add reqs

Author: woodthom2

Burrows Delta Walkthrough.ipynb

@@ -28,7 +28,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Python 3.12.7\n"
+     ]
+    }
+   ],
+   "source": [
+    "!python --version"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -37,37 +54,42 @@
      "text": [
       "\u001b[33mWARNING: Ignoring invalid distribution ~rotobuf (/home/thomas/anaconda3/lib/python3.12/site-packages)\u001b[0m\u001b[33m\n",
       "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution ~rotobuf (/home/thomas/anaconda3/lib/python3.12/site-packages)\u001b[0m\u001b[33m\n",
-      "\u001b[0mCollecting faststylometry\n",
-      "  Using cached faststylometry-1.0.7-py3-none-any.whl.metadata (12 kB)\n",
-      "Requirement already satisfied: numpy>=2.3.1 in /home/thomas/anaconda3/lib/python3.12/site-packages (from faststylometry) (2.3.1)\n",
-      "Requirement already satisfied: pandas>=2.3.1 in /home/thomas/anaconda3/lib/python3.12/site-packages (from faststylometry) (2.3.1)\n",
-      "Requirement already satisfied: scikit-learn>=1.7.1 in /home/thomas/anaconda3/lib/python3.12/site-packages (from faststylometry) (1.7.1)\n",
-      "Requirement already satisfied: wget>=3.2 in /home/thomas/anaconda3/lib/python3.12/site-packages (from faststylometry) (3.2)\n",
-      "Requirement already satisfied: python-dateutil>=2.8.2 in /home/thomas/anaconda3/lib/python3.12/site-packages (from pandas>=2.3.1->faststylometry) (2.9.0.post0)\n",
-      "Requirement already satisfied: pytz>=2020.1 in /home/thomas/anaconda3/lib/python3.12/site-packages (from pandas>=2.3.1->faststylometry) (2024.1)\n",
-      "Requirement already satisfied: tzdata>=2022.7 in /home/thomas/anaconda3/lib/python3.12/site-packages (from pandas>=2.3.1->faststylometry) (2023.3)\n",
-      "Requirement already satisfied: scipy>=1.8.0 in /home/thomas/anaconda3/lib/python3.12/site-packages (from scikit-learn>=1.7.1->faststylometry) (1.16.0)\n",
-      "Requirement already satisfied: joblib>=1.2.0 in /home/thomas/anaconda3/lib/python3.12/site-packages (from scikit-learn>=1.7.1->faststylometry) (1.4.2)\n",
-      "Requirement already satisfied: threadpoolctl>=3.1.0 in /home/thomas/anaconda3/lib/python3.12/site-packages (from scikit-learn>=1.7.1->faststylometry) (3.5.0)\n",
-      "Requirement already satisfied: six>=1.5 in /home/thomas/anaconda3/lib/python3.12/site-packages (from python-dateutil>=2.8.2->pandas>=2.3.1->faststylometry) (1.16.0)\n",
-      "Using cached faststylometry-1.0.7-py3-none-any.whl (18 kB)\n",
+      "\u001b[0mCollecting faststylometry==1.0.13\n",
+      "  Downloading faststylometry-1.0.13-py3-none-any.whl.metadata (14 kB)\n",
+      "Requirement already satisfied: numpy>=2.3.1 in /home/thomas/anaconda3/lib/python3.12/site-packages (from faststylometry==1.0.13) (2.3.1)\n",
+      "Requirement already satisfied: pandas>=2.3.1 in /home/thomas/anaconda3/lib/python3.12/site-packages (from faststylometry==1.0.13) (2.3.1)\n",
+      "Requirement already satisfied: scikit-learn>=1.7.1 in /home/thomas/anaconda3/lib/python3.12/site-packages (from faststylometry==1.0.13) (1.7.1)\n",
+      "Requirement already satisfied: wget>=3.2 in /home/thomas/anaconda3/lib/python3.12/site-packages (from faststylometry==1.0.13) (3.2)\n",
+      "Requirement already satisfied: python-dateutil>=2.8.2 in /home/thomas/anaconda3/lib/python3.12/site-packages (from pandas>=2.3.1->faststylometry==1.0.13) (2.9.0.post0)\n",
+      "Requirement already satisfied: pytz>=2020.1 in /home/thomas/anaconda3/lib/python3.12/site-packages (from pandas>=2.3.1->faststylometry==1.0.13) (2024.1)\n",
+      "Requirement already satisfied: tzdata>=2022.7 in /home/thomas/anaconda3/lib/python3.12/site-packages (from pandas>=2.3.1->faststylometry==1.0.13) (2023.3)\n",
+      "Requirement already satisfied: scipy>=1.8.0 in /home/thomas/anaconda3/lib/python3.12/site-packages (from scikit-learn>=1.7.1->faststylometry==1.0.13) (1.16.0)\n",
+      "Requirement already satisfied: joblib>=1.2.0 in /home/thomas/anaconda3/lib/python3.12/site-packages (from scikit-learn>=1.7.1->faststylometry==1.0.13) (1.4.2)\n",
+      "Requirement already satisfied: threadpoolctl>=3.1.0 in /home/thomas/anaconda3/lib/python3.12/site-packages (from scikit-learn>=1.7.1->faststylometry==1.0.13) (3.5.0)\n",
+      "Requirement already satisfied: six>=1.5 in /home/thomas/anaconda3/lib/python3.12/site-packages (from python-dateutil>=2.8.2->pandas>=2.3.1->faststylometry==1.0.13) (1.16.0)\n",
+      "Downloading faststylometry-1.0.13-py3-none-any.whl (19 kB)\n",
       "\u001b[33mWARNING: Ignoring invalid distribution ~rotobuf (/home/thomas/anaconda3/lib/python3.12/site-packages)\u001b[0m\u001b[33m\n",
       "\u001b[0mInstalling collected packages: faststylometry\n",
+      "  Attempting uninstall: faststylometry\n",
+      "\u001b[33m    WARNING: Ignoring invalid distribution ~rotobuf (/home/thomas/anaconda3/lib/python3.12/site-packages)\u001b[0m\u001b[33m\n",
+      "\u001b[0m    Found existing installation: faststylometry 1.0.11\n",
+      "    Uninstalling faststylometry-1.0.11:\n",
+      "      Successfully uninstalled faststylometry-1.0.11\n",
       "\u001b[33mWARNING: Ignoring invalid distribution ~rotobuf (/home/thomas/anaconda3/lib/python3.12/site-packages)\u001b[0m\u001b[33m\n",
-      "\u001b[0mSuccessfully installed faststylometry-1.0.7\n",
+      "\u001b[0mSuccessfully installed faststylometry-1.0.13\n",
       "\u001b[33mWARNING: Ignoring invalid distribution ~rotobuf (/home/thomas/anaconda3/lib/python3.12/site-packages)\u001b[0m\u001b[33m\n",
       "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution ~rotobuf (/home/thomas/anaconda3/lib/python3.12/site-packages)\u001b[0m\u001b[33m\n",
       "\u001b[0m"
      ]
     }
    ],
    "source": [
-    "!pip install faststylometry"
+    "!pip install faststylometry==1.0.13"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 9,
    "metadata": {
     "scrolled": true
    },
@@ -126,7 +148,7 @@
       "    if await self.run_code(code, result, async_=asy):\n",
       "  File \"/home/thomas/anaconda3/lib/python3.12/site-packages/IPython/core/interactiveshell.py\", line 3577, in run_code\n",
       "    exec(code_obj, self.user_global_ns, self.user_ns)\n",
-      "  File \"/tmp/ipykernel_127318/1668831037.py\", line 1, in <module>\n",
+      "  File \"/tmp/ipykernel_130328/1668831037.py\", line 1, in <module>\n",
       "    from faststylometry import Corpus\n",
       "  File \"/home/thomas/anaconda3/lib/python3.12/site-packages/faststylometry/__init__.py\", line 37, in <module>\n",
       "    from faststylometry.probability import predict_proba, calibrate, get_calibration_curve\n",
@@ -170,7 +192,7 @@
      "traceback": [
       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
       "\u001b[0;31mImportError\u001b[0m                               Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[5], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mfaststylometry\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Corpus\n\u001b[1;32m      3\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mfaststylometry\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m download_examples\n\u001b[1;32m      4\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mfaststylometry\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m load_corpus_from_folder\n",
+      "Cell \u001b[0;32mIn[9], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mfaststylometry\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Corpus\n\u001b[1;32m      3\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mfaststylometry\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m download_examples\n\u001b[1;32m      4\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mfaststylometry\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m load_corpus_from_folder\n",
       "File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/faststylometry/__init__.py:37\u001b[0m\n\u001b[1;32m     35\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mfaststylometry\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01men\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m tokenise_remove_pronouns_en\n\u001b[1;32m     36\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mfaststylometry\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mburrows_delta\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m calculate_burrows_delta\n\u001b[0;32m---> 37\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mfaststylometry\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mprobability\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m predict_proba, calibrate, get_calibration_curve\n\u001b[1;32m     38\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mfaststylometry\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mexamples\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m download_examples\n",
       "File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/faststylometry/probability.py:32\u001b[0m\n\u001b[1;32m     30\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mnumpy\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mnp\u001b[39;00m\n\u001b[1;32m     31\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mpandas\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mpd\u001b[39;00m\n\u001b[0;32m---> 32\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01msklearn\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mlinear_model\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m LogisticRegression\n\u001b[1;32m     34\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mfaststylometry\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mburrows_delta\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m calculate_burrows_delta\n\u001b[1;32m     35\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mfaststylometry\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcorpus\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Corpus\n",
       "File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/sklearn/__init__.py:73\u001b[0m\n\u001b[1;32m     62\u001b[0m \u001b[38;5;66;03m# `_distributor_init` allows distributors to run custom init code.\u001b[39;00m\n\u001b[1;32m     63\u001b[0m \u001b[38;5;66;03m# For instance, for the Windows wheel, this is used to pre-load the\u001b[39;00m\n\u001b[1;32m     64\u001b[0m \u001b[38;5;66;03m# vcomp shared library runtime for OpenMP embedded in the sklearn/.libs\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     67\u001b[0m \u001b[38;5;66;03m# later is linked to the OpenMP runtime to make it possible to introspect\u001b[39;00m\n\u001b[1;32m     68\u001b[0m \u001b[38;5;66;03m# it and importing it first would fail if the OpenMP dll cannot be found.\u001b[39;00m\n\u001b[1;32m     69\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m (  \u001b[38;5;66;03m# noqa: F401 E402\u001b[39;00m\n\u001b[1;32m     70\u001b[0m     __check_build,\n\u001b[1;32m     71\u001b[0m     _distributor_init,\n\u001b[1;32m     72\u001b[0m )\n\u001b[0;32m---> 73\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mbase\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m clone  \u001b[38;5;66;03m# noqa: E402\u001b[39;00m\n\u001b[1;32m     74\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mutils\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m_show_versions\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m show_versions  \u001b[38;5;66;03m# noqa: E402\u001b[39;00m\n\u001b[1;32m     76\u001b[0m _submodules \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m     77\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcalibration\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m     78\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcluster\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    114\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcompose\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m    115\u001b[0m ]\n",

requirements.txt

@@ -0,0 +1,4 @@
+numpy>=2.3.1
+pandas>=2.3.1
+scikit-learn>=1.7.1
+wget>=3.2