Merge branch 'master' into prompts-eval

wandb · Jan 30, 2024 · dbb73b7 · dbb73b7
2 parents 46e7ca7 + 71ecbc5
commit dbb73b7
Show file tree

Hide file tree

Showing 152 changed files with 17,886 additions and 5,368 deletions.
diff --git a/.github/nb_scripts/fix_login.ipynb b/.github/nb_scripts/fix_login.ipynb
@@ -0,0 +1,247 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import nbformat\n",
+    "from pathlib import Path\n",
+    "from nb_helpers.utils import find_nbs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "152"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "nbs_paths = find_nbs(\"../../\")\n",
+    "len(nbs_paths)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Path('/Users/tcapelle/work/examples/colabs/boosting/Credit_Scorecards_with_XGBoost_and_W&B.ipynb')"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "nb_path = nbs_paths[3]\n",
+    "nb_path\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "wandb.login()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "nb = nbformat.read(nb_path, 4)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "18"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "login_idx = idx_login_cell(nb, delete_line=False)\n",
+    "login_idx"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "login_code = \"wandb.login()\"  # or !wandb login\n",
+    "\n",
+    "def insert_login_cell(nb, idx, code=login_code, replace=True):\n",
+    "    n_cells = len(nb[\"cells\"])\n",
+    "    login_cell = nbformat.v4.new_code_cell(source=code)\n",
+    "    nb[\"cells\"].insert(idx+1, login_cell)\n",
+    "    return nb"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "nb = insert_login_cell(nb, login_idx)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'cell_type': 'code',\n",
+       " 'execution_count': None,\n",
+       " 'metadata': {},\n",
+       " 'outputs': [],\n",
+       " 'source': '!wandb login'}"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "nb[\"cells\"][login_idx] "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'id': 'ff6708eb',\n",
+       " 'cell_type': 'code',\n",
+       " 'metadata': {},\n",
+       " 'execution_count': None,\n",
+       " 'source': '!wandb login',\n",
+       " 'outputs': []}"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "nb[\"cells\"][login_idx+1] "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'attachments': {},\n",
+       " 'cell_type': 'markdown',\n",
+       " 'metadata': {},\n",
+       " 'source': '## Vehicle Loan Dataset\\n\\nWe will be using a simplified version of the [Vehicle Loan Default Prediction dataset](https://www.kaggle.com/sneharshinde/ltfs-av-data) from L&T which has been stored in W&B Artifacts. '}"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "nb[\"cells\"][login_idx+2] "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def remove_properties(nb, props=[\"id\", \"idx_\", \"path_\"]):\n",
+    "    for cell in nb[\"cells\"]:\n",
+    "        for prop in props:\n",
+    "            cell.pop(prop, None)\n",
+    "    return nb\n",
+    "\n",
+    "def remove_empty_cells(nb):\n",
+    "    nb[\"cells\"] = [cell for cell in nb[\"cells\"] if cell[\"source\"] != \"\"]\n",
+    "    return nb"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "nb = remove_properties(nb)\n",
+    "nb = remove_empty_cells(nb)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for nb_path in nbs_paths:\n",
+    "    nb = nbformat.read(nb_path, 4)\n",
+    "    login_idx = idx_login_cell(nb)\n",
+    "    if login_idx is not None:\n",
+    "        nb = insert_login_cell(nb, login_idx)\n",
+    "        # delete path_ attribute\n",
+    "    nb.pop(\"path_\", None)\n",
+    "    nb = remove_properties(nb)\n",
+    "    nb = remove_empty_cells(nb)\n",
+    "    nbformat.validate(nb)\n",
+    "    nbformat.write(nb, nb_path)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "nbdev2",
+   "language": "python",
+   "name": "python3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}