Rename CodeVectorizer

Author: egor-bogomolov

py_example/README.md

@@ -74,8 +74,8 @@ of `PathMinerLoader` to i.e. Tensorflow tensors or ndarrays.
 
 ### Model
 
-`model.Code2Vec` contains a model to vectorize snippets of code based on their path-context representation.
-This model had been originally implemented as a part of [code2vec](https://github.com/tech-srl/code2vec).
+`model.CodeVectorizer` contains a model to vectorize snippets of code based on their path-context representation.
+This model works similarly to the part of [code2vec's](https://github.com/tech-srl/code2vec) that is responsible for code vectorization.
 It is implemented as a PyTorch module and can be easily reused.
 
 A usage example can be found in `model.ProjectClassifier`.

py_example/data_processing/PathMinerDataset.py

@@ -7,7 +7,7 @@
 class PathMinerDataset(Dataset):
 
     # Converts data to PyTorch Tensors for further usage in the model
-    # Number of contexts per file is limited as it was done in the original implementation of Code2Vec
+    # Number of contexts per file is limited to allow fast computations
     def __init__(self, loader, indices, keep_contexts=200):
         self.size = len(indices)
         sample = loader.path_contexts.iloc[indices]

py_example/model/Code2Vec.py py_example/model/CodeVectorizer.pypy_example/model/Code2Vec.py renamed to py_example/model/CodeVectorizer.py

@@ -5,10 +5,10 @@
 
 # Implementation of code2vec's vectorization part in PyTorch.
 # Since it is a PyTorch Module, it can be reused as a part of another pipeline.
-class Code2Vec(nn.Module):
+class CodeVectorizer(nn.Module):
 
     def __init__(self, n_tokens, n_paths, dim):
-        super(Code2Vec, self).__init__()
+        super(CodeVectorizer, self).__init__()
         self.tokens_embed = nn.Embedding(n_tokens, dim)
         self.paths_embed = nn.Embedding(n_paths, dim)
         self.transform = nn.Sequential(nn.Linear(3 * dim, dim), nn.Tanh())

py_example/model/ProjectClassifier.py

@@ -1,14 +1,14 @@
 import torch
 from torch import nn
-from model.Code2Vec import Code2Vec
+from model.CodeVectorizer import CodeVectorizer
 
 
 # Classifier distinguishing files between two projects based on code2vec vectorization for files.
 class ProjectClassifier(nn.Module):
 
     def __init__(self, n_tokens, n_paths, dim):
         super(ProjectClassifier, self).__init__()
-        self.vectorization = Code2Vec(n_tokens, n_paths, dim)
+        self.vectorization = CodeVectorizer(n_tokens, n_paths, dim)
         self.classifier = nn.Linear(dim, 1)
 
     def forward(self, contexts):