simplify requirements file (#76)

appendix-A/02_installing-python-libraries/README.md

@@ -2,18 +2,9 @@
 
 This document provides more information on double-checking your installed Python version and packages. (Please see the [../01_optional-python-setup-preferences](../01_optional-python-setup-preferences) folder for more information on installing Python and Python packages.)
 
-I used the following main libraries in this book. Newer versions of these libraries are likely compatible as well. However, if you experience any problems with the code, you can try these library versions as a fallback:
+I used the following libraries listed [here](https://github.com/rasbt/LLMs-from-scratch/blob/main/requirements.txt) for this book. Newer versions of these libraries are likely compatible as well. However, if you experience any problems with the code, you can try these library versions as a fallback.
 
--  numpy  1.24.3
+To install these requirements most conveniently, you can use the `requirements.txt` file in the root directory for this code repository and execute the following command:
--  scipy 1.10.1
--  pandas  2.0.2
--  matplotlib  3.7.1
--  jupyterlab  4.0
--  watermark  2.4.2
--  torch  2.0.1
--  tiktoken  0.5.1
-
-To install these requirements most conveniently, you can use the `requirements.txt` file:
 
 ```
 pip install -r requirements.txt
@@ -36,7 +27,6 @@ If you see the following issues, it's likely that your JupyterLab instance is co
 
 <img src="figures/jupyter-issues.jpg" width="450px">
 
-
 In this case, you may want to use `watermark` to check if you opened the JupyterLab instance in the right conda environment using the `--conda` flag:
 
 <img src="figures/watermark.jpg" width="350px">

appendix-A/02_installing-python-libraries/python_environment_check.ipynb

@@ -10,15 +10,14 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[OK] Your Python version is 3.11.4\n",
+      "[OK] Your Python version is 3.10.12\n",
-      "[OK] numpy 1.25.2\n",
+      "numpy >= 1.24.3       \n",
-      "[OK] scipy 1.11.1\n",
+      "matplotlib >= 3.7.1.  \n",
-      "[OK] pandas 2.0.3\n",
+      "jupyterlab >= 4.0.    \n",
-      "[OK] matplotlib 3.7.2\n",
+      "tensorflow >= 2.15.0  \n",
-      "[OK] jupyterlab 4.0.4\n",
+      "torch >= 2.0.1        \n",
-      "[OK] watermark 2.4.3\n",
+      "tqdm >= 4.66.1        \n",
-      "[OK] torch 2.0.1\n",
+      "tiktoken >= 0.5.1     \n"
-      "[OK] tiktoken 0.5.1\n"
      ]
     }
    ],
@@ -28,14 +27,6 @@
     "d = get_requirements_dict()\n",
     "check_packages(d)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "d5ca05fc-98e0-4bba-a95e-350e1764a12c",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -54,7 +45,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

appendix-A/02_installing-python-libraries/python_environment_check.py

@@ -42,11 +42,18 @@ def get_packages(pkgs):
 
 def get_requirements_dict():
     PROJECT_ROOT = dirname(realpath(__file__))
-    REQUIREMENTS_FILE = join(PROJECT_ROOT, "requirements.txt")
+    PROJECT_ROOT_UP_TWO = dirname(dirname(PROJECT_ROOT))
+    REQUIREMENTS_FILE = join(PROJECT_ROOT_UP_TWO, "requirements.txt")
     d = {}
     with open(REQUIREMENTS_FILE) as f:
         for line in f:
+            if not line.strip():
+                continue
+            line = line.split("#")[0]
+            print(line)
             line = line.split(" ")
+            if not line[0].strip() or not line[-1].strip():
+                continue
             d[line[0]] = line[-1]
     return d
 

appendix-A/02_installing-python-libraries/requirements.txt

@@ -1,8 +0,0 @@
-numpy >= 1.24.3
-scipy >= 1.10.1
-pandas >= 2.0.2
-matplotlib >= 3.7.1
-jupyterlab >= 4.0
-watermark >= 2.4.2
-torch >= 2.0.1
-tiktoken >= 0.5.1

ch05/01_main-chapter-code/previous_chapters.py

@@ -35,7 +35,7 @@ class GPTDatasetV1(Dataset):
         return self.input_ids[idx], self.target_ids[idx]
 
 
-def create_dataloader_v1(txt, batch_size=4, max_length=256, 
+def create_dataloader_v1(txt, batch_size=4, max_length=256,
                          stride=128, shuffle=True, drop_last=True):
     # Initialize the tokenizer
     tokenizer = tiktoken.get_encoding("gpt2")
@@ -78,7 +78,7 @@ class MultiHeadAttention(nn.Module):
 
         # We implicitly split the matrix by adding a `num_heads` dimension
         # Unroll last dim: (b, num_tokens, d_out) -> (b, num_tokens, num_heads, head_dim)
-        keys = keys.view(b, num_tokens, self.num_heads, self.head_dim) 
+        keys = keys.view(b, num_tokens, self.num_heads, self.head_dim)
         values = values.view(b, num_tokens, self.num_heads, self.head_dim)
         queries = queries.view(b, num_tokens, self.num_heads, self.head_dim)
 

requirements.txt

@@ -1,8 +1,7 @@
-numpy >= 1.24.3
+numpy >= 1.24.3       # ch05
-scipy >= 1.10.1
+matplotlib >= 3.7.1.  # ch04, ch05
-pandas >= 2.0.2
+jupyterlab >= 4.0.    # all
-matplotlib >= 3.7.1
+tensorflow >= 2.15.0  # ch05
-jupyterlab >= 4.0
+torch >= 2.0.1        # all
-watermark >= 2.4.2
+tqdm >= 4.66.1        # ch05
-torch >= 2.0.1
+tiktoken >= 0.5.1     # ch02, ch04, ch05
-tiktoken >= 0.5.1