Update pep8 (#78)

* simplify requirements file

* style

* apply linter

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

@@ -25,9 +25,10 @@ def get_packages(pkgs):
                 except AttributeError:
                     try:
                         versions.append(imported.version_info)
-                    except:
+                    except AttributeError:
                         try:
-                            import importlib, importlib_metadata
+                            import importlib
+                            import importlib_metadata
                             imported = importlib.import_module(p)
                             version = importlib_metadata.version(p)
                             versions.append(version)

appendix-A/03_main-chapter-code/DDP-script.py

@@ -131,7 +131,7 @@ def main(rank, world_size, num_epochs):
             loss.backward()
             optimizer.step()
 
-            ### LOGGING
+            # LOGGING
             print(f"[GPU{rank}] Epoch: {epoch+1:03d}/{num_epochs:03d}"
                   f" | Batchsize {labels.shape[0]:03d}"
                   f" | Train/Val Loss: {loss:.2f}")

ch02/02_bonus_bytepair-encoder/bpe_openai_gpt2.py

@@ -1,39 +1,3 @@
-"""
-Byte pair encoding utilities
-
-Code from https://github.com/openai/gpt-2/blob/master/src/encoder.py
-
-And modified code (download_vocab) from
-https://github.com/openai/gpt-2/blob/master/download_model.py
-
-Modified MIT License
-
-Software Copyright (c) 2019 OpenAI
-
-We don’t claim ownership of the content you create with GPT-2, so it is yours to do with as you please.
-We only ask that you use GPT-2 responsibly and clearly indicate your content was created using GPT-2.
-
-Permission is hereby granted, free of charge, to any person obtaining a copy of this software and
-associated documentation files (the "Software"), to deal in the Software without restriction,
-including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense,
-and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so,
-subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included
-in all copies or substantial portions of the Software.
-The above copyright notice and this permission notice need not be included
-with content created by the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
-INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
-BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
-TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE
-OR OTHER DEALINGS IN THE SOFTWARE.
-
-
-"""
-
 import os
 import json
 import regex as re
@@ -41,6 +5,7 @@ import requests
 from tqdm import tqdm
 from functools import lru_cache
 
+
 @lru_cache()
 def bytes_to_unicode():
     """
@@ -63,9 +28,10 @@ def bytes_to_unicode():
     cs = [chr(n) for n in cs]
     return dict(zip(bs, cs))
 
-def get_pairs(word):
-    """Return set of symbol pairs in a word.
 
+def get_pairs(word):
+    """
+    Return set of symbol pairs in a word.
     Word is represented as tuple of symbols (symbols being variable-length strings).
     """
     pairs = set()
@@ -75,6 +41,7 @@ def get_pairs(word):
         prev_char = char
     return pairs
 
+
 class Encoder:
     def __init__(self, encoder, bpe_merges, errors='replace'):
         self.encoder = encoder
@@ -85,7 +52,7 @@ class Encoder:
         self.bpe_ranks = dict(zip(bpe_merges, range(len(bpe_merges))))
         self.cache = {}
 
-        # Should haved added re.IGNORECASE so BPE merges can happen for capitalized versions of contractions
+        # Should have added re.IGNORECASE so BPE merges can happen for capitalized versions of contractions
         self.pat = re.compile(r"""'s|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+""")
 
     def bpe(self, token):
@@ -109,7 +76,7 @@ class Encoder:
                     j = word.index(first, i)
                     new_word.extend(word[i:j])
                     i = j
-                except:
+                except ValueError:
                     new_word.extend(word[i:])
                     break
 
@@ -141,16 +108,14 @@ class Encoder:
         text = bytearray([self.byte_decoder[c] for c in text]).decode('utf-8', errors=self.errors)
         return text
 
+
 def get_encoder(model_name, models_dir):
     with open(os.path.join(models_dir, model_name, 'encoder.json'), 'r') as f:
         encoder = json.load(f)
     with open(os.path.join(models_dir, model_name, 'vocab.bpe'), 'r', encoding="utf-8") as f:
         bpe_data = f.read()
     bpe_merges = [tuple(merge_str.split()) for merge_str in bpe_data.split('\n')[1:-1]]
-    return Encoder(
-        encoder=encoder,
-        bpe_merges=bpe_merges,
-    )
+    return Encoder(encoder=encoder, bpe_merges=bpe_merges)
 
 
 def download_vocab():
@@ -161,8 +126,7 @@ def download_vocab():
     subdir = subdir.replace('\\', '/')  # needed for Windows
 
     for filename in ['encoder.json', 'vocab.bpe']:
-
-        r = requests.get("https://openaipublic.blob.core.windows.net/gpt-2/models/117M" + "/" + filename, stream=True)
+        r = requests.get("https://openaipublic.blob.core.windows.net/gpt-2/models/117M/" + filename, stream=True)
 
         with open(os.path.join(subdir, filename), 'wb') as f:
             file_size = int(r.headers["content-length"])

ch03/02_bonus_efficient-multihead-attention/ch03.py

@@ -44,7 +44,6 @@ class MultiHeadAttentionWrapper(nn.Module):
         return self.out_proj(context_vec)
 
 
-
 class MultiHeadAttention(nn.Module):
     def __init__(self, d_in, d_out, block_size, dropout, num_heads, qkv_bias=False):
         super().__init__()

ch05/03_bonus_pretraining_on_gutenberg/pretraining_simple.py

@@ -99,7 +99,7 @@ def train_model_simple(model, optimizer, device, n_epochs,
                     max_length=GPT_CONFIG_124M["ctx_len"],
                     stride=GPT_CONFIG_124M["ctx_len"]
                 )
-                print(f"Training ...")
+                print("Training ...")
                 model.train()
                 for input_batch, target_batch in train_loader:
                     optimizer.zero_grad()

ch05/03_bonus_pretraining_on_gutenberg/previous_chapters.py

@@ -9,11 +9,11 @@ from torch.utils.data import Dataset, DataLoader
 import matplotlib.pyplot as plt
 
 
-
 #####################################
 # Chapter 2
 #####################################
 
+
 class GPTDatasetV1(Dataset):
     def __init__(self, txt, tokenizer, max_length, stride):
         self.tokenizer = tokenizer
@@ -310,5 +310,3 @@ def text_to_token_ids(text, tokenizer):
 def token_ids_to_text(token_ids, tokenizer):
     flat = token_ids.squeeze(0)  # remove batch dimension
     return tokenizer.decode(flat.tolist())
-
-