Upload 4 files

app.py

@@ -0,0 +1,102 @@
+import gradio as gr
+
+from huggingface_hub import list_models, list_spaces
+from pathlib import Path
+from toolz import concat
+from datasets import Dataset
+import polars as pl
+from datetime import date
+from datasets import load_dataset
+import plotly.express as px
+import os
+
+HF_TOKEN = os.getenv("HF_TOKEN")
+assert HF_TOKEN
+
+
+def yield_models():
+    for model in iter(list_models(full=True)):
+        yield "model", model
+
+
+def yield_spaces():
+    for space in iter(list_spaces(full=True)):
+        yield "space", space
+
+
+def yield_notebooks():
+    for repo_type, repo in concat([yield_models(), yield_spaces()]):
+        files = (f.rfilename for f in repo.siblings)
+        if jupyter_notebook := [f for f in files if Path(f).suffix == ".ipynb"]:
+            yield {
+                "date": date.today(),
+                "repo_type": repo_type,
+                "repo_id": repo.id,
+                "repo_notebook_count": len(jupyter_notebook),
+            }
+
+
+def update_stats():
+    df = pl.LazyFrame(yield_notebooks())
+
+    df = (
+        df.with_columns(pl.col("repo_id").str.split_exact("/", 1))
+        .unnest("repo_id")
+        .rename({"field_0": "user", "field_1": "repo_id"})
+    )
+    by_user_count = (
+        df.groupby("user")
+        .agg(pl.col("repo_notebook_count").sum())
+        .sort("repo_notebook_count", descending=True)
+        .collect()
+    )
+
+    by_user_count.mean().select(
+        pl.col("repo_notebook_count").alias("mean notebooks  per user")
+    )
+
+    ds = Dataset(by_user_count.to_arrow())
+
+    ds.push_to_hub("davanstrien/notebooks_by_user", token=HF_TOKEN)
+
+    grouped = df.groupby("repo_type").agg(pl.col("repo_notebook_count").sum())
+    final_df = grouped.with_columns(pl.lit(date.today()).alias("date")).collect()
+    previous_df = pl.DataFrame(
+        load_dataset("davanstrien/notebooks_by_repo_type", split="train").data.table
+    )
+    final_df = pl.concat([previous_df, final_df]).unique()
+    spaces = final_df.filter(pl.col("repo_type") == "space").unique(
+        subset=["date"], keep="last"
+    )
+    models = final_df.filter(pl.col("repo_type") == "model").unique(
+        subset=["date"], keep="last"
+    )
+    final_df = pl.concat([spaces, models]).unique()
+    Dataset(final_df.to_arrow()).push_to_hub(
+        "davanstrien/notebooks_by_repo_type", token=HF_TOKEN
+    )
+
+    final_df = final_df.sort("date")
+    pandas_df = final_df.to_pandas()
+    # final_df.to_pandas().set_index("date", drop=True).sort_index()
+    return pandas_df, final_df
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Notebooks on the Hub (updated daily)")
+    pandas_df, final_df = update_stats()
+    gr.Markdown("## Notebooks on the Hub over time")
+    gr.Plot(px.line(pandas_df, x="date", y="repo_notebook_count", color="repo_type"))
+    gr.Markdown("## Notebooks on the Hub (total by date)")
+    gr.DataFrame(
+        final_df.select(pl.col(["date", "repo_notebook_count"]))
+        .groupby("date")
+        .sum()
+        .sort("date")
+        .to_pandas()
+    )
+    gr.Markdown("## Notebooks on the Hub raw data")
+    gr.DataFrame(pandas_df)
+
+
+demo.launch(debug=True)

notebooks_on_the_hub.ipynb

@@ -0,0 +1,1966 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "metadata": {
+    "id": "iNgLgZ27Dlq6"
+   },
+   "outputs": [],
+   "source": [
+    "from huggingface_hub import list_models, list_spaces\n",
+    "from pathlib import Path\n",
+    "from toolz import concat\n",
+    "from datasets import Dataset\n",
+    "import polars as pl\n",
+    "from datetime import date\n",
+    "from datetime import date, timedelta\n",
+    "from datasets import load_dataset\n",
+    "import plotly.express as px\n",
+    "import os"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "HF_TOKEN = os.getenv(\"HF_TOKEN\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {
+    "id": "mBMDThV4FA3m"
+   },
+   "outputs": [],
+   "source": [
+    "def yield_models():\n",
+    "    for model in iter(list_models(full=True)):\n",
+    "        yield \"model\", model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {
+    "id": "hDqiwFD3uTR8"
+   },
+   "outputs": [],
+   "source": [
+    "def yield_spaces():\n",
+    "    for space in iter(list_spaces(full=True)):\n",
+    "        yield \"space\", space"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {
+    "id": "mZEhftoNFHGN"
+   },
+   "outputs": [],
+   "source": [
+    "def yield_notebooks():\n",
+    "    for repo_type, repo in concat([yield_models(), yield_spaces()]):\n",
+    "        files = (f.rfilename for f in repo.siblings)\n",
+    "        if jupyter_notebook := [f for f in files if Path(f).suffix == \".ipynb\"]:\n",
+    "            yield {\n",
+    "                \"date\": date.today(),\n",
+    "                \"repo_type\": repo_type,\n",
+    "                \"repo_id\": repo.id,\n",
+    "                \"repo_notebook_count\": len(jupyter_notebook),\n",
+    "            }"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pl.LazyFrame(yield_notebooks())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = (\n",
+    "    df.with_columns(pl.col(\"repo_id\").str.split_exact(\"/\", 1))\n",
+    "    .unnest(\"repo_id\")\n",
+    "    .rename({\"field_0\": \"user\", \"field_1\": \"repo_id\"})\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "by_user_count = (\n",
+    "    df.groupby(\"user\")\n",
+    "    .agg(pl.col(\"repo_notebook_count\").sum())\n",
+    "    .sort(\"repo_notebook_count\", descending=True)\n",
+    "    .collect()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div><style>\n",
+       ".dataframe > thead > tr > th,\n",
+       ".dataframe > tbody > tr > td {\n",
+       "  text-align: right;\n",
+       "}\n",
+       "</style>\n",
+       "<small>shape: (1540, 2)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>user</th><th>repo_notebook_count</th></tr><tr><td>str</td><td>i64</td></tr></thead><tbody><tr><td>&quot;gradio-pr-depl…</td><td>1798</td></tr><tr><td>&quot;gradio&quot;</td><td>414</td></tr><tr><td>&quot;sgoodfriend&quot;</td><td>240</td></tr><tr><td>&quot;merve&quot;</td><td>63</td></tr><tr><td>&quot;chrisjay&quot;</td><td>62</td></tr><tr><td>&quot;infinitejoy&quot;</td><td>32</td></tr><tr><td>&quot;fabricius&quot;</td><td>29</td></tr><tr><td>&quot;aammari&quot;</td><td>26</td></tr><tr><td>&quot;flax-community…</td><td>24</td></tr><tr><td>&quot;rajesh1729&quot;</td><td>24</td></tr><tr><td>&quot;gabri14el&quot;</td><td>23</td></tr><tr><td>&quot;srush&quot;</td><td>23</td></tr><tr><td>&hellip;</td><td>&hellip;</td></tr><tr><td>&quot;fredbrito&quot;</td><td>1</td></tr><tr><td>&quot;JimmyLee08&quot;</td><td>1</td></tr><tr><td>&quot;BenjaminFraser…</td><td>1</td></tr><tr><td>&quot;MRamzam&quot;</td><td>1</td></tr><tr><td>&quot;Deepak107&quot;</td><td>1</td></tr><tr><td>&quot;ozyman&quot;</td><td>1</td></tr><tr><td>&quot;ELIA&quot;</td><td>1</td></tr><tr><td>&quot;zaidmukaddam&quot;</td><td>1</td></tr><tr><td>&quot;Jack003&quot;</td><td>1</td></tr><tr><td>&quot;SiddhantOjha&quot;</td><td>1</td></tr><tr><td>&quot;lowrollr&quot;</td><td>1</td></tr><tr><td>&quot;edwardpraveen&quot;</td><td>1</td></tr></tbody></table></div>"
+      ],
+      "text/plain": [
+       "shape: (1540, 2)\n",
+       "┌───────────────────┬─────────────────────┐\n",
+       "│ user              ┆ repo_notebook_count │\n",
+       "│ ---               ┆ ---                 │\n",
+       "│ str               ┆ i64                 │\n",
+       "╞═══════════════════╪═══════════════��═════╡\n",
+       "│ gradio-pr-deploys ┆ 1798                │\n",
+       "│ gradio            ┆ 414                 │\n",
+       "│ sgoodfriend       ┆ 240                 │\n",
+       "│ merve             ┆ 63                  │\n",
+       "│ …                 ┆ …                   │\n",
+       "│ Jack003           ┆ 1                   │\n",
+       "│ SiddhantOjha      ┆ 1                   │\n",
+       "│ lowrollr          ┆ 1                   │\n",
+       "│ edwardpraveen     ┆ 1                   │\n",
+       "└───────────────────┴─────────────────────┘"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "by_user_count"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div><style>\n",
+       ".dataframe > thead > tr > th,\n",
+       ".dataframe > tbody > tr > td {\n",
+       "  text-align: right;\n",
+       "}\n",
+       "</style>\n",
+       "<small>shape: (7, 3)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>describe</th><th>user</th><th>repo_notebook_count</th></tr><tr><td>str</td><td>str</td><td>f64</td></tr></thead><tbody><tr><td>&quot;count&quot;</td><td>&quot;1540&quot;</td><td>1540.0</td></tr><tr><td>&quot;null_count&quot;</td><td>&quot;0&quot;</td><td>0.0</td></tr><tr><td>&quot;mean&quot;</td><td>null</td><td>3.787013</td></tr><tr><td>&quot;std&quot;</td><td>null</td><td>47.455407</td></tr><tr><td>&quot;min&quot;</td><td>&quot;007aneesh&quot;</td><td>1.0</td></tr><tr><td>&quot;max&quot;</td><td>&quot;zinoubm&quot;</td><td>1798.0</td></tr><tr><td>&quot;median&quot;</td><td>null</td><td>1.0</td></tr></tbody></table></div>"
+      ],
+      "text/plain": [
+       "shape: (7, 3)\n",
+       "┌────────────┬───────────┬─────────────────────┐\n",
+       "│ describe   ┆ user      ┆ repo_notebook_count │\n",
+       "│ ---        ┆ ---       ┆ ---                 │\n",
+       "│ str        ┆ str       ┆ f64                 │\n",
+       "╞════════════╪═══════════╪═════════════════════╡\n",
+       "│ count      ┆ 1540      ┆ 1540.0              │\n",
+       "│ null_count ┆ 0         ┆ 0.0                 │\n",
+       "│ mean       ┆ null      ┆ 3.787013            │\n",
+       "│ std        ┆ null      ┆ 47.455407           │\n",
+       "│ min        ┆ 007aneesh ┆ 1.0                 │\n",
+       "│ max        ┆ zinoubm   ┆ 1798.0              │\n",
+       "│ median     ┆ null      ┆ 1.0                 │\n",
+       "└────────────┴───────────┴─────────────────────┘"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "by_user_count.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div><style>\n",
+       ".dataframe > thead > tr > th,\n",
+       ".dataframe > tbody > tr > td {\n",
+       "  text-align: right;\n",
+       "}\n",
+       "</style>\n",
+       "<small>shape: (1, 1)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>mean notebooks  per user</th></tr><tr><td>f64</td></tr></thead><tbody><tr><td>3.787013</td></tr></tbody></table></div>"
+      ],
+      "text/plain": [
+       "shape: (1, 1)\n",
+       "┌──────────────────────────┐\n",
+       "│ mean notebooks  per user │\n",
+       "│ ---                      │\n",
+       "│ f64                      │\n",
+       "╞══════════════════════════╡\n",
+       "│ 3.787013                 │\n",
+       "└──────────────────────────┘"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "by_user_count.mean().select(\n",
+    "    pl.col(\"repo_notebook_count\").alias(\"mean notebooks  per user\")\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Dataset({\n",
+       "    features: ['user', 'repo_notebook_count'],\n",
+       "    num_rows: 1540\n",
+       "})"
+      ]
+     },
+     "execution_count": 32,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ds = Dataset(by_user_count.to_arrow())\n",
+    "ds"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Creating parquet from Arrow format: 100%|██████████| 2/2 [00:00<00:00, 617.08ba/s]\n",
+      "Upload 1 LFS files: 100%|██████████| 1/1 [00:00<00:00,  1.05it/s]\n",
+      "Pushing dataset shards to the dataset hub: 100%|██████████| 1/1 [00:02<00:00,  2.39s/it]\n",
+      "Deleting unused files from dataset repository: 100%|██████████| 1/1 [00:00<00:00,  2.01it/s]\n",
+      "Downloading metadata: 100%|██████████| 406/406 [00:00<00:00, 126kB/s]\n",
+      "Updating downloaded metadata with the new split.\n"
+     ]
+    }
+   ],
+   "source": [
+    "ds.push_to_hub(\"davanstrien/notebooks_by_user\", token=HF_TOKEN)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {
+    "id": "h6AaHRSCV397"
+   },
+   "outputs": [],
+   "source": [
+    "grouped = df.groupby(\"repo_type\").agg(pl.col(\"repo_notebook_count\").sum())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div><style>\n",
+       ".dataframe > thead > tr > th,\n",
+       ".dataframe > tbody > tr > td {\n",
+       "  text-align: right;\n",
+       "}\n",
+       "</style>\n",
+       "<small>shape: (2, 3)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>repo_type</th><th>repo_notebook_count</th><th>date</th></tr><tr><td>str</td><td>i64</td><td>date</td></tr></thead><tbody><tr><td>&quot;space&quot;</td><td>4443</td><td>2023-03-30</td></tr><tr><td>&quot;model&quot;</td><td>1389</td><td>2023-03-30</td></tr></tbody></table></div>"
+      ],
+      "text/plain": [
+       "shape: (2, 3)\n",
+       "┌───────────┬─────────────────────┬────────────┐\n",
+       "│ repo_type ┆ repo_notebook_count ┆ date       │\n",
+       "│ ---       ┆ ---                 ┆ ---        │\n",
+       "│ str       ┆ i64                 ┆ date       │\n",
+       "╞═══════════╪═════════════════════╪════════════╡\n",
+       "│ space     ┆ 4443                ┆ 2023-03-30 │\n",
+       "│ model     ┆ 1389                ┆ 2023-03-30 │\n",
+       "└───────────┴─────────────────────┴────────────┘"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "final_df = grouped.with_columns(pl.lit(date.today()).alias(\"date\")).collect()\n",
+    "final_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Downloading readme: 100%|██████████| 441/441 [00:00<00:00, 130kB/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Downloading and preparing dataset None/None to /Users/davanstrien/.cache/huggingface/datasets/davanstrien___parquet/davanstrien--notebooks_by_repo_type-1004c11b0535dac5/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec...\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Downloading data: 100%|██████████| 1.87k/1.87k [00:00<00:00, 705kB/s]\n",
+      "Downloading data files: 100%|██████████| 1/1 [00:01<00:00,  1.71s/it]\n",
+      "Extracting data files: 100%|██████████| 1/1 [00:00<00:00, 786.78it/s]\n",
+      "                                                                    "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dataset parquet downloaded and prepared to /Users/davanstrien/.cache/huggingface/datasets/davanstrien___parquet/davanstrien--notebooks_by_repo_type-1004c11b0535dac5/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec. Subsequent calls will reuse this data.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><style>\n",
+       ".dataframe > thead > tr > th,\n",
+       ".dataframe > tbody > tr > td {\n",
+       "  text-align: right;\n",
+       "}\n",
+       "</style>\n",
+       "<small>shape: (7, 3)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>repo_type</th><th>repo_notebook_count</th><th>date</th></tr><tr><td>str</td><td>i64</td><td>date</td></tr></thead><tbody><tr><td>&quot;space&quot;</td><td>3956</td><td>2023-03-27</td></tr><tr><td>&quot;model&quot;</td><td>1346</td><td>2023-03-27</td></tr><tr><td>&quot;model&quot;</td><td>1348</td><td>2023-03-28</td></tr><tr><td>&quot;space&quot;</td><td>4386</td><td>2023-03-28</td></tr><tr><td>&quot;space&quot;</td><td>4422</td><td>2023-03-28</td></tr><tr><td>&quot;space&quot;</td><td>4579</td><td>2023-03-29</td></tr><tr><td>&quot;model&quot;</td><td>1384</td><td>2023-03-29</td></tr></tbody></table></div>"
+      ],
+      "text/plain": [
+       "shape: (7, 3)\n",
+       "┌───────────┬─────────────────────┬────────────┐\n",
+       "│ repo_type ┆ repo_notebook_count ┆ date       │\n",
+       "│ ---       ┆ ---                 ┆ ---        │\n",
+       "│ str       ┆ i64                 ┆ date       │\n",
+       "╞═══════════╪═════════════════════╪════════════╡\n",
+       "│ space     ┆ 3956                ┆ 2023-03-27 │\n",
+       "│ model     ┆ 1346                ┆ 2023-03-27 │\n",
+       "│ model     ┆ 1348                ┆ 2023-03-28 │\n",
+       "│ space     ┆ 4386                ┆ 2023-03-28 │\n",
+       "│ space     ┆ 4422                ┆ 2023-03-28 │\n",
+       "│ space     ┆ 4579                ┆ 2023-03-29 │\n",
+       "│ model     ┆ 1384                ┆ 2023-03-29 │\n",
+       "└───────────┴─────────────────────┴────────────┘"
+      ]
+     },
+     "execution_count": 36,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "previous_df = pl.DataFrame(\n",
+    "    load_dataset(\"davanstrien/notebooks_by_repo_type\", split=\"train\").data.table\n",
+    ")\n",
+    "previous_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "final_df = pl.concat([previous_df, final_df]).unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "spaces = final_df.filter(pl.col(\"repo_type\") == \"space\").unique(subset=[\"date\"])\n",
+    "models = final_df.filter(pl.col(\"repo_type\") == \"model\").unique(subset=[\"date\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "final_df = pl.concat([spaces, models]).unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div><style>\n",
+       ".dataframe > thead > tr > th,\n",
+       ".dataframe > tbody > tr > td {\n",
+       "  text-align: right;\n",
+       "}\n",
+       "</style>\n",
+       "<small>shape: (8, 3)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>repo_type</th><th>repo_notebook_count</th><th>date</th></tr><tr><td>str</td><td>i64</td><td>date</td></tr></thead><tbody><tr><td>&quot;space&quot;</td><td>3956</td><td>2023-03-27</td></tr><tr><td>&quot;model&quot;</td><td>1346</td><td>2023-03-27</td></tr><tr><td>&quot;space&quot;</td><td>4386</td><td>2023-03-28</td></tr><tr><td>&quot;model&quot;</td><td>1348</td><td>2023-03-28</td></tr><tr><td>&quot;space&quot;</td><td>4579</td><td>2023-03-29</td></tr><tr><td>&quot;model&quot;</td><td>1384</td><td>2023-03-29</td></tr><tr><td>&quot;space&quot;</td><td>4443</td><td>2023-03-30</td></tr><tr><td>&quot;model&quot;</td><td>1389</td><td>2023-03-30</td></tr></tbody></table></div>"
+      ],
+      "text/plain": [
+       "shape: (8, 3)\n",
+       "┌───────────┬─────────────────────┬────────────┐\n",
+       "│ repo_type ┆ repo_notebook_count ┆ date       │\n",
+       "│ ---       ┆ ---                 ┆ ---        │\n",
+       "│ str       ┆ i64                 ┆ date       │\n",
+       "╞═══════════╪═════════════════════╪════════════╡\n",
+       "│ space     ┆ 3956                ┆ 2023-03-27 │\n",
+       "│ model     ┆ 1346                ┆ 2023-03-27 │\n",
+       "│ space     ┆ 4386                ┆ 2023-03-28 │\n",
+       "│ model     ┆ 1348                ┆ 2023-03-28 │\n",
+       "│ space     ┆ 4579                ┆ 2023-03-29 │\n",
+       "│ model     ┆ 1384                ┆ 2023-03-29 │\n",
+       "│ space     ┆ 4443                ┆ 2023-03-30 │\n",
+       "│ model     ┆ 1389                ┆ 2023-03-30 │\n",
+       "└───────────┴─────────────────────┴────────────┘"
+      ]
+     },
+     "execution_count": 62,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "final_df = final_df.sort(\"date\")\n",
+    "final_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<polars.dataframe.groupby.GroupBy at 0x2a1035d10>"
+      ]
+     },
+     "execution_count": 55,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "final_df.groupby(\"repo_type\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Creating parquet from Arrow format: 100%|██████████| 1/1 [00:00<00:00, 730.46ba/s]\n",
+      "Upload 1 LFS files: 100%|██████████| 1/1 [00:00<00:00,  1.26it/s]\n",
+      "Pushing dataset shards to the dataset hub: 100%|██████████| 1/1 [00:02<00:00,  2.14s/it]\n",
+      "Deleting unused files from dataset repository: 100%|██████████| 1/1 [00:00<00:00,  1.87it/s]\n",
+      "Downloading metadata: 100%|██████████| 441/441 [00:00<00:00, 173kB/s]\n",
+      "Updating downloaded metadata with the new split.\n"
+     ]
+    }
+   ],
+   "source": [
+    "Dataset(final_df.to_arrow()).push_to_hub(\n",
+    "    \"davanstrien/notebooks_by_repo_type\", token=HF_TOKEN\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 73,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 224
+    },
+    "id": "T3vhuLpgdyKh",
+    "outputId": "82a58845-ec9f-40d7-cbad-abddf7ad467a"
+   },
+   "outputs": [],
+   "source": [
+    "final_df = final_df.sort(\"date\")\n",
+    "pandas_df = final_df.to_pandas()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>repo_type</th>\n",
+       "      <th>repo_notebook_count</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>date</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2023-03-27</th>\n",
+       "      <td>space</td>\n",
+       "      <td>3956</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2023-03-27</th>\n",
+       "      <td>model</td>\n",
+       "      <td>1346</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2023-03-28</th>\n",
+       "      <td>space</td>\n",
+       "      <td>4386</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2023-03-28</th>\n",
+       "      <td>model</td>\n",
+       "      <td>1348</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2023-03-29</th>\n",
+       "      <td>space</td>\n",
+       "      <td>4579</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2023-03-29</th>\n",
+       "      <td>model</td>\n",
+       "      <td>1384</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2023-03-30</th>\n",
+       "      <td>space</td>\n",
+       "      <td>4443</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2023-03-30</th>\n",
+       "      <td>model</td>\n",
+       "      <td>1389</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "           repo_type  repo_notebook_count\n",
+       "date                                     \n",
+       "2023-03-27     space                 3956\n",
+       "2023-03-27     model                 1346\n",
+       "2023-03-28     space                 4386\n",
+       "2023-03-28     model                 1348\n",
+       "2023-03-29     space                 4579\n",
+       "2023-03-29     model                 1384\n",
+       "2023-03-30     space                 4443\n",
+       "2023-03-30     model                 1389"
+      ]
+     },
+     "execution_count": 65,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# final_df.to_pandas().set_index(\"date\", drop=True).sort_index()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.plotly.v1+json": {
+       "config": {
+        "plotlyServerURL": "https://plot.ly"
+       },
+       "data": [
+        {
+         "hovertemplate": "repo_type=space<br>date=%{x}<br>repo_notebook_count=%{y}<extra></extra>",
+         "legendgroup": "space",
+         "line": {
+          "color": "#636efa",
+          "dash": "solid"
+         },
+         "marker": {
+          "symbol": "circle"
+         },
+         "mode": "lines",
+         "name": "space",
+         "orientation": "v",
+         "showlegend": true,
+         "type": "scatter",
+         "x": [
+          "2023-03-27T00:00:00",
+          "2023-03-28T00:00:00",
+          "2023-03-29T00:00:00",
+          "2023-03-30T00:00:00"
+         ],
+         "xaxis": "x",
+         "y": [
+          3956,
+          4386,
+          4579,
+          4443
+         ],
+         "yaxis": "y"
+        },
+        {
+         "hovertemplate": "repo_type=model<br>date=%{x}<br>repo_notebook_count=%{y}<extra></extra>",
+         "legendgroup": "model",
+         "line": {
+          "color": "#EF553B",
+          "dash": "solid"
+         },
+         "marker": {
+          "symbol": "circle"
+         },
+         "mode": "lines",
+         "name": "model",
+         "orientation": "v",
+         "showlegend": true,
+         "type": "scatter",
+         "x": [
+          "2023-03-27T00:00:00",
+          "2023-03-28T00:00:00",
+          "2023-03-29T00:00:00",
+          "2023-03-30T00:00:00"
+         ],
+         "xaxis": "x",
+         "y": [
+          1346,
+          1348,
+          1384,
+          1389
+         ],
+         "yaxis": "y"
+        }
+       ],
+       "layout": {
+        "legend": {
+         "title": {
+          "text": "repo_type"
+         },
+         "tracegroupgap": 0
+        },
+        "margin": {
+         "t": 60
+        },
+        "template": {
+         "data": {
+          "bar": [
+           {
+            "error_x": {
+             "color": "#2a3f5f"
+            },
+            "error_y": {
+             "color": "#2a3f5f"
+            },
+            "marker": {
+             "line": {
+              "color": "#E5ECF6",
+              "width": 0.5
+             },
+             "pattern": {
+              "fillmode": "overlay",
+              "size": 10,
+              "solidity": 0.2
+             }
+            },
+            "type": "bar"
+           }
+          ],
+          "barpolar": [
+           {
+            "marker": {
+             "line": {
+              "color": "#E5ECF6",
+              "width": 0.5
+             },
+             "pattern": {
+              "fillmode": "overlay",
+              "size": 10,
+              "solidity": 0.2
+             }
+            },
+            "type": "barpolar"
+           }
+          ],
+          "carpet": [
+           {
+            "aaxis": {
+             "endlinecolor": "#2a3f5f",
+             "gridcolor": "white",
+             "linecolor": "white",
+             "minorgridcolor": "white",
+             "startlinecolor": "#2a3f5f"
+            },
+            "baxis": {
+             "endlinecolor": "#2a3f5f",
+             "gridcolor": "white",
+             "linecolor": "white",
+             "minorgridcolor": "white",
+             "startlinecolor": "#2a3f5f"
+            },
+            "type": "carpet"
+           }
+          ],
+          "choropleth": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "type": "choropleth"
+           }
+          ],
+          "contour": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "contour"
+           }
+          ],
+          "contourcarpet": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "type": "contourcarpet"
+           }
+          ],
+          "heatmap": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "heatmap"
+           }
+          ],
+          "heatmapgl": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "heatmapgl"
+           }
+          ],
+          "histogram": [
+           {
+            "marker": {
+             "pattern": {
+              "fillmode": "overlay",
+              "size": 10,
+              "solidity": 0.2
+             }
+            },
+            "type": "histogram"
+           }
+          ],
+          "histogram2d": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "histogram2d"
+           }
+          ],
+          "histogram2dcontour": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "histogram2dcontour"
+           }
+          ],
+          "mesh3d": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "type": "mesh3d"
+           }
+          ],
+          "parcoords": [
+           {
+            "line": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "parcoords"
+           }
+          ],
+          "pie": [
+           {
+            "automargin": true,
+            "type": "pie"
+           }
+          ],
+          "scatter": [
+           {
+            "fillpattern": {
+             "fillmode": "overlay",
+             "size": 10,
+             "solidity": 0.2
+            },
+            "type": "scatter"
+           }
+          ],
+          "scatter3d": [
+           {
+            "line": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatter3d"
+           }
+          ],
+          "scattercarpet": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattercarpet"
+           }
+          ],
+          "scattergeo": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattergeo"
+           }
+          ],
+          "scattergl": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattergl"
+           }
+          ],
+          "scattermapbox": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scattermapbox"
+           }
+          ],
+          "scatterpolar": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatterpolar"
+           }
+          ],
+          "scatterpolargl": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatterpolargl"
+           }
+          ],
+          "scatterternary": [
+           {
+            "marker": {
+             "colorbar": {
+              "outlinewidth": 0,
+              "ticks": ""
+             }
+            },
+            "type": "scatterternary"
+           }
+          ],
+          "surface": [
+           {
+            "colorbar": {
+             "outlinewidth": 0,
+             "ticks": ""
+            },
+            "colorscale": [
+             [
+              0,
+              "#0d0887"
+             ],
+             [
+              0.1111111111111111,
+              "#46039f"
+             ],
+             [
+              0.2222222222222222,
+              "#7201a8"
+             ],
+             [
+              0.3333333333333333,
+              "#9c179e"
+             ],
+             [
+              0.4444444444444444,
+              "#bd3786"
+             ],
+             [
+              0.5555555555555556,
+              "#d8576b"
+             ],
+             [
+              0.6666666666666666,
+              "#ed7953"
+             ],
+             [
+              0.7777777777777778,
+              "#fb9f3a"
+             ],
+             [
+              0.8888888888888888,
+              "#fdca26"
+             ],
+             [
+              1,
+              "#f0f921"
+             ]
+            ],
+            "type": "surface"
+           }
+          ],
+          "table": [
+           {
+            "cells": {
+             "fill": {
+              "color": "#EBF0F8"
+             },
+             "line": {
+              "color": "white"
+             }
+            },
+            "header": {
+             "fill": {
+              "color": "#C8D4E3"
+             },
+             "line": {
+              "color": "white"
+             }
+            },
+            "type": "table"
+           }
+          ]
+         },
+         "layout": {
+          "annotationdefaults": {
+           "arrowcolor": "#2a3f5f",
+           "arrowhead": 0,
+           "arrowwidth": 1
+          },
+          "autotypenumbers": "strict",
+          "coloraxis": {
+           "colorbar": {
+            "outlinewidth": 0,
+            "ticks": ""
+           }
+          },
+          "colorscale": {
+           "diverging": [
+            [
+             0,
+             "#8e0152"
+            ],
+            [
+             0.1,
+             "#c51b7d"
+            ],
+            [
+             0.2,
+             "#de77ae"
+            ],
+            [
+             0.3,
+             "#f1b6da"
+            ],
+            [
+             0.4,
+             "#fde0ef"
+            ],
+            [
+             0.5,
+             "#f7f7f7"
+            ],
+            [
+             0.6,
+             "#e6f5d0"
+            ],
+            [
+             0.7,
+             "#b8e186"
+            ],
+            [
+             0.8,
+             "#7fbc41"
+            ],
+            [
+             0.9,
+             "#4d9221"
+            ],
+            [
+             1,
+             "#276419"
+            ]
+           ],
+           "sequential": [
+            [
+             0,
+             "#0d0887"
+            ],
+            [
+             0.1111111111111111,
+             "#46039f"
+            ],
+            [
+             0.2222222222222222,
+             "#7201a8"
+            ],
+            [
+             0.3333333333333333,
+             "#9c179e"
+            ],
+            [
+             0.4444444444444444,
+             "#bd3786"
+            ],
+            [
+             0.5555555555555556,
+             "#d8576b"
+            ],
+            [
+             0.6666666666666666,
+             "#ed7953"
+            ],
+            [
+             0.7777777777777778,
+             "#fb9f3a"
+            ],
+            [
+             0.8888888888888888,
+             "#fdca26"
+            ],
+            [
+             1,
+             "#f0f921"
+            ]
+           ],
+           "sequentialminus": [
+            [
+             0,
+             "#0d0887"
+            ],
+            [
+             0.1111111111111111,
+             "#46039f"
+            ],
+            [
+             0.2222222222222222,
+             "#7201a8"
+            ],
+            [
+             0.3333333333333333,
+             "#9c179e"
+            ],
+            [
+             0.4444444444444444,
+             "#bd3786"
+            ],
+            [
+             0.5555555555555556,
+             "#d8576b"
+            ],
+            [
+             0.6666666666666666,
+             "#ed7953"
+            ],
+            [
+             0.7777777777777778,
+             "#fb9f3a"
+            ],
+            [
+             0.8888888888888888,
+             "#fdca26"
+            ],
+            [
+             1,
+             "#f0f921"
+            ]
+           ]
+          },
+          "colorway": [
+           "#636efa",
+           "#EF553B",
+           "#00cc96",
+           "#ab63fa",
+           "#FFA15A",
+           "#19d3f3",
+           "#FF6692",
+           "#B6E880",
+           "#FF97FF",
+           "#FECB52"
+          ],
+          "font": {
+           "color": "#2a3f5f"
+          },
+          "geo": {
+           "bgcolor": "white",
+           "lakecolor": "white",
+           "landcolor": "#E5ECF6",
+           "showlakes": true,
+           "showland": true,
+           "subunitcolor": "white"
+          },
+          "hoverlabel": {
+           "align": "left"
+          },
+          "hovermode": "closest",
+          "mapbox": {
+           "style": "light"
+          },
+          "paper_bgcolor": "white",
+          "plot_bgcolor": "#E5ECF6",
+          "polar": {
+           "angularaxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           },
+           "bgcolor": "#E5ECF6",
+           "radialaxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           }
+          },
+          "scene": {
+           "xaxis": {
+            "backgroundcolor": "#E5ECF6",
+            "gridcolor": "white",
+            "gridwidth": 2,
+            "linecolor": "white",
+            "showbackground": true,
+            "ticks": "",
+            "zerolinecolor": "white"
+           },
+           "yaxis": {
+            "backgroundcolor": "#E5ECF6",
+            "gridcolor": "white",
+            "gridwidth": 2,
+            "linecolor": "white",
+            "showbackground": true,
+            "ticks": "",
+            "zerolinecolor": "white"
+           },
+           "zaxis": {
+            "backgroundcolor": "#E5ECF6",
+            "gridcolor": "white",
+            "gridwidth": 2,
+            "linecolor": "white",
+            "showbackground": true,
+            "ticks": "",
+            "zerolinecolor": "white"
+           }
+          },
+          "shapedefaults": {
+           "line": {
+            "color": "#2a3f5f"
+           }
+          },
+          "ternary": {
+           "aaxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           },
+           "baxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           },
+           "bgcolor": "#E5ECF6",
+           "caxis": {
+            "gridcolor": "white",
+            "linecolor": "white",
+            "ticks": ""
+           }
+          },
+          "title": {
+           "x": 0.05
+          },
+          "xaxis": {
+           "automargin": true,
+           "gridcolor": "white",
+           "linecolor": "white",
+           "ticks": "",
+           "title": {
+            "standoff": 15
+           },
+           "zerolinecolor": "white",
+           "zerolinewidth": 2
+          },
+          "yaxis": {
+           "automargin": true,
+           "gridcolor": "white",
+           "linecolor": "white",
+           "ticks": "",
+           "title": {
+            "standoff": 15
+           },
+           "zerolinecolor": "white",
+           "zerolinewidth": 2
+          }
+         }
+        },
+        "xaxis": {
+         "anchor": "y",
+         "domain": [
+          0,
+          1
+         ],
+         "title": {
+          "text": "date"
+         }
+        },
+        "yaxis": {
+         "anchor": "x",
+         "domain": [
+          0,
+          1
+         ],
+         "title": {
+          "text": "repo_notebook_count"
+         }
+        }
+       }
+      }
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "px.line(pandas_df, x=\"date\", y=\"repo_notebook_count\", color=\"repo_type\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "name": "scratchpad",
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.2"
+  },
+  "widgets": {
+   "application/vnd.jupyter.widget-state+json": {
+    "0b7aa472a433465bbe03d9f5a596d07c": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "1.5.0",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_590d7059bf1e4c5285ca40e5298b7ee7",
+       "IPY_MODEL_a82a83de315c43f6b7f9fa787227b2e3",
+       "IPY_MODEL_4f66bea4e3ce4f508a407788729c958e"
+      ],
+      "layout": "IPY_MODEL_190d66e96c4b427e998fc412dd2bbd7b"
+     }
+    },
+    "190d66e96c4b427e998fc412dd2bbd7b": {
+     "model_module": "@jupyter-widgets/base",
+     "model_module_version": "1.2.0",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": "hidden",
+      "width": null
+     }
+    },
+    "266a59ce352c4a65aea3c6e8402ac1ed": {
+     "model_module": "@jupyter-widgets/base",
+     "model_module_version": "1.2.0",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "4c31add106194a728e308ed486fc2e54": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "1.5.0",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": ""
+     }
+    },
+    "4f66bea4e3ce4f508a407788729c958e": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "1.5.0",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_266a59ce352c4a65aea3c6e8402ac1ed",
+      "placeholder": "​",
+      "style": "IPY_MODEL_c28bf5f9ac624739a48d62510d3bb05d",
+      "value": " 2490/0 [02:11&lt;00:00, 236.08 examples/s]"
+     }
+    },
+    "590d7059bf1e4c5285ca40e5298b7ee7": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "1.5.0",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_711a5f5d14ac4af180b54954e814f394",
+      "placeholder": "​",
+      "style": "IPY_MODEL_605acdd7a4cb4f118951fc79933f62f6",
+      "value": "Generating train split: "
+     }
+    },
+    "605acdd7a4cb4f118951fc79933f62f6": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "1.5.0",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "711a5f5d14ac4af180b54954e814f394": {
+     "model_module": "@jupyter-widgets/base",
+     "model_module_version": "1.2.0",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "a82a83de315c43f6b7f9fa787227b2e3": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "1.5.0",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "info",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_c13a0581f0ff46c4a399627cd8aa1c0c",
+      "max": 1,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_4c31add106194a728e308ed486fc2e54",
+      "value": 1
+     }
+    },
+    "c13a0581f0ff46c4a399627cd8aa1c0c": {
+     "model_module": "@jupyter-widgets/base",
+     "model_module_version": "1.2.0",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": "20px"
+     }
+    },
+    "c28bf5f9ac624739a48d62510d3bb05d": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "1.5.0",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    }
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

requirements.in

@@ -0,0 +1,8 @@
+polars
+datasets
+pandas
+toolz
+matplotlib
+gradio
+plotly
+gradio

requirements.txt

@@ -0,0 +1,224 @@
+#
+# This file is autogenerated by pip-compile with Python 3.11
+# by the following command:
+#
+#    pip-compile --resolver=backtracking requirements.in
+#
+aiofiles==23.1.0
+    # via gradio
+aiohttp==3.8.4
+    # via
+    #   datasets
+    #   fsspec
+    #   gradio
+aiosignal==1.3.1
+    # via aiohttp
+altair==4.2.2
+    # via gradio
+anyio==3.6.2
+    # via
+    #   httpcore
+    #   starlette
+async-timeout==4.0.2
+    # via aiohttp
+attrs==22.2.0
+    # via
+    #   aiohttp
+    #   jsonschema
+certifi==2022.12.7
+    # via
+    #   httpcore
+    #   httpx
+    #   requests
+charset-normalizer==3.1.0
+    # via
+    #   aiohttp
+    #   requests
+click==8.1.3
+    # via uvicorn
+contourpy==1.0.7
+    # via matplotlib
+cycler==0.11.0
+    # via matplotlib
+datasets==2.10.1
+    # via -r requirements.in
+dill==0.3.6
+    # via
+    #   datasets
+    #   multiprocess
+entrypoints==0.4
+    # via altair
+fastapi==0.95.0
+    # via gradio
+ffmpy==0.3.0
+    # via gradio
+filelock==3.10.4
+    # via huggingface-hub
+fonttools==4.39.2
+    # via matplotlib
+frozenlist==1.3.3
+    # via
+    #   aiohttp
+    #   aiosignal
+fsspec[http]==2023.3.0
+    # via
+    #   datasets
+    #   gradio
+gradio==3.23.0
+    # via -r requirements.in
+h11==0.14.0
+    # via
+    #   httpcore
+    #   uvicorn
+httpcore==0.16.3
+    # via httpx
+httpx==0.23.3
+    # via gradio
+huggingface-hub==0.13.3
+    # via
+    #   datasets
+    #   gradio
+idna==3.4
+    # via
+    #   anyio
+    #   requests
+    #   rfc3986
+    #   yarl
+jinja2==3.1.2
+    # via
+    #   altair
+    #   gradio
+jsonschema==4.17.3
+    # via altair
+kiwisolver==1.4.4
+    # via matplotlib
+linkify-it-py==2.0.0
+    # via markdown-it-py
+markdown-it-py[linkify]==2.2.0
+    # via
+    #   gradio
+    #   mdit-py-plugins
+markupsafe==2.1.2
+    # via
+    #   gradio
+    #   jinja2
+matplotlib==3.7.1
+    # via
+    #   -r requirements.in
+    #   gradio
+mdit-py-plugins==0.3.3
+    # via gradio
+mdurl==0.1.2
+    # via markdown-it-py
+multidict==6.0.4
+    # via
+    #   aiohttp
+    #   yarl
+multiprocess==0.70.14
+    # via datasets
+numpy==1.24.2
+    # via
+    #   altair
+    #   contourpy
+    #   datasets
+    #   gradio
+    #   matplotlib
+    #   pandas
+    #   pyarrow
+orjson==3.8.8
+    # via gradio
+packaging==23.0
+    # via
+    #   datasets
+    #   huggingface-hub
+    #   matplotlib
+pandas==1.5.3
+    # via
+    #   -r requirements.in
+    #   altair
+    #   datasets
+    #   gradio
+pillow==9.4.0
+    # via
+    #   gradio
+    #   matplotlib
+plotly==5.13.1
+    # via -r requirements.in
+polars==0.16.15
+    # via -r requirements.in
+pyarrow==11.0.0
+    # via datasets
+pydantic==1.10.7
+    # via
+    #   fastapi
+    #   gradio
+pydub==0.25.1
+    # via gradio
+pyparsing==3.0.9
+    # via matplotlib
+pyrsistent==0.19.3
+    # via jsonschema
+python-dateutil==2.8.2
+    # via
+    #   matplotlib
+    #   pandas
+python-multipart==0.0.6
+    # via gradio
+pytz==2022.7.1
+    # via pandas
+pyyaml==6.0
+    # via
+    #   datasets
+    #   gradio
+    #   huggingface-hub
+requests==2.28.2
+    # via
+    #   datasets
+    #   fsspec
+    #   gradio
+    #   huggingface-hub
+    #   responses
+responses==0.18.0
+    # via datasets
+rfc3986[idna2008]==1.5.0
+    # via httpx
+semantic-version==2.10.0
+    # via gradio
+six==1.16.0
+    # via python-dateutil
+sniffio==1.3.0
+    # via
+    #   anyio
+    #   httpcore
+    #   httpx
+starlette==0.26.1
+    # via fastapi
+tenacity==8.2.2
+    # via plotly
+toolz==0.12.0
+    # via
+    #   -r requirements.in
+    #   altair
+tqdm==4.65.0
+    # via
+    #   datasets
+    #   huggingface-hub
+typing-extensions==4.5.0
+    # via
+    #   gradio
+    #   huggingface-hub
+    #   pydantic
+uc-micro-py==1.0.1
+    # via linkify-it-py
+urllib3==1.26.15
+    # via
+    #   requests
+    #   responses
+uvicorn==0.21.1
+    # via gradio
+websockets==10.4
+    # via gradio
+xxhash==3.2.0
+    # via datasets
+yarl==1.8.2
+    # via aiohttp