True
         )
 
-        start_year.change(
+        start_year_dropdown.change(
             filter,
             [dummy_leaderboard_table, lang_dropdown, parameter_slider,
              input_pricing_slider, output_pricing_slider, multimodal_checkbox,
-             context_slider, open_weight_checkbox, start_year, start_month, end_year, end_month, license_checkbox],
+             context_slider, open_weight_checkbox, start_year_dropdown, start_month_dropdown, end_year_dropdown, end_month_dropdown, license_checkbox],
             [leaderboard_table],
             queue=True
         )
 
-        start_month.change(
+        start_month_dropdown.change(
             filter,
             [dummy_leaderboard_table, lang_dropdown, parameter_slider,
              input_pricing_slider, output_pricing_slider, multimodal_checkbox,
-             context_slider, open_weight_checkbox, start_year, start_month, end_year, end_month, license_checkbox],
+             context_slider, open_weight_checkbox, start_year_dropdown, start_month_dropdown, end_year_dropdown, end_month_dropdown, license_checkbox],
             [leaderboard_table],
             queue=True
         )
 
-        end_year.change(
+        end_year_dropdown.change(
             filter,
             [dummy_leaderboard_table, lang_dropdown, parameter_slider,
              input_pricing_slider, output_pricing_slider, multimodal_checkbox,
-             context_slider, open_weight_checkbox, start_year, start_month, end_year, end_month, license_checkbox],
+             context_slider, open_weight_checkbox, start_year_dropdown, start_month_dropdown, end_year_dropdown, end_month_dropdown, license_checkbox],
             [leaderboard_table],
             queue=True
         )
 
-        end_month.change(
+        end_month_dropdown.change(
             filter,
             [dummy_leaderboard_table, lang_dropdown, parameter_slider,
              input_pricing_slider, output_pricing_slider, multimodal_checkbox,
-             context_slider, open_weight_checkbox, start_year, start_month, end_year, end_month, license_checkbox],
+             context_slider, open_weight_checkbox, start_year_dropdown, start_month_dropdown, end_year_dropdown, end_month_dropdown, license_checkbox],
             [leaderboard_table],
             queue=True
         )
@@ -324,7 +328,7 @@ with llm_calc_app:
             filter,
             [dummy_leaderboard_table, lang_dropdown, parameter_slider,
              input_pricing_slider, output_pricing_slider, multimodal_checkbox,
-             context_slider, open_weight_checkbox, start_year, start_month, end_year, end_month, license_checkbox],
+             context_slider, open_weight_checkbox, start_year_dropdown, start_month_dropdown, end_year_dropdown, end_month_dropdown, license_checkbox],
             [leaderboard_table],
             queue=True
         )
@@ -332,38 +336,3 @@ with llm_calc_app:
     llm_calc_app.load()
 llm_calc_app.queue()
 llm_calc_app.launch()
-
-
-
-"""
-model_name, input_price, output_price,
-multimodality_image,multimodality_multiple_image,multimodality_audio,multimodality_video,
-source,licence_name,licence_url,languages,release_date,
-parameters_estimated,parameters_actual,
-
-open_weight,context, 
-
-additional_prices_context_caching,
-additional_prices_context_storage,
-additional_prices_image_input,additional_prices_image_output,additional_prices_video_input,additional_prices_video_output,additional_prices_audio_input,additional_prices_audio_output,clemscore_v1.6.5_multimodal,clemscore_v1.6.5_ascii,clemscore_v1.6,latency_v1.6,latency_v1.6.5_multimodal,latency_v1.6.5_ascii,
-
-average_clemscore,average_latency,parameters
-
-Final list
-
-model_name, input_price, output_price,
-multimodality_image,multimodality_multiple_image,multimodality_audio,multimodality_video,
-source,licence_name,licence_url,languages,release_date, open_weight,context, average_clemscore,average_latency,parameters
-
-
-Filter
-multimodality_image,multimodality_multiple_image,multimodality_audio,multimodality_video,
-licence_name+licence_url, languages, release_date, open_weight
-
-RR
-model_name, input_price, output_price,
-source, release_date
-
-"""
-
-

assets/merged_data.csv

@@ -1,4 +1,4 @@
-Model Name,Latency (s),Clemscore,Parameters (B),Release Date,Open Weight,Languages,Context Size (k),License Name,License URL,Single Image,Multiple Images,Audio,Video,Input $/1M tokens,Output $/1M tokens,License,Temp Date
+Model Name,Latency (s),Clemscore,Parameters (B),Release Date,Open Weight,Languages,Context Size (k),License Name,License URL,Single Image,Multi Image,Audio,Video,Input $/1M tokens,Output $/1M tokens,License,Temp Date
 o1-preview-2024-09-12,7.368572853601854,73.63,,2024-09-12,False,English,,Apache 2.0,https://www.apache.org/licenses/LICENSE-2.0,False,False,False,False,15.0,60.0,"<a href=""https://www.apache.org/licenses/LICENSE-2.0"" style=""color: blue;"">Apache 2.0</a>",2024-09-12
 gpt-4-1106-vision-preview,4.712557435752081,73.55,,2023-11-06,False,English,,Apache 2.0,https://www.apache.org/licenses/LICENSE-2.0,True,True,False,False,10.0,30.0,"<a href=""https://www.apache.org/licenses/LICENSE-2.0"" style=""color: blue;"">Apache 2.0</a>",2023-11-06
 claude-3-5-sonnet-20240620,2.0645066812060726,68.925,,2024-06-20,False,English,,Apache 2.0,https://www.apache.org/licenses/LICENSE-2.0,True,True,False,False,3.0,15.0,"<a href=""https://www.apache.org/licenses/LICENSE-2.0"" style=""color: blue;"">Apache 2.0</a>",2024-06-20

assets/text_content.py

@@ -10,6 +10,9 @@ RESULT_FILE = "results.csv"
 LATENCY_SUFFIX = "_latency.csv"
 
 # Setup Column Names
+# Note - Changing this does not affect the already generated csv `merged_data.csv`
+# Run `src/process_data.py` for this
+
 DEFAULT_MODEL_NAME = "Unnamed: 0"
 DEFAULT_CLEMSCORE = "-, clemscore"
 
@@ -24,7 +27,7 @@ CONTEXT = "Context Size (k)"
 LICENSE_NAME = "License Name"
 LICENSE_URL = "License URL"
 SINGLE_IMG = "Single Image"
-MULT_IMG = "Multiple Images"
+MULT_IMG = "Multi Image"
 AUDIO = "Audio"
 VIDEO = "Video"
 INPUT = "Input $/1M tokens"
@@ -39,4 +42,18 @@ COMM = "Commercial"
 TITLE = """<h1 align="center" id="space-title"> LLM Calculator ⚖️⚡ 📏💰</h1>"""
 
 # Date Picker (set as Dropdown until datetime object is fixed)
-START_YEAR = "2020"
+START_YEAR = "2020"
+MONTH_MAP = {
+    "January": 1,
+    "February": 2,
+    "March": 3,
+    "April": 4,
+    "May": 5,
+    "June": 6,
+    "July": 7,
+    "August": 8,
+    "September": 9,
+    "October": 10,
+    "November": 11,
+    "December": 12
+}

src/filter_utils.py

@@ -2,6 +2,11 @@
 
 import pandas as pd
 import assets.text_content as tc
+import calendar
+from typing import Union, List
+from datetime import datetime
+
+current_year = str(datetime.now().year)
 
 def filter_cols(df):
 
@@ -19,6 +24,7 @@ def filter_cols(df):
     
     return df
 
+
 def convert_date_components_to_timestamp(year: str, month: str) -> int:
     """Convert year and month strings to timestamp."""
     # Create a datetime object for the first day of the month
@@ -26,70 +32,79 @@ def convert_date_components_to_timestamp(year: str, month: str) -> int:
     return int(pd.to_datetime(date_str).timestamp())
 
 def filter_by_date(df: pd.DataFrame, 
-                  start_year: str, 
-                  start_month: str,
-                  end_year: str,
-                  end_month: str,
-                  date_column: str) -> pd.DataFrame:
+                  start_year, start_month,
+                  end_year, end_month,
+                  date_column: str = tc.RELEASE_DATE) -> pd.DataFrame:
     """
     Filter DataFrame by date range using separate year and month components.
-    
-    Args:
-        df: DataFrame to filter
-        start_year: Starting year (e.g., "2023")
-        start_month: Starting month (e.g., "1" for January)
-        end_year: Ending year (e.g., "2024")
-        end_month: Ending month (e.g., "12" for December)
-        date_column: Name of the date column to filter on
     """
-    # Convert string inputs to integers for date creation
-    start_timestamp = convert_date_components_to_timestamp(
-        int(start_year), 
-        int(start_month)
-    )
-    
-    end_timestamp = convert_date_components_to_timestamp(
-        int(end_year), 
-        int(end_month)
-    )
-    
-    # Convert the DataFrame's date column to timestamps for comparison
-    date_timestamps = pd.to_datetime(df[date_column]).apply(lambda x: int(x.timestamp()))
-    
-    # Filter the DataFrame
-    return df[
-        (date_timestamps >= start_timestamp) & 
-        (date_timestamps <= end_timestamp)
-    ]
+    # All lists are passed at once, so set default values here instead of passing them in args- Overwritten by empty lists
+    if not start_year:
+        start_year = tc.START_YEAR
+    if not end_year:
+        end_year = current_year
     
+    if not start_month:
+        start_month = "January"
+    if not end_month:
+        end_month = "December"
+
+    try:
+        # Convert string inputs to integers for date creation
+        start_timestamp = convert_date_components_to_timestamp(
+            int(start_year), 
+            int(tc.MONTH_MAP[start_month])
+        )
+        
+        end_timestamp = convert_date_components_to_timestamp(
+            int(end_year), 
+            int(tc.MONTH_MAP[end_month])
+        )
+        
+        # Convert the DataFrame's date column to timestamps for comparison
+        date_timestamps = pd.to_datetime(df[date_column]).apply(lambda x: int(x.timestamp()))
+        
+        # Filter the DataFrame
+        return df[
+            (date_timestamps >= start_timestamp) & 
+            (date_timestamps <= end_timestamp)
+        ]
+    except (ValueError, TypeError) as e:
+        print(f"Error processing dates: {e}")
+        return df  # Return unfiltered DataFrame if there's an error
 
 
 def filter(df, language_list, parameters, input_price, output_price, multimodal,
-           context, open_weight, start_year, start_month, end_year, end_month, license ):
-    
+           context, open_weight, 
+           start_year, start_month, end_year, end_month, 
+           license ):
 
+    
     if not df.empty:  # Check if df is non-empty
         df = df[df[tc.LANGS].apply(lambda x: all(lang in x for lang in language_list))]
 
     if not df.empty:
-        # Split dataframe by Open Weight
-        open_weight_true = df[df[tc.OPEN_WEIGHT] == True]
-        open_weight_false = df[df[tc.OPEN_WEIGHT] == False]
+        # Split dataframe by Open Weight, ensuring mutual exclusivity
+        open_weight_true = df[
+            (df[tc.OPEN_WEIGHT] == True) & 
+            (~df[tc.PARAMS].isna())
+        ]
+        open_weight_false = df[
+            (df[tc.OPEN_WEIGHT] == False) | 
+            (df[tc.PARAMS].isna()) |
+            (~df.index.isin(open_weight_true.index))  # Catch any remaining rows
+        ]
         
-        # Get max parameter size for open weight models
-        max_parameter_size = open_weight_true[tc.PARAMS].max() if not open_weight_true.empty else 0
+        # Verify no overlap and no data loss
+        assert len(df) == len(open_weight_true) + len(open_weight_false), "Data loss detected"
+        assert len(set(open_weight_true.index) & set(open_weight_false.index)) == 0, "Duplicate entries detected"
         
         # Filter only the open weight models based on parameters
         if not open_weight_true.empty:
-            if parameters[1] >= max_parameter_size:
-                filtered_open = open_weight_true[
-                    (open_weight_true[tc.PARAMS] >= parameters[0])
-                ]
-            else:
-                filtered_open = open_weight_true[
-                    (open_weight_true[tc.PARAMS] >= parameters[0]) & 
-                    (open_weight_true[tc.PARAMS] <= parameters[1])
-                ]
+            filtered_open = open_weight_true[
+                (open_weight_true[tc.PARAMS] >= parameters[0]) & 
+                (open_weight_true[tc.PARAMS] <= parameters[1])
+            ]
             
             # Combine filtered open weight models with unfiltered commercial models
             df = pd.concat([filtered_open, open_weight_false])
@@ -125,18 +140,6 @@ def filter(df, language_list, parameters, input_price, output_price, multimodal,
     if not df.empty:  # Check if df is non-empty
         df = df[df[tc.LICENSE_NAME].apply(lambda x: any(lic in x for lic in license))]
 
-    # # Convert 'Release Date' to int temporarily
-    # if not df.empty:  # Check if df is non-empty
-    #     df[tc.TEMP_DATE] = pd.to_datetime(df[tc.TEMP_DATE]).astype(int) // 10**9  # Convert to seconds since epoch
-
-    # # Convert start and end to int (seconds since epoch)
-    # start = int(pd.to_datetime(start).timestamp())  
-    # end = int(pd.to_datetime(end).timestamp())    
-
-    # # Filter based on the converted 'Release Date'
-    # if not df.empty:  # Check if df is non-empty
-    #     df = df[(df[tc.TEMP_DATE] >= start) & (df[tc.TEMP_DATE] <= end)]
-
     df = filter_by_date(df, start_year, start_month, end_year, end_month, tc.TEMP_DATE)
 
     df = filter_cols(df)

test.py

@@ -1,10 +0,0 @@
-import calendar
-import datetime
-
-today = datetime.date.today()
-
-year = today.year
-
-print(year)
-
-print(list(calendar.month_name[1:]))