removing trailing s from units

app.py

@@ -54,14 +54,14 @@ def process_dataset():
         columns={
             "type": "Repository Type",
             "num_files": "Number of Files",
-            "total_size": "Total Size (PBs)",
+            "total_size": "Total Size (PB)",
         }
     )
     file_counts_and_sizes = file_counts_and_sizes.drop(columns=["Number of Files"])
 
     # sort the dataframe by total size in descending order
     file_counts_and_sizes = file_counts_and_sizes.sort_values(
-        by="Total Size (PBs)", ascending=False
+        by="Total Size (PB)", ascending=False
     )
 
     # drop nas from the extension column
@@ -121,9 +121,9 @@ def compare_last_10_months(_cumulative_df, _cumulative_df_deduped):
     last_10_months = last_10_months.rename(
         columns={
             "date": "Date",
-            "total_change": "Month-to-Month Growth (PBs)",
-            "deduped_change": "Growth with File-Level Deduplication (PBs)",
-            "savings": "Dedupe Savings (PBs)",
+            "total_change": "Month-to-Month Growth (PB)",
+            "deduped_change": "Growth with File-Level Deduplication (PB)",
+            "savings": "Dedupe Savings (PB)",
         }
     )
     return last_10_months
@@ -131,8 +131,8 @@ def compare_last_10_months(_cumulative_df, _cumulative_df_deduped):
 
 def tabular_analysis(repo_sizes, cumulative_df, cumulative_df_deduped):
     # create a new column in the repository sizes dataframe for "deduped size" and set it to empty atif rist
-    repo_sizes["Deduped Size (PBs)"] = ""
-    repo_sizes["Dedupe Savings (PBs)"] = ""
+    repo_sizes["Deduped Size (PB)"] = ""
+    repo_sizes["Dedupe Savings (PB)"] = ""
 
     for column in cumulative_df.columns:
         cum_repo_size = cumulative_df[column].iloc[-1]
@@ -140,10 +140,10 @@ def tabular_analysis(repo_sizes, cumulative_df, cumulative_df_deduped):
         repo_size_diff = cum_repo_size - comp_repo_size
         repo_sizes.loc[
             repo_sizes["Repository Type"] == column.capitalize(),
-            "Deduped Size (PBs)",
+            "Deduped Size (PB)",
         ] = comp_repo_size
         repo_sizes.loc[
-            repo_sizes["Repository Type"] == column.capitalize(), "Dedupe Savings (PBs)"
+            repo_sizes["Repository Type"] == column.capitalize(), "Dedupe Savings (PB)"
         ] = repo_size_diff
 
     # add a row that sums the total size and deduped size
@@ -207,7 +207,7 @@ def cumulative_growth_plot_analysis(cumulative_df, cumulative_df_deduped):
     fig.update_layout(
         title="Cumulative Growth of Models, Spaces, and Datasets Over Time<br><sup>Dotted lines represent growth with file-level deduplication</sup>",
         xaxis_title="Date",
-        yaxis_title="Cumulative Size (PBs)",
+        yaxis_title="Cumulative Size (PB)",
         legend_title="Type",
         yaxis=dict(tickformat=".2f"),  # Format y-axis labels to 2 decimal places
     )
@@ -254,7 +254,7 @@ def cumulative_growth_single(_df):
     fig.update_layout(
         title="Cumulative Growth of Models, Spaces, and Datasets",
         xaxis_title="Date",
-        yaxis_title="Size (PBs)",
+        yaxis_title="Size (PB)",
         legend_title="Type",
         yaxis=dict(tickformat=".2f"),  # Format y-axis labels to 2 decimal places
     )
@@ -280,9 +280,9 @@ def plot_total_sum(by_type_arr):
 
     # Update layout
     fig.update_layout(
-        title="Top 20 File Extensions by Total Size (in PBs)",
+        title="Top 20 File Extensions by Total Size (in PB)",
         xaxis_title="File Extension",
-        yaxis_title="Total Size (PBs)",
+        yaxis_title="Total Size (PB)",
         yaxis=dict(tickformat=".2f"),  # Format y-axis labels to 2 decimal places
         colorway=px.colors.qualitative.Alphabet,  # Use Plotly color palette
     )
@@ -350,11 +350,11 @@ def area_plot_by_extension_month(_df):
     fig = px.area(_df, x="date", y="total_size", color="extension")
     # Update layout
     fig.update_layout(
-        title="File Extension Monthly Additions (in PBs) Over Time",
+        title="File Extension Monthly Additions (in PB) Over Time",
         xaxis_title="Date",
-        yaxis_title="Size (PBs)",
+        yaxis_title="Size (PB)",
         legend_title="Type",
-        # format y-axis to be PBs (currently bytes) with two decimal places
+        # format y-axis to be PB (currently bytes) with two decimal places
         yaxis=dict(tickformat=".2f"),
     )
 
@@ -437,9 +437,9 @@ with gr.Blocks(theme="citrus") as demo:
             # Convert the total size to petabytes and format to two decimal places
             current_storage = format_dataframe_size_column(
                 by_repo_type_analysis,
-                ["Total Size (PBs)", "Deduped Size (PBs)", "Dedupe Savings (PBs)"],
+                ["Total Size (PB)", "Deduped Size (PB)", "Dedupe Savings (PB)"],
             )
-            gr.Dataframe(current_storage[["Repository Type", "Total Size (PBs)"]])
+            gr.Dataframe(current_storage[["Repository Type", "Total Size (PB)"]])
 
     gr.HTML(div_px(25))
     # File Extension analysis
@@ -448,7 +448,7 @@ with gr.Blocks(theme="citrus") as demo:
         "What types of files are stored on the Hub? The Xet team's backend architecture allows for storage optimizations by file type, so seeing the breakdown of the most popular stored file types helps to prioritize our roadmap. The following sections filter the analysis to the top 20 file extensions stored (by bytes) using Git LFS. Taken together, these 20 file extensions account for 82% of the total bytes stored in LFS."
     )
     gr.Markdown(
-        "[Safetensors](https://huggingface.co/docs/safetensors/en/index) is quickly becoming the defacto standard on the Hub for storing tensor files, accounting for over 7PBs (25%) of LFS storage. [GGUF (GPT-Generated Unified Format)](https://huggingface.co/docs/hub/gguf), a format for storing tensor files with a different set of optimizations, is also on the rise, accounting for 3.2 PBs (11%) of LFS storage."
+        "[Safetensors](https://huggingface.co/docs/safetensors/en/index) is quickly becoming the defacto standard on the Hub for storing tensor files, accounting for over 7PB (25%) of LFS storage. [GGUF (GPT-Generated Unified Format)](https://huggingface.co/docs/hub/gguf), a format for storing tensor files with a different set of optimizations, is also on the rise, accounting for 3.2 PB (11%) of LFS storage."
     )
     # Get the top 10 file extensions by size
     by_extension_size = by_extension.sort_values(by="size", ascending=False).head(22)
@@ -473,7 +473,7 @@ with gr.Blocks(theme="citrus") as demo:
         columns={
             "extension": "File Extension",
             "count": "Number of Files",
-            "size": "Total Size (PBs)",
+            "size": "Total Size (PB)",
         }
     )
 
@@ -485,7 +485,7 @@ with gr.Blocks(theme="citrus") as demo:
         by_extension_size[
             [
                 "File Extension",
-                "Total Size (PBs)",
+                "Total Size (PB)",
                 "Number of Files",
                 "Average File Size (MBs)",
             ]
@@ -493,7 +493,7 @@ with gr.Blocks(theme="citrus") as demo:
     )
 
     gr.HTML(div_px(5))
-    gr.Markdown("### Storage Growth by File Extension (Monthly PBs Added)")
+    gr.Markdown("### Storage Growth by File Extension (Monthly PB Added)")
     gr.Markdown(
         "The following area chart shows the number of bytes added to LFS storage each month, faceted by file extension."
     )
@@ -534,7 +534,7 @@ with gr.Blocks(theme="citrus") as demo:
         with gr.Column(scale=1):
             gr.Markdown("### Current Storage Usage + File-level Deduplication")
             gr.Markdown(
-                "This simple change to the storage backend will save 3.24 PBs (the equivalent of 7.2 Common Crawls)."
+                "This simple change to the storage backend will save 3.24 PB (the equivalent of 7.2 Common Crawls)."
             )
         with gr.Column(scale=3):
             # Convert the total size to petabytes and format to two decimal places
@@ -545,7 +545,7 @@ with gr.Blocks(theme="citrus") as demo:
         with gr.Column(scale=1):
             gr.Markdown("### Month-to-Month Growth + File-level Deduplication")
             gr.Markdown(
-                "This table shows month-to-month growth in model, dataset, and space storage. In 2024, the Hub has averaged nearly **2.3 PBs uploaded to Git LFS per month**. Deduplicating at the file level saves nearly 225 TB (half a Common Crawl) monthly."
+                "This table shows month-to-month growth in model, dataset, and space storage. In 2024, the Hub has averaged nearly **2.3 PB uploaded to Git LFS per month**. Deduplicating at the file level saves nearly 225 TB (half a Common Crawl) monthly."
             )
         with gr.Column(scale=3):
             gr.Dataframe(last_10_months)