2024-02-08 00:37:24 Publish script update

app.py

@@ -35,7 +35,7 @@ When it comes to pricing most providers charge per token count, while HuggingFac
 """
 
 time_periods_explanation_df = pd.DataFrame({
-    'name': ["early morning", "morning", "afternoon", "late afternoon", "evening", "late evening", "midnight", "night"],
+    'time_of_day': ["early morning", "morning", "afternoon", "late afternoon", "evening", "late evening", "midnight", "night"],
     'hour_range': ["6-8", "9-11", "12-14", "15-17", "18-20", "21-23", "0-2", "3-5"]
 })
 
@@ -50,12 +50,7 @@ summary_df: pd.DataFrame = pd.read_csv("data/2024-02-05 23:33:22.947120_summary.
 time_of_day_comparison_df = pd.read_csv("data/2024-02-06 09:49:19.637072_time_of_day_comparison.csv")
 general_plots = pd.read_csv("data/2024-02-06 15:35:24.490454_general_plot.csv")
 model_costs_df = pd.read_csv("data/2024-02-05 12:03:45.281624_model_costs.csv")
-
-
-with open("data/time_of_day_plot.json", "r") as f:
-    time_of_day_plot = plotly.io.from_json(f.read())
-    time_of_day_plot.update_layout(autosize=True)
-
+time_of_day_plots = pd.read_csv("data/time_of_day_plots.csv")
 
 searched_model_name = ""
 collapse_languages = False
@@ -174,9 +169,13 @@ To count words we split the output string by whitespace `\w` regex character.
 Chunk sizes are measured in the characters count.""")
 
     with gr.Tab("Preformance by time of the day"):
-        time_of_day_comparison_ui = gr.DataFrame(dataframe_style(time_of_day_comparison_df), label="Time of day")
-        time_of_day_plot_ui = gr.Plot(time_of_day_plot, label="Time of the day plot", scale=1)
+        # display only first plot for all models
+        for index, row in time_of_day_plots[0:1].iterrows():
+            plot = plotly.io.from_json(row["plot_json"])
+            plot.update_layout(autosize=True)
+            gr.Plot(plot, label=row["header"], scale=1)
         time_periods_explanation_ui = gr.DataFrame(dataframe_style(time_periods_explanation_df), label="Times of day ranges")
+        time_of_day_comparison_ui = gr.DataFrame(dataframe_style(time_of_day_comparison_df), label="Time of day")
         gr.Markdown("""\
 These measurements were made by testing the models using the same dataset as in the other comparisons every hour for 24 hours.
                     
@@ -186,6 +185,11 @@ Hours and times of day in the table and in the plot are based on Central Europea
                     
 Measurements were made during a normal work week.
 """)
+        # display rest of the plots 
+        for index, row in time_of_day_plots[1:].iterrows():
+            plot = plotly.io.from_json(row["plot_json"])
+            plot.update_layout(autosize=True)
+            gr.Plot(plot, label=row["header"], scale=1)
 
     with gr.Tab("Costs comparison"):
         models_costs_ui = gr.DataFrame(dataframe_style(model_costs_df), label="Costs comparison")

pipeline/config.py

@@ -33,9 +33,10 @@ class QueriesConfig(Config):
     }
 
 
-class OpenAIConfig(Config):
+class MeasurementsConfig(Config):
     mock: bool = False
     remove_old_measurements: bool = False
+    small_dataset: bool = False
 
 
 class QueriesDatasetConfig(Config):