updated requirements and readme

README.md

@@ -7,6 +7,8 @@ In the Notebooks module you can view all of the different experiments we ran.
 
 ### Demo
 To run the demo:
+clone the repository using ```git clone https://github.com/tulane-cmps6730/project-legal.git```
+open up your terminal and cd into ```project-legal``` 
 Move into the app directory with by using ```cd app``` in your command line
 To run the app use ```flask run```
 This should run the flask app locally on your computer, so you should be able to use the demo in your web browser at http://127.0.0.1:5000 (the port number may differ depending on your computer)

notebooks/BoWExperiments(2).ipynb

@@ -776,32 +776,31 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 17,
+      "execution_count": 19,
       "metadata": {},
       "outputs": [
         {
-          "ename": "TypeError",
-          "evalue": "sparse array length is ambiguous; use getnnz() or shape[0]",
+          "ename": "NameError",
+          "evalue": "name 'bow_classifier' is not defined",
           "output_type": "error",
           "traceback": [
             "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-            "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
-            "Cell \u001b[0;32mIn[17], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m bow_tensor \u001b[38;5;241m=\u001b[39m \u001b[43mtorch\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtensor\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbow_text\u001b[49m\u001b[43m)\u001b[49m\n",
-            "File \u001b[0;32m~/school/NLP/project-legal/nlp-virtual/lib/python3.10/site-packages/scipy/sparse/_base.py:395\u001b[0m, in \u001b[0;36m_spbase.__len__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    394\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__len__\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[0;32m--> 395\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msparse array length is ambiguous; use getnnz()\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    396\u001b[0m                     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m or shape[0]\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
-            "\u001b[0;31mTypeError\u001b[0m: sparse array length is ambiguous; use getnnz() or shape[0]"
+            "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+            "Cell \u001b[0;32mIn[19], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m logits \u001b[38;5;241m=\u001b[39m \u001b[43mbow_classifier\u001b[49m\u001b[38;5;241m.\u001b[39mdecision_function(bow_text)\n\u001b[1;32m      2\u001b[0m logits\n",
+            "\u001b[0;31mNameError\u001b[0m: name 'bow_classifier' is not defined"
           ]
         }
       ],
       "source": [
-        "import scipy.sparse as sp\n",
-        "sparse_matrix = sp.coo_matrix(bow_text)\n",
-        "values = torch.tensor(sparse_matrix.data)\n",
-        "indices = torch.tensor(np.vstack((sparse_matrix.row, sparse_matrix.col)), dtype=torch.long)\n",
-        "shape = torch.Size(sparse_matrix.shape)\n",
-        "\n",
-        "# Create sparse tensor\n",
-        "torch_sparse_tensor = torch.sparse_coo_tensor(indices, values, shape)\n",
-        "torch_sparse_tensor"
+        "logits = classifier.decision_function(bow_text)\n",
+        "logits"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "If we want to make an ensemble method, we will have to use tensorflow because it has more support for sparse matrices, which we need for the bag of words method, compared to pytorch"
       ]
     },
     {

requirements.txt

@@ -1,4 +1,5 @@
 absl-py==2.1.0
+accelerate==0.29.2
 aiohttp==3.9.3
 aiosignal==1.3.1
 appdirs==1.4.4
@@ -70,6 +71,7 @@ multiprocess==0.70.16
 namex==0.0.7
 nest-asyncio==1.6.0
 networkx==3.3
+-e git+ssh://[email protected]/tulane-cmps6730/project-legal.git@d3d959cb3a9baec00d1c388539dd18e5dcceaea9#egg=nlp
 nltk==3.8.1
 numpy==1.26.4
 nvidia-cublas-cu12==12.1.3.1
@@ -129,6 +131,7 @@ threadpoolctl==3.3.0
 tokenizers==0.15.2
 torch==2.2.2
 torchinfo==1.8.0
+torchtext==0.17.2
 tornado==6.4
 tqdm==4.66.2
 traitlets==5.14.2